From 9428d6a3a14f0501d86ce81214637c7aac5365f8 Mon Sep 17 00:00:00 2001
From: Cameron Mattson <camo@oak.ucdenver.pvt>
Date: Fri, 1 Sep 2023 07:13:51 -0600
Subject: [PATCH 1/3] Trained shuffled and unshuffled logistic regression and
 saved indices

---
 .../nbconverted/plate_4_classify_genotype.py  | 255 ++++++++
 .../plate_4/plate_4_classify_genotype.ipynb   | 575 ++++++++++++++++++
 2 files changed, 830 insertions(+)
 create mode 100644 1.train_models/log_reg_plates_cp_fs_data/plate_4/nbconverted/plate_4_classify_genotype.py
 create mode 100644 1.train_models/log_reg_plates_cp_fs_data/plate_4/plate_4_classify_genotype.ipynb

diff --git a/1.train_models/log_reg_plates_cp_fs_data/plate_4/nbconverted/plate_4_classify_genotype.py b/1.train_models/log_reg_plates_cp_fs_data/plate_4/nbconverted/plate_4_classify_genotype.py
new file mode 100644
index 0000000..e9c4749
--- /dev/null
+++ b/1.train_models/log_reg_plates_cp_fs_data/plate_4/nbconverted/plate_4_classify_genotype.py
@@ -0,0 +1,255 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+# # Train a logistic regression to classify genotypes for plate 4
+
+# In[1]:
+
+
+import pathlib
+import warnings
+
+import numpy as np
+import pandas as pd
+from joblib import dump
+from scipy.stats import uniform
+from sklearn.exceptions import ConvergenceWarning
+from sklearn.linear_model import LogisticRegression
+from sklearn.model_selection import (
+    RandomizedSearchCV,
+    StratifiedKFold,
+    train_test_split,
+)
+from sklearn.preprocessing import LabelEncoder
+from sklearn.utils import parallel_backend
+
+# ## Find the root of the git repo on the host system
+
+# In[2]:
+
+
+# Get the current working directory
+cwd = pathlib.Path.cwd()
+
+if (cwd / ".git").is_dir():
+    root_dir = cwd
+
+else:
+    root_dir = None
+    for parent in cwd.parents:
+        if (parent / ".git").is_dir():
+            root_dir = parent
+            break
+
+# Check if a Git root directory was found
+if root_dir is None:
+    raise FileNotFoundError("No Git root directory found.")
+
+
+# ## Define and create paths
+
+# In[3]:
+
+
+# Input paths
+plate_path = "Plate_4_sc_norm_fs.parquet"
+plate_path = pathlib.Path(f"{root_dir}/nf1_painting_repo/3.processing_features/data/feature_selected_data/{plate_path}")
+
+# Output paths
+models_path = pathlib.Path("trained_models")
+data_path = pathlib.Path("model_data")
+
+# Create output paths if nonexistent
+models_path.mkdir(parents=True, exist_ok=True)
+data_path.mkdir(parents=True, exist_ok=True)
+
+
+# ## Load the dataframe
+
+# In[4]:
+
+
+platedf = pd.read_parquet(plate_path)
+
+
+# ## Define column names
+
+# In[5]:
+
+
+well_column = "Metadata_Well"
+gene_column = "Metadata_genotype"
+concentration_column = "Metadata_Concentration"
+
+
+# # Process data
+
+# ## Down-sample by genotype
+
+# In[6]:
+
+
+# Filter data where the siRNA construct concentration is zero
+platedf = platedf[platedf[concentration_column] == 0]
+
+min_gene = platedf[gene_column].value_counts().min()
+platedf = platedf.groupby(gene_column, group_keys=False).apply(lambda x: x.sample(n=min_gene, random_state=0))
+
+
+# ## Encode genotypes
+
+# In[7]:
+
+
+# Encode classes
+le = LabelEncoder()
+featdf = platedf.copy()
+featdf[gene_column] = le.fit_transform(featdf[gene_column])
+
+
+# ## Remove Metadata and encode labels
+
+# In[8]:
+
+
+# Create dataframe without Metadata
+feat_columns = [col for col in platedf.columns if "Metadata" not in col]
+featdf = platedf[feat_columns]
+
+# Encode labels
+platedf[gene_column] = le.transform(platedf[gene_column])
+
+
+# ## Split the Data
+
+# In[9]:
+
+
+test_frac = 0.2
+val_frac = 0.15
+
+X_train, X_test, y_train, y_test = train_test_split(featdf, platedf[gene_column], test_size = test_frac, random_state=0, shuffle=True)
+
+
+# ## Shuffle the training data for the shuffled model
+
+# In[10]:
+
+
+X_train_shuf = X_train.copy()
+
+rng = np.random.default_rng(0)
+
+for column in X_train_shuf.columns:
+    X_train_shuf[column] = rng.permutation(X_train_shuf[column])
+
+
+# # Train Models
+
+# ## Define model variables
+
+# In[11]:
+
+
+# Define the hyperparameter search space
+param_dist = {
+    'C': uniform(loc=0.5, scale=1.5),
+    "l1_ratio": uniform(loc=0, scale=1),
+}
+
+# Define stratification method
+strat_obj = StratifiedKFold(n_splits=5, shuffle=True, random_state=0)
+
+# Create a Logistic Regression model
+logreg_params = {
+    "max_iter": 1000,
+    "multi_class": "ovr",
+    "penalty": 'elasticnet',
+    "solver": 'saga'
+}
+
+# Initialize the RandomizedSearchCV
+random_search_params = {
+    "param_distributions": param_dist,
+    "scoring": "precision",
+    "n_iter": 100,
+    "cv": strat_obj,
+    "random_state": 0,
+    "n_jobs": -1,
+}
+
+
+# ## Train the unshuffled model
+
+# In[12]:
+
+
+logreg = LogisticRegression(**logreg_params)
+
+# Initialize the RandomizedSearchCV
+random_search = RandomizedSearchCV(logreg, **random_search_params)
+
+# Prevent the convergence warning in sklearn
+with parallel_backend("multiprocessing"):
+    with warnings.catch_warnings():
+        warnings.filterwarnings(
+            "ignore", category=ConvergenceWarning, module="sklearn"
+        )
+        # Perform the random hyperparameter search
+        random_search.fit(X_train, y_train)
+
+
+# ## Train the shuffled model
+
+# In[13]:
+
+
+# Create a Logistic Regression model for shuffled data
+shuf_logreg = LogisticRegression(**logreg_params)
+
+# Initialize the RandomizedSearchCV for shuffled data
+shuf_random_search = RandomizedSearchCV(shuf_logreg, **random_search_params)
+
+# Prevent the convergence warning in sklearn
+with parallel_backend("multiprocessing"):
+    with warnings.catch_warnings():
+        warnings.filterwarnings(
+            "ignore", category=ConvergenceWarning, module="sklearn"
+        )
+        # Perform the random hyperparameter search
+        shuf_random_search.fit(X_train_shuf, y_train)
+
+
+# # Save models and model data
+
+# In[14]:
+
+
+data_suf = "log_reg_cp_fs_data_plate_4"
+
+# Save the models
+dump(random_search.best_estimator_, f"{models_path}/{data_suf}.joblib")
+dump(shuf_random_search.best_estimator_, f"{models_path}/log_reg_shuf_cp_fs_data_plate_4.joblib")
+
+# Save label encoder
+dump(le, f"{data_path}/label_encoder_{data_suf}.joblib")
+
+
+# ## Save data indices
+
+# In[15]:
+
+
+# Assign indices and name each of the splits
+X_train_shuf_idxdf = pd.DataFrame({"Metadata_split_name": "X_train_shuf"}, index=X_train_shuf.index)
+X_train_idxdf = pd.DataFrame({"Metadata_split_name": "X_train"}, index=X_train.index)
+y_train_idxdf = pd.DataFrame({"Metadata_split_name": "y_train"}, index=y_train.index)
+y_test_idxdf = pd.DataFrame({"Metadata_split_name": "y_test"}, index=y_test.index)
+X_test_idxdf = pd.DataFrame({"Metadata_split_name": "X_test"}, index=X_test.index)
+
+# Concatenate the splits
+data_split_indices = pd.concat([X_train_shuf_idxdf, X_train_idxdf, y_train_idxdf, y_test_idxdf, X_test_idxdf])
+
+# Save the splits to a tsv file
+data_split_indices.to_csv(f"{data_path}/data_split_indices_{data_suf}.tsv", sep="\t")
+
diff --git a/1.train_models/log_reg_plates_cp_fs_data/plate_4/plate_4_classify_genotype.ipynb b/1.train_models/log_reg_plates_cp_fs_data/plate_4/plate_4_classify_genotype.ipynb
new file mode 100644
index 0000000..d3dca30
--- /dev/null
+++ b/1.train_models/log_reg_plates_cp_fs_data/plate_4/plate_4_classify_genotype.ipynb
@@ -0,0 +1,575 @@
+{
+    "cells": [
+        {
+            "cell_type": "markdown",
+            "metadata": {
+                "jukit_cell_id": "RUaS7hws7w"
+            },
+            "source": [
+                "# Train a logistic regression to classify genotypes for plate 4"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 1,
+            "metadata": {
+                "execution": {
+                    "iopub.execute_input": "2023-08-17T16:46:33.640054Z",
+                    "iopub.status.busy": "2023-08-17T16:46:33.639955Z",
+                    "iopub.status.idle": "2023-08-17T16:46:34.017899Z",
+                    "shell.execute_reply": "2023-08-17T16:46:34.017500Z"
+                },
+                "jukit_cell_id": "Uldv3YbqHx"
+            },
+            "outputs": [],
+            "source": [
+                "import pathlib\n",
+                "import warnings\n",
+                "\n",
+                "import numpy as np\n",
+                "import pandas as pd\n",
+                "from joblib import dump\n",
+                "from scipy.stats import uniform\n",
+                "from sklearn.exceptions import ConvergenceWarning\n",
+                "from sklearn.linear_model import LogisticRegression\n",
+                "from sklearn.model_selection import (\n",
+                "    RandomizedSearchCV,\n",
+                "    StratifiedKFold,\n",
+                "    train_test_split,\n",
+                ")\n",
+                "from sklearn.preprocessing import LabelEncoder\n",
+                "from sklearn.utils import parallel_backend"
+            ]
+        },
+        {
+            "cell_type": "markdown",
+            "metadata": {
+                "jukit_cell_id": "pPalNPcUrw"
+            },
+            "source": [
+                "## Find the root of the git repo on the host system"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 2,
+            "metadata": {
+                "execution": {
+                    "iopub.execute_input": "2023-08-17T16:46:34.019971Z",
+                    "iopub.status.busy": "2023-08-17T16:46:34.019815Z",
+                    "iopub.status.idle": "2023-08-17T16:46:34.022807Z",
+                    "shell.execute_reply": "2023-08-17T16:46:34.022530Z"
+                },
+                "jukit_cell_id": "6bmUxXR0eb"
+            },
+            "outputs": [],
+            "source": [
+                "# Get the current working directory\n",
+                "cwd = pathlib.Path.cwd()\n",
+                "\n",
+                "if (cwd / \".git\").is_dir():\n",
+                "    root_dir = cwd\n",
+                "\n",
+                "else:\n",
+                "    root_dir = None\n",
+                "    for parent in cwd.parents:\n",
+                "        if (parent / \".git\").is_dir():\n",
+                "            root_dir = parent\n",
+                "            break\n",
+                "\n",
+                "# Check if a Git root directory was found\n",
+                "if root_dir is None:\n",
+                "    raise FileNotFoundError(\"No Git root directory found.\")"
+            ]
+        },
+        {
+            "cell_type": "markdown",
+            "metadata": {
+                "jukit_cell_id": "JBaRt3jExj"
+            },
+            "source": [
+                "## Define and create paths"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 3,
+            "metadata": {
+                "execution": {
+                    "iopub.execute_input": "2023-08-17T16:46:34.024421Z",
+                    "iopub.status.busy": "2023-08-17T16:46:34.024164Z",
+                    "iopub.status.idle": "2023-08-17T16:46:34.026483Z",
+                    "shell.execute_reply": "2023-08-17T16:46:34.026219Z"
+                },
+                "jukit_cell_id": "NVeszTxjt5"
+            },
+            "outputs": [],
+            "source": [
+                "# Input paths\n",
+                "plate_path = \"Plate_4_sc_norm_fs.parquet\"\n",
+                "plate_path = pathlib.Path(f\"{root_dir}/nf1_painting_repo/3.processing_features/data/feature_selected_data/{plate_path}\")\n",
+                "\n",
+                "# Output paths\n",
+                "models_path = pathlib.Path(\"trained_models\")\n",
+                "data_path = pathlib.Path(\"model_data\")\n",
+                "\n",
+                "# Create output paths if nonexistent\n",
+                "models_path.mkdir(parents=True, exist_ok=True)\n",
+                "data_path.mkdir(parents=True, exist_ok=True)"
+            ]
+        },
+        {
+            "cell_type": "markdown",
+            "metadata": {
+                "jukit_cell_id": "HDCCDvAbvX"
+            },
+            "source": [
+                "## Load the dataframe"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 4,
+            "metadata": {
+                "execution": {
+                    "iopub.execute_input": "2023-08-17T16:46:34.028051Z",
+                    "iopub.status.busy": "2023-08-17T16:46:34.027799Z",
+                    "iopub.status.idle": "2023-08-17T16:46:34.155147Z",
+                    "shell.execute_reply": "2023-08-17T16:46:34.154776Z"
+                },
+                "jukit_cell_id": "q2xQ1rmSbQ"
+            },
+            "outputs": [],
+            "source": [
+                "platedf = pd.read_parquet(plate_path)"
+            ]
+        },
+        {
+            "cell_type": "markdown",
+            "metadata": {
+                "jukit_cell_id": "XfgLhC8kvj"
+            },
+            "source": [
+                "## Define column names"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 5,
+            "metadata": {
+                "execution": {
+                    "iopub.execute_input": "2023-08-17T16:46:34.157148Z",
+                    "iopub.status.busy": "2023-08-17T16:46:34.156899Z",
+                    "iopub.status.idle": "2023-08-17T16:46:34.159366Z",
+                    "shell.execute_reply": "2023-08-17T16:46:34.159035Z"
+                },
+                "jukit_cell_id": "pwIe7C4Ax4"
+            },
+            "outputs": [],
+            "source": [
+                "well_column = \"Metadata_Well\"\n",
+                "gene_column = \"Metadata_genotype\"\n",
+                "concentration_column = \"Metadata_Concentration\""
+            ]
+        },
+        {
+            "cell_type": "markdown",
+            "metadata": {
+                "jukit_cell_id": "wgULt453GT"
+            },
+            "source": [
+                "# Process data"
+            ]
+        },
+        {
+            "cell_type": "markdown",
+            "metadata": {
+                "jukit_cell_id": "oktgCP29ar"
+            },
+            "source": [
+                "## Down-sample by genotype"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 6,
+            "metadata": {
+                "execution": {
+                    "iopub.execute_input": "2023-08-17T16:46:34.160788Z",
+                    "iopub.status.busy": "2023-08-17T16:46:34.160526Z",
+                    "iopub.status.idle": "2023-08-17T16:46:34.180111Z",
+                    "shell.execute_reply": "2023-08-17T16:46:34.179662Z"
+                },
+                "jukit_cell_id": "sGkl0bhWnv"
+            },
+            "outputs": [],
+            "source": [
+                "# Filter data where the siRNA construct concentration is zero\n",
+                "platedf = platedf[platedf[concentration_column] == 0]\n",
+                "\n",
+                "min_gene = platedf[gene_column].value_counts().min()\n",
+                "platedf = platedf.groupby(gene_column, group_keys=False).apply(lambda x: x.sample(n=min_gene, random_state=0))"
+            ]
+        },
+        {
+            "cell_type": "markdown",
+            "metadata": {
+                "jukit_cell_id": "W1pE36XauH"
+            },
+            "source": [
+                "## Encode genotypes"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 7,
+            "metadata": {
+                "execution": {
+                    "iopub.execute_input": "2023-08-17T16:46:34.181968Z",
+                    "iopub.status.busy": "2023-08-17T16:46:34.181718Z",
+                    "iopub.status.idle": "2023-08-17T16:46:34.187517Z",
+                    "shell.execute_reply": "2023-08-17T16:46:34.187199Z"
+                },
+                "jukit_cell_id": "qcMAUWzcSj"
+            },
+            "outputs": [],
+            "source": [
+                "# Encode classes\n",
+                "le = LabelEncoder()\n",
+                "featdf = platedf.copy()\n",
+                "featdf[gene_column] = le.fit_transform(featdf[gene_column])"
+            ]
+        },
+        {
+            "cell_type": "markdown",
+            "metadata": {
+                "jukit_cell_id": "nbEILT7wXY"
+            },
+            "source": [
+                "## Remove Metadata and encode labels"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 8,
+            "metadata": {
+                "execution": {
+                    "iopub.execute_input": "2023-08-17T16:46:34.189001Z",
+                    "iopub.status.busy": "2023-08-17T16:46:34.188784Z",
+                    "iopub.status.idle": "2023-08-17T16:46:34.193131Z",
+                    "shell.execute_reply": "2023-08-17T16:46:34.192708Z"
+                },
+                "jukit_cell_id": "kbCV2fS53j"
+            },
+            "outputs": [],
+            "source": [
+                "# Create dataframe without Metadata\n",
+                "feat_columns = [col for col in platedf.columns if \"Metadata\" not in col]\n",
+                "featdf = platedf[feat_columns]\n",
+                "\n",
+                "# Encode labels\n",
+                "platedf[gene_column] = le.transform(platedf[gene_column])"
+            ]
+        },
+        {
+            "cell_type": "markdown",
+            "metadata": {
+                "jukit_cell_id": "MfXHjGvcSp"
+            },
+            "source": [
+                "## Split the Data"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 9,
+            "metadata": {
+                "execution": {
+                    "iopub.execute_input": "2023-08-17T16:46:34.194450Z",
+                    "iopub.status.busy": "2023-08-17T16:46:34.194241Z",
+                    "iopub.status.idle": "2023-08-17T16:46:34.199940Z",
+                    "shell.execute_reply": "2023-08-17T16:46:34.199576Z"
+                },
+                "jukit_cell_id": "MHDxE0uhWH"
+            },
+            "outputs": [],
+            "source": [
+                "test_frac = 0.2\n",
+                "val_frac = 0.15\n",
+                "\n",
+                "X_train, X_test, y_train, y_test = train_test_split(featdf, platedf[gene_column], test_size = test_frac, random_state=0, shuffle=True)"
+            ]
+        },
+        {
+            "cell_type": "markdown",
+            "metadata": {
+                "jukit_cell_id": "3pqmtkoWvR"
+            },
+            "source": [
+                "## Shuffle the training data for the shuffled model"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 10,
+            "metadata": {
+                "execution": {
+                    "iopub.execute_input": "2023-08-17T16:46:34.201234Z",
+                    "iopub.status.busy": "2023-08-17T16:46:34.200985Z",
+                    "iopub.status.idle": "2023-08-17T16:46:34.315457Z",
+                    "shell.execute_reply": "2023-08-17T16:46:34.314938Z"
+                },
+                "jukit_cell_id": "EoWGvinowW"
+            },
+            "outputs": [],
+            "source": [
+                "X_train_shuf = X_train.copy()\n",
+                "\n",
+                "rng = np.random.default_rng(0)\n",
+                "\n",
+                "for column in X_train_shuf.columns:\n",
+                "    X_train_shuf[column] = rng.permutation(X_train_shuf[column])"
+            ]
+        },
+        {
+            "cell_type": "markdown",
+            "metadata": {
+                "jukit_cell_id": "kPw9YcKK2H"
+            },
+            "source": [
+                "# Train Models"
+            ]
+        },
+        {
+            "cell_type": "markdown",
+            "metadata": {
+                "jukit_cell_id": "U6eyLl0ZPH"
+            },
+            "source": [
+                "## Define model variables"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 11,
+            "metadata": {
+                "execution": {
+                    "iopub.execute_input": "2023-08-17T16:46:34.317478Z",
+                    "iopub.status.busy": "2023-08-17T16:46:34.317339Z",
+                    "iopub.status.idle": "2023-08-17T16:46:34.321051Z",
+                    "shell.execute_reply": "2023-08-17T16:46:34.320680Z"
+                },
+                "jukit_cell_id": "4E094VqTVl"
+            },
+            "outputs": [],
+            "source": [
+                "# Define the hyperparameter search space\n",
+                "param_dist = {\n",
+                "    'C': uniform(loc=0.5, scale=1.5),\n",
+                "    \"l1_ratio\": uniform(loc=0, scale=1),\n",
+                "}\n",
+                "\n",
+                "# Define stratification method\n",
+                "strat_obj = StratifiedKFold(n_splits=5, shuffle=True, random_state=0)\n",
+                "\n",
+                "# Create a Logistic Regression model\n",
+                "logreg_params = {\n",
+                "    \"max_iter\": 1000,\n",
+                "    \"multi_class\": \"ovr\",\n",
+                "    \"penalty\": 'elasticnet',\n",
+                "    \"solver\": 'saga'\n",
+                "}\n",
+                "\n",
+                "# Initialize the RandomizedSearchCV\n",
+                "random_search_params = {\n",
+                "    \"param_distributions\": param_dist,\n",
+                "    \"scoring\": \"precision\",\n",
+                "    \"n_iter\": 100,\n",
+                "    \"cv\": strat_obj,\n",
+                "    \"random_state\": 0,\n",
+                "    \"n_jobs\": -1,\n",
+                "}"
+            ]
+        },
+        {
+            "cell_type": "markdown",
+            "metadata": {
+                "jukit_cell_id": "mDLhwaTQV8"
+            },
+            "source": [
+                "## Train the unshuffled model"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 12,
+            "metadata": {
+                "execution": {
+                    "iopub.execute_input": "2023-08-17T16:46:34.322867Z",
+                    "iopub.status.busy": "2023-08-17T16:46:34.322625Z",
+                    "iopub.status.idle": "2023-08-17T16:53:19.476298Z",
+                    "shell.execute_reply": "2023-08-17T16:53:19.475891Z"
+                },
+                "jukit_cell_id": "YY8qaxm1l1"
+            },
+            "outputs": [],
+            "source": [
+                "logreg = LogisticRegression(**logreg_params)\n",
+                "\n",
+                "# Initialize the RandomizedSearchCV\n",
+                "random_search = RandomizedSearchCV(logreg, **random_search_params)\n",
+                "\n",
+                "# Prevent the convergence warning in sklearn\n",
+                "with parallel_backend(\"multiprocessing\"):\n",
+                "    with warnings.catch_warnings():\n",
+                "        warnings.filterwarnings(\n",
+                "            \"ignore\", category=ConvergenceWarning, module=\"sklearn\"\n",
+                "        )\n",
+                "        # Perform the random hyperparameter search\n",
+                "        random_search.fit(X_train, y_train)"
+            ]
+        },
+        {
+            "cell_type": "markdown",
+            "metadata": {
+                "jukit_cell_id": "Olcix57UR4"
+            },
+            "source": [
+                "## Train the shuffled model"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 13,
+            "metadata": {
+                "execution": {
+                    "iopub.execute_input": "2023-08-17T16:53:19.478510Z",
+                    "iopub.status.busy": "2023-08-17T16:53:19.478352Z",
+                    "iopub.status.idle": "2023-08-17T16:59:48.318350Z",
+                    "shell.execute_reply": "2023-08-17T16:59:48.317710Z"
+                },
+                "jukit_cell_id": "HoOPZ90KFZ"
+            },
+            "outputs": [],
+            "source": [
+                "# Create a Logistic Regression model for shuffled data\n",
+                "shuf_logreg = LogisticRegression(**logreg_params)\n",
+                "\n",
+                "# Initialize the RandomizedSearchCV for shuffled data\n",
+                "shuf_random_search = RandomizedSearchCV(shuf_logreg, **random_search_params)\n",
+                "\n",
+                "# Prevent the convergence warning in sklearn\n",
+                "with parallel_backend(\"multiprocessing\"):\n",
+                "    with warnings.catch_warnings():\n",
+                "        warnings.filterwarnings(\n",
+                "            \"ignore\", category=ConvergenceWarning, module=\"sklearn\"\n",
+                "        )\n",
+                "        # Perform the random hyperparameter search\n",
+                "        shuf_random_search.fit(X_train_shuf, y_train)"
+            ]
+        },
+        {
+            "cell_type": "markdown",
+            "metadata": {
+                "jukit_cell_id": "oCendLQHaN"
+            },
+            "source": [
+                "# Save models and model data"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 14,
+            "metadata": {
+                "execution": {
+                    "iopub.execute_input": "2023-08-17T16:59:48.321003Z",
+                    "iopub.status.busy": "2023-08-17T16:59:48.320788Z",
+                    "iopub.status.idle": "2023-08-17T16:59:48.328672Z",
+                    "shell.execute_reply": "2023-08-17T16:59:48.328422Z"
+                },
+                "jukit_cell_id": "XmQTfarxJe"
+            },
+            "outputs": [
+                {
+                    "data": {
+                        "text/plain": [
+                            "['model_data/label_encoder_log_reg_cp_fs_data_plate_4.joblib']"
+                        ]
+                    },
+                    "execution_count": 14,
+                    "metadata": {},
+                    "output_type": "execute_result"
+                }
+            ],
+            "source": [
+                "data_suf = \"log_reg_cp_fs_data_plate_4\"\n",
+                "\n",
+                "# Save the models\n",
+                "dump(random_search.best_estimator_, f\"{models_path}/{data_suf}.joblib\")\n",
+                "dump(shuf_random_search.best_estimator_, f\"{models_path}/log_reg_shuf_cp_fs_data_plate_4.joblib\")\n",
+                "\n",
+                "# Save label encoder\n",
+                "dump(le, f\"{data_path}/label_encoder_{data_suf}.joblib\")"
+            ]
+        },
+        {
+            "cell_type": "markdown",
+            "metadata": {
+                "jukit_cell_id": "XKO1PYhtSW"
+            },
+            "source": [
+                "## Save data indices"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 15,
+            "metadata": {
+                "execution": {
+                    "iopub.execute_input": "2023-08-17T16:59:48.358203Z",
+                    "iopub.status.busy": "2023-08-17T16:59:48.358037Z",
+                    "iopub.status.idle": "2023-08-17T16:59:48.368806Z",
+                    "shell.execute_reply": "2023-08-17T16:59:48.368428Z"
+                },
+                "jukit_cell_id": "KRaXZbEIzO"
+            },
+            "outputs": [],
+            "source": [
+                "# Assign indices and name each of the splits\n",
+                "X_train_shuf_idxdf = pd.DataFrame({\"Metadata_split_name\": \"X_train_shuf\"}, index=X_train_shuf.index)\n",
+                "X_train_idxdf = pd.DataFrame({\"Metadata_split_name\": \"X_train\"}, index=X_train.index)\n",
+                "y_train_idxdf = pd.DataFrame({\"Metadata_split_name\": \"y_train\"}, index=y_train.index)\n",
+                "y_test_idxdf = pd.DataFrame({\"Metadata_split_name\": \"y_test\"}, index=y_test.index)\n",
+                "X_test_idxdf = pd.DataFrame({\"Metadata_split_name\": \"X_test\"}, index=X_test.index)\n",
+                "\n",
+                "# Concatenate the splits\n",
+                "data_split_indices = pd.concat([X_train_shuf_idxdf, X_train_idxdf, y_train_idxdf, y_test_idxdf, X_test_idxdf])\n",
+                "\n",
+                "# Save the splits to a tsv file\n",
+                "data_split_indices.to_csv(f\"{data_path}/data_split_indices_{data_suf}.tsv\", sep=\"\\t\")"
+            ]
+        }
+    ],
+    "metadata": {
+        "anaconda-cloud": {},
+        "kernelspec": {
+            "display_name": "Python 3 (ipykernel)",
+            "language": "python",
+            "name": "python3"
+        },
+        "language_info": {
+            "codemirror_mode": {
+                "name": "ipython",
+                "version": 3
+            },
+            "file_extension": ".py",
+            "mimetype": "text/x-python",
+            "name": "python",
+            "nbconvert_exporter": "python",
+            "pygments_lexer": "ipython3",
+            "version": "3.9.17"
+        }
+    },
+    "nbformat": 4,
+    "nbformat_minor": 4
+}

From 4a7274bfbc30e5f3b87ff3af17a1181908716221 Mon Sep 17 00:00:00 2001
From: Cameron Mattson <camo@oak.ucdenver.pvt>
Date: Fri, 1 Sep 2023 07:30:12 -0600
Subject: [PATCH 2/3] Added the trained models and the data splits

---
 ...lit_indices_log_reg_cp_fs_data_plate_4.tsv | 4688 +++++++++++++++++
 ..._encoder_log_reg_cp_fs_data_plate_4.joblib |  Bin 0 -> 532 bytes
 .../log_reg_cp_fs_data_plate_4.joblib         |  Bin 0 -> 70879 bytes
 .../log_reg_shuf_cp_fs_data_plate_4.joblib    |  Bin 0 -> 70879 bytes
 4 files changed, 4688 insertions(+)
 create mode 100644 1.train_models/log_reg_plates_cp_fs_data/plate_4/model_data/data_split_indices_log_reg_cp_fs_data_plate_4.tsv
 create mode 100644 1.train_models/log_reg_plates_cp_fs_data/plate_4/model_data/label_encoder_log_reg_cp_fs_data_plate_4.joblib
 create mode 100644 1.train_models/log_reg_plates_cp_fs_data/plate_4/trained_models/log_reg_cp_fs_data_plate_4.joblib
 create mode 100644 1.train_models/log_reg_plates_cp_fs_data/plate_4/trained_models/log_reg_shuf_cp_fs_data_plate_4.joblib

diff --git a/1.train_models/log_reg_plates_cp_fs_data/plate_4/model_data/data_split_indices_log_reg_cp_fs_data_plate_4.tsv b/1.train_models/log_reg_plates_cp_fs_data/plate_4/model_data/data_split_indices_log_reg_cp_fs_data_plate_4.tsv
new file mode 100644
index 0000000..d36837c
--- /dev/null
+++ b/1.train_models/log_reg_plates_cp_fs_data/plate_4/model_data/data_split_indices_log_reg_cp_fs_data_plate_4.tsv
@@ -0,0 +1,4688 @@
+	Metadata_split_name
+1591	X_train_shuf
+2117	X_train_shuf
+1791	X_train_shuf
+1220	X_train_shuf
+6079	X_train_shuf
+1526	X_train_shuf
+2946	X_train_shuf
+413	X_train_shuf
+7477	X_train_shuf
+2577	X_train_shuf
+1180	X_train_shuf
+2914	X_train_shuf
+7423	X_train_shuf
+7403	X_train_shuf
+1852	X_train_shuf
+2213	X_train_shuf
+49	X_train_shuf
+3279	X_train_shuf
+2173	X_train_shuf
+6066	X_train_shuf
+768	X_train_shuf
+79	X_train_shuf
+3199	X_train_shuf
+2141	X_train_shuf
+2917	X_train_shuf
+2981	X_train_shuf
+3292	X_train_shuf
+1251	X_train_shuf
+394	X_train_shuf
+2234	X_train_shuf
+4533	X_train_shuf
+5985	X_train_shuf
+3304	X_train_shuf
+3225	X_train_shuf
+2091	X_train_shuf
+3297	X_train_shuf
+1205	X_train_shuf
+2965	X_train_shuf
+355	X_train_shuf
+93	X_train_shuf
+2609	X_train_shuf
+404	X_train_shuf
+4570	X_train_shuf
+2551	X_train_shuf
+1169	X_train_shuf
+7420	X_train_shuf
+2076	X_train_shuf
+375	X_train_shuf
+7428	X_train_shuf
+1509	X_train_shuf
+3321	X_train_shuf
+440	X_train_shuf
+1564	X_train_shuf
+1226	X_train_shuf
+1861	X_train_shuf
+3280	X_train_shuf
+2944	X_train_shuf
+2130	X_train_shuf
+6039	X_train_shuf
+1130	X_train_shuf
+2614	X_train_shuf
+3315	X_train_shuf
+1837	X_train_shuf
+2918	X_train_shuf
+438	X_train_shuf
+20	X_train_shuf
+2165	X_train_shuf
+1586	X_train_shuf
+6034	X_train_shuf
+456	X_train_shuf
+1855	X_train_shuf
+396	X_train_shuf
+4600	X_train_shuf
+3223	X_train_shuf
+354	X_train_shuf
+3211	X_train_shuf
+2915	X_train_shuf
+108	X_train_shuf
+2973	X_train_shuf
+831	X_train_shuf
+408	X_train_shuf
+7446	X_train_shuf
+2553	X_train_shuf
+1545	X_train_shuf
+4605	X_train_shuf
+7479	X_train_shuf
+3306	X_train_shuf
+4599	X_train_shuf
+1215	X_train_shuf
+1496	X_train_shuf
+2233	X_train_shuf
+426	X_train_shuf
+1067	X_train_shuf
+465	X_train_shuf
+1272	X_train_shuf
+1871	X_train_shuf
+1174	X_train_shuf
+6041	X_train_shuf
+771	X_train_shuf
+7492	X_train_shuf
+4643	X_train_shuf
+1099	X_train_shuf
+1115	X_train_shuf
+4566	X_train_shuf
+2226	X_train_shuf
+3219	X_train_shuf
+7471	X_train_shuf
+9	X_train_shuf
+1061	X_train_shuf
+69	X_train_shuf
+2241	X_train_shuf
+2933	X_train_shuf
+2115	X_train_shuf
+1155	X_train_shuf
+2223	X_train_shuf
+3201	X_train_shuf
+2542	X_train_shuf
+2209	X_train_shuf
+6078	X_train_shuf
+4649	X_train_shuf
+445	X_train_shuf
+1570	X_train_shuf
+1582	X_train_shuf
+7394	X_train_shuf
+1803	X_train_shuf
+4608	X_train_shuf
+59	X_train_shuf
+3282	X_train_shuf
+6003	X_train_shuf
+1164	X_train_shuf
+4526	X_train_shuf
+1549	X_train_shuf
+1279	X_train_shuf
+4522	X_train_shuf
+7430	X_train_shuf
+2218	X_train_shuf
+2911	X_train_shuf
+1581	X_train_shuf
+1495	X_train_shuf
+1494	X_train_shuf
+1116	X_train_shuf
+434	X_train_shuf
+1269	X_train_shuf
+7473	X_train_shuf
+783	X_train_shuf
+1537	X_train_shuf
+7496	X_train_shuf
+5988	X_train_shuf
+1136	X_train_shuf
+1066	X_train_shuf
+70	X_train_shuf
+2902	X_train_shuf
+403	X_train_shuf
+2583	X_train_shuf
+2216	X_train_shuf
+45	X_train_shuf
+2201	X_train_shuf
+1890	X_train_shuf
+2238	X_train_shuf
+360	X_train_shuf
+96	X_train_shuf
+727	X_train_shuf
+1571	X_train_shuf
+3311	X_train_shuf
+2174	X_train_shuf
+3302	X_train_shuf
+2903	X_train_shuf
+2203	X_train_shuf
+3194	X_train_shuf
+778	X_train_shuf
+7392	X_train_shuf
+751	X_train_shuf
+3222	X_train_shuf
+6084	X_train_shuf
+2200	X_train_shuf
+2143	X_train_shuf
+4597	X_train_shuf
+2086	X_train_shuf
+1555	X_train_shuf
+2974	X_train_shuf
+6075	X_train_shuf
+7464	X_train_shuf
+1183	X_train_shuf
+467	X_train_shuf
+780	X_train_shuf
+6098	X_train_shuf
+1513	X_train_shuf
+1249	X_train_shuf
+2983	X_train_shuf
+2967	X_train_shuf
+4639	X_train_shuf
+471	X_train_shuf
+2558	X_train_shuf
+1597	X_train_shuf
+826	X_train_shuf
+3227	X_train_shuf
+3296	X_train_shuf
+2966	X_train_shuf
+97	X_train_shuf
+2190	X_train_shuf
+2217	X_train_shuf
+4585	X_train_shuf
+1145	X_train_shuf
+4603	X_train_shuf
+1096	X_train_shuf
+1889	X_train_shuf
+1497	X_train_shuf
+2924	X_train_shuf
+1888	X_train_shuf
+744	X_train_shuf
+111	X_train_shuf
+716	X_train_shuf
+1502	X_train_shuf
+3277	X_train_shuf
+1148	X_train_shuf
+1247	X_train_shuf
+1577	X_train_shuf
+2923	X_train_shuf
+3251	X_train_shuf
+14	X_train_shuf
+1224	X_train_shuf
+754	X_train_shuf
+2189	X_train_shuf
+769	X_train_shuf
+2150	X_train_shuf
+3291	X_train_shuf
+3259	X_train_shuf
+1554	X_train_shuf
+4546	X_train_shuf
+2144	X_train_shuf
+782	X_train_shuf
+2155	X_train_shuf
+2089	X_train_shuf
+7497	X_train_shuf
+2166	X_train_shuf
+3186	X_train_shuf
+1843	X_train_shuf
+6013	X_train_shuf
+450	X_train_shuf
+362	X_train_shuf
+730	X_train_shuf
+429	X_train_shuf
+1266	X_train_shuf
+7466	X_train_shuf
+2590	X_train_shuf
+1869	X_train_shuf
+1821	X_train_shuf
+1214	X_train_shuf
+6018	X_train_shuf
+370	X_train_shuf
+2116	X_train_shuf
+2579	X_train_shuf
+455	X_train_shuf
+3293	X_train_shuf
+40	X_train_shuf
+457	X_train_shuf
+1804	X_train_shuf
+4563	X_train_shuf
+2913	X_train_shuf
+6067	X_train_shuf
+2537	X_train_shuf
+1277	X_train_shuf
+1242	X_train_shuf
+4523	X_train_shuf
+2235	X_train_shuf
+3288	X_train_shuf
+7391	X_train_shuf
+1209	X_train_shuf
+2206	X_train_shuf
+1102	X_train_shuf
+7494	X_train_shuf
+814	X_train_shuf
+3256	X_train_shuf
+1278	X_train_shuf
+1206	X_train_shuf
+6049	X_train_shuf
+6063	X_train_shuf
+7443	X_train_shuf
+6044	X_train_shuf
+2100	X_train_shuf
+1260	X_train_shuf
+357	X_train_shuf
+364	X_train_shuf
+100	X_train_shuf
+2565	X_train_shuf
+4532	X_train_shuf
+81	X_train_shuf
+3192	X_train_shuf
+7389	X_train_shuf
+1540	X_train_shuf
+4564	X_train_shuf
+2123	X_train_shuf
+1584	X_train_shuf
+4582	X_train_shuf
+1508	X_train_shuf
+2889	X_train_shuf
+3318	X_train_shuf
+2941	X_train_shuf
+2940	X_train_shuf
+3197	X_train_shuf
+24	X_train_shuf
+6024	X_train_shuf
+763	X_train_shuf
+2585	X_train_shuf
+25	X_train_shuf
+1072	X_train_shuf
+1565	X_train_shuf
+3240	X_train_shuf
+793	X_train_shuf
+1165	X_train_shuf
+397	X_train_shuf
+1529	X_train_shuf
+2597	X_train_shuf
+1233	X_train_shuf
+4641	X_train_shuf
+2530	X_train_shuf
+2615	X_train_shuf
+7426	X_train_shuf
+1552	X_train_shuf
+1086	X_train_shuf
+65	X_train_shuf
+75	X_train_shuf
+4580	X_train_shuf
+3209	X_train_shuf
+7490	X_train_shuf
+1811	X_train_shuf
+2534	X_train_shuf
+3258	X_train_shuf
+1084	X_train_shuf
+2594	X_train_shuf
+4586	X_train_shuf
+1856	X_train_shuf
+18	X_train_shuf
+1500	X_train_shuf
+1857	X_train_shuf
+4602	X_train_shuf
+2112	X_train_shuf
+2177	X_train_shuf
+2605	X_train_shuf
+1575	X_train_shuf
+6052	X_train_shuf
+1507	X_train_shuf
+2984	X_train_shuf
+4593	X_train_shuf
+382	X_train_shuf
+2222	X_train_shuf
+353	X_train_shuf
+7404	X_train_shuf
+427	X_train_shuf
+2148	X_train_shuf
+7498	X_train_shuf
+4581	X_train_shuf
+2240	X_train_shuf
+1884	X_train_shuf
+1106	X_train_shuf
+4601	X_train_shuf
+2197	X_train_shuf
+4534	X_train_shuf
+2567	X_train_shuf
+7388	X_train_shuf
+717	X_train_shuf
+5984	X_train_shuf
+804	X_train_shuf
+5992	X_train_shuf
+446	X_train_shuf
+3205	X_train_shuf
+1602	X_train_shuf
+777	X_train_shuf
+6088	X_train_shuf
+2170	X_train_shuf
+1530	X_train_shuf
+2242	X_train_shuf
+2942	X_train_shuf
+4631	X_train_shuf
+3284	X_train_shuf
+3230	X_train_shuf
+1227	X_train_shuf
+359	X_train_shuf
+4541	X_train_shuf
+414	X_train_shuf
+4632	X_train_shuf
+3266	X_train_shuf
+1808	X_train_shuf
+759	X_train_shuf
+7	X_train_shuf
+2593	X_train_shuf
+2232	X_train_shuf
+770	X_train_shuf
+3303	X_train_shuf
+1139	X_train_shuf
+6056	X_train_shuf
+2236	X_train_shuf
+6028	X_train_shuf
+1280	X_train_shuf
+789	X_train_shuf
+63	X_train_shuf
+1868	X_train_shuf
+1504	X_train_shuf
+34	X_train_shuf
+358	X_train_shuf
+73	X_train_shuf
+5	X_train_shuf
+1542	X_train_shuf
+4615	X_train_shuf
+50	X_train_shuf
+417	X_train_shuf
+1189	X_train_shuf
+3246	X_train_shuf
+5999	X_train_shuf
+1190	X_train_shuf
+794	X_train_shuf
+2134	X_train_shuf
+787	X_train_shuf
+2096	X_train_shuf
+3224	X_train_shuf
+779	X_train_shuf
+4556	X_train_shuf
+723	X_train_shuf
+92	X_train_shuf
+2133	X_train_shuf
+761	X_train_shuf
+1824	X_train_shuf
+1207	X_train_shuf
+1054	X_train_shuf
+1574	X_train_shuf
+1144	X_train_shuf
+1514	X_train_shuf
+1534	X_train_shuf
+461	X_train_shuf
+7448	X_train_shuf
+76	X_train_shuf
+745	X_train_shuf
+1196	X_train_shuf
+464	X_train_shuf
+795	X_train_shuf
+1847	X_train_shuf
+113	X_train_shuf
+1881	X_train_shuf
+3238	X_train_shuf
+2180	X_train_shuf
+2109	X_train_shuf
+3200	X_train_shuf
+7467	X_train_shuf
+2570	X_train_shuf
+1580	X_train_shuf
+54	X_train_shuf
+2533	X_train_shuf
+2215	X_train_shuf
+4644	X_train_shuf
+2147	X_train_shuf
+2932	X_train_shuf
+1070	X_train_shuf
+2191	X_train_shuf
+3283	X_train_shuf
+4662	X_train_shuf
+753	X_train_shuf
+2135	X_train_shuf
+2550	X_train_shuf
+1876	X_train_shuf
+2943	X_train_shuf
+1118	X_train_shuf
+720	X_train_shuf
+4650	X_train_shuf
+2186	X_train_shuf
+6083	X_train_shuf
+1873	X_train_shuf
+1261	X_train_shuf
+1056	X_train_shuf
+2220	X_train_shuf
+454	X_train_shuf
+55	X_train_shuf
+1877	X_train_shuf
+1596	X_train_shuf
+1600	X_train_shuf
+3314	X_train_shuf
+2884	X_train_shuf
+37	X_train_shuf
+2118	X_train_shuf
+2958	X_train_shuf
+1566	X_train_shuf
+1051	X_train_shuf
+1263	X_train_shuf
+2183	X_train_shuf
+2113	X_train_shuf
+3320	X_train_shuf
+2928	X_train_shuf
+3249	X_train_shuf
+1870	X_train_shuf
+764	X_train_shuf
+1048	X_train_shuf
+6076	X_train_shuf
+749	X_train_shuf
+3264	X_train_shuf
+4550	X_train_shuf
+72	X_train_shuf
+7453	X_train_shuf
+1091	X_train_shuf
+1081	X_train_shuf
+1267	X_train_shuf
+819	X_train_shuf
+773	X_train_shuf
+3241	X_train_shuf
+399	X_train_shuf
+2564	X_train_shuf
+1860	X_train_shuf
+7416	X_train_shuf
+8	X_train_shuf
+3308	X_train_shuf
+3232	X_train_shuf
+1236	X_train_shuf
+2184	X_train_shuf
+2532	X_train_shuf
+6009	X_train_shuf
+374	X_train_shuf
+1516	X_train_shuf
+6055	X_train_shuf
+1838	X_train_shuf
+1831	X_train_shuf
+4524	X_train_shuf
+6033	X_train_shuf
+7412	X_train_shuf
+2131	X_train_shuf
+3203	X_train_shuf
+6020	X_train_shuf
+829	X_train_shuf
+719	X_train_shuf
+2205	X_train_shuf
+3286	X_train_shuf
+7465	X_train_shuf
+2080	X_train_shuf
+2181	X_train_shuf
+1134	X_train_shuf
+2895	X_train_shuf
+7440	X_train_shuf
+2977	X_train_shuf
+3226	X_train_shuf
+4538	X_train_shuf
+1171	X_train_shuf
+6	X_train_shuf
+1256	X_train_shuf
+2538	X_train_shuf
+4557	X_train_shuf
+428	X_train_shuf
+7495	X_train_shuf
+2589	X_train_shuf
+1104	X_train_shuf
+2954	X_train_shuf
+415	X_train_shuf
+4651	X_train_shuf
+1512	X_train_shuf
+32	X_train_shuf
+56	X_train_shuf
+746	X_train_shuf
+4575	X_train_shuf
+1192	X_train_shuf
+2900	X_train_shuf
+2888	X_train_shuf
+785	X_train_shuf
+737	X_train_shuf
+2580	X_train_shuf
+2602	X_train_shuf
+6031	X_train_shuf
+6085	X_train_shuf
+3281	X_train_shuf
+412	X_train_shuf
+4565	X_train_shuf
+2950	X_train_shuf
+4661	X_train_shuf
+1195	X_train_shuf
+2087	X_train_shuf
+42	X_train_shuf
+2122	X_train_shuf
+87	X_train_shuf
+1187	X_train_shuf
+1222	X_train_shuf
+2157	X_train_shuf
+3254	X_train_shuf
+1878	X_train_shuf
+2243	X_train_shuf
+2885	X_train_shuf
+2905	X_train_shuf
+1863	X_train_shuf
+102	X_train_shuf
+6071	X_train_shuf
+1221	X_train_shuf
+30	X_train_shuf
+1120	X_train_shuf
+6030	X_train_shuf
+4531	X_train_shuf
+1101	X_train_shuf
+1886	X_train_shuf
+1556	X_train_shuf
+1839	X_train_shuf
+3252	X_train_shuf
+2094	X_train_shuf
+392	X_train_shuf
+1585	X_train_shuf
+1576	X_train_shuf
+7408	X_train_shuf
+6064	X_train_shuf
+453	X_train_shuf
+101	X_train_shuf
+4548	X_train_shuf
+2921	X_train_shuf
+459	X_train_shuf
+7469	X_train_shuf
+4621	X_train_shuf
+4594	X_train_shuf
+765	X_train_shuf
+5994	X_train_shuf
+387	X_train_shuf
+373	X_train_shuf
+4587	X_train_shuf
+2948	X_train_shuf
+796	X_train_shuf
+1097	X_train_shuf
+820	X_train_shuf
+110	X_train_shuf
+729	X_train_shuf
+4543	X_train_shuf
+2557	X_train_shuf
+0	X_train_shuf
+6032	X_train_shuf
+3210	X_train_shuf
+1880	X_train_shuf
+2	X_train_shuf
+721	X_train_shuf
+2077	X_train_shuf
+51	X_train_shuf
+4654	X_train_shuf
+78	X_train_shuf
+7480	X_train_shuf
+1123	X_train_shuf
+715	X_train_shuf
+2576	X_train_shuf
+7432	X_train_shuf
+379	X_train_shuf
+1854	X_train_shuf
+1825	X_train_shuf
+2083	X_train_shuf
+3272	X_train_shuf
+1503	X_train_shuf
+2156	X_train_shuf
+7454	X_train_shuf
+2081	X_train_shuf
+1090	X_train_shuf
+4653	X_train_shuf
+828	X_train_shuf
+4607	X_train_shuf
+1832	X_train_shuf
+1593	X_train_shuf
+47	X_train_shuf
+1149	X_train_shuf
+473	X_train_shuf
+1203	X_train_shuf
+1188	X_train_shuf
+4642	X_train_shuf
+3244	X_train_shuf
+6045	X_train_shuf
+1270	X_train_shuf
+470	X_train_shuf
+728	X_train_shuf
+2596	X_train_shuf
+1528	X_train_shuf
+1064	X_train_shuf
+6014	X_train_shuf
+3295	X_train_shuf
+106	X_train_shuf
+4555	X_train_shuf
+2207	X_train_shuf
+3313	X_train_shuf
+1194	X_train_shuf
+3307	X_train_shuf
+4604	X_train_shuf
+1095	X_train_shuf
+1157	X_train_shuf
+1225	X_train_shuf
+7397	X_train_shuf
+4576	X_train_shuf
+1181	X_train_shuf
+1797	X_train_shuf
+35	X_train_shuf
+786	X_train_shuf
+1281	X_train_shuf
+811	X_train_shuf
+4539	X_train_shuf
+1059	X_train_shuf
+7488	X_train_shuf
+2938	X_train_shuf
+4540	X_train_shuf
+4620	X_train_shuf
+1243	X_train_shuf
+1103	X_train_shuf
+77	X_train_shuf
+4559	X_train_shuf
+1176	X_train_shuf
+803	X_train_shuf
+1235	X_train_shuf
+1511	X_train_shuf
+2934	X_train_shuf
+7447	X_train_shuf
+1499	X_train_shuf
+6000	X_train_shuf
+6047	X_train_shuf
+422	X_train_shuf
+82	X_train_shuf
+2910	X_train_shuf
+5993	X_train_shuf
+2188	X_train_shuf
+4657	X_train_shuf
+367	X_train_shuf
+2185	X_train_shuf
+4551	X_train_shuf
+2214	X_train_shuf
+1078	X_train_shuf
+2985	X_train_shuf
+2239	X_train_shuf
+1058	X_train_shuf
+85	X_train_shuf
+2543	X_train_shuf
+2896	X_train_shuf
+6004	X_train_shuf
+2192	X_train_shuf
+406	X_train_shuf
+2129	X_train_shuf
+2149	X_train_shuf
+1589	X_train_shuf
+400	X_train_shuf
+2931	X_train_shuf
+1114	X_train_shuf
+781	X_train_shuf
+2569	X_train_shuf
+1212	X_train_shuf
+6057	X_train_shuf
+2890	X_train_shuf
+3193	X_train_shuf
+4647	X_train_shuf
+1807	X_train_shuf
+4592	X_train_shuf
+1801	X_train_shuf
+3228	X_train_shuf
+775	X_train_shuf
+2164	X_train_shuf
+1816	X_train_shuf
+2541	X_train_shuf
+2600	X_train_shuf
+7396	X_train_shuf
+419	X_train_shuf
+68	X_train_shuf
+2608	X_train_shuf
+7500	X_train_shuf
+1879	X_train_shuf
+755	X_train_shuf
+1168	X_train_shuf
+3269	X_train_shuf
+7499	X_train_shuf
+6017	X_train_shuf
+1795	X_train_shuf
+2916	X_train_shuf
+6012	X_train_shuf
+6016	X_train_shuf
+1232	X_train_shuf
+368	X_train_shuf
+5997	X_train_shuf
+2936	X_train_shuf
+2160	X_train_shuf
+2892	X_train_shuf
+758	X_train_shuf
+1538	X_train_shuf
+7460	X_train_shuf
+2607	X_train_shuf
+11	X_train_shuf
+4598	X_train_shuf
+88	X_train_shuf
+2616	X_train_shuf
+23	X_train_shuf
+1578	X_train_shuf
+418	X_train_shuf
+1844	X_train_shuf
+1173	X_train_shuf
+743	X_train_shuf
+1809	X_train_shuf
+2572	X_train_shuf
+2960	X_train_shuf
+38	X_train_shuf
+1517	X_train_shuf
+4588	X_train_shuf
+4622	X_train_shuf
+1557	X_train_shuf
+3322	X_train_shuf
+6026	X_train_shuf
+1119	X_train_shuf
+6010	X_train_shuf
+2224	X_train_shuf
+2176	X_train_shuf
+53	X_train_shuf
+1100	X_train_shuf
+351	X_train_shuf
+740	X_train_shuf
+1865	X_train_shuf
+36	X_train_shuf
+1828	X_train_shuf
+4629	X_train_shuf
+3274	X_train_shuf
+6095	X_train_shuf
+825	X_train_shuf
+6040	X_train_shuf
+1806	X_train_shuf
+1135	X_train_shuf
+90	X_train_shuf
+1071	X_train_shuf
+6015	X_train_shuf
+6082	X_train_shuf
+389	X_train_shuf
+365	X_train_shuf
+2961	X_train_shuf
+3188	X_train_shuf
+1282	X_train_shuf
+1204	X_train_shuf
+3271	X_train_shuf
+378	X_train_shuf
+7436	X_train_shuf
+3267	X_train_shuf
+6048	X_train_shuf
+6001	X_train_shuf
+1887	X_train_shuf
+1601	X_train_shuf
+3218	X_train_shuf
+1083	X_train_shuf
+1245	X_train_shuf
+7445	X_train_shuf
+3260	X_train_shuf
+7470	X_train_shuf
+6069	X_train_shuf
+1073	X_train_shuf
+4549	X_train_shuf
+2230	X_train_shuf
+4609	X_train_shuf
+10	X_train_shuf
+1077	X_train_shuf
+1848	X_train_shuf
+4630	X_train_shuf
+2969	X_train_shuf
+2079	X_train_shuf
+4645	X_train_shuf
+443	X_train_shuf
+2099	X_train_shuf
+1	X_train_shuf
+4561	X_train_shuf
+4	X_train_shuf
+91	X_train_shuf
+2145	X_train_shuf
+4562	X_train_shuf
+2546	X_train_shuf
+748	X_train_shuf
+2092	X_train_shuf
+7401	X_train_shuf
+6043	X_train_shuf
+2228	X_train_shuf
+1853	X_train_shuf
+2891	X_train_shuf
+1141	X_train_shuf
+4590	X_train_shuf
+386	X_train_shuf
+7481	X_train_shuf
+2599	X_train_shuf
+6019	X_train_shuf
+2104	X_train_shuf
+762	X_train_shuf
+1274	X_train_shuf
+421	X_train_shuf
+1213	X_train_shuf
+1544	X_train_shuf
+832	X_train_shuf
+3301	X_train_shuf
+436	X_train_shuf
+3278	X_train_shuf
+1894	X_train_shuf
+1063	X_train_shuf
+3285	X_train_shuf
+6093	X_train_shuf
+2582	X_train_shuf
+3191	X_train_shuf
+2573	X_train_shuf
+1833	X_train_shuf
+46	X_train_shuf
+6096	X_train_shuf
+2971	X_train_shuf
+2982	X_train_shuf
+2926	X_train_shuf
+383	X_train_shuf
+7421	X_train_shuf
+2975	X_train_shuf
+2120	X_train_shuf
+774	X_train_shuf
+6029	X_train_shuf
+1175	X_train_shuf
+747	X_train_shuf
+6070	X_train_shuf
+3265	X_train_shuf
+83	X_train_shuf
+757	X_train_shuf
+3255	X_train_shuf
+798	X_train_shuf
+1049	X_train_shuf
+1108	X_train_shuf
+3221	X_train_shuf
+2531	X_train_shuf
+809	X_train_shuf
+7452	X_train_shuf
+6053	X_train_shuf
+2161	X_train_shuf
+433	X_train_shuf
+7429	X_train_shuf
+17	X_train_shuf
+2210	X_train_shuf
+1229	X_train_shuf
+4625	X_train_shuf
+1872	X_train_shuf
+2612	X_train_shuf
+1820	X_train_shuf
+366	X_train_shuf
+4554	X_train_shuf
+1275	X_train_shuf
+1125	X_train_shuf
+1819	X_train_shuf
+2601	X_train_shuf
+3247	X_train_shuf
+1590	X_train_shuf
+3317	X_train_shuf
+1850	X_train_shuf
+1525	X_train_shuf
+2090	X_train_shuf
+750	X_train_shuf
+6086	X_train_shuf
+2111	X_train_shuf
+2907	X_train_shuf
+1053	X_train_shuf
+452	X_train_shuf
+356	X_train_shuf
+6062	X_train_shuf
+805	X_train_shuf
+1112	X_train_shuf
+4527	X_train_shuf
+28	X_train_shuf
+6042	X_train_shuf
+2535	X_train_shuf
+3206	X_train_shuf
+3298	X_train_shuf
+2906	X_train_shuf
+444	X_train_shuf
+4595	X_train_shuf
+391	X_train_shuf
+7450	X_train_shuf
+6074	X_train_shuf
+7414	X_train_shuf
+4652	X_train_shuf
+1862	X_train_shuf
+1799	X_train_shuf
+2549	X_train_shuf
+2212	X_train_shuf
+2925	X_train_shuf
+2110	X_train_shuf
+2221	X_train_shuf
+469	X_train_shuf
+3190	X_train_shuf
+6046	X_train_shuf
+792	X_train_shuf
+1240	X_train_shuf
+1533	X_train_shuf
+1548	X_train_shuf
+1122	X_train_shuf
+1062	X_train_shuf
+2955	X_train_shuf
+7449	X_train_shuf
+2951	X_train_shuf
+1599	X_train_shuf
+2584	X_train_shuf
+1138	X_train_shuf
+466	X_train_shuf
+821	X_train_shuf
+6058	X_train_shuf
+2978	X_train_shuf
+1265	X_train_shuf
+7422	X_train_shuf
+3276	X_train_shuf
+2132	X_train_shuf
+7405	X_train_shuf
+718	X_train_shuf
+752	X_train_shuf
+4636	X_train_shuf
+2935	X_train_shuf
+4529	X_train_shuf
+448	X_train_shuf
+58	X_train_shuf
+5991	X_train_shuf
+2121	X_train_shuf
+4567	X_train_shuf
+2883	X_train_shuf
+1201	X_train_shuf
+4521	X_train_shuf
+3300	X_train_shuf
+104	X_train_shuf
+1140	X_train_shuf
+2237	X_train_shuf
+3236	X_train_shuf
+742	X_train_shuf
+405	X_train_shuf
+2158	X_train_shuf
+99	X_train_shuf
+1075	X_train_shuf
+815	X_train_shuf
+3215	X_train_shuf
+1563	X_train_shuf
+6090	X_train_shuf
+2171	X_train_shuf
+2140	X_train_shuf
+5990	X_train_shuf
+1891	X_train_shuf
+6027	X_train_shuf
+441	X_train_shuf
+3257	X_train_shuf
+6101	X_train_shuf
+2919	X_train_shuf
+2162	X_train_shuf
+7398	X_train_shuf
+7390	X_train_shuf
+1253	X_train_shuf
+1262	X_train_shuf
+741	X_train_shuf
+1184	X_train_shuf
+3294	X_train_shuf
+2922	X_train_shuf
+1841	X_train_shuf
+2119	X_train_shuf
+799	X_train_shuf
+2908	X_train_shuf
+1246	X_train_shuf
+1132	X_train_shuf
+4655	X_train_shuf
+463	X_train_shuf
+2930	X_train_shuf
+1237	X_train_shuf
+2179	X_train_shuf
+2182	X_train_shuf
+2929	X_train_shuf
+1068	X_train_shuf
+833	X_train_shuf
+4663	X_train_shuf
+31	X_train_shuf
+2107	X_train_shuf
+6008	X_train_shuf
+2976	X_train_shuf
+7501	X_train_shuf
+6068	X_train_shuf
+7413	X_train_shuf
+2231	X_train_shuf
+384	X_train_shuf
+80	X_train_shuf
+1093	X_train_shuf
+2587	X_train_shuf
+2610	X_train_shuf
+1827	X_train_shuf
+1257	X_train_shuf
+1276	X_train_shuf
+4584	X_train_shuf
+7485	X_train_shuf
+1092	X_train_shuf
+1163	X_train_shuf
+2957	X_train_shuf
+4659	X_train_shuf
+802	X_train_shuf
+2545	X_train_shuf
+2106	X_train_shuf
+4573	X_train_shuf
+4617	X_train_shuf
+2595	X_train_shuf
+1170	X_train_shuf
+1079	X_train_shuf
+1248	X_train_shuf
+2598	X_train_shuf
+756	X_train_shuf
+7474	X_train_shuf
+1546	X_train_shuf
+2592	X_train_shuf
+1105	X_train_shuf
+1050	X_train_shuf
+2920	X_train_shuf
+95	X_train_shuf
+1283	X_train_shuf
+1573	X_train_shuf
+60	X_train_shuf
+48	X_train_shuf
+2963	X_train_shuf
+4658	X_train_shuf
+3195	X_train_shuf
+1851	X_train_shuf
+84	X_train_shuf
+2588	X_train_shuf
+4619	X_train_shuf
+381	X_train_shuf
+1521	X_train_shuf
+458	X_train_shuf
+402	X_train_shuf
+1842	X_train_shuf
+1592	X_train_shuf
+766	X_train_shuf
+2125	X_train_shuf
+4606	X_train_shuf
+385	X_train_shuf
+1815	X_train_shuf
+4634	X_train_shuf
+1813	X_train_shuf
+460	X_train_shuf
+7478	X_train_shuf
+4618	X_train_shuf
+1178	X_train_shuf
+1588	X_train_shuf
+3268	X_train_shuf
+6061	X_train_shuf
+1200	X_train_shuf
+739	X_train_shuf
+3214	X_train_shuf
+736	X_train_shuf
+6025	X_train_shuf
+2953	X_train_shuf
+1510	X_train_shuf
+2142	X_train_shuf
+2962	X_train_shuf
+6077	X_train_shuf
+1156	X_train_shuf
+3196	X_train_shuf
+7439	X_train_shuf
+1560	X_train_shuf
+827	X_train_shuf
+712	X_train_shuf
+425	X_train_shuf
+1211	X_train_shuf
+3316	X_train_shuf
+2199	X_train_shuf
+830	X_train_shuf
+1126	X_train_shuf
+2591	X_train_shuf
+2886	X_train_shuf
+6011	X_train_shuf
+4610	X_train_shuf
+6035	X_train_shuf
+2168	X_train_shuf
+2563	X_train_shuf
+1133	X_train_shuf
+3243	X_train_shuf
+6100	X_train_shuf
+1796	X_train_shuf
+1532	X_train_shuf
+2178	X_train_shuf
+3275	X_train_shuf
+1094	X_train_shuf
+1089	X_train_shuf
+2124	X_train_shuf
+2105	X_train_shuf
+1523	X_train_shuf
+2187	X_train_shuf
+1883	X_train_shuf
+4583	X_train_shuf
+1074	X_train_shuf
+1845	X_train_shuf
+1812	X_train_shuf
+1128	X_train_shuf
+2227	X_train_shuf
+732	X_train_shuf
+7402	X_train_shuf
+1567	X_train_shuf
+2947	X_train_shuf
+2968	X_train_shuf
+2108	X_train_shuf
+57	X_train_shuf
+4536	X_train_shuf
+6007	X_train_shuf
+2893	X_train_shuf
+4558	X_train_shuf
+4616	X_train_shuf
+1805	X_train_shuf
+1543	X_train_shuf
+725	X_train_shuf
+2138	X_train_shuf
+1166	X_train_shuf
+1088	X_train_shuf
+26	X_train_shuf
+4640	X_train_shuf
+5989	X_train_shuf
+1823	X_train_shuf
+1866	X_train_shuf
+2979	X_train_shuf
+424	X_train_shuf
+2225	X_train_shuf
+7461	X_train_shuf
+7431	X_train_shuf
+2552	X_train_shuf
+1518	X_train_shuf
+6065	X_train_shuf
+4560	X_train_shuf
+3229	X_train_shuf
+1153	X_train_shuf
+1498	X_train_shuf
+2959	X_train_shuf
+2562	X_train_shuf
+2101	X_train_shuf
+1536	X_train_shuf
+41	X_train_shuf
+767	X_train_shuf
+2085	X_train_shuf
+1864	X_train_shuf
+4574	X_train_shuf
+2204	X_train_shuf
+2103	X_train_shuf
+726	X_train_shuf
+363	X_train_shuf
+4547	X_train_shuf
+1234	X_train_shuf
+1052	X_train_shuf
+1558	X_train_shuf
+4596	X_train_shuf
+2559	X_train_shuf
+807	X_train_shuf
+7434	X_train_shuf
+3253	X_train_shuf
+1836	X_train_shuf
+1583	X_train_shuf
+4542	X_train_shuf
+2088	X_train_shuf
+371	X_train_shuf
+1182	X_train_shuf
+468	X_train_shuf
+738	X_train_shuf
+1228	X_train_shuf
+776	X_train_shuf
+1598	X_train_shuf
+1834	X_train_shuf
+1885	X_train_shuf
+2894	X_train_shuf
+1800	X_train_shuf
+1792	X_train_shuf
+16	X_train_shuf
+1152	X_train_shuf
+800	X_train_shuf
+4646	X_train_shuf
+15	X_train_shuf
+1259	X_train_shuf
+3289	X_train_shuf
+472	X_train_shuf
+1160	X_train_shuf
+2084	X_train_shuf
+4519	X_train_shuf
+3217	X_train_shuf
+3	X_train_shuf
+2202	X_train_shuf
+462	X_train_shuf
+430	X_train_shuf
+2169	X_train_shuf
+1197	X_train_shuf
+1159	X_train_shuf
+1255	X_train_shuf
+1150	X_train_shuf
+2937	X_train_shuf
+5996	X_train_shuf
+6036	X_train_shuf
+432	X_train_shuf
+7409	X_train_shuf
+112	X_train_shuf
+3187	X_train_shuf
+2195	X_train_shuf
+4589	X_train_shuf
+4624	X_train_shuf
+411	X_train_shuf
+1802	X_train_shuf
+2136	X_train_shuf
+107	X_train_shuf
+3305	X_train_shuf
+4552	X_train_shuf
+439	X_train_shuf
+6080	X_train_shuf
+7457	X_train_shuf
+2574	X_train_shuf
+722	X_train_shuf
+1143	X_train_shuf
+2539	X_train_shuf
+2127	X_train_shuf
+4591	X_train_shuf
+1569	X_train_shuf
+1501	X_train_shuf
+1798	X_train_shuf
+1553	X_train_shuf
+2956	X_train_shuf
+1859	X_train_shuf
+2128	X_train_shuf
+7400	X_train_shuf
+2153	X_train_shuf
+2219	X_train_shuf
+1146	X_train_shuf
+4660	X_train_shuf
+4623	X_train_shuf
+2581	X_train_shuf
+7444	X_train_shuf
+1142	X_train_shuf
+2568	X_train_shuf
+4613	X_train_shuf
+2571	X_train_shuf
+52	X_train_shuf
+7451	X_train_shuf
+2945	X_train_shuf
+3235	X_train_shuf
+1822	X_train_shuf
+7441	X_train_shuf
+788	X_train_shuf
+2163	X_train_shuf
+7437	X_train_shuf
+1057	X_train_shuf
+1519	X_train_shuf
+3202	X_train_shuf
+7459	X_train_shuf
+449	X_train_shuf
+7393	X_train_shuf
+3309	X_train_shuf
+1167	X_train_shuf
+86	X_train_shuf
+1506	X_train_shuf
+6060	X_train_shuf
+2154	X_train_shuf
+1551	X_train_shuf
+109	X_train_shuf
+7482	X_train_shuf
+410	X_train_shuf
+5987	X_train_shuf
+67	X_train_shuf
+4568	X_train_shuf
+1867	X_train_shuf
+376	X_train_shuf
+1076	X_train_shuf
+1055	X_train_shuf
+1591	X_train
+2117	X_train
+1791	X_train
+1220	X_train
+6079	X_train
+1526	X_train
+2946	X_train
+413	X_train
+7477	X_train
+2577	X_train
+1180	X_train
+2914	X_train
+7423	X_train
+7403	X_train
+1852	X_train
+2213	X_train
+49	X_train
+3279	X_train
+2173	X_train
+6066	X_train
+768	X_train
+79	X_train
+3199	X_train
+2141	X_train
+2917	X_train
+2981	X_train
+3292	X_train
+1251	X_train
+394	X_train
+2234	X_train
+4533	X_train
+5985	X_train
+3304	X_train
+3225	X_train
+2091	X_train
+3297	X_train
+1205	X_train
+2965	X_train
+355	X_train
+93	X_train
+2609	X_train
+404	X_train
+4570	X_train
+2551	X_train
+1169	X_train
+7420	X_train
+2076	X_train
+375	X_train
+7428	X_train
+1509	X_train
+3321	X_train
+440	X_train
+1564	X_train
+1226	X_train
+1861	X_train
+3280	X_train
+2944	X_train
+2130	X_train
+6039	X_train
+1130	X_train
+2614	X_train
+3315	X_train
+1837	X_train
+2918	X_train
+438	X_train
+20	X_train
+2165	X_train
+1586	X_train
+6034	X_train
+456	X_train
+1855	X_train
+396	X_train
+4600	X_train
+3223	X_train
+354	X_train
+3211	X_train
+2915	X_train
+108	X_train
+2973	X_train
+831	X_train
+408	X_train
+7446	X_train
+2553	X_train
+1545	X_train
+4605	X_train
+7479	X_train
+3306	X_train
+4599	X_train
+1215	X_train
+1496	X_train
+2233	X_train
+426	X_train
+1067	X_train
+465	X_train
+1272	X_train
+1871	X_train
+1174	X_train
+6041	X_train
+771	X_train
+7492	X_train
+4643	X_train
+1099	X_train
+1115	X_train
+4566	X_train
+2226	X_train
+3219	X_train
+7471	X_train
+9	X_train
+1061	X_train
+69	X_train
+2241	X_train
+2933	X_train
+2115	X_train
+1155	X_train
+2223	X_train
+3201	X_train
+2542	X_train
+2209	X_train
+6078	X_train
+4649	X_train
+445	X_train
+1570	X_train
+1582	X_train
+7394	X_train
+1803	X_train
+4608	X_train
+59	X_train
+3282	X_train
+6003	X_train
+1164	X_train
+4526	X_train
+1549	X_train
+1279	X_train
+4522	X_train
+7430	X_train
+2218	X_train
+2911	X_train
+1581	X_train
+1495	X_train
+1494	X_train
+1116	X_train
+434	X_train
+1269	X_train
+7473	X_train
+783	X_train
+1537	X_train
+7496	X_train
+5988	X_train
+1136	X_train
+1066	X_train
+70	X_train
+2902	X_train
+403	X_train
+2583	X_train
+2216	X_train
+45	X_train
+2201	X_train
+1890	X_train
+2238	X_train
+360	X_train
+96	X_train
+727	X_train
+1571	X_train
+3311	X_train
+2174	X_train
+3302	X_train
+2903	X_train
+2203	X_train
+3194	X_train
+778	X_train
+7392	X_train
+751	X_train
+3222	X_train
+6084	X_train
+2200	X_train
+2143	X_train
+4597	X_train
+2086	X_train
+1555	X_train
+2974	X_train
+6075	X_train
+7464	X_train
+1183	X_train
+467	X_train
+780	X_train
+6098	X_train
+1513	X_train
+1249	X_train
+2983	X_train
+2967	X_train
+4639	X_train
+471	X_train
+2558	X_train
+1597	X_train
+826	X_train
+3227	X_train
+3296	X_train
+2966	X_train
+97	X_train
+2190	X_train
+2217	X_train
+4585	X_train
+1145	X_train
+4603	X_train
+1096	X_train
+1889	X_train
+1497	X_train
+2924	X_train
+1888	X_train
+744	X_train
+111	X_train
+716	X_train
+1502	X_train
+3277	X_train
+1148	X_train
+1247	X_train
+1577	X_train
+2923	X_train
+3251	X_train
+14	X_train
+1224	X_train
+754	X_train
+2189	X_train
+769	X_train
+2150	X_train
+3291	X_train
+3259	X_train
+1554	X_train
+4546	X_train
+2144	X_train
+782	X_train
+2155	X_train
+2089	X_train
+7497	X_train
+2166	X_train
+3186	X_train
+1843	X_train
+6013	X_train
+450	X_train
+362	X_train
+730	X_train
+429	X_train
+1266	X_train
+7466	X_train
+2590	X_train
+1869	X_train
+1821	X_train
+1214	X_train
+6018	X_train
+370	X_train
+2116	X_train
+2579	X_train
+455	X_train
+3293	X_train
+40	X_train
+457	X_train
+1804	X_train
+4563	X_train
+2913	X_train
+6067	X_train
+2537	X_train
+1277	X_train
+1242	X_train
+4523	X_train
+2235	X_train
+3288	X_train
+7391	X_train
+1209	X_train
+2206	X_train
+1102	X_train
+7494	X_train
+814	X_train
+3256	X_train
+1278	X_train
+1206	X_train
+6049	X_train
+6063	X_train
+7443	X_train
+6044	X_train
+2100	X_train
+1260	X_train
+357	X_train
+364	X_train
+100	X_train
+2565	X_train
+4532	X_train
+81	X_train
+3192	X_train
+7389	X_train
+1540	X_train
+4564	X_train
+2123	X_train
+1584	X_train
+4582	X_train
+1508	X_train
+2889	X_train
+3318	X_train
+2941	X_train
+2940	X_train
+3197	X_train
+24	X_train
+6024	X_train
+763	X_train
+2585	X_train
+25	X_train
+1072	X_train
+1565	X_train
+3240	X_train
+793	X_train
+1165	X_train
+397	X_train
+1529	X_train
+2597	X_train
+1233	X_train
+4641	X_train
+2530	X_train
+2615	X_train
+7426	X_train
+1552	X_train
+1086	X_train
+65	X_train
+75	X_train
+4580	X_train
+3209	X_train
+7490	X_train
+1811	X_train
+2534	X_train
+3258	X_train
+1084	X_train
+2594	X_train
+4586	X_train
+1856	X_train
+18	X_train
+1500	X_train
+1857	X_train
+4602	X_train
+2112	X_train
+2177	X_train
+2605	X_train
+1575	X_train
+6052	X_train
+1507	X_train
+2984	X_train
+4593	X_train
+382	X_train
+2222	X_train
+353	X_train
+7404	X_train
+427	X_train
+2148	X_train
+7498	X_train
+4581	X_train
+2240	X_train
+1884	X_train
+1106	X_train
+4601	X_train
+2197	X_train
+4534	X_train
+2567	X_train
+7388	X_train
+717	X_train
+5984	X_train
+804	X_train
+5992	X_train
+446	X_train
+3205	X_train
+1602	X_train
+777	X_train
+6088	X_train
+2170	X_train
+1530	X_train
+2242	X_train
+2942	X_train
+4631	X_train
+3284	X_train
+3230	X_train
+1227	X_train
+359	X_train
+4541	X_train
+414	X_train
+4632	X_train
+3266	X_train
+1808	X_train
+759	X_train
+7	X_train
+2593	X_train
+2232	X_train
+770	X_train
+3303	X_train
+1139	X_train
+6056	X_train
+2236	X_train
+6028	X_train
+1280	X_train
+789	X_train
+63	X_train
+1868	X_train
+1504	X_train
+34	X_train
+358	X_train
+73	X_train
+5	X_train
+1542	X_train
+4615	X_train
+50	X_train
+417	X_train
+1189	X_train
+3246	X_train
+5999	X_train
+1190	X_train
+794	X_train
+2134	X_train
+787	X_train
+2096	X_train
+3224	X_train
+779	X_train
+4556	X_train
+723	X_train
+92	X_train
+2133	X_train
+761	X_train
+1824	X_train
+1207	X_train
+1054	X_train
+1574	X_train
+1144	X_train
+1514	X_train
+1534	X_train
+461	X_train
+7448	X_train
+76	X_train
+745	X_train
+1196	X_train
+464	X_train
+795	X_train
+1847	X_train
+113	X_train
+1881	X_train
+3238	X_train
+2180	X_train
+2109	X_train
+3200	X_train
+7467	X_train
+2570	X_train
+1580	X_train
+54	X_train
+2533	X_train
+2215	X_train
+4644	X_train
+2147	X_train
+2932	X_train
+1070	X_train
+2191	X_train
+3283	X_train
+4662	X_train
+753	X_train
+2135	X_train
+2550	X_train
+1876	X_train
+2943	X_train
+1118	X_train
+720	X_train
+4650	X_train
+2186	X_train
+6083	X_train
+1873	X_train
+1261	X_train
+1056	X_train
+2220	X_train
+454	X_train
+55	X_train
+1877	X_train
+1596	X_train
+1600	X_train
+3314	X_train
+2884	X_train
+37	X_train
+2118	X_train
+2958	X_train
+1566	X_train
+1051	X_train
+1263	X_train
+2183	X_train
+2113	X_train
+3320	X_train
+2928	X_train
+3249	X_train
+1870	X_train
+764	X_train
+1048	X_train
+6076	X_train
+749	X_train
+3264	X_train
+4550	X_train
+72	X_train
+7453	X_train
+1091	X_train
+1081	X_train
+1267	X_train
+819	X_train
+773	X_train
+3241	X_train
+399	X_train
+2564	X_train
+1860	X_train
+7416	X_train
+8	X_train
+3308	X_train
+3232	X_train
+1236	X_train
+2184	X_train
+2532	X_train
+6009	X_train
+374	X_train
+1516	X_train
+6055	X_train
+1838	X_train
+1831	X_train
+4524	X_train
+6033	X_train
+7412	X_train
+2131	X_train
+3203	X_train
+6020	X_train
+829	X_train
+719	X_train
+2205	X_train
+3286	X_train
+7465	X_train
+2080	X_train
+2181	X_train
+1134	X_train
+2895	X_train
+7440	X_train
+2977	X_train
+3226	X_train
+4538	X_train
+1171	X_train
+6	X_train
+1256	X_train
+2538	X_train
+4557	X_train
+428	X_train
+7495	X_train
+2589	X_train
+1104	X_train
+2954	X_train
+415	X_train
+4651	X_train
+1512	X_train
+32	X_train
+56	X_train
+746	X_train
+4575	X_train
+1192	X_train
+2900	X_train
+2888	X_train
+785	X_train
+737	X_train
+2580	X_train
+2602	X_train
+6031	X_train
+6085	X_train
+3281	X_train
+412	X_train
+4565	X_train
+2950	X_train
+4661	X_train
+1195	X_train
+2087	X_train
+42	X_train
+2122	X_train
+87	X_train
+1187	X_train
+1222	X_train
+2157	X_train
+3254	X_train
+1878	X_train
+2243	X_train
+2885	X_train
+2905	X_train
+1863	X_train
+102	X_train
+6071	X_train
+1221	X_train
+30	X_train
+1120	X_train
+6030	X_train
+4531	X_train
+1101	X_train
+1886	X_train
+1556	X_train
+1839	X_train
+3252	X_train
+2094	X_train
+392	X_train
+1585	X_train
+1576	X_train
+7408	X_train
+6064	X_train
+453	X_train
+101	X_train
+4548	X_train
+2921	X_train
+459	X_train
+7469	X_train
+4621	X_train
+4594	X_train
+765	X_train
+5994	X_train
+387	X_train
+373	X_train
+4587	X_train
+2948	X_train
+796	X_train
+1097	X_train
+820	X_train
+110	X_train
+729	X_train
+4543	X_train
+2557	X_train
+0	X_train
+6032	X_train
+3210	X_train
+1880	X_train
+2	X_train
+721	X_train
+2077	X_train
+51	X_train
+4654	X_train
+78	X_train
+7480	X_train
+1123	X_train
+715	X_train
+2576	X_train
+7432	X_train
+379	X_train
+1854	X_train
+1825	X_train
+2083	X_train
+3272	X_train
+1503	X_train
+2156	X_train
+7454	X_train
+2081	X_train
+1090	X_train
+4653	X_train
+828	X_train
+4607	X_train
+1832	X_train
+1593	X_train
+47	X_train
+1149	X_train
+473	X_train
+1203	X_train
+1188	X_train
+4642	X_train
+3244	X_train
+6045	X_train
+1270	X_train
+470	X_train
+728	X_train
+2596	X_train
+1528	X_train
+1064	X_train
+6014	X_train
+3295	X_train
+106	X_train
+4555	X_train
+2207	X_train
+3313	X_train
+1194	X_train
+3307	X_train
+4604	X_train
+1095	X_train
+1157	X_train
+1225	X_train
+7397	X_train
+4576	X_train
+1181	X_train
+1797	X_train
+35	X_train
+786	X_train
+1281	X_train
+811	X_train
+4539	X_train
+1059	X_train
+7488	X_train
+2938	X_train
+4540	X_train
+4620	X_train
+1243	X_train
+1103	X_train
+77	X_train
+4559	X_train
+1176	X_train
+803	X_train
+1235	X_train
+1511	X_train
+2934	X_train
+7447	X_train
+1499	X_train
+6000	X_train
+6047	X_train
+422	X_train
+82	X_train
+2910	X_train
+5993	X_train
+2188	X_train
+4657	X_train
+367	X_train
+2185	X_train
+4551	X_train
+2214	X_train
+1078	X_train
+2985	X_train
+2239	X_train
+1058	X_train
+85	X_train
+2543	X_train
+2896	X_train
+6004	X_train
+2192	X_train
+406	X_train
+2129	X_train
+2149	X_train
+1589	X_train
+400	X_train
+2931	X_train
+1114	X_train
+781	X_train
+2569	X_train
+1212	X_train
+6057	X_train
+2890	X_train
+3193	X_train
+4647	X_train
+1807	X_train
+4592	X_train
+1801	X_train
+3228	X_train
+775	X_train
+2164	X_train
+1816	X_train
+2541	X_train
+2600	X_train
+7396	X_train
+419	X_train
+68	X_train
+2608	X_train
+7500	X_train
+1879	X_train
+755	X_train
+1168	X_train
+3269	X_train
+7499	X_train
+6017	X_train
+1795	X_train
+2916	X_train
+6012	X_train
+6016	X_train
+1232	X_train
+368	X_train
+5997	X_train
+2936	X_train
+2160	X_train
+2892	X_train
+758	X_train
+1538	X_train
+7460	X_train
+2607	X_train
+11	X_train
+4598	X_train
+88	X_train
+2616	X_train
+23	X_train
+1578	X_train
+418	X_train
+1844	X_train
+1173	X_train
+743	X_train
+1809	X_train
+2572	X_train
+2960	X_train
+38	X_train
+1517	X_train
+4588	X_train
+4622	X_train
+1557	X_train
+3322	X_train
+6026	X_train
+1119	X_train
+6010	X_train
+2224	X_train
+2176	X_train
+53	X_train
+1100	X_train
+351	X_train
+740	X_train
+1865	X_train
+36	X_train
+1828	X_train
+4629	X_train
+3274	X_train
+6095	X_train
+825	X_train
+6040	X_train
+1806	X_train
+1135	X_train
+90	X_train
+1071	X_train
+6015	X_train
+6082	X_train
+389	X_train
+365	X_train
+2961	X_train
+3188	X_train
+1282	X_train
+1204	X_train
+3271	X_train
+378	X_train
+7436	X_train
+3267	X_train
+6048	X_train
+6001	X_train
+1887	X_train
+1601	X_train
+3218	X_train
+1083	X_train
+1245	X_train
+7445	X_train
+3260	X_train
+7470	X_train
+6069	X_train
+1073	X_train
+4549	X_train
+2230	X_train
+4609	X_train
+10	X_train
+1077	X_train
+1848	X_train
+4630	X_train
+2969	X_train
+2079	X_train
+4645	X_train
+443	X_train
+2099	X_train
+1	X_train
+4561	X_train
+4	X_train
+91	X_train
+2145	X_train
+4562	X_train
+2546	X_train
+748	X_train
+2092	X_train
+7401	X_train
+6043	X_train
+2228	X_train
+1853	X_train
+2891	X_train
+1141	X_train
+4590	X_train
+386	X_train
+7481	X_train
+2599	X_train
+6019	X_train
+2104	X_train
+762	X_train
+1274	X_train
+421	X_train
+1213	X_train
+1544	X_train
+832	X_train
+3301	X_train
+436	X_train
+3278	X_train
+1894	X_train
+1063	X_train
+3285	X_train
+6093	X_train
+2582	X_train
+3191	X_train
+2573	X_train
+1833	X_train
+46	X_train
+6096	X_train
+2971	X_train
+2982	X_train
+2926	X_train
+383	X_train
+7421	X_train
+2975	X_train
+2120	X_train
+774	X_train
+6029	X_train
+1175	X_train
+747	X_train
+6070	X_train
+3265	X_train
+83	X_train
+757	X_train
+3255	X_train
+798	X_train
+1049	X_train
+1108	X_train
+3221	X_train
+2531	X_train
+809	X_train
+7452	X_train
+6053	X_train
+2161	X_train
+433	X_train
+7429	X_train
+17	X_train
+2210	X_train
+1229	X_train
+4625	X_train
+1872	X_train
+2612	X_train
+1820	X_train
+366	X_train
+4554	X_train
+1275	X_train
+1125	X_train
+1819	X_train
+2601	X_train
+3247	X_train
+1590	X_train
+3317	X_train
+1850	X_train
+1525	X_train
+2090	X_train
+750	X_train
+6086	X_train
+2111	X_train
+2907	X_train
+1053	X_train
+452	X_train
+356	X_train
+6062	X_train
+805	X_train
+1112	X_train
+4527	X_train
+28	X_train
+6042	X_train
+2535	X_train
+3206	X_train
+3298	X_train
+2906	X_train
+444	X_train
+4595	X_train
+391	X_train
+7450	X_train
+6074	X_train
+7414	X_train
+4652	X_train
+1862	X_train
+1799	X_train
+2549	X_train
+2212	X_train
+2925	X_train
+2110	X_train
+2221	X_train
+469	X_train
+3190	X_train
+6046	X_train
+792	X_train
+1240	X_train
+1533	X_train
+1548	X_train
+1122	X_train
+1062	X_train
+2955	X_train
+7449	X_train
+2951	X_train
+1599	X_train
+2584	X_train
+1138	X_train
+466	X_train
+821	X_train
+6058	X_train
+2978	X_train
+1265	X_train
+7422	X_train
+3276	X_train
+2132	X_train
+7405	X_train
+718	X_train
+752	X_train
+4636	X_train
+2935	X_train
+4529	X_train
+448	X_train
+58	X_train
+5991	X_train
+2121	X_train
+4567	X_train
+2883	X_train
+1201	X_train
+4521	X_train
+3300	X_train
+104	X_train
+1140	X_train
+2237	X_train
+3236	X_train
+742	X_train
+405	X_train
+2158	X_train
+99	X_train
+1075	X_train
+815	X_train
+3215	X_train
+1563	X_train
+6090	X_train
+2171	X_train
+2140	X_train
+5990	X_train
+1891	X_train
+6027	X_train
+441	X_train
+3257	X_train
+6101	X_train
+2919	X_train
+2162	X_train
+7398	X_train
+7390	X_train
+1253	X_train
+1262	X_train
+741	X_train
+1184	X_train
+3294	X_train
+2922	X_train
+1841	X_train
+2119	X_train
+799	X_train
+2908	X_train
+1246	X_train
+1132	X_train
+4655	X_train
+463	X_train
+2930	X_train
+1237	X_train
+2179	X_train
+2182	X_train
+2929	X_train
+1068	X_train
+833	X_train
+4663	X_train
+31	X_train
+2107	X_train
+6008	X_train
+2976	X_train
+7501	X_train
+6068	X_train
+7413	X_train
+2231	X_train
+384	X_train
+80	X_train
+1093	X_train
+2587	X_train
+2610	X_train
+1827	X_train
+1257	X_train
+1276	X_train
+4584	X_train
+7485	X_train
+1092	X_train
+1163	X_train
+2957	X_train
+4659	X_train
+802	X_train
+2545	X_train
+2106	X_train
+4573	X_train
+4617	X_train
+2595	X_train
+1170	X_train
+1079	X_train
+1248	X_train
+2598	X_train
+756	X_train
+7474	X_train
+1546	X_train
+2592	X_train
+1105	X_train
+1050	X_train
+2920	X_train
+95	X_train
+1283	X_train
+1573	X_train
+60	X_train
+48	X_train
+2963	X_train
+4658	X_train
+3195	X_train
+1851	X_train
+84	X_train
+2588	X_train
+4619	X_train
+381	X_train
+1521	X_train
+458	X_train
+402	X_train
+1842	X_train
+1592	X_train
+766	X_train
+2125	X_train
+4606	X_train
+385	X_train
+1815	X_train
+4634	X_train
+1813	X_train
+460	X_train
+7478	X_train
+4618	X_train
+1178	X_train
+1588	X_train
+3268	X_train
+6061	X_train
+1200	X_train
+739	X_train
+3214	X_train
+736	X_train
+6025	X_train
+2953	X_train
+1510	X_train
+2142	X_train
+2962	X_train
+6077	X_train
+1156	X_train
+3196	X_train
+7439	X_train
+1560	X_train
+827	X_train
+712	X_train
+425	X_train
+1211	X_train
+3316	X_train
+2199	X_train
+830	X_train
+1126	X_train
+2591	X_train
+2886	X_train
+6011	X_train
+4610	X_train
+6035	X_train
+2168	X_train
+2563	X_train
+1133	X_train
+3243	X_train
+6100	X_train
+1796	X_train
+1532	X_train
+2178	X_train
+3275	X_train
+1094	X_train
+1089	X_train
+2124	X_train
+2105	X_train
+1523	X_train
+2187	X_train
+1883	X_train
+4583	X_train
+1074	X_train
+1845	X_train
+1812	X_train
+1128	X_train
+2227	X_train
+732	X_train
+7402	X_train
+1567	X_train
+2947	X_train
+2968	X_train
+2108	X_train
+57	X_train
+4536	X_train
+6007	X_train
+2893	X_train
+4558	X_train
+4616	X_train
+1805	X_train
+1543	X_train
+725	X_train
+2138	X_train
+1166	X_train
+1088	X_train
+26	X_train
+4640	X_train
+5989	X_train
+1823	X_train
+1866	X_train
+2979	X_train
+424	X_train
+2225	X_train
+7461	X_train
+7431	X_train
+2552	X_train
+1518	X_train
+6065	X_train
+4560	X_train
+3229	X_train
+1153	X_train
+1498	X_train
+2959	X_train
+2562	X_train
+2101	X_train
+1536	X_train
+41	X_train
+767	X_train
+2085	X_train
+1864	X_train
+4574	X_train
+2204	X_train
+2103	X_train
+726	X_train
+363	X_train
+4547	X_train
+1234	X_train
+1052	X_train
+1558	X_train
+4596	X_train
+2559	X_train
+807	X_train
+7434	X_train
+3253	X_train
+1836	X_train
+1583	X_train
+4542	X_train
+2088	X_train
+371	X_train
+1182	X_train
+468	X_train
+738	X_train
+1228	X_train
+776	X_train
+1598	X_train
+1834	X_train
+1885	X_train
+2894	X_train
+1800	X_train
+1792	X_train
+16	X_train
+1152	X_train
+800	X_train
+4646	X_train
+15	X_train
+1259	X_train
+3289	X_train
+472	X_train
+1160	X_train
+2084	X_train
+4519	X_train
+3217	X_train
+3	X_train
+2202	X_train
+462	X_train
+430	X_train
+2169	X_train
+1197	X_train
+1159	X_train
+1255	X_train
+1150	X_train
+2937	X_train
+5996	X_train
+6036	X_train
+432	X_train
+7409	X_train
+112	X_train
+3187	X_train
+2195	X_train
+4589	X_train
+4624	X_train
+411	X_train
+1802	X_train
+2136	X_train
+107	X_train
+3305	X_train
+4552	X_train
+439	X_train
+6080	X_train
+7457	X_train
+2574	X_train
+722	X_train
+1143	X_train
+2539	X_train
+2127	X_train
+4591	X_train
+1569	X_train
+1501	X_train
+1798	X_train
+1553	X_train
+2956	X_train
+1859	X_train
+2128	X_train
+7400	X_train
+2153	X_train
+2219	X_train
+1146	X_train
+4660	X_train
+4623	X_train
+2581	X_train
+7444	X_train
+1142	X_train
+2568	X_train
+4613	X_train
+2571	X_train
+52	X_train
+7451	X_train
+2945	X_train
+3235	X_train
+1822	X_train
+7441	X_train
+788	X_train
+2163	X_train
+7437	X_train
+1057	X_train
+1519	X_train
+3202	X_train
+7459	X_train
+449	X_train
+7393	X_train
+3309	X_train
+1167	X_train
+86	X_train
+1506	X_train
+6060	X_train
+2154	X_train
+1551	X_train
+109	X_train
+7482	X_train
+410	X_train
+5987	X_train
+67	X_train
+4568	X_train
+1867	X_train
+376	X_train
+1076	X_train
+1055	X_train
+1591	y_train
+2117	y_train
+1791	y_train
+1220	y_train
+6079	y_train
+1526	y_train
+2946	y_train
+413	y_train
+7477	y_train
+2577	y_train
+1180	y_train
+2914	y_train
+7423	y_train
+7403	y_train
+1852	y_train
+2213	y_train
+49	y_train
+3279	y_train
+2173	y_train
+6066	y_train
+768	y_train
+79	y_train
+3199	y_train
+2141	y_train
+2917	y_train
+2981	y_train
+3292	y_train
+1251	y_train
+394	y_train
+2234	y_train
+4533	y_train
+5985	y_train
+3304	y_train
+3225	y_train
+2091	y_train
+3297	y_train
+1205	y_train
+2965	y_train
+355	y_train
+93	y_train
+2609	y_train
+404	y_train
+4570	y_train
+2551	y_train
+1169	y_train
+7420	y_train
+2076	y_train
+375	y_train
+7428	y_train
+1509	y_train
+3321	y_train
+440	y_train
+1564	y_train
+1226	y_train
+1861	y_train
+3280	y_train
+2944	y_train
+2130	y_train
+6039	y_train
+1130	y_train
+2614	y_train
+3315	y_train
+1837	y_train
+2918	y_train
+438	y_train
+20	y_train
+2165	y_train
+1586	y_train
+6034	y_train
+456	y_train
+1855	y_train
+396	y_train
+4600	y_train
+3223	y_train
+354	y_train
+3211	y_train
+2915	y_train
+108	y_train
+2973	y_train
+831	y_train
+408	y_train
+7446	y_train
+2553	y_train
+1545	y_train
+4605	y_train
+7479	y_train
+3306	y_train
+4599	y_train
+1215	y_train
+1496	y_train
+2233	y_train
+426	y_train
+1067	y_train
+465	y_train
+1272	y_train
+1871	y_train
+1174	y_train
+6041	y_train
+771	y_train
+7492	y_train
+4643	y_train
+1099	y_train
+1115	y_train
+4566	y_train
+2226	y_train
+3219	y_train
+7471	y_train
+9	y_train
+1061	y_train
+69	y_train
+2241	y_train
+2933	y_train
+2115	y_train
+1155	y_train
+2223	y_train
+3201	y_train
+2542	y_train
+2209	y_train
+6078	y_train
+4649	y_train
+445	y_train
+1570	y_train
+1582	y_train
+7394	y_train
+1803	y_train
+4608	y_train
+59	y_train
+3282	y_train
+6003	y_train
+1164	y_train
+4526	y_train
+1549	y_train
+1279	y_train
+4522	y_train
+7430	y_train
+2218	y_train
+2911	y_train
+1581	y_train
+1495	y_train
+1494	y_train
+1116	y_train
+434	y_train
+1269	y_train
+7473	y_train
+783	y_train
+1537	y_train
+7496	y_train
+5988	y_train
+1136	y_train
+1066	y_train
+70	y_train
+2902	y_train
+403	y_train
+2583	y_train
+2216	y_train
+45	y_train
+2201	y_train
+1890	y_train
+2238	y_train
+360	y_train
+96	y_train
+727	y_train
+1571	y_train
+3311	y_train
+2174	y_train
+3302	y_train
+2903	y_train
+2203	y_train
+3194	y_train
+778	y_train
+7392	y_train
+751	y_train
+3222	y_train
+6084	y_train
+2200	y_train
+2143	y_train
+4597	y_train
+2086	y_train
+1555	y_train
+2974	y_train
+6075	y_train
+7464	y_train
+1183	y_train
+467	y_train
+780	y_train
+6098	y_train
+1513	y_train
+1249	y_train
+2983	y_train
+2967	y_train
+4639	y_train
+471	y_train
+2558	y_train
+1597	y_train
+826	y_train
+3227	y_train
+3296	y_train
+2966	y_train
+97	y_train
+2190	y_train
+2217	y_train
+4585	y_train
+1145	y_train
+4603	y_train
+1096	y_train
+1889	y_train
+1497	y_train
+2924	y_train
+1888	y_train
+744	y_train
+111	y_train
+716	y_train
+1502	y_train
+3277	y_train
+1148	y_train
+1247	y_train
+1577	y_train
+2923	y_train
+3251	y_train
+14	y_train
+1224	y_train
+754	y_train
+2189	y_train
+769	y_train
+2150	y_train
+3291	y_train
+3259	y_train
+1554	y_train
+4546	y_train
+2144	y_train
+782	y_train
+2155	y_train
+2089	y_train
+7497	y_train
+2166	y_train
+3186	y_train
+1843	y_train
+6013	y_train
+450	y_train
+362	y_train
+730	y_train
+429	y_train
+1266	y_train
+7466	y_train
+2590	y_train
+1869	y_train
+1821	y_train
+1214	y_train
+6018	y_train
+370	y_train
+2116	y_train
+2579	y_train
+455	y_train
+3293	y_train
+40	y_train
+457	y_train
+1804	y_train
+4563	y_train
+2913	y_train
+6067	y_train
+2537	y_train
+1277	y_train
+1242	y_train
+4523	y_train
+2235	y_train
+3288	y_train
+7391	y_train
+1209	y_train
+2206	y_train
+1102	y_train
+7494	y_train
+814	y_train
+3256	y_train
+1278	y_train
+1206	y_train
+6049	y_train
+6063	y_train
+7443	y_train
+6044	y_train
+2100	y_train
+1260	y_train
+357	y_train
+364	y_train
+100	y_train
+2565	y_train
+4532	y_train
+81	y_train
+3192	y_train
+7389	y_train
+1540	y_train
+4564	y_train
+2123	y_train
+1584	y_train
+4582	y_train
+1508	y_train
+2889	y_train
+3318	y_train
+2941	y_train
+2940	y_train
+3197	y_train
+24	y_train
+6024	y_train
+763	y_train
+2585	y_train
+25	y_train
+1072	y_train
+1565	y_train
+3240	y_train
+793	y_train
+1165	y_train
+397	y_train
+1529	y_train
+2597	y_train
+1233	y_train
+4641	y_train
+2530	y_train
+2615	y_train
+7426	y_train
+1552	y_train
+1086	y_train
+65	y_train
+75	y_train
+4580	y_train
+3209	y_train
+7490	y_train
+1811	y_train
+2534	y_train
+3258	y_train
+1084	y_train
+2594	y_train
+4586	y_train
+1856	y_train
+18	y_train
+1500	y_train
+1857	y_train
+4602	y_train
+2112	y_train
+2177	y_train
+2605	y_train
+1575	y_train
+6052	y_train
+1507	y_train
+2984	y_train
+4593	y_train
+382	y_train
+2222	y_train
+353	y_train
+7404	y_train
+427	y_train
+2148	y_train
+7498	y_train
+4581	y_train
+2240	y_train
+1884	y_train
+1106	y_train
+4601	y_train
+2197	y_train
+4534	y_train
+2567	y_train
+7388	y_train
+717	y_train
+5984	y_train
+804	y_train
+5992	y_train
+446	y_train
+3205	y_train
+1602	y_train
+777	y_train
+6088	y_train
+2170	y_train
+1530	y_train
+2242	y_train
+2942	y_train
+4631	y_train
+3284	y_train
+3230	y_train
+1227	y_train
+359	y_train
+4541	y_train
+414	y_train
+4632	y_train
+3266	y_train
+1808	y_train
+759	y_train
+7	y_train
+2593	y_train
+2232	y_train
+770	y_train
+3303	y_train
+1139	y_train
+6056	y_train
+2236	y_train
+6028	y_train
+1280	y_train
+789	y_train
+63	y_train
+1868	y_train
+1504	y_train
+34	y_train
+358	y_train
+73	y_train
+5	y_train
+1542	y_train
+4615	y_train
+50	y_train
+417	y_train
+1189	y_train
+3246	y_train
+5999	y_train
+1190	y_train
+794	y_train
+2134	y_train
+787	y_train
+2096	y_train
+3224	y_train
+779	y_train
+4556	y_train
+723	y_train
+92	y_train
+2133	y_train
+761	y_train
+1824	y_train
+1207	y_train
+1054	y_train
+1574	y_train
+1144	y_train
+1514	y_train
+1534	y_train
+461	y_train
+7448	y_train
+76	y_train
+745	y_train
+1196	y_train
+464	y_train
+795	y_train
+1847	y_train
+113	y_train
+1881	y_train
+3238	y_train
+2180	y_train
+2109	y_train
+3200	y_train
+7467	y_train
+2570	y_train
+1580	y_train
+54	y_train
+2533	y_train
+2215	y_train
+4644	y_train
+2147	y_train
+2932	y_train
+1070	y_train
+2191	y_train
+3283	y_train
+4662	y_train
+753	y_train
+2135	y_train
+2550	y_train
+1876	y_train
+2943	y_train
+1118	y_train
+720	y_train
+4650	y_train
+2186	y_train
+6083	y_train
+1873	y_train
+1261	y_train
+1056	y_train
+2220	y_train
+454	y_train
+55	y_train
+1877	y_train
+1596	y_train
+1600	y_train
+3314	y_train
+2884	y_train
+37	y_train
+2118	y_train
+2958	y_train
+1566	y_train
+1051	y_train
+1263	y_train
+2183	y_train
+2113	y_train
+3320	y_train
+2928	y_train
+3249	y_train
+1870	y_train
+764	y_train
+1048	y_train
+6076	y_train
+749	y_train
+3264	y_train
+4550	y_train
+72	y_train
+7453	y_train
+1091	y_train
+1081	y_train
+1267	y_train
+819	y_train
+773	y_train
+3241	y_train
+399	y_train
+2564	y_train
+1860	y_train
+7416	y_train
+8	y_train
+3308	y_train
+3232	y_train
+1236	y_train
+2184	y_train
+2532	y_train
+6009	y_train
+374	y_train
+1516	y_train
+6055	y_train
+1838	y_train
+1831	y_train
+4524	y_train
+6033	y_train
+7412	y_train
+2131	y_train
+3203	y_train
+6020	y_train
+829	y_train
+719	y_train
+2205	y_train
+3286	y_train
+7465	y_train
+2080	y_train
+2181	y_train
+1134	y_train
+2895	y_train
+7440	y_train
+2977	y_train
+3226	y_train
+4538	y_train
+1171	y_train
+6	y_train
+1256	y_train
+2538	y_train
+4557	y_train
+428	y_train
+7495	y_train
+2589	y_train
+1104	y_train
+2954	y_train
+415	y_train
+4651	y_train
+1512	y_train
+32	y_train
+56	y_train
+746	y_train
+4575	y_train
+1192	y_train
+2900	y_train
+2888	y_train
+785	y_train
+737	y_train
+2580	y_train
+2602	y_train
+6031	y_train
+6085	y_train
+3281	y_train
+412	y_train
+4565	y_train
+2950	y_train
+4661	y_train
+1195	y_train
+2087	y_train
+42	y_train
+2122	y_train
+87	y_train
+1187	y_train
+1222	y_train
+2157	y_train
+3254	y_train
+1878	y_train
+2243	y_train
+2885	y_train
+2905	y_train
+1863	y_train
+102	y_train
+6071	y_train
+1221	y_train
+30	y_train
+1120	y_train
+6030	y_train
+4531	y_train
+1101	y_train
+1886	y_train
+1556	y_train
+1839	y_train
+3252	y_train
+2094	y_train
+392	y_train
+1585	y_train
+1576	y_train
+7408	y_train
+6064	y_train
+453	y_train
+101	y_train
+4548	y_train
+2921	y_train
+459	y_train
+7469	y_train
+4621	y_train
+4594	y_train
+765	y_train
+5994	y_train
+387	y_train
+373	y_train
+4587	y_train
+2948	y_train
+796	y_train
+1097	y_train
+820	y_train
+110	y_train
+729	y_train
+4543	y_train
+2557	y_train
+0	y_train
+6032	y_train
+3210	y_train
+1880	y_train
+2	y_train
+721	y_train
+2077	y_train
+51	y_train
+4654	y_train
+78	y_train
+7480	y_train
+1123	y_train
+715	y_train
+2576	y_train
+7432	y_train
+379	y_train
+1854	y_train
+1825	y_train
+2083	y_train
+3272	y_train
+1503	y_train
+2156	y_train
+7454	y_train
+2081	y_train
+1090	y_train
+4653	y_train
+828	y_train
+4607	y_train
+1832	y_train
+1593	y_train
+47	y_train
+1149	y_train
+473	y_train
+1203	y_train
+1188	y_train
+4642	y_train
+3244	y_train
+6045	y_train
+1270	y_train
+470	y_train
+728	y_train
+2596	y_train
+1528	y_train
+1064	y_train
+6014	y_train
+3295	y_train
+106	y_train
+4555	y_train
+2207	y_train
+3313	y_train
+1194	y_train
+3307	y_train
+4604	y_train
+1095	y_train
+1157	y_train
+1225	y_train
+7397	y_train
+4576	y_train
+1181	y_train
+1797	y_train
+35	y_train
+786	y_train
+1281	y_train
+811	y_train
+4539	y_train
+1059	y_train
+7488	y_train
+2938	y_train
+4540	y_train
+4620	y_train
+1243	y_train
+1103	y_train
+77	y_train
+4559	y_train
+1176	y_train
+803	y_train
+1235	y_train
+1511	y_train
+2934	y_train
+7447	y_train
+1499	y_train
+6000	y_train
+6047	y_train
+422	y_train
+82	y_train
+2910	y_train
+5993	y_train
+2188	y_train
+4657	y_train
+367	y_train
+2185	y_train
+4551	y_train
+2214	y_train
+1078	y_train
+2985	y_train
+2239	y_train
+1058	y_train
+85	y_train
+2543	y_train
+2896	y_train
+6004	y_train
+2192	y_train
+406	y_train
+2129	y_train
+2149	y_train
+1589	y_train
+400	y_train
+2931	y_train
+1114	y_train
+781	y_train
+2569	y_train
+1212	y_train
+6057	y_train
+2890	y_train
+3193	y_train
+4647	y_train
+1807	y_train
+4592	y_train
+1801	y_train
+3228	y_train
+775	y_train
+2164	y_train
+1816	y_train
+2541	y_train
+2600	y_train
+7396	y_train
+419	y_train
+68	y_train
+2608	y_train
+7500	y_train
+1879	y_train
+755	y_train
+1168	y_train
+3269	y_train
+7499	y_train
+6017	y_train
+1795	y_train
+2916	y_train
+6012	y_train
+6016	y_train
+1232	y_train
+368	y_train
+5997	y_train
+2936	y_train
+2160	y_train
+2892	y_train
+758	y_train
+1538	y_train
+7460	y_train
+2607	y_train
+11	y_train
+4598	y_train
+88	y_train
+2616	y_train
+23	y_train
+1578	y_train
+418	y_train
+1844	y_train
+1173	y_train
+743	y_train
+1809	y_train
+2572	y_train
+2960	y_train
+38	y_train
+1517	y_train
+4588	y_train
+4622	y_train
+1557	y_train
+3322	y_train
+6026	y_train
+1119	y_train
+6010	y_train
+2224	y_train
+2176	y_train
+53	y_train
+1100	y_train
+351	y_train
+740	y_train
+1865	y_train
+36	y_train
+1828	y_train
+4629	y_train
+3274	y_train
+6095	y_train
+825	y_train
+6040	y_train
+1806	y_train
+1135	y_train
+90	y_train
+1071	y_train
+6015	y_train
+6082	y_train
+389	y_train
+365	y_train
+2961	y_train
+3188	y_train
+1282	y_train
+1204	y_train
+3271	y_train
+378	y_train
+7436	y_train
+3267	y_train
+6048	y_train
+6001	y_train
+1887	y_train
+1601	y_train
+3218	y_train
+1083	y_train
+1245	y_train
+7445	y_train
+3260	y_train
+7470	y_train
+6069	y_train
+1073	y_train
+4549	y_train
+2230	y_train
+4609	y_train
+10	y_train
+1077	y_train
+1848	y_train
+4630	y_train
+2969	y_train
+2079	y_train
+4645	y_train
+443	y_train
+2099	y_train
+1	y_train
+4561	y_train
+4	y_train
+91	y_train
+2145	y_train
+4562	y_train
+2546	y_train
+748	y_train
+2092	y_train
+7401	y_train
+6043	y_train
+2228	y_train
+1853	y_train
+2891	y_train
+1141	y_train
+4590	y_train
+386	y_train
+7481	y_train
+2599	y_train
+6019	y_train
+2104	y_train
+762	y_train
+1274	y_train
+421	y_train
+1213	y_train
+1544	y_train
+832	y_train
+3301	y_train
+436	y_train
+3278	y_train
+1894	y_train
+1063	y_train
+3285	y_train
+6093	y_train
+2582	y_train
+3191	y_train
+2573	y_train
+1833	y_train
+46	y_train
+6096	y_train
+2971	y_train
+2982	y_train
+2926	y_train
+383	y_train
+7421	y_train
+2975	y_train
+2120	y_train
+774	y_train
+6029	y_train
+1175	y_train
+747	y_train
+6070	y_train
+3265	y_train
+83	y_train
+757	y_train
+3255	y_train
+798	y_train
+1049	y_train
+1108	y_train
+3221	y_train
+2531	y_train
+809	y_train
+7452	y_train
+6053	y_train
+2161	y_train
+433	y_train
+7429	y_train
+17	y_train
+2210	y_train
+1229	y_train
+4625	y_train
+1872	y_train
+2612	y_train
+1820	y_train
+366	y_train
+4554	y_train
+1275	y_train
+1125	y_train
+1819	y_train
+2601	y_train
+3247	y_train
+1590	y_train
+3317	y_train
+1850	y_train
+1525	y_train
+2090	y_train
+750	y_train
+6086	y_train
+2111	y_train
+2907	y_train
+1053	y_train
+452	y_train
+356	y_train
+6062	y_train
+805	y_train
+1112	y_train
+4527	y_train
+28	y_train
+6042	y_train
+2535	y_train
+3206	y_train
+3298	y_train
+2906	y_train
+444	y_train
+4595	y_train
+391	y_train
+7450	y_train
+6074	y_train
+7414	y_train
+4652	y_train
+1862	y_train
+1799	y_train
+2549	y_train
+2212	y_train
+2925	y_train
+2110	y_train
+2221	y_train
+469	y_train
+3190	y_train
+6046	y_train
+792	y_train
+1240	y_train
+1533	y_train
+1548	y_train
+1122	y_train
+1062	y_train
+2955	y_train
+7449	y_train
+2951	y_train
+1599	y_train
+2584	y_train
+1138	y_train
+466	y_train
+821	y_train
+6058	y_train
+2978	y_train
+1265	y_train
+7422	y_train
+3276	y_train
+2132	y_train
+7405	y_train
+718	y_train
+752	y_train
+4636	y_train
+2935	y_train
+4529	y_train
+448	y_train
+58	y_train
+5991	y_train
+2121	y_train
+4567	y_train
+2883	y_train
+1201	y_train
+4521	y_train
+3300	y_train
+104	y_train
+1140	y_train
+2237	y_train
+3236	y_train
+742	y_train
+405	y_train
+2158	y_train
+99	y_train
+1075	y_train
+815	y_train
+3215	y_train
+1563	y_train
+6090	y_train
+2171	y_train
+2140	y_train
+5990	y_train
+1891	y_train
+6027	y_train
+441	y_train
+3257	y_train
+6101	y_train
+2919	y_train
+2162	y_train
+7398	y_train
+7390	y_train
+1253	y_train
+1262	y_train
+741	y_train
+1184	y_train
+3294	y_train
+2922	y_train
+1841	y_train
+2119	y_train
+799	y_train
+2908	y_train
+1246	y_train
+1132	y_train
+4655	y_train
+463	y_train
+2930	y_train
+1237	y_train
+2179	y_train
+2182	y_train
+2929	y_train
+1068	y_train
+833	y_train
+4663	y_train
+31	y_train
+2107	y_train
+6008	y_train
+2976	y_train
+7501	y_train
+6068	y_train
+7413	y_train
+2231	y_train
+384	y_train
+80	y_train
+1093	y_train
+2587	y_train
+2610	y_train
+1827	y_train
+1257	y_train
+1276	y_train
+4584	y_train
+7485	y_train
+1092	y_train
+1163	y_train
+2957	y_train
+4659	y_train
+802	y_train
+2545	y_train
+2106	y_train
+4573	y_train
+4617	y_train
+2595	y_train
+1170	y_train
+1079	y_train
+1248	y_train
+2598	y_train
+756	y_train
+7474	y_train
+1546	y_train
+2592	y_train
+1105	y_train
+1050	y_train
+2920	y_train
+95	y_train
+1283	y_train
+1573	y_train
+60	y_train
+48	y_train
+2963	y_train
+4658	y_train
+3195	y_train
+1851	y_train
+84	y_train
+2588	y_train
+4619	y_train
+381	y_train
+1521	y_train
+458	y_train
+402	y_train
+1842	y_train
+1592	y_train
+766	y_train
+2125	y_train
+4606	y_train
+385	y_train
+1815	y_train
+4634	y_train
+1813	y_train
+460	y_train
+7478	y_train
+4618	y_train
+1178	y_train
+1588	y_train
+3268	y_train
+6061	y_train
+1200	y_train
+739	y_train
+3214	y_train
+736	y_train
+6025	y_train
+2953	y_train
+1510	y_train
+2142	y_train
+2962	y_train
+6077	y_train
+1156	y_train
+3196	y_train
+7439	y_train
+1560	y_train
+827	y_train
+712	y_train
+425	y_train
+1211	y_train
+3316	y_train
+2199	y_train
+830	y_train
+1126	y_train
+2591	y_train
+2886	y_train
+6011	y_train
+4610	y_train
+6035	y_train
+2168	y_train
+2563	y_train
+1133	y_train
+3243	y_train
+6100	y_train
+1796	y_train
+1532	y_train
+2178	y_train
+3275	y_train
+1094	y_train
+1089	y_train
+2124	y_train
+2105	y_train
+1523	y_train
+2187	y_train
+1883	y_train
+4583	y_train
+1074	y_train
+1845	y_train
+1812	y_train
+1128	y_train
+2227	y_train
+732	y_train
+7402	y_train
+1567	y_train
+2947	y_train
+2968	y_train
+2108	y_train
+57	y_train
+4536	y_train
+6007	y_train
+2893	y_train
+4558	y_train
+4616	y_train
+1805	y_train
+1543	y_train
+725	y_train
+2138	y_train
+1166	y_train
+1088	y_train
+26	y_train
+4640	y_train
+5989	y_train
+1823	y_train
+1866	y_train
+2979	y_train
+424	y_train
+2225	y_train
+7461	y_train
+7431	y_train
+2552	y_train
+1518	y_train
+6065	y_train
+4560	y_train
+3229	y_train
+1153	y_train
+1498	y_train
+2959	y_train
+2562	y_train
+2101	y_train
+1536	y_train
+41	y_train
+767	y_train
+2085	y_train
+1864	y_train
+4574	y_train
+2204	y_train
+2103	y_train
+726	y_train
+363	y_train
+4547	y_train
+1234	y_train
+1052	y_train
+1558	y_train
+4596	y_train
+2559	y_train
+807	y_train
+7434	y_train
+3253	y_train
+1836	y_train
+1583	y_train
+4542	y_train
+2088	y_train
+371	y_train
+1182	y_train
+468	y_train
+738	y_train
+1228	y_train
+776	y_train
+1598	y_train
+1834	y_train
+1885	y_train
+2894	y_train
+1800	y_train
+1792	y_train
+16	y_train
+1152	y_train
+800	y_train
+4646	y_train
+15	y_train
+1259	y_train
+3289	y_train
+472	y_train
+1160	y_train
+2084	y_train
+4519	y_train
+3217	y_train
+3	y_train
+2202	y_train
+462	y_train
+430	y_train
+2169	y_train
+1197	y_train
+1159	y_train
+1255	y_train
+1150	y_train
+2937	y_train
+5996	y_train
+6036	y_train
+432	y_train
+7409	y_train
+112	y_train
+3187	y_train
+2195	y_train
+4589	y_train
+4624	y_train
+411	y_train
+1802	y_train
+2136	y_train
+107	y_train
+3305	y_train
+4552	y_train
+439	y_train
+6080	y_train
+7457	y_train
+2574	y_train
+722	y_train
+1143	y_train
+2539	y_train
+2127	y_train
+4591	y_train
+1569	y_train
+1501	y_train
+1798	y_train
+1553	y_train
+2956	y_train
+1859	y_train
+2128	y_train
+7400	y_train
+2153	y_train
+2219	y_train
+1146	y_train
+4660	y_train
+4623	y_train
+2581	y_train
+7444	y_train
+1142	y_train
+2568	y_train
+4613	y_train
+2571	y_train
+52	y_train
+7451	y_train
+2945	y_train
+3235	y_train
+1822	y_train
+7441	y_train
+788	y_train
+2163	y_train
+7437	y_train
+1057	y_train
+1519	y_train
+3202	y_train
+7459	y_train
+449	y_train
+7393	y_train
+3309	y_train
+1167	y_train
+86	y_train
+1506	y_train
+6060	y_train
+2154	y_train
+1551	y_train
+109	y_train
+7482	y_train
+410	y_train
+5987	y_train
+67	y_train
+4568	y_train
+1867	y_train
+376	y_train
+1076	y_train
+1055	y_train
+6006	y_test
+4528	y_test
+2970	y_test
+4577	y_test
+1127	y_test
+64	y_test
+3242	y_test
+2167	y_test
+1147	y_test
+2544	y_test
+6092	y_test
+2126	y_test
+3234	y_test
+2912	y_test
+1258	y_test
+1595	y_test
+2909	y_test
+7417	y_test
+2082	y_test
+1098	y_test
+1535	y_test
+1264	y_test
+1231	y_test
+369	y_test
+3237	y_test
+380	y_test
+6072	y_test
+4637	y_test
+431	y_test
+3204	y_test
+1179	y_test
+724	y_test
+27	y_test
+2949	y_test
+1527	y_test
+772	y_test
+94	y_test
+5986	y_test
+2606	y_test
+447	y_test
+2575	y_test
+6087	y_test
+2196	y_test
+2137	y_test
+435	y_test
+4633	y_test
+1241	y_test
+7472	y_test
+6094	y_test
+1216	y_test
+2554	y_test
+4569	y_test
+817	y_test
+1185	y_test
+1172	y_test
+7455	y_test
+3216	y_test
+1550	y_test
+2901	y_test
+6097	y_test
+4635	y_test
+1210	y_test
+2146	y_test
+1199	y_test
+1524	y_test
+6059	y_test
+2151	y_test
+1191	y_test
+2097	y_test
+442	y_test
+2898	y_test
+1830	y_test
+7424	y_test
+3207	y_test
+1113	y_test
+7399	y_test
+1110	y_test
+21	y_test
+1531	y_test
+1840	y_test
+7458	y_test
+1893	y_test
+7425	y_test
+1572	y_test
+4525	y_test
+3263	y_test
+2887	y_test
+1515	y_test
+6023	y_test
+7435	y_test
+812	y_test
+4626	y_test
+3239	y_test
+1814	y_test
+816	y_test
+6005	y_test
+2536	y_test
+1250	y_test
+1069	y_test
+2556	y_test
+6021	y_test
+2939	y_test
+1129	y_test
+1810	y_test
+1177	y_test
+6081	y_test
+4571	y_test
+409	y_test
+2547	y_test
+4648	y_test
+1849	y_test
+822	y_test
+1239	y_test
+7468	y_test
+437	y_test
+713	y_test
+791	y_test
+5998	y_test
+7475	y_test
+398	y_test
+1790	y_test
+790	y_test
+823	y_test
+784	y_test
+2560	y_test
+388	y_test
+2952	y_test
+2904	y_test
+7489	y_test
+6037	y_test
+3220	y_test
+1161	y_test
+7484	y_test
+89	y_test
+1202	y_test
+19	y_test
+1230	y_test
+6038	y_test
+735	y_test
+7407	y_test
+2208	y_test
+806	y_test
+2198	y_test
+4614	y_test
+2897	y_test
+835	y_test
+451	y_test
+1522	y_test
+801	y_test
+423	y_test
+1826	y_test
+7491	y_test
+6054	y_test
+1793	y_test
+105	y_test
+3208	y_test
+1846	y_test
+401	y_test
+7438	y_test
+1594	y_test
+1218	y_test
+7411	y_test
+13	y_test
+3312	y_test
+1539	y_test
+6051	y_test
+1109	y_test
+352	y_test
+1561	y_test
+1193	y_test
+1858	y_test
+372	y_test
+2604	y_test
+1794	y_test
+4530	y_test
+2586	y_test
+2964	y_test
+1882	y_test
+4579	y_test
+1117	y_test
+2172	y_test
+1107	y_test
+1124	y_test
+4612	y_test
+1082	y_test
+3287	y_test
+1223	y_test
+4520	y_test
+2159	y_test
+3319	y_test
+98	y_test
+4572	y_test
+2194	y_test
+4628	y_test
+2193	y_test
+734	y_test
+1198	y_test
+1186	y_test
+4638	y_test
+1121	y_test
+1244	y_test
+1520	y_test
+29	y_test
+74	y_test
+6099	y_test
+2229	y_test
+1217	y_test
+33	y_test
+1060	y_test
+71	y_test
+4627	y_test
+1131	y_test
+7462	y_test
+813	y_test
+1273	y_test
+1505	y_test
+3273	y_test
+824	y_test
+834	y_test
+2611	y_test
+2540	y_test
+4578	y_test
+1162	y_test
+1252	y_test
+3310	y_test
+4535	y_test
+7486	y_test
+2102	y_test
+2899	y_test
+1254	y_test
+7476	y_test
+114	y_test
+7410	y_test
+2093	y_test
+1817	y_test
+103	y_test
+1579	y_test
+1603	y_test
+3262	y_test
+1047	y_test
+3261	y_test
+3245	y_test
+3250	y_test
+1587	y_test
+1875	y_test
+1271	y_test
+7395	y_test
+1835	y_test
+3212	y_test
+7427	y_test
+7418	y_test
+66	y_test
+22	y_test
+2603	y_test
+2078	y_test
+361	y_test
+4656	y_test
+7483	y_test
+1111	y_test
+818	y_test
+1087	y_test
+731	y_test
+62	y_test
+2555	y_test
+1219	y_test
+7442	y_test
+4553	y_test
+3213	y_test
+3290	y_test
+733	y_test
+2578	y_test
+43	y_test
+1238	y_test
+2548	y_test
+6022	y_test
+1568	y_test
+1137	y_test
+1559	y_test
+6091	y_test
+6002	y_test
+808	y_test
+2561	y_test
+2972	y_test
+3233	y_test
+7493	y_test
+2152	y_test
+2566	y_test
+1829	y_test
+1065	y_test
+4544	y_test
+1080	y_test
+416	y_test
+4537	y_test
+7419	y_test
+2211	y_test
+3270	y_test
+377	y_test
+1158	y_test
+390	y_test
+7463	y_test
+1268	y_test
+44	y_test
+2613	y_test
+1541	y_test
+39	y_test
+3231	y_test
+420	y_test
+3299	y_test
+3189	y_test
+2095	y_test
+393	y_test
+407	y_test
+3248	y_test
+797	y_test
+1892	y_test
+4545	y_test
+2139	y_test
+7433	y_test
+2114	y_test
+760	y_test
+12	y_test
+4611	y_test
+395	y_test
+1151	y_test
+1562	y_test
+714	y_test
+1208	y_test
+1085	y_test
+61	y_test
+3198	y_test
+1874	y_test
+810	y_test
+2980	y_test
+2098	y_test
+3323	y_test
+6006	X_test
+4528	X_test
+2970	X_test
+4577	X_test
+1127	X_test
+64	X_test
+3242	X_test
+2167	X_test
+1147	X_test
+2544	X_test
+6092	X_test
+2126	X_test
+3234	X_test
+2912	X_test
+1258	X_test
+1595	X_test
+2909	X_test
+7417	X_test
+2082	X_test
+1098	X_test
+1535	X_test
+1264	X_test
+1231	X_test
+369	X_test
+3237	X_test
+380	X_test
+6072	X_test
+4637	X_test
+431	X_test
+3204	X_test
+1179	X_test
+724	X_test
+27	X_test
+2949	X_test
+1527	X_test
+772	X_test
+94	X_test
+5986	X_test
+2606	X_test
+447	X_test
+2575	X_test
+6087	X_test
+2196	X_test
+2137	X_test
+435	X_test
+4633	X_test
+1241	X_test
+7472	X_test
+6094	X_test
+1216	X_test
+2554	X_test
+4569	X_test
+817	X_test
+1185	X_test
+1172	X_test
+7455	X_test
+3216	X_test
+1550	X_test
+2901	X_test
+6097	X_test
+4635	X_test
+1210	X_test
+2146	X_test
+1199	X_test
+1524	X_test
+6059	X_test
+2151	X_test
+1191	X_test
+2097	X_test
+442	X_test
+2898	X_test
+1830	X_test
+7424	X_test
+3207	X_test
+1113	X_test
+7399	X_test
+1110	X_test
+21	X_test
+1531	X_test
+1840	X_test
+7458	X_test
+1893	X_test
+7425	X_test
+1572	X_test
+4525	X_test
+3263	X_test
+2887	X_test
+1515	X_test
+6023	X_test
+7435	X_test
+812	X_test
+4626	X_test
+3239	X_test
+1814	X_test
+816	X_test
+6005	X_test
+2536	X_test
+1250	X_test
+1069	X_test
+2556	X_test
+6021	X_test
+2939	X_test
+1129	X_test
+1810	X_test
+1177	X_test
+6081	X_test
+4571	X_test
+409	X_test
+2547	X_test
+4648	X_test
+1849	X_test
+822	X_test
+1239	X_test
+7468	X_test
+437	X_test
+713	X_test
+791	X_test
+5998	X_test
+7475	X_test
+398	X_test
+1790	X_test
+790	X_test
+823	X_test
+784	X_test
+2560	X_test
+388	X_test
+2952	X_test
+2904	X_test
+7489	X_test
+6037	X_test
+3220	X_test
+1161	X_test
+7484	X_test
+89	X_test
+1202	X_test
+19	X_test
+1230	X_test
+6038	X_test
+735	X_test
+7407	X_test
+2208	X_test
+806	X_test
+2198	X_test
+4614	X_test
+2897	X_test
+835	X_test
+451	X_test
+1522	X_test
+801	X_test
+423	X_test
+1826	X_test
+7491	X_test
+6054	X_test
+1793	X_test
+105	X_test
+3208	X_test
+1846	X_test
+401	X_test
+7438	X_test
+1594	X_test
+1218	X_test
+7411	X_test
+13	X_test
+3312	X_test
+1539	X_test
+6051	X_test
+1109	X_test
+352	X_test
+1561	X_test
+1193	X_test
+1858	X_test
+372	X_test
+2604	X_test
+1794	X_test
+4530	X_test
+2586	X_test
+2964	X_test
+1882	X_test
+4579	X_test
+1117	X_test
+2172	X_test
+1107	X_test
+1124	X_test
+4612	X_test
+1082	X_test
+3287	X_test
+1223	X_test
+4520	X_test
+2159	X_test
+3319	X_test
+98	X_test
+4572	X_test
+2194	X_test
+4628	X_test
+2193	X_test
+734	X_test
+1198	X_test
+1186	X_test
+4638	X_test
+1121	X_test
+1244	X_test
+1520	X_test
+29	X_test
+74	X_test
+6099	X_test
+2229	X_test
+1217	X_test
+33	X_test
+1060	X_test
+71	X_test
+4627	X_test
+1131	X_test
+7462	X_test
+813	X_test
+1273	X_test
+1505	X_test
+3273	X_test
+824	X_test
+834	X_test
+2611	X_test
+2540	X_test
+4578	X_test
+1162	X_test
+1252	X_test
+3310	X_test
+4535	X_test
+7486	X_test
+2102	X_test
+2899	X_test
+1254	X_test
+7476	X_test
+114	X_test
+7410	X_test
+2093	X_test
+1817	X_test
+103	X_test
+1579	X_test
+1603	X_test
+3262	X_test
+1047	X_test
+3261	X_test
+3245	X_test
+3250	X_test
+1587	X_test
+1875	X_test
+1271	X_test
+7395	X_test
+1835	X_test
+3212	X_test
+7427	X_test
+7418	X_test
+66	X_test
+22	X_test
+2603	X_test
+2078	X_test
+361	X_test
+4656	X_test
+7483	X_test
+1111	X_test
+818	X_test
+1087	X_test
+731	X_test
+62	X_test
+2555	X_test
+1219	X_test
+7442	X_test
+4553	X_test
+3213	X_test
+3290	X_test
+733	X_test
+2578	X_test
+43	X_test
+1238	X_test
+2548	X_test
+6022	X_test
+1568	X_test
+1137	X_test
+1559	X_test
+6091	X_test
+6002	X_test
+808	X_test
+2561	X_test
+2972	X_test
+3233	X_test
+7493	X_test
+2152	X_test
+2566	X_test
+1829	X_test
+1065	X_test
+4544	X_test
+1080	X_test
+416	X_test
+4537	X_test
+7419	X_test
+2211	X_test
+3270	X_test
+377	X_test
+1158	X_test
+390	X_test
+7463	X_test
+1268	X_test
+44	X_test
+2613	X_test
+1541	X_test
+39	X_test
+3231	X_test
+420	X_test
+3299	X_test
+3189	X_test
+2095	X_test
+393	X_test
+407	X_test
+3248	X_test
+797	X_test
+1892	X_test
+4545	X_test
+2139	X_test
+7433	X_test
+2114	X_test
+760	X_test
+12	X_test
+4611	X_test
+395	X_test
+1151	X_test
+1562	X_test
+714	X_test
+1208	X_test
+1085	X_test
+61	X_test
+3198	X_test
+1874	X_test
+810	X_test
+2980	X_test
+2098	X_test
+3323	X_test
diff --git a/1.train_models/log_reg_plates_cp_fs_data/plate_4/model_data/label_encoder_log_reg_cp_fs_data_plate_4.joblib b/1.train_models/log_reg_plates_cp_fs_data/plate_4/model_data/label_encoder_log_reg_cp_fs_data_plate_4.joblib
new file mode 100644
index 0000000000000000000000000000000000000000..fe606e8a75a2cf21e0066a3385ae66dca5f6bc1d
GIT binary patch
literal 532
zcmZ8eO>Yx15Y29rewY9$>8*%!xL8zNdP4~H!lJDdAvKrEvK^~g@OpP_FDOzgl|w0!
zd}I21!RzJ%bFjzudo%N%Z-)=#Y>*<nbYHdN*3j0f);3Z(SD7oyG#5%^7=P;bGb5X&
zviKWc|G*oZg?*{HbILIc(=UzCm7u1p+cj$|8S7y<Ec@eoYx(-Z^0xhl>^hP77)FVO
zVb3gikBuF|$gOy*u*mOX-q^lx$Uek;>DTdoHC|04DnCEP&98f$<E+>T*)^7B`SDMT
zv=r|=ia@y5&39JUyv0p8ew;A%VO&>NrdGx?vG&SgG3mr@E)#^x#wuEO+E)oom{qbd
z&f89U0)s~s*^W#gD+YIvOV)cN9Z|_F0y~S|V*$g(ZrnBZl{taYPuQKq-aYKk;b2x|
zQ6-RV!K9DClSLl!=ch1^`rzpto<)VJ)-^o;UnNY$<`NEPi(%xHo!0Oo(Jwy3RCzcO
d^x;)}=_5?o_OIDDWnI;n=;;Z4OW$B8=wD|0!Pfu)

literal 0
HcmV?d00001

diff --git a/1.train_models/log_reg_plates_cp_fs_data/plate_4/trained_models/log_reg_cp_fs_data_plate_4.joblib b/1.train_models/log_reg_plates_cp_fs_data/plate_4/trained_models/log_reg_cp_fs_data_plate_4.joblib
new file mode 100644
index 0000000000000000000000000000000000000000..2b0a3d858ed4c28de86fd676dc2019fca3600779
GIT binary patch
literal 70879
zcmbWAXFwB67ls8<QL*>l3o0rp6!khHSP?~RSVMpaQ3zxRf*rA;VkOu`MHED&Nf8AH
zM6g%vy?0SR8+xz$?d*~bp=EdcVMutNnRCv}o|)av9)gU*rG{1Lf1z#tW_!t`P|@2<
zuAp8e-ahU!uig?b9}l^oO75l(Z8)m<M<<yFl==C|eH7|2wdoS|LUs4h8on}x)Jrv2
z9a>A~CB=Y3rc#F*x%*4K)T=_Ps(ifE!$3=mr|(+ZnuQwJszaM7{JnkW_IC4uvfkeQ
zUMjg1LMg>p_j8kaNg>sAXf;|wy}GOB`pWPphBK|yt3p<)oz&g!tA-j3P>&uxdgNc~
zAN`+w6_wi6)_6{YSgkC24Ad(qU1*(|a+O4`P|2X1%vYrj32nf>k>IZ63J<ltL8yrv
zWwxIrKqmL_RH;XYnn0<--N#$vr;@5<)cfjwK3;QVkaEdS>LFE!8hc9vC331&wZrSG
zp|xobBy=0<(5gOjC}9ms?&{+wQ`=VwtrZ}JbX!nGMWebxGRw!+k80J}%UlAbD!Gr^
z)5No(t?~T!*Cp4Y-WHqQV5Ur}@`o~sLh3E^qnwbaLmN?~m)x~C9U6(R+>IJFb!dap
zIG8p#f|H=s*OxMj9U5ale^<sZ&pM$s6z)u%ad`barBqlQf{m6_Z+xITMS0frtm|1X
z)NqVWoEMaeGoa!eT1)EX<r5(B_LllmKDA;Dq8pb`QT0%G%M>b!>s*!0Pi<e{-!;h4
zjh2)i@mdlnbMsO7si41`s+O_}qpDSGXDy|HeU;@(LpO;VH6PvlYRMG%hg!<2&IZ)H
zbyXTUSEpXRs2D2DmDN@#t2-%ctW+91DQkAOH^8nbYZbRhPoi4N+Rk{!kFipkP!ma6
z$4Ob2no4wI3zYSArxQ>q>$|R+u58fVxjDty&Q<yNQnSQcVgqH;aX5JNPs)bQohtbC
zU>|>lJ2k@w`vhV}*~qzF1xi~VZ(pgKN<kf1%Er#^D^Lw_bEBdP<!*A-TxApImKDhY
zRg_HG)VXa1f}uXpdnnbN4^%d*(0B*wEFWkSDEAvBQ+TL6mCY+`&Os(sI7!{*{(j09
z6*nhW=rq^Txpf8Bjq~x6yJHVqRT!=*GN_QxmPz_b`YK!NRhdi7m2LE@1XNpXIj986
zc6wDps>k*mR6=D3y($r9S4R#ifwB_^l}OoHuS!f=--UxpsO-u?C02IRtFoYc?9M?Y
zP?~a3iIhD!s4SE{^{OnXNc7^M5-QC&s4SJe^{T9>Nc7>L5-9s}P>Gc098?xcfnJq0
z6$v2+l~5_-pb{&^98}gy3+Em>Ny63#LTZCSt(Xdl&d-y@5<45m5lTyr02WJz4Rusn
z@d2DDz}nfAlSx$L60Gl6Dw~%y+g@U;F}#1Nc$Af4YX|66;V%EFv`gA`s$b<m{W9Dq
z&@aQC4ysg!qd^alO{E@C4dIX|2RnDIFvt$n&P)dVw4t+g?!rloow4K4Fl*}&4q|LE
z?by&t#AB$vpqJEFYx1y4OfD(LCJ*PR#e*<{gAwf1AIVjWTejz51r8k6j&kl;;ea?z
zvekyc!MTH8Ar8T44m#ZN7(E@cQ{Rz`5cfQmix7A1q(_KjL(h|OdVJ9Yal9TK)hT_b
zOwiLY*3lhL<j^2?d6IK0ok1B!oeKF=r)1QQOkz%V>0D~-rmLVkn_OulxSJ`JDsV`r
zR-zElhD@tef!mnw+(*Zm5!9KW!VkNGfAXMCzGUv~XG7dQWOTbTocr>mXs0E-JHvr+
z;Z0%3q|QCLn@Bt5>fDP5K|AE;+`9r~luv*Rj`f#9mE23l29WN@oiBugAma<+7|e9;
zT!DEGHg>v3d6Y_D+TZF(X|FxGHH*!bbCY6YXE}GT$XM#igPq)uI=6I_(Pzzg1)N=K
zn^D5x(sJ5pFYe7_YrHFw2eN&!2ZVyV9EZh+yBr(iTk+sXwZ<@6Oj&WnOKPzdu;LI>
zC#+?i^eeR$WEB#8g3G?6gF?q##iIjkkiT=cil%_fU0$LK`Z$_XVe8{mrE(T+O+bY~
zFQdoC1ag<-F`8T90XhL+Zz`J#a3AwZ4eTf%H)ikdP;#uC=}p6YPTI+|c7d~*P9X8c
z2dNiz3{lrcT>a^@gP~CBW}~vhk(8MG%oHgXmU5sH28WY@7V(6HxTnQDArXdxxVuC}
zma%RLKZZ6gm^(uaJJZinehl5uGJXslgXQ`IhmS-&wAyi9!4smbTUlz&EoU;YJ!xk{
z2wzHoM|KroineeyUy6?48Xm!5r%@<Rh_-JnPlz^e9S?||ed~EbbkH~OglL~O@`Pxg
zHtC0$*=0LXJ88psLbOk6o)GO*I8TW7X|w*x$NHo_Jht$qXs@>NrD(Ud@ug_Lw(|%E
zdwA^N3DI8d<O$JE?cxd1K1J|=*kfupPl)zu4^N2pX)jNR_9@a?tZ#iUz60PO^-#!F
z{_ga78+CeWuG~k+;>-V0#H>KMpOD433JwsnLS-}|i*GB$5VHd1K|&VaT!<xRg~~&O
zEWX7MN6ZS8hlyE{GM<pdw;vLSS)nqKki|D4l89M>GMShaDUT4c_y$D^F)LK260>4u
znzIG(e8sGrl+o#=FwR&<NnxCJGDu;ZJC2dV0_Aa17-x@6a#*O$B874OI6)2zl!zP_
zDYHpooI-NQVWILQIV@J@lEOFxog#+?$~<z|LYYqr<0N#N92P3iki%l-S#sD?d5#>m
zR-PwFp7aKriq{1~7N@_9#H>JhiIBya^D;3jR9+!uanij?%nFp(2w9wR3y4{v@;V`l
z6YdRSR-n8|%!-t^2w9wMZxgdZ<sCv6r^~y<tU!5>kj44#J~1m)J|JM}lUS<XhlDK7
z8;^)tf$}jSi}S`4VpgbpO3328@r;-iD4!FuIB&clW`)X^ge=Y*uZUTJ@--ogkNr2q
ztWf!ukj2OTJ7QL#d{4}ZlphFLoHq)IS)uYHF)LPnayI99vgYV1_0wKh`b@wHBm(9C
z2soT8z7TOj<yQhuMA`X`h!ZKl6L2^;{2=0l$|538to%v9Sx|BLMZ}4e{}OOGhx|vx
z36;NzII;2%5of9VOTbx41h5MA&3z(N1Pw@03us7+TEVJhD3#-&5h*H!)ksk>td3Cu
zuOz3r8U<?*vQ(yn#)K@D?O;t}RtRemvQ*ZCwTW2~G$CZE><8-*vqD&xm=(i%ge;W_
zVSQp&1RD^u7O){9OJ!5oh?o_^#>A``HX&v$VN*gDXV+%LtOzzIW-VX~V%7?_BxG@h
zZAHuqVQXSm4BHU1mar``YYp3Bmfr@p_(B_OPln>m-hm9oiM=B!DukWLP@L8~lc6{>
zcOgZEuq!DlhTX_eoR+(jq9SNYhT_E9gA^6Qo}{Q4_98_sp&1#9lWK2LR0R8wq86|(
zDQX4H$xxh71*E7D3Q18h6p^BqP|P1KzJv%Z$WWXSEy+-v5v|BjoYt&KQ4#D%hT@Fa
zpA;3s0i>uH{zHc1j5v@K6+u9T;*2<m6cs`nQdA5FlcJW;mJG!i(T)@q!69TQ&P_u}
zQ6U^gii+WIQq&TTz^Lw-_;^_$UDUxw;ens38i%VNxI6f09{i99C4J2$0<i@g$&bam
zJc<?4tUW&#=R>yNQJB?zP(fp}tq)awfGY1nf02~}`qG^_a0eLAMso+KR7-_o40nL>
z-w^}4&)byofxhIyIx&_9!Fb`sgJ9ek$Ae(}7>@}(V^KWt%vem|4lrI!<PI=SOyUkO
zKH%aSrJk(Ojzx*bxv2*=*wL8Gi(x#O!i!;?naYb{{F#Os-G}eW^GA1jP3H$O9?jqf
zF)m5?L5xo>7}9;zzC53Frka!&!+7M%i(wpc<Ha!kxMN258BUEqcJi4sWss^PBO5{`
zGaui%xD0@H=E(?1#?G01NS%!9fl1wS`m)weq@KW)QdVnnFB4Et5|oLN9HZs0P1+c-
zy=ta2<LfM5-Rdk&vw5L9aq_~bZeajToHS#JANQiN2;-r*e!Y%q3ar<y?x1OZgkq)-
z^+b@LIsFu(cDnfRL6{-)<%2NcR`Nj@-yufIUja3~(9ck7UGd{VFlMRrn<Zf5#W?TJ
z2Vr`d!v|rU58&cT@zi2E3B-i%mw2^9PgQU5lWC6$-OU=a?#?CVnYhd&<{A6v6Z1^O
z7GT~|=a!K^|8+CMLjDHm<lRNYJQKjh#5@zgAYz^g;1bN2zk-hQ_qL&?kd!Jepotk{
zb1-Jg&o>mKNomFNl$mEsF;f2KgF?z=Yo?!NmD<KaI=OH;X6OQAGA}Q`5+%>5bAUNA
zx||tYQIQ5eJBc3<^Y?=*v4$=vQL3FWP)-#oqaO!`Ar*-<b-t+YY{6CfMEKguYJDQ=
z+fZ<gevtr%>J#BBBWv}Ggm9fc5%rBFxL&_V05|9tiQq<kB7Ci4lYWs9hUpiHp<17a
z`hF4&*Dn&l&H6<mxJAFn3U1XW!WR>^=@$v%cKsqT+@W7&33p-<y?LPzgp&20bbc-_
z2nBaxJzdyHubw(^VFb74=>&xJyLsrT3<URJJzcS{j5+p9TBEjJaIan!?mJSi3ir4V
ztF)P;WRUFXJv;6&s<NhVLc<Qj{rZ~1{T--Ggp)8fJsOMX>PBV4P`WM^jKSItculQT
zi<>=IakC}MLD9~{>esTPd<bjlDv)JNC|QUJ##OGP+r!~L%t43!iRYlhF;Bp{Hsyv0
z+lL1bcbiywb67@)CaH2A9z<G~jCFKPPdY4R>leWz6)Tu6Elk0RW~}KY+Yr!GB^3+k
zrJC-9tshcZ<sq2H7sAm_#}K{O*WVKpfTNh8uPbpNa2FYT06enCDsrTP%0cwF9LG?5
zHm2H;=@jX~Ga?f!JLpr=jb?Fb6gznWE43-NMEB*D+<^$o=?X-pg6L3MjvLReSgoyb
zqbaxpb1F8al$!SOB<IGlDY=~0cqC6@b-9C5vWN>FlsryK+-5#jmK*6Zm3DB$r?FhS
zc9s~JGIBZ`XSg?y<8hX|92<WQ%gY^id8sNvSbe@Cb(yL>*wYJ~)!6WhoYmNpOIY2Z
zoMWb>B}{&}jHTt}t_q6%&{4mFA-Z4~eLRfDwX|J*s7j60tqw2QV3{gFCR3F7)O{9J
z@QS(ycNKGVL7!6GP&xEd*?Lh$wEa}LxDS2#%SMA;tEfBXmP&<O0p{qlF1ovNO23q@
z9R#oQLU7#!cmpH!`JldDaO@<wzyiF<kD>dy#o07!!qDY>;B8(AZP^`O2yNJ1UI;Gx
z0Pk@|sOil3a-SDM`|^MnLi_TN7ef2;2qTq_KU-jkI_?=~9`j>pZ=UdDXm_4sMtgLZ
za|E!q(UTL`&w|f*LbP?yc|x>#FL*+9ykBC7TfEr=;T1oI_UJV~hIZ%;cZQwVZ}~B_
zZSVLov~BPCF?6gy=w;aIK<wNu<j2tdeB{T_{(R!c(EfbJOr^&I>yP$$_#aP*_UH>w
zh<52KPl)#E8-^-99$25)<Ka6$hW6+OKZbUwh#y1y^OHNn9z(zQF|<Gb@?&U!{^Q5c
z{`|%aeb29={Xw}Ej_@_kKV&Gr^7)q(r5@X%{%!_=!T2hv0VyhkhGZzdqFR*{6+k0W
zR0OM$q4=6?by8FaYmlO1XiSFUtGYEwQ30$)ii%)uQq&5XkfHc$aUD{WdR&JTrJmLy
zMJ-`{Qq&qYz$pFA0M5CIIf<d>L_<OrC$>g}EY56=30a(<nh>%$%QPissb_TvS)44I
z6SDZYZ9&WmU`s+4A49E(S?XCGVwQSVhnTg7Z86JloyPkqJSE$ap?F5NCqwas>_CbN
zU`H|(PsdKAs1SB0L-9oJLW&AtS5j02yOE*z2<T3V3ZW?}Duz8sQA^m96t#xE_@j8|
zj*lEOQd9(clcD&a>qCl)VP7&7AFt-5r~nE`Q4ti9q83m@hT<$CCPjtNf)o`)OH$Ml
zT9KhRH(8US0@#lf6~X?bs0AEAidw;c$WWXS2a=*f2uM*e97Kv*LK{-l8V<&&_C`lJ
z*IkRx`E?4<KwJJ8^_@0o#~;I+@F66a5Dw*!;Ro7=kzgV?oIi#${0I_E2uJeA@Kb2^
zB$x<}BEc-61Ah#s<k2LU5RM_i#L$sHhMzVYOM;1@6A5Mk$MMH-CL2$J3E>11ObjQI
zV3u$a31$uPAI&XsYgb?9Vy==?F_}!j;oLQafWygaDiJ4y(+D`6zNQm#A~=J9!wF16
z#0jAb5hsTD&x7+FcbxiMi8v8-BjPNeI{}BYpNxnT!kI*z7<v$Kme7-c!--Q)#EIZ6
zBF+NNCgQB17XgQJt~U`UgbE@~41I_=OXy3)Swkh}xbGP0J9$)CAb$*JT|fR9PP!@*
zObGq?V>so`A;Cm2fIo&4ZXgLJgmd|0IBm`&!9;LA31$Ho@W*h@Tu6cm;UW@D3>Wjq
zaN-Lh!9;Kg31$I<`C~YHEhWK(a2W|EhRaDXYq)|RM&Ep=d|SyM!?`4c1QWtl{4tzM
zR`bVjQdmQR31KLI3@3%PB$x=UBf%`-dj1$r3L8i;A>7Cx!$<cf5=;ccNH7biCc&&=
zIDZT$h0P?G5N;vC#BeJKW(~JtjQ-2Y^c`Z&qoU>2G@;K0*+;UsV^I4Y;mSaqNmy<N
z=Ct3r)^Kb=5=}46Q<6J5s+q?lcX3oR4~j-`R5Oo-?#Aj)?02rq*j?--WA+|yV#eyd
z+{BF0k=(?L&HJ!e`*4WXW^J(!-Ec>72N>J;a|amv4{!$<AEGg!ePW<IAMj?GnqN!@
zG5Ym7Lv@g|p7A)Av!1c%5NAE(ZyeUsf8Sf@fYd&;u6ddme<73dnwfBic~Xoo@jNNU
zqXeE5<5wc4v?oBCaV+bXW=1ldC2{RcXHb)QQcPb*cv6gGDf%2^AIsLsgQ*znSSFun
zMz>hYj8hucmd%-(@(<>kN+Qf$Nav_#+CIur&4eg}qnZiLF|5`;9Hbd@t=*cjW(+^h
zRnAzR$yLsnp2bzp*nR@bD~ow?)?rLX9Mz2F*&Nl3;W-@DjNK>osdWyNT#jnS?o%Aq
zjNN%0)r{Twm8(mYI62Kx&Ded0qnfe%EJrnC_c^Stc#fAYn{r-X<2uvof<Cp*U|!^?
zW`c5wqnZiIWsYhlC|9srSSGoRpbAcuSAa#62AHm{Vp#j7MQzq7AJ)l~*Dzalw@^;u
z4yLby3iYM4HWRe#Sl^y<Y_z|dmrP!wn#N!se}%hT;W5~UDXDP-EAeCYWt6r)-o8>d
zl|ts{2XA5(er&poYKR;CNS)kGu9^#PVHtizxvVTug`d2;jRp7-`!a%|KG1t8)twK7
zcd)2^c_IhtEFWkSDEAvBQ+TL6;oS<GD^U>S9u{>dw>i0DC{>w@del$qEmO%LypN^j
z2BT#0kOx@RqPzyj`FP3QaUdR6*pQ~cNMGt38;|s=sJ|}^AL~`&VkJ*Fs08q-UKPG3
z@{EH@2%qa!;cr&G;Ghz~mmE|g_)4z|Uo3geK_!H5IH<(%tzH%WM%6nGDgk`YK_!A8
zIH)XOp<WffM)Hw^N(eu3P>JDZ4k}CdKfNmaO{Fg!R08;wgGvOyaZp*n?;KQC@P}R%
zzFtzqK_!GgIjF?&7YCIk{Fj5u8vch>_$<0Ox0bA5qVuz+;LC3e;6;c7KrQ$14-Y-H
z+QGjZ4WgG-+(DJ9+&rKG+=BrIICy|JD_C!c^(B_El3}r@&rWdDuqu|7SO&_<u(d{d
zRk+J)m8!5|_$mDAl^TXsv|%;$Hio-2u2e-S=q_vORbeM<VO7WS=SayyF<4uhqZZp}
zg0-D0Z<n1Hb-0Rg%XK+efdh)Q^{}>G`BvzZtErELxU5Y%hl)msL(qVO4tLy8Psgn5
zjkpMLi;ea4j9tbvt%;rnv5uZ=O*u4(J8q^&M``Geo9pQq>*$VKaA*+6x+T`(nmWZ}
zQnDZpeW?Mq!io|bHC+YWS?fw0!QHf}RDmPV7Ax>2qhdp})k5%39#E>1xwD_q1y|^<
z+hGh}LF0^JbK3K!u!$Wog$wp@>5Cq&j=TtLStniuwyHBG@MF+rtg4`951znXFjQ{X
zDuC!<cjem^_NW_Q2s_msLnTf(*pZi%sVQWNr6rPU1yb699^9J6X7}VK#m4r+QhZgQ
z%m|bzDTHHhhUF#J+Y$zsu0TW^-J5&!*zi8w<=FVXl~_|=%_4KGFMni87Zws=Y55~l
zQc621<kl>9P{d7&ofBheiQQa@P?ukV$N~f9k4+f>+hSR<zI0U~+D$90FMq0(*5l@_
zxy!M;{jj|Ju_@6yotgS$Y58MQQc4>=fLpWJ;D0JKxMZ~=wqDjiEH5|QW#qIafP3@U
znnB#<ID9r(j_-07AII9FN0pZ}8jLx7TeS?Qr>2oD2645AVz8Vq=$0vJWXF%8D;*5s
z$Iz7yhGM3~vQmj{cxaeXIKy~Cv~|OILbQ1!xVuEn1jf3N{202hggrloc4!nohW5vS
zJ3~!X#-Gvr7}}pP{21CFM}7?L&sfY<K7H6~Mbx6mION0=qCFbN6QW%j&l943nt-7a
zo2GIO3Dzg=F)@)ZMSC@gFGaiM%$K75nv5xqW5pg!Q+PtOS5tXHv{Tb~LbOlQc|hy|
zHG?Na`y}BB(LTBGglM0n`XOdY+D^o4JabIB@`Pxg+;~E?PwqS++9w%?DnF)JpR~u+
zOuiKDl?PvncFU75Mf)YkROQDM>lb@W&Eg5sUd`qS(N1~sglM0<c|hzjrQiwCKKby3
zXrFv}LbOjx4B`8a6>q`Ht>}dBDM3OO-)ZtAW(811$l|+F{=}>h&LL#+9jpLiRsaKu
zSrME|$l`lo^N3j?oKMV(;Q~Sy-$h$U%nINlVpaqf6SDXYTM#iTgiDB7F$^YVE#Xo^
z7T>vBM$8J}a$;5lR}ixna3wKo1w#l~e4lU?F)M_tiCHmRL(E#jP-4~^uEi|=G7XRQ
zh}joW!CFTO;}vN=IZXYD6H*wjNgK&wA>2d?<5ek)92P(|IV^(Vq%dBXHj~5DBM0O#
z_22<1jMt`Z<gfs4Cx=CF2Puq~r=8@m5bh#}#V~>#wuHM$VZ21`A%_KUFF7oNk>s!i
z+(!;u!6;G~uT%TUVIe#~4vS$lIcy1I$YE=E5W_sro#=C2DqgXKEMBP&5wijqN66xJ
z>M$`Ygz<zdUZoO<SpiHWW<@ZGki|<>GBGQJM~GQ5Od(|P`jkq{3Sb&BD}w37tOYzu
z$l`@9gP0Y<W5lc&9w%lkVJ0Dq7qu*6Rsc^Bvm%IySqqp=%v!-5LKd%QCy7}h%q3>U
z@Dwp?3G;|qYnV^K($_etSe+(h@mh9<m=(aYge+dm&JnXhc%G2OYuN>2Rsb&&vm$tj
zki~1+WnxwcuMo3hc$JXFYuPnoRsai#SrNQW%v!)3ge+dmZW6OXc#D`7!`sBHCA>q(
z;<fB9F)M)gh*=T5Pt01t2gIxud`QURwd@fwD};}USuuP<%v!>y#H=-ZhS?I|V=Cu+
z3guQTeNMnpPu9T~1RP$2UJ`La_=<qTbz@!=aU%GJfWzy?TOv*f-w|<Q_@02nrD{G9
zaUxhq#96?P1RT!spNKdi{7l4&;s1y@OZbI=!}W2#5^>biTSOf7JQop1J>f;b;XGVK
z#8FRyQJkzh-;8E0p`HvQ>XCX@jEJM29>ZLTZ-VN}yzHHu-y|T;y?;nRoP7V1fkIft
zh`>jjehtV#5i}$LaRRPN1`44O87PL;NI;x}tCN8uSc43-fW{;sPQx|HKq0I}28v;A
zGSCv5kbpQ9*C7K%ur3*B0qc>0R<J$^h|_TcGEfK`l7V8_hzzuZjmbc3*aU+-w!)g*
z6HN&?oK>3<aYERffWtYp1raBLEeSZBQCksl)Zc+3;;6p?MZn>7+LnkD!FEKP1#C~i
z;au8*h!et&M4T9QBH}DzX95oA(Jn-s2zDjnEMPYx&I)!X;BXE#CE|pz2N5TRJ&8C=
z*o%m>hGslD%_Z^P1RUPZ_95VK-t9}o386Uwhx4w0h@<|169I?wu84>eLNO61h86@I
z&byXGoCsPGaTd^;fWvvW9}y>n{fRg+96-cb!hZ-joOcHjaUuwaI14z4h_iw=1RT!0
zgNZmHv?b!i(2j_+ghPlpYd92hB`zdr>Y|lbsuw@%L)8XlYL*S-0piUr3l8T2;w(>r
zO!>DF80@V5#;V3tw#aX>eM}9ukyu^g0q8Pn`jQA+>eQaAobi4XS2<&h16MiY>1ZtP
zT#2W}0cEO0j^U_gEO+FnW(*(8QO(%xq)%Nuo{Zh&II0=D$8%IOc2D4_X6&Ab)g_+Z
z*UlAfN#o+l#h5;cJHS})%pG7Hn9Lnue3*iP5;a50^FepYPvt={UQFXbFm6oeK`?&I
zz=WQ$(3$=c?f~P33wMBVLdqRrd~oFe=o|`e+yTZ1ckTe=gN!@C_%IU#CCcPz=2O|y
z$~tM+17jtwgH(*^PDW4O91{pRZ;pw_EZ!Uwmf4u&6qe#i%5>+&8Pk~;-h448C<?w9
zW26sXj0uS^#ws0hw(4o|RAD$J=E~W6XlEG9>CP3%y~E-`U^?`}T&J?js-`-2v2{!g
zReHoaE&J;c>+ECZU~xG+6Kw%&9YX@R${8mEvAjg36U_mrZCw*g#?QHWo7c&<^YqGf
zCh&Z&a>keiT;<G!UC33=gl3T*d8um9i?O_tNR}?b9K>1ASigj`o-sdIulYJ7wN$TM
zXQY;Kl`|u?oU5Gibp=;B<LXK*FY$1ib`qCgty$-Q3E>GBM~yLb6;D_vhO5b7CZcP|
zV8-lFGMI_>S`3%7<)Z3aYf_^oXE4Az43u+ZlmK+%vcBRD*c7ibgc~qW&SsYCfCV%r
zG11$|p$naqy@>-*>;%(87zM~wP))tK_6~QamJ$3fw5~!jQzljULz$mMu8^o5f{j9r
z-Mpv*Yt#p7&z`1B)C<+!J$rlh^)$CPT(0&Mde-!;>sc?<P;RAO6|z$8r0#BC)w9v)
z(W6KHrT)?X*;i4iT|KQsJp0+#_jj#<Kd1gNJyxk=Q2ayqnBpHoYbYdgsv>ro{tR^b
z6Y=a1e~l^JQPW2?Hy_!|vOQ4#t|;NuOs-BDYW;a{)@977%;RX=&6+d*{0T=IKQ*s@
z-dmq1_udaQ?@PZ9YTuw$^~;&;?;Vc}TG0CCS(LTDo5{4FIUsrW_t_J7#vzNoW8Pg2
zT!((nUUmIPbp)c_F0aVkoP+AW5HD%}-v;0?OKO}Y?S~FLnD@H~rj)Ux+KjZvGwRL)
zxt9{E&aV~8_UAig;)pqZIqZ9lee2f5{gl+o0nd$;E`8H;QSaK0og3fZ$F}=u^89?$
z#))OPGc7lTJk5+pVW)EqW}7Fm`ofoECZCh-19OuU=6l}eqMQ57nuKH?VSk_J-2YE+
z=PT@cjUAfTkfuZ6oQs=*Y;M3TQK2u}@8$ZFrC(0wp=Gbr0)Nc7fZh!2v-OSJKD4;*
ztEp$-Ywh)aZ2I?+K?-si^eb|{=~M8)dq<yt4Ud7;XP0(I{PhBJZq?X2<w-Kz|9iU*
zErv`lKvNQuch<5#j*6BQUOnu53ycLdznI-|L1(<8zA66PW$k!<fBZI|no;cgI_(^z
zJ1@xtpIcos{}ddHI{#YVG3M(D_V;TRN)4a%x{16dru3XM{2VB{n=$w1gcwxh`Ejw~
zn%!vFx}o<IQnm35G_8F*BPABd?c?o51D~+%ytiEXSgeXie>d!CFsZ*M>eBP~rt`n|
zfe7*PS9^`FvN}y1otsqI^zwg~(7?i_f!|kUAZveVm*H1)(5xe^w+^baA9ZdKTU9A<
z1YTy=?^kHO1Uw9zt==|pEBbq)?xbIl``Gp_+il#J=6n_0m^FO*-1t<aX<zed{KM&E
z?f7M=%GAKcfAgk-(?+M_Ebs3?amh9QNtuw%>eEv?PI>y_4EuhbZ{h1@%jU7~HSK9$
z`(GclZeR3Lpn3oOfB6G$wONI(SS8f#<+2sU-CFzSUdvFhWM6|(hcjc*$y$%H!pzmI
zUc))}a*)+*vIWF8AF@ASbsF1WQtF|IZ69}{=>{3mYR4#4)i8Wj!{K|`-+L_lX6qW1
zg!~Fmw|$<R1frG~404)(1WlZy$h;UI2O2ee-OulO3Rr%wwS#ZHli*0_8{2!zSAnkw
zLwxI<ISD45?`Ugmyoa^tR(6r#=l_z?kQ-q}6Ra|k$)5FjPgbU(=0Q`ho9>8Z`vu=m
zEo&4Wjb0X9PyBE&p5?#n%<s~5c`o~2<Dcf$q>;(?ch#am4`;`7&8uts)%;%bI$+E*
z$BB2cQP-?`xt=}a!G5o(%Te_rz{yuz{FW?DLi-KscUjRamF;Kp#h*9q4ELioh28xo
zZQ6)xtBlUZ+N@^n_3vrkZ0!&2@u2CaqSr$ScN$sw9AMiotqYI;Q_%auR<`}Ik%N@J
zMX4YsuJ_kfd*YDgP)R~?U?ThbkhK<lUzqPk&(?k)wRGAc)GPAxxE(MDbh_92+BCC0
ztnSA)6U+ZxHlU}m`>Ssfrj+U5@z=&%1@*OdMXtHDc30osAi*|BJ!45Adg6Oy`%kYZ
z5Ndb%?!z4$P~+N`8PN@Qpc+3WWxh09g5D{XcF&x$280i3GjYG_INSc57wbfEO;4eS
zKKWO(Z8BMVKK)FzYifLmeQ(ly@U|5NNkIOrnTh|r-7NpJ-A(7y4>q&!HSv0QM_MZ}
zH~>vNzGUH#TH);P3m;4#+9~ZQ$Xzn|(fjBuwta<5tH|fg^MGx;@Gsq+eUYng-<Cn&
zLcl+H^IX1VxUsyZ{Z~D9jvQ3`5NP2s%dT$gBOs;9gE7y7quKWAu1>3+?X?|r+LT?i
z$YVLn&$pa<?viIDtNT>smURC9Ms&#bcIKAQT$K59?fIScGtlg5k?Vx_51_w)CO2H_
zca-Ia)q6C$TF*!@<%Yq1`+=uG)6|rpZvW(=Q^#5hJG|AdcWZaLInDUH7bSEsK2@U|
zLZ+>t^Pi`y*nX||tO)b!HXnVQ{jNsGcX{mR`9~THp5F}z?=D=i4Cs3cnS}PP|KWBx
z7#3~QZ1>-NNVdOCjmJ#`K<|D>XKnj)j^)PK!3)7o2f!TrpykqmS>XMX(E&Ff9s!ws
z(?=>})o5&thrO%eIn+?C3{Kt=5B9cPhRltJfDIo~n*8IJhTaa|&~wwDMAXc5rLaxw
z9MJU6<1I}<2paq>X5?c3wZLn|^Pq^PxnRbtuD7p5YuD+}wcS><sGkhlwi)efl9i3p
zwoKmDMU=$GYwH+w>c7_yqs51NEu6n_J2<u|^?Zu$de-ix=b}%yypWCN-hVr^XKp5H
z?rP)GpnEvDC0ciL&+L65>utX+kGq~^^}Qy>S!Fusf%RK@RDJm;4iq_8J>JzK8(cW>
z(QQKOxop2Lry5KOP7OmQd9{B{9=-;QGMlg|f8Y+b9nC!2n!RyjgX+mFr}_N5<2{#A
z#u2REv`({5>R-9wM|`u5iHV8GBqyVAnbASiZinKKAoVhO1+zycpWB7n9eDbvLGwdk
zPx$1w1r}Su?b8i+^q6uM{E@mY?RGaCd>egz%Ddo1U>je>rLKA*7#Vp@`6eO`yu3O2
z@P*@h(WlStlA62j1y%a*dF<tv3=X$_^XXyGanR?QX-=FCm5(Ek`R@}6tX(EOHn=Y^
ziUl(dZ%GWdIt$i%O445D#<2b@S+(Ba=_EB6q3rnl+odejGBU*1^161utr9-mKCk{!
zw!QnQjsB_kdjR;*x!=4qH!h&wjlv68+MYuH{l47Odc`@E-pTLZT2uC;UCW{xHlK#T
z@=ae?wJ3}N+iLFHkr|c){@p(=Ft%1cSk^f(?P~KA==;{MBOKSAW!u-p*QB6x`l#;O
z^(<Q&lX_wK8P;x}`jfkyd2}Ags;!R-4h};haXD#u2`T8npZE>isJyVm_H(Y&lmw7>
zBhRG2%@XvV)l7M?>j6;k=d9t=w`KRa4;Qyc{%|K61o<qz)Op1&wjYf>Ll3nz{n<Gi
z*@^EPWu4DKr^D2Zy7iAn{le<c30u1WtV@h(s&dxm%?4?Pqg1Ba^<UGD=Jly%r?`pl
z*MiBG^UPP?K8XARF75yNXeT;3{$OH}U<Df7=k<<hZMFNb>E}E$Zk@JA8*H1UyVlA<
zZSNFFdZH8PgjwjC+byHP<$Hev{^u0S+CA*Zljp7C)yT?dOGs-mVn5gP-~7;wW=M4$
zO>EvLYD(3MV1jXe>ed%~P@fTDuZ>qN0|{S(f@V+Hk9_ln58Yv%3{00axILp<G&ncb
zv);mt40L)E{C+q18p;jn_1fZ82r!l({js`JHrV4>_4l8%xk%HG=5@K_^=4N#oB}mX
z4DN_;Y2!5L#!d6ctv6ZwUY)7&P!e(n8PB|SdxqZy)YxdY<Z06cByX!|Gkj?x@H~CZ
zzU9Kp=$Xr-*y&fJLF$}`%?e|;fUPD+ch2pR3~EX(N1E@s1l|=UOulg-4ctg<Zk7~z
z6hsc56Emb*3K%#3r16V6so-0KS{_55r=vpCz|Z4tW6+GCOaFv7$pnGxb5ruCWT21n
zBW;Gf4g)vZ9^1TZQ2}e;*k2dA|M%JqJsq&(K&^}oVDglRFKVfFKVBG=z9sGBI@HqT
z?tA-bnZV$x>DC%2vOuq2E|TxBPNDN1XKY?{Jq^rWKWO}w=!<N-Gv0nWHn8SZ^zf=(
z^t)I7;NHl7c6VZukfT%h#ldO$VDsb7S-Focf_~=nX8gA!6}`0^)5*~IEb9KMWuH2Y
zQqd*p*E(;%9YnB~r%Au#;xh4HmpiG-l+Ib`%dn885s}B(-@iO>V|u7n2>V_$Ue}9$
z7EDi%Mk#$>o<G_57`m=*KIPi2WU#(yVe|DlM^W8b!4}G&St!J+cISwC`%#R?%_lRW
z(m?(T^#IWjZ9FvX9W}8__h=r73YOjqZ|c68?Jrr@YKz&;Kp=rFg!T@HfJU!*Judgl
z8v1kvt2cOGz4_Hx?fSCvzu}DsXAeQq@<;8h6SV7!hCeu5wmY9X9~iXuZ?mL{R6gkw
zG2VI6KGd-3fUUo_9!DYhpTBK7u??l<|CV~p*@LzpDU_z&T?_ts`E~J)iJ7R?!^0OY
zFA<>Y4MPrm7eLmI&q3yQ@;{$O5wg&rE<fjj-fK?m+tESm*UQOo-!EH-SpA2MX0pjM
zQo*`bL!Mtw(eCT!`Yr4!^evnJH1@ZTNgppaJc&+=&l*1(dK#sDyr@|7R(oDD;PAM5
z;hQ3mO~7-rYTZ-Ng>eU6d{o+fpr)N&t@r-^I7H3b^Zajqe47^9^WyzuJ59fIXaUgZ
zWr>G=d>nWTrPkbk=IiZrV7O@8$XB<Lz*IN8yH!NV;D#)=OU&U@Xz}{K_tbUIv7Cn2
zyiUGw+Gb-x2HS6k$q7F`7;5)nK?}y#D)Q2v{{~y`IXIqL7q=%wElhDpLND##^$}h;
zj@C`9EAa1@1SV{FzA55k*>TqNSG4n*;?g{XE<f0Idco~9;ObW+<x&0$Fn9fTw>PoJ
zfr-Paf)_K_R%oxLozky)HE(z89KHeAFPc%S%1dp0TU84@yZNSeU$+3x3Q9Yh3)Y+X
z=2?g2f<AF;h12gxfOh>B+}t%U5H;Q#*S2$;%V5gQMjy8tY0u|0{q6WR&+%v2QLy8F
z^P;9(k05Ds+r`JMR|AK*BWW#*62Sd?)q6BKmkZi<P=0&k5(66do%Bx=n>;Y6Xjt9F
zi?4wNbAKFn4$nb{H}2e=a552Hzw&W!a(;hg_<LPWV&*Y4VqvGI*0mDRY{jSvKVQeQ
z<6_o$)YRA!o6+o6c{8834F?IUGw*d<b{d!sKRUs*N!jzU)H9-Mp560-(csUnGwd(2
z?P&bay!sTFjC<m~58N?+@V@!&MBt&G;~#Aqjdtx6w)iz*Kg&sOT-fSeq}|7D{~&c4
zc{mQ;EQqMS?NtIhUYCa4XxBlQ2@2M{_6zQ>)oc2TkH}e+XO)gxb>2MV<n&#r-qwBA
z=bA<V*SXy+eC8&jfoI*1WVJiZ_PeLaA+Ki}qtLwp2duu|%V$5=wAaeGL;i$qF6c?i
z-o~{>LqUppc+Yyd2s{kD>16OM4Y+I{ad$w$DlpCP?bi6)`@v_mub^?WQ{eXaMI%}s
z$wC8F3E$#goCfWd9?UR*eiYRX`0w4m814GE?c^7UcfTa`-MEJ2OY1%8{)5_a`wkod
z)>Wz`%t^`xf=SPkr|wBc)B4TG%UYiUh9za)zGb%={doS$v|EiUDE)?8qoLQd=Ytcc
zM&7p0hy=35TgT>ZS%zMZY!Th#Ogw0OE5UJUK?+h%*dDuR?@45Fa7%|Fv!hY(jeAZP
zx@}<nHd-*f&gmYJXv5Xu`WXwCqd}&tJ6O6zpv*Uu`?X%8J+Icpr}V4UhhD24+_n3w
z&2`t#RLqD3%6Y2vu94dFywcpM6CJP5z3307eA^V}-SRwG@^<0y?oaolzUPf@0sn2t
zdi98A=gkw*=AeGT{tGUm51-r5%>OC}C}_{176*@l-Df6kSma5q_Y2((+#RFY`BJ(c
z?@g0z#ErLs--V}qI-cLh>RfkQCEs*C%*LTKr+I&HV~yT5&$@!dd7hul7i+JF-d!5@
z!gXFG>N%$K-iCGZP=V6>&Wh{|G;epkQy+cPQ0uCNXGXNtUN1V)^n>5xW(V2+W?fhv
zyns3nJJi%;)EMe~D`CdIMaWKjexd1K^V;<I@(C9fY-R1&e6D$Y(ZzOu_2&Cg;riWs
zi>gLcsMF{*uj`g<TOl;nKh7Gx*!TSPfvP~(56$PzGanA_@>#`x-q7$#jp)Psz)j0h
zmeJFaQ2lB9a)wd)F|JLE;9J(7tWLu>{?TylsNET0^4U!*I*!-wC$pZ}ZfX1?6@*rs
z7=N|9_PqPhynX*vvDO~H|DFu~_`2sYaJOmjCxPQpblmgCn%9D($Rm3~{>;=Abjr5i
zTS~n4yzaDdZgx*w?S6asyBA+RSK9~9&u{+Q>SQYTQ){<vlg(?u@<U+(a>r~?buyeg
zVp3Rzab5Jjaq@>PCy>B@NSE$|7og=*-wv%iW+T&ybAD}%(XMwbALOg#oAXh|*Z3*}
zCS{>s9ePZ;-)Jv*Z@;ur-sn8E^yuf?ertE5i}BXe4|L1{hlTk@k`V3sWp@1I`SItX
z(9(Lp@<#jTpvQ)*9ELWH1lw2o&-vn5cAXr0sa=!k@mJBG?1`ex#Mx}zzqTK?qG((M
zn6F&fC+g}c)~^{~zRmXk_a-Qc?Y1nxsW*}@syCwL&|I+h&OFmWhMB0z;gwg^ozsE!
z+nD%X)V@kHerc=!PG2xO1SB4GI?+X_y^eFG{)EB8oz!)lem!gk_1uM=wqO3V!$rFv
zx^S)L{GL5FgN0Vow!dSjeNDuQ_A48#LE#Cf+l2Mdu9w3%{pq=7`DyTT{Q82`y|a=3
z+v$#{t+T=O8aJw^Ryl}v_jewiYr6@3II!wg{QDem<<~N&?k7*M_Rap$x?SPz9B^Ra
z-=l^<a@fxY&M54^OnMTX`&4C3-}vKT^ZP6Bo7it*e{a2HtWUUe8gkfcGb-s}CWwrx
z_ipOjNO0{z->~kj=7UBDj=BFdjRMPlDaPj?j{!y*o0WFIbHR<Am;D4V66Fk2HQVD#
zU2m@7-@(02>-;b7G-&Cy0S!{bp+)~DdB<NlfQI`%k_>d(1HQNZe6srI6QGr+K~JlC
zF%`B`y7~G&?ytFAxD~|6XI1+lK8tQ&4!QUIavtc`DAc-7)Dh6^O#1YdEB65tNuwPT
zZE`^T+yw)Szoeu8YHaqs-60M|Kd?BMxG4&>F@1NVd&gj~ckGV8bsxkc_ZLr+ru;))
zk0}0U|I2t<Y+xKZa_m2&Z{O#GKR=%|Z}l?|4YY86Ip<^?xaU7G!|2LEkYuNv*SJG8
z>e;FN@03^Cb$sLXu0zKy$V2{)ZFl~+-WNG;xAr)la+z)a?+DX--qr_^zk7b6^Wh}c
z|G)FjCJslZfT()hq``?P0HSV!z=avW;JQiX?zg8v?96!U|C((=zP6|8i!-Cp@=WiC
zzNwqRv!)Y<=6%WlOYb#Fts0n&Bx_E-y0JG3wSBMJ?(sPi^|}>o<mbN^n7!OSywT@T
z;6LSwEjh9SsB6#Y-phJiK#CF9$22;V3O2TWQO*587N{>-;IM5~8rbC7Z@_}9+I`{1
zsPp}eTsEVadQZnqJ+uea|JBVbxqc2>Fe#%)zOOb9Y2v7PeLMY7&d$HF;PFu3tHUi<
zvvJV;-rela?XzvP=lz<`@6Kqv*t*v~FmliGhp~2L^MFP-(>LpF+l|rG`RS-*f`n9H
zpe|B6f3X8*r|Rv=n3#{ixS?+Koz5ex8wd8iNLPV7v)eRXv{Re+3eA6yw!D1~obBf~
zYIgHfls0xz!-hvTgNW9N>0eeZM}H5t8SvXhyB|0^_{XEPHap7rvHQ)q*EfaUNZERD
z<CNf??6?ZQd#W<4YWIms*?zBi(VNiNKoEScm-h33J2gaiWa%ttvvHWcS-@_z@<Nk0
zn<Y7Dd%E+B_Dzo=#o3NY{$I7nyIh{Ibk_PbQ1i+i!xPkXfq+w^2B7ZIXm;Yi_M>-d
z_f-iWH=X!=WIvjsd}noO#96d{POxX@v}0gQ%t*VbyH25|Lr2`Ti9ZU8R>#TPbxKDH
zd%<9zJyEPZRu;pjO7H9kEff8^#EO&9rHIK36Q67I(a7J0Z5K_<M!R12ow)w}b~Zj4
zgN>6i<=X3#&pr$|XIu9mT6Sbor~UP{<C;DD;R3H+*}!RVQI5f!viq#j_v<%2rSbvO
zbN`)`9~K52Jgy7mA@LyW;V_TtuQJfF!IH?o|88gPZF$|yV)N=tpkeCA<O9LmLCWC1
z9U^)hL{6WK{Cq#C0P5l#S#wh;D(amyDZuO$P|S54HL9-mcyx#<ST}mK*1jF#6My$^
z9)&t|NL`uGM2%dM@^){Jm<Bq%w6pBDYz^zLW?tTW9CadWV-T1VQ)}A!8XoNL-}JlK
zHQ??MwChaO$ENL9gZ_(u$X?n;f*}rbq^AByfm6!XV8_N`VA-EVRay*7K_>#n>^WtA
z9E_j#CdvKY9`InT!N55?4}b`v{79d$K#=Qm&;H)<c+|0$Z}gKbd0?ikGOYUu?Rjy)
zhv#{9V>f^UO?QtSJ#QLF@VIUF<mo1mb#bPDVfF!_>?PeaYvNvT^32%>W9Di7uX<0u
zcTYe%INJALNB`-&LCE0W4lQD}=Z)`X`@Xk(uf49?=u)cNl=BGeozi4ke*RoE_^d*?
za!4{r?l;lk!G<i>|0Yv+E<_pH>-veO(;rm1zlj~U+;)l#xA~huf%C>``2|^^SzbZz
z{tfHVJ*UYos+_|hdic<>`(t*XmsvG7q$Fyux8!t<Z{8~T1n4oZ^WLSVM^OJSc}X2+
z#h~>r_B*=GKY%tYO}jSJJr!KszU1P(b|=Aj<D0=Xx9tJlqpJ;1FgpSUH1;==oec*W
z{i?sNe^`6}XWeVR+A*I`p$i`$SkL@+232>s@n*ov)4*%a|DLW**bPD>Ofu81Ww8Ef
z#y@VJpV@tvEvUBm$G{d%wEN`n&;4&d^U&spE%*B;rq9kspFajJ3p39^Q}=(e@Dk>N
zwar4lrB%rTjt~BAkzf>szWsWU`+ZOtYL(LCK@N3Y?&JX{wZYUR(00(4Z%RKodQbz1
zV^(PQ|GR3`DEN41Cph))k!kyJcff_GJNhq7U5hSOu`xW{awjlYcP(;r7D5ZQe+mki
zm5G+`|JvozQWw^bK!ZMZ>6XbT^3IJ<1Ny84w=Nqd92Mq)j3-Y<o<2@pzqL#4SMBc+
zG{mA|#OTyqlr!JdWzFMxpp9gVam&;T$n3NC0B6fHVC%YILl^%7VEe&k+W77pQ2UAg
zW(NeBD5XR6@n!w9QG+3?e<;VyN725bBR<=&vHfe}SoG|Q$-8HHU`4>20j>te!2A{~
zT#EdnSY2vry*D2|p9F2YKI?TfU5#qTws<-@a5XZ_?|)@)%@fG+@uxQ%*F>SYtsh?L
zV6zl>4SLeEVDTZ)w#5|VBE?bg_*Zs-@2?2pFvWOkw}5RZD9!5pz~=`+*QmWsGc2_E
zvrg3@?@mW!QN)3tm)?uC*Tvkoin?umcmrwd&70Kc(uiAe$ZWvOwnuKKqo<QhVz=DN
zMf*%V;?Ub1l#&?o^x&4A=-{7~G4m|E!IqY9(!_tX*SD`5eM5=~iJ<C$L$&*y*~qqg
zYm#3??ulg3^X;)t8ztKPsHWcm>#q(^KYtnhPx#<<%|h*Q*(6BOuklDF8!wH%Wh?K!
zBTi}O;m@uItKG6qL@OUR5v;e<-lrH8P&3daUz@*=q>1nTfyY6|W?gOt4UPgY7kq1F
zIXeriY-DR&)OsVB9^3fE*=pz5{(4ujKc`LzX5X(vpVsbJ5f5qyZJ8_Wv>B{$${O11
zt@b{{<W~DsK{xWiO)rsmx<Z?eG<JvgE&eIAmYn)itk6y7t1A12BlaszPV5(?s?%SO
x`kUB(adgI`_aGeq>0kUWw7$e|wwFu_6%zctLAj4Y9a_!2x3G6#wZCic{{v3iKW+d3

literal 0
HcmV?d00001

diff --git a/1.train_models/log_reg_plates_cp_fs_data/plate_4/trained_models/log_reg_shuf_cp_fs_data_plate_4.joblib b/1.train_models/log_reg_plates_cp_fs_data/plate_4/trained_models/log_reg_shuf_cp_fs_data_plate_4.joblib
new file mode 100644
index 0000000000000000000000000000000000000000..57eb5c41a1041084e0f88cce5621d8bceedb12e3
GIT binary patch
literal 70879
zcmbWAbwCtP8^`ScyAuNg3-yAqMgdVl5K$59MdE-{>V`wH6Gg;6^@oWlpcsG%A|gX6
zf~b^YcXzk)?(A}V9Cf?nA0F}j%skICv(IeJ!}2=Y9c$H~{{`##&h?NuLN9#}sTcL>
z;OXrm@z8hh@OG2>%B9YV;1=UczqFOOL5Z)g)Z0t3P0?qCVu?a8xW13X%h5x=KoP7Z
z@o>a|mqe}zuH)k8=%H8_TwCt#p%?=?7(9C2$#g()O;bg1YcD@fp9T8P-cX|N>E|Jr
zIzs43@%4P29X%W&)pT%OT0(ug$QSrX@K0*F8Y$KVu2tA7^ek%!*Bqv>wzjq?q5jeT
zS=Nv%oJ<?c+b34Yemnq*HIy#6v8z<>AoY?<ptHnBt_Tcn&VJ*7yOMgjDJ*LSH*%)T
z_H~#qk-E9d71qIxpre<Ix2J=z+)*x}zOU!&?J-XRDVKa5-5eFc4LlwF9i&vN3ab~j
zgSBZ79OyO_!L_~TQNsF^+{xQlqOhzHtTo>e(rrOG6^(jc4s*Pne5qC&cno%cj&iBD
z!o87u3)2RRx)wPU9C}r1dUIEaqudWl9K0MoCBBps4vOHG6zL&#(x*e?;3IXWMokgi
z+!_aS6pr9j=;-4^nZ*uG17ANU#xVEB!S%gdm^kC``no$(VYOOWCxH6K8@f=Gdqejo
z?oEShO;C&T;&O2YRGfpg96da|=R0_MI{HvPbz}^p8+V|h>gMGs@sc|@Es#rm6_(BX
zoR-&erX}S^T+0DUoV~q#<<QSrt|hC%sI*G$)RNV-tPvoq<?P^0%|~ZnEr}QYLQ7WL
zz9uzqon&?F>rtN`R1Cca%j&L?)w7k=Un^^1D{H7{SrfY^(<*I|o<v$QZF@Z9Cm6{Z
zQ4>kl*jCnrno4wIi)BsKrxTFNnmMhTC2Ou{-;QET7s$PRs9ECaFbYZ>C*k1HU&&h7
z>sIk=6K_8+7ixx?c>7~U*3!O96-rZYPaj8TxfgX{$y(WWtwJ^0*_nzelsZf03uLYB
zJ5(j}ms2uX8+)B91m@n*)12zg8_L>NX}p!=9B(+vU+Ozv;^iiHm$j?1IV*{ym#w3V
z)X!JezUt<rUTV#Cu<ulbb(6e3q%PRQj#Y+hx&(Sj=Smy~ISi6@(x@8jFj&@Eqe?)v
zrNcobkaf|h5>h>O<)9MEx@lC2D7(6IPzhwZ98@A%4~;4@WqnT$Dxs_w2bEaXTcgT=
z@==e2N+9dQK_!y)<)AW<_0y;_q$1IugGwkHz(Hjw)7Pjnq9QSngGwM9#6cyJ4d$RS
zkO?%ZjHyTnIjDp(5eJo6Cgz|rmKoUhRZ9}4-VjnJ7}SdC<)HTUG_ix(D4TIILyiCz
zJB%^6ks0v;Y$?Flz7HppsKy<zen`1&Ue;_&2UDftL(9dZq6}L*Orr{SIlS5~Y1gTK
zWg|4paGyZ440k%RS{aT8JwT(X^?+&!heT##->b?XTTy3b66mW6ovD3KPGang8Ha{h
zTSs#cV~c6W%&QSkpw0z79DP(KkEzDwvSMuVSdLme2;(>y!A^Y(u43G>B?l{T;IMYQ
zefKH{#CEEwDhyWk-82eu2&_5iaK{rgbj(hD8!kfJ^F%H}+_kL+A&w0_PbO*bMH$4&
z8gx{r^r13EL&sQ0cWlR@LG1EW`;KaZGKRVo@}n-vs53H$!E~4Q<xbty6?A9Qs%->!
zGrd{`4(W_)6aw0inbj(A8?)>OsyQ=`x)SvA#jfD5+^CB$i3|I)(JpQhy50ZT58_GD
zPCM}K3<qL1Zwfo+Xy1>!iL_Hr_WgMfv_sDJ`c)v~z2{5dL_bF;mwHIp0Mh-q@P%*?
zBzz$p16TVVRhVZr%1qrTw{q!A^;<P5?X^3%X0h2)Zc=RQ9DBX0jHT{8m`Q!9YfEPd
zebtOtz`5m4Gs+lTUQQeB!M%BGjb}A-f3`37fbilj$6@j2F2~0BR6RJ3Dr1-|CaXH)
zWwqD}Sak@g3)YHG`j$HtWEBqh0+;=c4hkJ}IgbvoL4NkVtC|857ipO;=;LT!m90;b
zm&;kSHS?<sdIdc;#-F<!kI{lE56~(2epAI%fcscjZeYiIJ2U6*R%OS^o<3<<#7R4i
z)-JXmpcY7c^TE-BI)<owBTjzw)qy#5bRH!)!;y3t?CmO&Eh*<fH4F|X11;qV32{%$
zctRo!E$8kM6<Nl*75o_5xRu-)YS@{6R`Fx#epd5i=okcO4jeub@zAQqbq!C5wr*{?
zHMf$<!1kn?4S{?q0Up_Pd@0((AifkG!Sy_X!A_%Ko)B%{2A&XY-bNk}JNq{Agy^7e
z<_Xb0ZQ%*gK5f+uF|*6mPBm$_@q}of6g(l?r|mo;+NT|wCm-vR>hRdfm!iG;k1s{L
z6~dRI{o2JN80_J(n<qqjwTCA}JGGZ5MEkUl2gDvz`*}jNPoX>^+NT3NA=;-fd$FeV
zz4Qrym7|-NRPN_OU$;@0r-Nk&30Zvm{}3@NkcAVn_)$RwF)Nfs60-QQ!eL@oAUi_H
z;)e@S#H>(ul#s=b7>*IM0@-n5RwO$?$l}Kj(ZsA!7DLG5hY+#EtUz{>m=($52wD7q
z;uJ9}l*JRXVp)Q{0q=aptece4r%7R)u@XsPoOaHT!Z>#%k;4MnSyC8hk7ROKC_6_A
z<NT3A4hv+692Ut^NnxBq(#T<<ES(${%Q8q|oPjdQVS(&CIcy-iKnmj|ltm5;Wf#d|
zu`HV$Hk9R%!^W~p1j&;=!KUJsOUUB%cbS+K$gU8wICEYlW`(jmLKY|8d}3B0D<EWX
z$}J>jg|Z?-7AM?m#H>JeotPELiV0bqZEp~>LfK717N^Tw#H>Jen~=r%?hY|4l-(s@
z>5EvZ-+P2C&KviMS%K^UA&c|ILt<7adql|Myz!Wr708|tvN&%%C1!=PXM`-y8_$VZ
zf$Rk#i;w-6#H>*Eijc*}{%c}ZAbUg1iezsIS)4cC5wk+sdtz2B`(Qtq<HeedyQ8n_
z#?nUuPT(MreInp+uJ}yE31wdhI1y#%S0YX%`$oXw-0+=<6Uu%Nabnp|0?vSn%P%5M
zB>PRk;T-aZh!e{G5^-YLKO)XhRzkoTIS614>dk#3R0M01q6V-QDQX03lc7|OgLOzz
zA*@S^ieWvB3V0<s<=rS)pOB?89c)0zQrQkRBxZ$Bi;$(V9@HjgMX(VeOJzUUn3xs9
zCd8~5HYH@KObDA1vm)4>m^FYc2w5td!j{CW5Vj&_#jrIoYY5vAvN*f8C1ypi9WiSF
z+Y_@!umd5BGi*m<RtP&0vtrnpm^Fkt#H=ywf?0kiu%$QJU{^8}XZCJnC{FC%Nl_ux
zB|~vq??Hy*%-oX{6~bPms2KJpLvdQxBSl594;hLRYhO}S2>X$uV%VP)HG~7mP@Git
zNl_6TNQxT3L8Pb=988Adgeo9Kg-}R}ilK-UHH2dRXz49PXh4SIjA%%P;*4lShT^nl
zOp1!&5Hb{J#G$095Dp_n#c((oiZkK}Qd9&18HzLFNK#Y?N0FjpXhMn_LQ^snXGAkn
zR0Kzpp*T00lcGX6h7=XUv81RW9EVZ$EAhz^f4Zo{C@(j>t7;Oie&Ax|t=#zGAaocs
z*g+sRfEN5%e3nPCLYlSY$Krg*_B$T4>Khf5Hk*1=)d#5Z9`uW>6flVH%!)g}cxKHV
zpi(UriV55S#(x_OsPDI_-~)ZjgLPse4}$T+mIuMOF^LDk_%Rt18pfh@;F+<Q!X03|
zu;UIePE6$vFh1bo8s&D@sK%nqc5Z5;20I$lcrlD8(|IwBGc$NGj6X9mqrUmBGJn*k
z*DQVz<I(^4L5xcd{2<1s*%(saYG0X8YE#XT7sGhu#EW4Za^}S_{<vU9eGjM7A2X?|
zs{~SYWF(`hWajO&0G9z!%{&PK$=K=2hg8eBZkSZRrmtwN9km13k+NEudzpZ`lb}qD
zq!_JyZBoUE?NvFQ8DHn{>Q-%On#&7Si<1XN)e8eC<D?u*yxoh+B8-Qgn)Pa?d11YJ
zbq8hp<GftGsU1PSgXvv}s_Ej*2VsWHhY!MpTgC@re1{mRd<9hcLhqqgx#G)%V9b(h
zHcP<9i*eqM55n{^j}O8)Kc9;$rBjRP#2*vtFY&5|o~qv9D^VR2>L+W=y1RgwXX3Ju
zm}l%?M9ec0Ta0-_wMRyp{8!HiOZXe0mUovD^GpDj5%Wv{mlN|$09RnX@)dNFpXVrQ
z3OQ261(Y#kY+i|(%JU7yC{tSLJZ0wDDvVTq@<AaLvNhAs>S}FcA+=l>fEl{Ln8d@w
zw@k@1>Kb64gf3?W*Hop!dnfS*F+X3p7HjB&66M;N0HsusGI~2O46I6|tn)>^vjx{_
z65)F*L7GI=+fZ=5W|05}YZBo*BO5e}gm9xK5%tCr+@x6~fSWaoL~x5H5x!TkRkKJ4
zw`mrMp+b|0dOrzn*DMmi9hyZVxKp#p2>z!@gl{H<Xch_KF3ln_+^tz;2=`zSeeyyd
z2xaR#seN5q5DM<adb+TYMm=@l!hPJDrxOs?@8_YXG7t>Kdb(m?1#>K!v__qJ!2=pq
zxbHBHD%|5itWsr;vO%(>&)IQ@hpKA|Cp7FZ4A;~Y?k}P`5l+I`^hhkCs~c4aL;1Q?
z@G#bP!)t1_THNfBs+%oa4vKarO0$+7<)c_jSAncxLfJx0@L2Uax;-53;~aF@pA#H(
zIOfq<*SXRVVf*j^;%;NAZw|}o(8N}+!-GicPGTKh(~}NM#rj1su4)ByN()b6MO)VN
zvTX?HsS=L`^ioZC!qyL|uJRB};0xhspT-b<uCKW#CIE?;pzkYjAaECF_yBlhld5v0
zipoLsxSYjMS2m`qkf{~v!80NmE4yh@(v6<u)F^f`1uIo4w@mkymE3^{%jpV4<$`Ec
zUXB}2ty-<Baic7_1JkNDrJS1fF`aYc*pv*;YCMveSY7F$lr7?d2jx5`C2sQqR#qD6
z3YB(n!&z9aT06@OOa(a|j*Hxz$MMMKF2}~_V0oqEE-hCj2&*qurLItw2YZ^!S&a?9
z%vp^sxq{W*DmiA#TEgUqt5{lD?y92L4;}S94ABL{=;Of}*V1<KrYbd3k2*XgCKCC4
ziNveSPhI9v1+S=kaQT>{3;LAf%%#v*Zt6i5(e{<&;y(24uTe^@psMbeM=Divg_xtS
zy6EmIDg9Eub`UJ$h2Xje@ES(w>p@Mu;Mh6f0t@guKZfq7n6qirgrUp%z#F^}+OnIx
z5ZbU?ybxUW0p8|}P}7<5<qj`|_T?@wg!bhgFNF5xK1Qk?f40C7b=)(~JmAOB-aO>T
z(C$3KjOysF<OpDGqbDb>p9LTDglOxY@Pugdp7Mm~ct67sw|KJ$!gGEM?a>Q<4DHZM
z?hHGzU-4sT+g|fyXxrZKW9V4F)yS~bf!MkIjvqt&^PV3=`}2VxL;Ld)Gu0jstUs#b
z;S*1Y_UJQDh<51<Pl)#ED~75)9$25)<KY`WhW6+?KZbVb2S0}P=O=fDJ%)bqV`zVV
z^J8d#{_taHfBs^Ie&$!z`9Y->j_^Ise`F}W^I1ZQQrmW@znei|FuqG#lN1%gT4X4`
zqgtC36~H>As0h|2L-9S?dZefj)+a^9umKs0@9H)rMFmic6cs^jQq%}GB17@r;>M&X
zwOxl4rFQF(qK2>;DQXOxW0Za~fOBqQE@G%T(Snf0iLE6ei!)m*LKf$z)`Tq1GHr-i
zYOf9<i<3n=LKYvl?TJ|d>_EukW2hrBOYPMmW~se8#H=yY!7RUZ8lO+$DcOY##WS)i
z8Hy)lH&RppyOW`KI_i?5LfC^0#S^(FDJp=yNKp~&O@`tlK#vp^!ak&^81^Ma4Pif0
z)EM^XkK!|TeB=xuMMY4b48;fCKvGl;2a%!pcpXfN3ZQ@#6+s~>Y5+xKD9#dMQd9^H
zNKr8~Bt;FO5gCeelQAhOfI~=85gba28o*(ss1Y1ahT@Dkf)o`(K#GdtNK(`gjv_^k
zp$SG+4>~Hj?^=4zuU2>ln)1h}ciNyCe+-|5k0!x{(40SpH?)l*!9;K@e+*~%aU_@!
zTJXp4E;LILOa#Z1U<S~NKZaAXH3=q!6G$*IwBe88-DVR>FcGvR!3^Le{us_=lSwck
zoI-+$p&bck2&a-@#t{F}+%k`LHDxa5E;$vGX#^b3UDF9ToV;cbaY8tgfWzr)77-_c
z|0CdV0&^hZgm5+yCx-aXgYzACocf%II1zLv;tZe*0f)1ngoqPDS0YXf-H13t=uW`l
z#3?1>L~srfX8`9CaYoRCfWtZ0lZX>SFCtD1y@@zO=tIOALmB3{pE1%;@~E&t{us`>
zzWgzqbmb(N5c=`QaLS!Wf{EaK{uoZU{v?<XF5r*hw7HN36Tw9!m;qeOAHz9w2?-{I
zOGz*>T*e>6iElXxCW0$SFax-fKZdi{DiTZxSCe337(jv<!!`Uc`r$j}+gkn@&Lx2)
zm=LbxkKtSr#2>>+VLb^Zgu(nVoD?>YU?RAY1T%n}_+vOJY$m~ka0`D7AKhC?FcI8F
zf*C*s31$Sh^T%*f*g=8`;Z71v4F4m+jA01I=)bH?KOt6b6|JnM34JZdZpq$-LDf6L
z)qyyZu-tCUsouF(a%@2oWiQMw$vqs^%=XB=9M#N5(S01%%(l?|Sgp&xb6vsiQYRU+
zL%E3=s}FD!Ge(DT6Eij+#A4Ov5S7iUVjb$?KExehY!BxSF!o1q2N)kBF`(KpP?-<-
zWSN>@Ob3TG>(z$p2xmRxaTI4gW6x2}ddA;lSWo|bZ?ywbwP{_sn;5^4NqNmoxZ^x2
z#+MU3DaNB{o)qI(45m~UK+18f=$CRvGM&Y8?M!V@Px7RgzT$XNjAN%XImT|wR?CC&
z80%gkpD0JSRLhK00@hZ{nac7HgO!y;n7MG8qnc?uk)xUk(HV|vCNxP{t=b%<9CMZ3
z%CTk)Kg(6lSf0#P&X|6VtDLbt1<R|8d1=;ROh+8mjOD2u)r{e39Mz27>6+AP2TBG<
zHDh-sM>S*jd5&tv?hDnc%au6E;;3fqzQ|F{*qzN$&DfoT)m6{&@?}#lX=+?;TIFg|
zs}1I5j%p?-S2(Jfpj_psW`dH3)xrwNZ5&l_qOt-k$~3@qm5*W7ON*+kQ8}!ZDGM-L
z@ob@z!W~Rsg;nayXKf~EMOfdJa?IM#*+U{NQ%%Ff+t15I>g8tQ&6L!*hLw1meFded
zx2KPzv)oJK>kF@A72Y;oK{eW$-cl!ZmdY2vVl2a3lq<^o<#^}a4J^Q0>?;V&y`iT$
z)txtlH?gQ|Wg;ubIo@!TztnfU#LG?Y4sTW2T$zF(x3Q>OrOipb%&E#;)K))7Pl;Rt
z;T<fkG#F)zhup=g_LVg_$=gHff&+1{%7&B$Mg~!DY~0tVqW-=xe4tT<i<La&pc24G
z8ddn7$YTyFA$+1yh2N}t%0VT7&p4<=@VQ16zFG2ugGvZra!`rkD~&4rM%8N$Dgk`M
zK_!B3Ij9WaJB=!QkK{cEl@Na5pc2E698`wzlSUPOQ|U7Yl>mO>pc28a98?DI8wZsU
z{H{@j@0a}Gpc2BL98_ZXi-XD#{^p=EhJUaMUqzSZ*0S|W)V@|0eEEw3ya;gssO291
z<DsWkJ6OWeAbMHF9n`4J%>x?1J=DYi2M_Sc3f9-c`ZCK{*|1pBS0}h>SR2dAECUr~
z*xEW8Rk+K#)vB;zco%-XY7N6G+OYZ>8^c{Ts8&TO=q?*-RADEzu&R6IbEIsc7_8Oi
zsKqum!dl(x+hylPW3FP{auW_#;DBOnQ>^V$xfN>VYMNmoE^AZCp`sMx5H#nY!yUKK
z&@t<JOD;m(Vk-?jW0&zvYptO{tfS{z8x9TPj@xR`Q5w4Ab{aayI=bWb92&&2?tpc;
zrcUXYlr4xu-)evzv7*e0n!1AStW&j(;BGostH2S^!3uoKsMHWuwGjN38+4RQT-cw{
z1y|^<yI>68LF0^JbGq`Tu!-F;g$wp@>5Cq&?z{+WnJzB^Th#*-cpG#DtE#BkgC}rL
z3{@JoDj+)8z4&&8J?hOD!cOU7sLbUCJMs<{Y6|ti(lW`l3MuVCUvAA}v-@$AVq^Pb
zDZVREVFW6a6vD9|faPV@+cE~1uRuf_t<SxAZ1_O#a%}vdYOJZOX3=1*uY6?67Zws=
zY2_nRR!Tc5<kl>9P{d7&ofBhenX|bvp{~3HkpTuOADapQw#Be&efg?Fw3|j)U-?ui
zugA?BbC+XxhhTZ-V^gMeIx`K$(#prCtdur-7`JAz!NaRGxNNl|wqDi<EUz@&738!f
zfP3@UnvvY)IDDh996#kOJ&sjHkE$<eWP&;TShWJDp{9{32645AQm~R2bSo4!GULb4
zl@3PpW9Ui;=9nq7tW;wg9vY?;&KRB$ZQWR&5N+N#?k-U?fw9hlA43<Gu;j<k4vpu>
z(EeC)XQ-*l_+!nFq5YY_kD>js;m6SaOvFs}(}%5AL@kPpL$*92+M`K4A=;(MJR#br
zDHtkq(p1SI!TO{+ChYi9v{zI4QnXw4d@0(mX_(?TR_wtvohL+lHG?NaJ2jIhMEf+0
z2gDvw|KkbKJ~{A&XrE^DglL}}HABplG_}KPJabGr@q}ofoOwdDPcA$m+9wHysz0V!
zpH#<`D_@HC%8f5YyXDT8qWzL$s`_J!^@}~G=J14QujcZEXs0}QLbOkwJRtU%^5O~6
zK6&$mXrFv|LbOjZ4B_XGRiA=YTG0tVQ-Xvne$wPi%nG2Kki}1>{D@g0oJYvwCs^}|
zSpoDXW<_uTA&Z}ZEhJ`za1k*phKmVV{1j~oF)M&eiCGa`M#$nPY|DvRAzVSsis4FP
z))1~DWbu=`)x@j-1`x9%xQ3WDfNP0aBN#}?;^&0xh*=>FB4)*KJuzztgNa#VxB;{H
zWf~sq5p!Nd1#2TIj8~*h<S_LoPDo+ACT$^yg>Wk=j8~;?<gfrL$YBxOP733NX$Lt>
zZ8;!^sf`DuFkYKN$YBB8MGlMLZc-R8PkYE=A>2z2i{U<U*bwd~h4B&<N)8L)0diOb
z!^mL+c#s@6f`>?9yiSFa!$KHA4vS$VIcx|Ilf%aF2!?rHJJHv=RJ@`HS-esmC1wTi
z7$J+-spG_~5S}1p@hTNf%nD!(F)M<xge+d7P7<?17)Q*C;VD8EuTSyBtN<nuvm$t!
zm^FZjge+dz&JeRgm_*Eq;aOtV5GE6{cu_k?%nD!%F)M<Im^FZ@#H<laBV_S<mQKtH
zVFocPhMB~yAv{ma8p8_&EPaoYid7aNi`TM?#H;{j6S8<M%OPfk@Dd@5*Rot<Rsb&(
zvm$tfki~1+Rbo~M^N3k7%qL{=T2?^J3Sc2ID}qJDtO2}6$l|r^Ix#DR#l)-_-XLZT
z;Y~souVuH0SpmFF%!=S0V%7lOC1#D_Jwg_*W%r3$A$&m0is3_I)(}1-W{u%v%$9kN
zsgm~;Dy>-hgn*-V*1@L)9A1N-5phEJoPfi1V_pz(BKVSk!|TQ?B2EZj6LDhrhJeGR
zYTgoYBKVGoGl1_2IGp1@5OG5Ik%$w+Pehy{{7k^%`Z!;RIBNG65l8LkBI2kWUIZM@
z!#{{PY8M#AN%Z(;G-C&9XBbhB)Lt<nj@mtjxiW8pYRbIqlbgRJAkMx2NI;x?OUOVW
ztWk%+N1T3Zl7S*viv+|8xHcImgmuV3F|11h;v8I$3>3loWS{|TKmy`4+>i_uLM<{-
z47JHXL)eG}#HqM387P8H$Up<wlngY2%}79;j+>K#LfC=~6vLKepdoBU1{%ZG802v(
ztb9DthJeFawJi}RgzX48oKxEqaU$4(fWsNJBN0da9VjA>`WsLL98RY?M4SkAA>s^R
zR{{>_(r!eY5Oycx#88)rGlV?|IGjg&5^*Bfi-<FTy@@y@s7Juz9NLG76T-ekoEY{a
z;tXMbBF-2N;K?a(iR%+^_;hw40f+PMAR<l(2NQ5O?+S=G>JK;(a5(RZh&Uk>6LDf_
zK)~U=Ye>Y2pb-&g0F4PaoOg#1aY8thh!ewMM4TZUPQc;3JA#N4K|sVAz>!3p5gbLp
z;k;`?#0jA(5hsRbM4TZUO~e^PbIg^wk)W)LR#~ZDyw!)Q4a(Fk8^Z&{C%Y^-mIsKl
zJOwi4-^O9Ehw6=0rKxO@-%|US8f+F=U1kGx1vPz3ge`Sy$yLsHKc1_cF~*9kobl8e
z%X?JgX=y;2Dv=X7su{~|II0=LCvsFXcH3%FmyRc6_au&L#_q`+)r{R!II0=D?XbGc
z?tRr<QI#|<om`CRQ@I0-_4eEW#(`<v0mg^v7${RSq%t4Wr~C{a1mnd_9t7jYEFJ{o
z$Nw;)VJy_9zXNxG@nSZ2fN{c+JHYth!~sw{6r8yOj1Ml{0mcUjcYyK16$53;<S6G;
z#nQ@ZY1a*7W$uGijj2yYcitQm2q|xliN_q?921tgnBx?d(n-p6=fN3Mn-`vZF(xQp
zd@;sIZ@w545+96JJLGKD)6%KJa5BtQa_XU)VJxRUS0MKeO9z4J&=+&M6_-_Ib?j2>
zm>9}6h}By5(;!wmkC}(Xm7JNV3RtTdGM}rQanc{l%Tzj19)POWmBD2ET%fUewQRdk
zqg-tQFXAd^j9JW8&P>=PT;)t?mTHifs|LLc%d3fG`6A5AIqMngS8&!d=C9OfzS>Bw
z(kNFOsnuNN%t!@rl{3Ds;VNfbU5n*qHm9j3apl#T)ee|Io^WZ@7(>_bgw<jgL<Tbv
zT~7uxW(SkOOtd#(xRO&Ys=l={H7auk18l@VB}YaXKrJqts_uYI@oGc383UD^%u*e&
zfYKx;dRsVjp_a0@asW!5V0zd_0TMY>P#;eE+g+$-1pf<e;^p8fag_T(iLZmy%Ryna
zvQBUVXAi2t8ubH(d%r#_6iXC(?)vV7+y`6M3Q)KU-5a_$ac>%2OKPN87r0hotI)Ho
z?cUPb+S;Oo`bYm~SwpUHayJfiA7a_e&#6BCIrWd}u||!WrC)5HQ2Ir1eJ=+oRS~;F
ze>K(m6Y=a1zs9uPM%hPQXK#sX#U3bs*OYO}m8(;=N=h0&+O|LQ`5|O(p5y(kPZUUO
zb@@<_YZ<8al9m=DBO;K}-%R8B?vKA^0__KBm*C|j6fk^S#Gq|Oz;49l$4gu@QQgg%
zX%++0Kw!?^7hlH*fsR9sWxsBuv%IpM!}13|j|@%%%I}q*@|h2(7-k0n_xFn*pR+mw
z5^kie-#0C$f-dyf?2O!2xoo>luO37H7H>v<Y$mV$J~<k#UEOcm-q$G=xL{F!t$-hK
zEVp`hJ^P!#6TtoEcb3oEeiQXfJlps~>tiTZSYqp^AIj?fYyMKaYwlSz0X%O%F69C+
z=?5Eie4op<FCINN<oKE#_Iss2X)W)|m$f_#%;&Cf89F_cZEw*2b+dGAF0kL<v~Biw
zv=7x@OykRoOp}q9=bEACPN!99Z{CYJZA6VWvOgcv<hyp(lpJuNw$V$iX33yg_U6rF
zyKe@^XFmJ7V@NJo)V{dRDT4&m=wOQ`%dQ5Xgf^nSe~ZqbZPDh|Cmj$F#+0<*WS_&@
zp|m^KZt1I$#i?vR%AbcDb~5|qx)WqgFK9UaaS9j$>$~=F4+V-n%WUS{$puYy&utFU
z*@Ko$o#i4tun&!1G@^aWfTQ4J<L#5IuN0z2pN8Z|)w{^H+kgJ59POIt!MICa;;?81
zda$T|zuPr3(8QGE&9nBY;{U$;@%v|=q@g!K^Gm*WF$0c2V){Odxrb(LZaDB?ms8;O
z&<k&Z<|Tl(-`+J0_}|3}{@fkfc6$0#1b+Uw9NbNk22QUZ(>c3tBznFkV}VVBSP-}U
zYu8`vc7j2j<^>ffl3BiE`}G5za`RYwbFRI4<XN%{Wz4nE$_c*+y8Kvb)Ms2a`+H@a
z>NN@U3%FE-=9`?{(Cm05x~XXDIAqcpw8`sy*hZZ+;NMoFn7Aq)*xxx{|AARN%3D<T
zpv}`epwUYg#mG&e=(dT;)So*}v35jB^>w#I7P0-b`VeW+;!_@KubpQ8z$zQ{GWF=S
zXx>Q>HXn|v@#p{;m{Zr?VDABzzaaa5|5=D?-YD(dXgv<-mSnTK=i4&^ygz0lhgo}$
z7?@s1SCcZny;(OO$#0CkGt*u*-z^VyNMF(=8f`cmyxYrbGi#T!UFB!!8U+k|SO7e~
z4A@lj^JO$jXJp6eYag=xHA{RMYHfIq{r=DH?*-vL*(j%NyZu8?s^-avpYsl$kY)iB
zuUY#Kyvt+t*XFyKo0_YRD}%ySwSQ*Bq7kmsV^2HA0^yJ5@lTqn#!qQimo~dMbZKxA
z=*N89U^PAh?VJ*lzBKSQ+pbclZ?nuip+^{4e8w*SL}~<R(IfryfZ^v^-T$`C%jw%J
z3k_?!%H!zA1)xi}?8Jaq3qgZJuKVn!+(ikxF}Iv7uOp8=weFoAb{4gCNW8VcDhgP`
z_gfZqEkN~7x#-^t%S7I>TYrCkn~G-4^iPS>Is}ycf1A1T;hVd~Y=6q1D?fdO2NzxF
zWB@!`j#*b<{}lS8e`Vx>`SBI>@;>_QPI_NQ;o_|Vzr{zv<6@Hs2hYcYex}Qehc!z_
zhvxLMdEIL$%QY~Gf0<WDm7kRTDL)sb?_T4gr<$L(F{wpBh`>OP^BIC~NuW{G$s1E;
z1;F@KgifaWbu@0!sfqn!FM@qpmlPip5`c?a(jD(%XIMXT4fhYcRdfb4bbsA3ZG1fP
znw?z#(exBBP4eM{uJ3seX0iC+(3J%s(`^5?>}gk6u7$Ix_WJQ*;6lHidsA-bpkteR
ztj+xt56l|oO{`~^4f3<sdw{MHXx^Rx$Cimv!2EB>?v<Aj>!(}pnSNFwd8lnhjqCk#
zPN5W?^&{#<tVK1X`x|b(f12&*k`zX^s+WLbZ`mdJ6eOVuU6*|K&&mc#rnz@!ce%{A
z_auI|OUkbOAb!#(-xQPp`ih4?UfD5<{r%>jL!P_U$pla8@7v$Q>k7I$!uE@Gt1J*c
zL8sw~uyA1ElW-+5OLd&TwL8%1^1s8#Kl*i-n)M3Uc9i2#&?@U)d(UhXlVJWet@cQ8
zWXj333HoVha(C&U#z_}Z%Zno$y2w?>_l1A`pLM%-p7ra$uD?B>7B5Ewd+mPQ!Y>Y8
z2R1kA?MMV;Ga_Fs54nQcI$s!LF)A0-vv>J>$u_e>|K8Weg-p>o57s-k3-mXNL>GMr
zSvCq+*(sOxEV!%}j%sg;?y}G(k?mJ$zw+~eclXqndN)wpHZz~Pzdr|{^n>=oGdajS
z>Z<vc8!G#cTCcEuKJ5WmH9zY2G1tfn?ZusVT|25%#rd!7XOdf=Raf<sfMa;idFz%O
zLA{6nEHa8nKwr0?(jH{7jrA|yHE`ST;zID?P+_Odi(}Y+24A;bq~o86YPxNmJKwMf
zd`-}aFPxVMegztRe6{Tc%deX1id@kJbbRSeuOVSsXiNL<mi2ZOpxy4S)-&yLQKMIl
zXDzsqgk+gL1A?aB05j{}*6y|=0)&lzb#-V;DDXGzb?M)YBDOuH{qh+o?3s5eh!WJ?
z=8>}<Tr4?g6Yg1zZhRX3S}Q6PZIkOH9{F<-S)~7)UdJz%wR_lRr*Ve`$Ix%xjgJEF
z<bmmf=7u+F90>ZZKKHTrzARLfIPcKw{n-e)*9oY5N_E_8Pv6%pZdeWoPy9SW5E6}M
zW}W_V>VNyd_PGa&cW+5Tp^ldezKn@PA6G2t{_5)_)c?x#O_#Ukq5h7Fpss#$py)qn
zu5IJPtQ`$I|5UVS9tJLjFY!IKC=>iQWv1Ke8TUb|SK9QO*=b<s@a6iG8|0woz1sKc
z>AC@#$J(~ox8@|6oVHju&?*yk@P9fGbtwiOy+^!>ot=h69?nBPOxXcylq~(;(jovk
zEV<F!yC9s6+s#96wX7ztM=cvY+1&YkCi-r_;q%NLC)wXC<Ju^%Me=_W5|QrpCp(6v
zsPg;iwX2M4Z%jskp>5;tcwT3@19olQlQJMU=`q=&qyBNUdg*+JpXaWCbr;*Y4Km0^
z4#h9hMjB>;&NF747x@(db1S<ePZwMTzGI&L&uL5%c-{5kjzNaeY+P1MJKUl{U>4{y
z{PdQL^Ra9{+di&JO<a_UZs@n0k)W-z%T8y$@ygF<!REHZMYWnt1``ha85pr711)^F
zIw@dZ0$BHGRm!j(X>2>jbK+}l>70l}JH{uy?oA#4!f8FNr)Pu3@TAO0Hx$W**+)R!
zHrAeHKgZtHo^uT4fAYAnwPz|w9Bt<D%`qCh4}1LeokKdXxVs?oz>U4Ys8MtyoxFUc
zJ15D^;aDNEOwABm-cybDScT!I7p~Vq*yMV}dH;3-`15X8sf9mUapHcD{H}$peadlA
zes&U|lDj<~gSd~;mZ{Wwu`>E@PIz<}nqd6z)Z$KODsY`+zO)~jvyZiZ!PzK9ubsu9
zYtZt77Cx~kqLcMu(?f|YH>7|2?GHSBfx&|xbAAoZ0MD9qbGA4V51MV8Q|E0*RUS~<
z^Jnyl+w)A4(BVC(-h|otVAxx?^@D340`=VXe>!GxitSga&q}%az3JOLq%-DQFVp4M
zQDlCmwsZGX<n!L;zHneN5|}29T6HB6)qne7()!Q&EdQU}@KW?8cNA^^t?Twl*HFo^
zQSDp(+zC1*%=tIr*%DT#?B~_6<X_Wv9zrQsuGfm`eg|1t>>F@YbgzOgT;bo-OgkG$
zWbR+;ExU@oEKPX6@=-3bIcVzdyEz`&>9iZNB{K~T2=pk-$X6ZzGwr8uPu!3W(i+zr
zd73)j5_@_+TC?dKs+V->a7_G85H>9&N!~9Ec}SXXaV@?Edbc??zGq=5TIKe)ZL_2>
zR4D0M$0y_%nt6GactBz*=)B?YnP17tp!G-BH@6#8=l6RX>OP*Fg+{&>bdG$R2{vo>
z{@uYg7i_HWzAWUbBMNvvxMhLWI?(-{G+#cd;&JQLYSXzO+g-?Y?F+BQBkmw&TvFSj
zU{gKSdUeF&vdKng)p~v*!&JX`@(mQS+HP*A=I6kvY0Gz=$gu*+Hor<%?af7KN%WsV
z`cWX|c}k4%#06j$Fe2!S;sAL2Vd(BUuanvMrn{UdY4Rfi46k#tf$8i*&~*8vX#bTr
zz>l!@jsFgcVeOgF_+HDpr+2d4qel608@=*C;f0V^KGgMOGe^5wS01OM_P=ko6*t`v
z3^IO>7E{;RkA8gEbt|V3z3;AH<f*d_6|9v_eY#UMkJnAL3}3b?9i?79KecCA5gPtv
zmo#)!9NX{VhW{Hs`jhJVJ2b}9XZ@7T;Qfa^`wY7;M}|YDH;&M|4T8?Tyb?Gm8U1(?
zU>8TNd(Yk|YX1nx1M_N4ni=0Q85BP}vEAA{7;PRhFMPp|Gw5&HYTf&t^T4kiql@>R
zD@Gxmwf&ba$wM~3+|7f=pGNyOKR@?poa(s94Oku7B>gnVH*38i@OLiQ>h-$7Z@@a%
zPUX0De7$*(`}srY&hy@POQZ-yh&y&pMvu{w+sVTOeNTd&H-7X_ZJ5T!QOPMkwHzJ<
z-;9a{Uv}LHnxz+wj^0@meWFDs*w-{}*PtN>QN(0L_UZmt*nS7v{k;FR^?xXJ3Uxl(
zDhEBia{JHSO>u1dE{z7<ilFkBvi<U(m*#Yv_t`cLJsCf0Va+?L`x&B7eI6bBa2ZI4
z4`{xuTLIhOm>C_G{_f|4o-Isxe&R?j`*UTx*J`}k_~}R*I{NqP!N`;q=%%)%)6s$?
z;PWy-oYN~6<e3fa-ZUu=dDZ(qvH8ka6d6Cz)$+<dww(i^OMc|(sjheYXFArXwJ8P7
z^c&yW!MYH%$*u1*`bsbu{46LfIY+ggMd=2)iL<jnwpne<yakEiT~TKb9jgK$=zjR_
zV9y}n<Nvz1-b2;(m^8AM{^7~0b=J96BLi30LN-oaUT+w?uy!QyUR(d%yNC?dKBb@U
z?HXvkoRyBgFTb7>V;B#*483S%a0-Ik@49Yn-C{FpmYY9op==BKWEuCwyvZJ5+r9CD
zj#H$dc9xIfoYkszO{+mnqeZrHXvNQ|Lj*1tz^t`;`*+m4ge+FndTlqW7{$XVlfU-a
zsBYo)kSXoc!PtVO+SwCS>u57w5BP0ZKCoE*O5Al)EI9qa<b&b40M-wsy*1aLe|*m4
zGRVLG_~Wtd=TZ2gF8@AgMX|cD0`17VU$fEt=7)kh&)5MhGk=fU*&qQ0@82%foA@B5
zSL1C@yJcKOU7d}No-;U&Qt#L8Yv&gM>Wn&g@JbC;J~3-QcHE+$7f_-1)1i5yOjLM(
z^4i&tFQNrW$1Q`c@38$neU_#_Y{ykl=g8ggZO4|QF|R}QEQeeL4O*XyG*1sgPwk=;
z8k<}~rUe6i_fhwGlzwRUNmzBbV*$8a=SAVVp_%N@*J!;xH)KyP`t_;Ve?9b8psPb~
zFK>20HNJ77dUcwK{sTuwCKhVfyNLeVYyA0C*ag&T&GlTpzZq!ordappl2d5JxIWpd
z8mP|KmHl?VV|_C`|13%z+V4Z;%qyV%VeRHe@8*JKx%#67HmZ50)Gyhe+H=#n10Z&q
z<%HAEW5MCXhUUwMT?g~p4r&%O`VzX?aQ)dDRNhwVYYuO>H~DiBSk!b}mck?q6}<Rf
zYbG^+mA_YhK0Va<)~?{SX!4=ou?eP`XxZn2-*?~TgHI`2mS~-F0*ZycW_}$mA*KFk
z>j@FCPa$aXH0yBRhcRIHx@iwj7OCdXGrRr^+k8z#J(_3rH**hTx$HhQ68BK|e-7C6
z^z__&7}@#$s`I3e>UzaF@zm1zV}+o5qe!DJHA2Cb7Z=>9GkKPGa7l_<;Svu-=Rb73
zu<j`O<u=^lb!r~+k!2hF2s@76bV$pOi&GuvlUJ`A;@t5VSk(Pzq3pHldeqnC3VQ!n
zb>C)sc1Xyx_)DmJvfJaPPqNtll>RC|eg3ED^Zac*I@8c3^!&FZR_7@G@wn-~0@O6`
zzR!iEEc9#E>a)wh4m5J)h#Dp93c-x2vpekAkq!n5!*tpvR2<h<i?p{s9Df94-X0y{
zW*z~Q{ptDyi_X894}Pb+<o}xy1DtA(_Jg$!f|3iM{>>#3;7-JF3%kL4P{5Y{{y)cE
zW;x08TmPknQs=X!|DN81-_!I{(eD!Ic%Xg?Yq#?Efi@TAopv8a1vByjQxhXWZ1bQK
z`+|zlpdim(-*;8K-x+Y;!Fy8En{4}COpia9Gcp4NB-eD?(n%G6W&7nn#nWRC4(+O1
zPn5rZxwdoq+FPo1`QYq@n?em@(bK)!I=V?I;LG0O{w=!2qZ=U9IjY?w){l<KJwII7
zmk3U6e&GFT+&0kJHZpJcbJcyT6@R1G%%-mYeRu0E*YBT+KJ@P9ZXC52wQO^`-Rxl1
z{8HNCvD~5dxBt$g?BQGf#-7Py{d8IC5`VEpB>MNsrIBK)KWMstY90CUB((p?DeIs1
znaI3JpT2YKsPm?-!^7heBEhez&11iONCf)R?l0@T?L63Xyql@B)lp>qq-Ol0lHF{(
zXM~-{ENq{JJ{LXw*`~);RHvD5&A_mWAn==iKysRDp7u59HmSqGbKsttc_Yd0<E;M!
zpBVfXT9N~7BOQh3m#WTFmHsF{cix{8AiI$R3e5K09QW`jLbvxl)(SZbwsgMMV_p4?
z=){B}LFau`aZ_@-{vRirJv__WtNi)hIYz5Zhav<rmY9w_nE>9HH4M8F8V|CL&EGZc
zO*~ro<kHnCdb^Nl_|Li7uB%wSkHn*Mo5B;|Yp%<}&QoI$FiT!AYjpt{IO<pZN268w
zK-o`=+y*AAJIz3S+g%mCmTUmwMb?W#eKSyghXXUbWvc7>Ht%cerEgJ<my%!fH}hty
z%VjXIbM%b+vKVyh<qr8W%Y~@@lc4-rKy}`@|K5+f39S!<Id9L_Eb&bT{cNr)&QG}p
z;?A|S>bb3$jrW@tb&3jW>_*+*`s?mXNJJe)_x%>wtL~2n3|%lNwZmR8$TIN~by^DU
z|5)GAkjlHYf~UImx);vIVWQrz@R)t7`@E?kkGp4XJB?bnY>G~tkqPPyDY8wvy9q^f
zZ~VHCRt{)g`1sPNGnZK2AbZF3wy|5l*G$31;J8HKm+jRm^kW<tWvCzOGU@_~p6|Xf
zaz_!kJNZbBPPJ1&aZug;DK@I}Z-0+NWBg7&WBpRbOZnL-94VH><f59RPHpvsE5V^X
zV}1;2smfm)-aFYm|9umE{nSsI@irPXxxYO!aU!+8pX`?tz4sW~uI1)wSNcRl&}z((
z2~c+>YyY)R->+Q=QJrsrThexU)cQUD#HYA>nb*;+Dcgk`9;?nD;~ls8&Fq>B0`!Vx
zZ%Xch%QwR_e>uegq4a+y(+*~!N&R~Zq-~CY8tty1{Wx|9IF{b3$K&3~NVj<3*yQvS
z(D7@GP;u-KYWR2I&8am{A;)X-5jP)P02ZlBbm8cuti4MA_2S=rdl8$4+KoN+@3HP>
z^#1vYeivsKqn|Fx69+s@0!b6E@1DNlI!IV)IOKWsI@G6a)NY%Y3#h@4ON$?AMIqa#
zyB7E9n@8QJ`Lna*oeQXzmUmu<4>17j=-hR|nvE#=?*oGx;3N=+X&sx}X*>FSd_j%&
zaZAC5tcKn4-(3eU8m073TX%UxXsrRuV6E$5{>Ahbtrn=BSIpgJva(i>>*zq6jq-5)
zG?4po_PO+_ThO%01ODeauK;x^`8h?Rmjk{k4m6zRd;&<X2Yl@BpMz4)J-pdw*enoG
z*VJj%+x=*9{gSp3NqK0**znE1mKWJLL<M(>o_r__bgS3PB|Ej^^}o+OpRCg{w^3m4
zT_3N9r-SI}-mfqA$!B?G9H)2QvhMNK3}n%#TXT<hS>RgIr@h}wa#&rhqaGJ7HOT>!
z*Uw+{aphrP7F9Q~jqgP?<!Kj%Vr>Ge(^<Rz%by?T07x3K-aa=R9G>;EXZ-7{K-tf%
zk56{iokiUr5BO~Q@-=lnHulgs!^OwZj~i!}Yd<;(K5Ez57+vE$FfI&S?ENGa^l6iu
zYHu_jT>cR?%b?C_l(~CYGsAbm;K21?AH}~au6qeTEZ)>}N@M$*dPQz^q|AN68~0s>
zaUCuKlj6Pd*L|Z|yX{uqF|2Q1$bN5awmf_4h*T8hHmPPp-3Oq(L+&I+K{m4V?qD))
z*J7~GTj6E4<NyjB+xkJ{$*SuIrJwCabd_8^5Qz#O$0tgxuAuniJ>U+XyR2Q$c0beo
z-ZdLd2r16bIj|lj+D#6*J#aJo`x*h?p8N|u3HCotE18?DdQR8&(Y=47L8|90%KqLz
z?=6go%>u*Pmn^Jx-4tE#<l5Q%?MXDi)cpOu6UAszuE)!p!{b%$E5Xvwi!1Le@$`xS
zGd8|?96hH1z5X}&te5UdU{t8>6lI+NGP^XG5}%!dEPlBZ34_i8crJhQrW3{B{Va#r
z#~&7=5Am6vE5@&2<M(?Cydyh#1$Z9zj%sd~$Ns#>kAdB%Z9l=<(eA*q=7BCN(fQjw
zT3d(20>8Ag>9-!|p?hsVJ9j+v0R8FcxDx@@d8_C5Q5GBaW}%_(&7{ySAEf1!><$@m
z7Fcyjn(395fxb-En$cVP5Na_eM4;7uAF>Mi)lo6$5UOW#QrKZc4j8@AsNFQNs=d!S
zE;6g$r%+Uw_6WzmVXR$s?oQafb<7#C=*&|2UZfhA{%;KLo|2qJ4?&QL-zDlkU8i%~
z{~k^Ov(nxzJGk>WdOBS(FTd|KbmidJI`Px4v3{2ecZF|H){HyyWJnJ3Ib5>REg}hB
z48NZ&tsf5x&PZbK=k5WD6=`kWbc;lhwXe>9pnU<@Oww6pVsaOqy!&~mqW?+O?x{mR
z-`QLDJn95oTRu8?611KiKe12}jV|4p1thMjb#zhgg0-!G9s!Mx>LST4)%oDBm%hzc
z80|#<hqV1#-wOs)kNh+n(5eUwTC%?GjO=V=<`=cCkK1CD_@MUrA3lkw?}>!@T6*V!
z)tJ=K(|N%a{5=tR$F26J|4`928<z&(3c#<y5qjNk7P0n@YSLb}(XJWn_Z?SGXz6%*
zHAtL%X85OuF{qBtru5|h#e<u{mbcqHjYoe>R`p+FTZ~%w?`HOH4MbBu-?yI^X91dy
z`qKE%v^Zq;s>_Brc|Lk!xBFIui>mnF%$Sn)aqmI4pRq&QYjy4Nfc<`2{Y&G<JE+cU
zbW2<#*3CHs<}Jw7>FJgZp0982ykbfMt5*)->>sh?gKtHncFkue3y+)!4T@(RGS^nE
zt0u?hCk9^20ineQr#|bMjM^Tycljwe3#2vIuAcSn3J5XLvDQ6u7Tg&6&9l4xVido0
ziX^6J9cXj2@bZwQ`;e*gmRilX7NCip-XF-1DMqhPH%`4bVGru>K6(6vdxhxd>DIRW
z;AsRyvKxtRYyw|4Et4eptIp4NNM7iO!!p2$e*%k+v!l?f5dSGREswB%*lxKQwEw{+
zutvX~``WxBuz&ffnjx<uk+3+wc)a*HI#<K@f{X28w6<60(O%gxpw~cyC$=`R=$Kjk
zFQc4P@lwWPcvQ2%q8+O9r!2I7&DhhI&^Dc6TTgw;1MSm<2EiLt<1%vM@dK~WU6eD$
zWoypz(@5D)@`<g-{<C?6Ud4V-);*pFn(X@VV(lMQ{H4!2e~DVK9KG!_eCGJQN5PSE
zI=_8BJVDzBm9`M9C8hopD|D9l$Sb~Z#J<vG%f290k9j{z-n4<uymlAScKoM*@xS0^
f4!(0eB#zL_0lzmW_4ZN(*Bz`c)E}hqbJG7m=Y!pX

literal 0
HcmV?d00001


From 14c99ba289fdaa667d6727fecfa081af052f3844 Mon Sep 17 00:00:00 2001
From: Cameron Mattson <camo@oak.ucdenver.pvt>
Date: Fri, 1 Sep 2023 08:04:38 -0600
Subject: [PATCH 3/3] Removed unnecessary imports and added comments

---
 .../nbconverted/plate_4_classify_genotype.py  |  15 +-
 .../plate_4/plate_4_classify_genotype.ipynb   | 137 +++++++++---------
 2 files changed, 69 insertions(+), 83 deletions(-)

diff --git a/1.train_models/log_reg_plates_cp_fs_data/plate_4/nbconverted/plate_4_classify_genotype.py b/1.train_models/log_reg_plates_cp_fs_data/plate_4/nbconverted/plate_4_classify_genotype.py
index e9c4749..2818e12 100644
--- a/1.train_models/log_reg_plates_cp_fs_data/plate_4/nbconverted/plate_4_classify_genotype.py
+++ b/1.train_models/log_reg_plates_cp_fs_data/plate_4/nbconverted/plate_4_classify_genotype.py
@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # coding: utf-8
 
-# # Train a logistic regression to classify genotypes for plate 4
+# # Train logistic regressions to classify genotypes for plate 4
 
 # In[1]:
 
@@ -15,11 +15,7 @@
 from scipy.stats import uniform
 from sklearn.exceptions import ConvergenceWarning
 from sklearn.linear_model import LogisticRegression
-from sklearn.model_selection import (
-    RandomizedSearchCV,
-    StratifiedKFold,
-    train_test_split,
-)
+from sklearn.model_selection import RandomizedSearchCV, train_test_split
 from sklearn.preprocessing import LabelEncoder
 from sklearn.utils import parallel_backend
 
@@ -128,7 +124,7 @@
 test_frac = 0.2
 val_frac = 0.15
 
-X_train, X_test, y_train, y_test = train_test_split(featdf, platedf[gene_column], test_size = test_frac, random_state=0, shuffle=True)
+X_train, X_test, y_train, y_test = train_test_split(featdf, platedf[gene_column], test_size = test_frac, random_state=0, shuffle=True, stratify=platedf[gene_column])
 
 
 # ## Shuffle the training data for the shuffled model
@@ -157,9 +153,6 @@
     "l1_ratio": uniform(loc=0, scale=1),
 }
 
-# Define stratification method
-strat_obj = StratifiedKFold(n_splits=5, shuffle=True, random_state=0)
-
 # Create a Logistic Regression model
 logreg_params = {
     "max_iter": 1000,
@@ -173,7 +166,7 @@
     "param_distributions": param_dist,
     "scoring": "precision",
     "n_iter": 100,
-    "cv": strat_obj,
+    "cv": 5,
     "random_state": 0,
     "n_jobs": -1,
 }
diff --git a/1.train_models/log_reg_plates_cp_fs_data/plate_4/plate_4_classify_genotype.ipynb b/1.train_models/log_reg_plates_cp_fs_data/plate_4/plate_4_classify_genotype.ipynb
index d3dca30..1729c35 100644
--- a/1.train_models/log_reg_plates_cp_fs_data/plate_4/plate_4_classify_genotype.ipynb
+++ b/1.train_models/log_reg_plates_cp_fs_data/plate_4/plate_4_classify_genotype.ipynb
@@ -6,7 +6,7 @@
                 "jukit_cell_id": "RUaS7hws7w"
             },
             "source": [
-                "# Train a logistic regression to classify genotypes for plate 4"
+                "# Train logistic regressions to classify genotypes for plate 4"
             ]
         },
         {
@@ -14,10 +14,10 @@
             "execution_count": 1,
             "metadata": {
                 "execution": {
-                    "iopub.execute_input": "2023-08-17T16:46:33.640054Z",
-                    "iopub.status.busy": "2023-08-17T16:46:33.639955Z",
-                    "iopub.status.idle": "2023-08-17T16:46:34.017899Z",
-                    "shell.execute_reply": "2023-08-17T16:46:34.017500Z"
+                    "iopub.execute_input": "2023-09-01T13:33:04.877843Z",
+                    "iopub.status.busy": "2023-09-01T13:33:04.877605Z",
+                    "iopub.status.idle": "2023-09-01T13:33:05.274218Z",
+                    "shell.execute_reply": "2023-09-01T13:33:05.273825Z"
                 },
                 "jukit_cell_id": "Uldv3YbqHx"
             },
@@ -32,11 +32,7 @@
                 "from scipy.stats import uniform\n",
                 "from sklearn.exceptions import ConvergenceWarning\n",
                 "from sklearn.linear_model import LogisticRegression\n",
-                "from sklearn.model_selection import (\n",
-                "    RandomizedSearchCV,\n",
-                "    StratifiedKFold,\n",
-                "    train_test_split,\n",
-                ")\n",
+                "from sklearn.model_selection import RandomizedSearchCV, train_test_split\n",
                 "from sklearn.preprocessing import LabelEncoder\n",
                 "from sklearn.utils import parallel_backend"
             ]
@@ -55,10 +51,10 @@
             "execution_count": 2,
             "metadata": {
                 "execution": {
-                    "iopub.execute_input": "2023-08-17T16:46:34.019971Z",
-                    "iopub.status.busy": "2023-08-17T16:46:34.019815Z",
-                    "iopub.status.idle": "2023-08-17T16:46:34.022807Z",
-                    "shell.execute_reply": "2023-08-17T16:46:34.022530Z"
+                    "iopub.execute_input": "2023-09-01T13:33:05.275946Z",
+                    "iopub.status.busy": "2023-09-01T13:33:05.275774Z",
+                    "iopub.status.idle": "2023-09-01T13:33:05.278473Z",
+                    "shell.execute_reply": "2023-09-01T13:33:05.278210Z"
                 },
                 "jukit_cell_id": "6bmUxXR0eb"
             },
@@ -96,10 +92,10 @@
             "execution_count": 3,
             "metadata": {
                 "execution": {
-                    "iopub.execute_input": "2023-08-17T16:46:34.024421Z",
-                    "iopub.status.busy": "2023-08-17T16:46:34.024164Z",
-                    "iopub.status.idle": "2023-08-17T16:46:34.026483Z",
-                    "shell.execute_reply": "2023-08-17T16:46:34.026219Z"
+                    "iopub.execute_input": "2023-09-01T13:33:05.279869Z",
+                    "iopub.status.busy": "2023-09-01T13:33:05.279626Z",
+                    "iopub.status.idle": "2023-09-01T13:33:05.281893Z",
+                    "shell.execute_reply": "2023-09-01T13:33:05.281643Z"
                 },
                 "jukit_cell_id": "NVeszTxjt5"
             },
@@ -132,10 +128,10 @@
             "execution_count": 4,
             "metadata": {
                 "execution": {
-                    "iopub.execute_input": "2023-08-17T16:46:34.028051Z",
-                    "iopub.status.busy": "2023-08-17T16:46:34.027799Z",
-                    "iopub.status.idle": "2023-08-17T16:46:34.155147Z",
-                    "shell.execute_reply": "2023-08-17T16:46:34.154776Z"
+                    "iopub.execute_input": "2023-09-01T13:33:05.283175Z",
+                    "iopub.status.busy": "2023-09-01T13:33:05.283077Z",
+                    "iopub.status.idle": "2023-09-01T13:33:05.416017Z",
+                    "shell.execute_reply": "2023-09-01T13:33:05.415616Z"
                 },
                 "jukit_cell_id": "q2xQ1rmSbQ"
             },
@@ -158,10 +154,10 @@
             "execution_count": 5,
             "metadata": {
                 "execution": {
-                    "iopub.execute_input": "2023-08-17T16:46:34.157148Z",
-                    "iopub.status.busy": "2023-08-17T16:46:34.156899Z",
-                    "iopub.status.idle": "2023-08-17T16:46:34.159366Z",
-                    "shell.execute_reply": "2023-08-17T16:46:34.159035Z"
+                    "iopub.execute_input": "2023-09-01T13:33:05.418028Z",
+                    "iopub.status.busy": "2023-09-01T13:33:05.417903Z",
+                    "iopub.status.idle": "2023-09-01T13:33:05.419989Z",
+                    "shell.execute_reply": "2023-09-01T13:33:05.419693Z"
                 },
                 "jukit_cell_id": "pwIe7C4Ax4"
             },
@@ -195,10 +191,10 @@
             "execution_count": 6,
             "metadata": {
                 "execution": {
-                    "iopub.execute_input": "2023-08-17T16:46:34.160788Z",
-                    "iopub.status.busy": "2023-08-17T16:46:34.160526Z",
-                    "iopub.status.idle": "2023-08-17T16:46:34.180111Z",
-                    "shell.execute_reply": "2023-08-17T16:46:34.179662Z"
+                    "iopub.execute_input": "2023-09-01T13:33:05.421355Z",
+                    "iopub.status.busy": "2023-09-01T13:33:05.421131Z",
+                    "iopub.status.idle": "2023-09-01T13:33:05.440767Z",
+                    "shell.execute_reply": "2023-09-01T13:33:05.440399Z"
                 },
                 "jukit_cell_id": "sGkl0bhWnv"
             },
@@ -225,10 +221,10 @@
             "execution_count": 7,
             "metadata": {
                 "execution": {
-                    "iopub.execute_input": "2023-08-17T16:46:34.181968Z",
-                    "iopub.status.busy": "2023-08-17T16:46:34.181718Z",
-                    "iopub.status.idle": "2023-08-17T16:46:34.187517Z",
-                    "shell.execute_reply": "2023-08-17T16:46:34.187199Z"
+                    "iopub.execute_input": "2023-09-01T13:33:05.442246Z",
+                    "iopub.status.busy": "2023-09-01T13:33:05.442141Z",
+                    "iopub.status.idle": "2023-09-01T13:33:05.447881Z",
+                    "shell.execute_reply": "2023-09-01T13:33:05.447587Z"
                 },
                 "jukit_cell_id": "qcMAUWzcSj"
             },
@@ -254,10 +250,10 @@
             "execution_count": 8,
             "metadata": {
                 "execution": {
-                    "iopub.execute_input": "2023-08-17T16:46:34.189001Z",
-                    "iopub.status.busy": "2023-08-17T16:46:34.188784Z",
-                    "iopub.status.idle": "2023-08-17T16:46:34.193131Z",
-                    "shell.execute_reply": "2023-08-17T16:46:34.192708Z"
+                    "iopub.execute_input": "2023-09-01T13:33:05.449247Z",
+                    "iopub.status.busy": "2023-09-01T13:33:05.449147Z",
+                    "iopub.status.idle": "2023-09-01T13:33:05.455730Z",
+                    "shell.execute_reply": "2023-09-01T13:33:05.455470Z"
                 },
                 "jukit_cell_id": "kbCV2fS53j"
             },
@@ -285,10 +281,10 @@
             "execution_count": 9,
             "metadata": {
                 "execution": {
-                    "iopub.execute_input": "2023-08-17T16:46:34.194450Z",
-                    "iopub.status.busy": "2023-08-17T16:46:34.194241Z",
-                    "iopub.status.idle": "2023-08-17T16:46:34.199940Z",
-                    "shell.execute_reply": "2023-08-17T16:46:34.199576Z"
+                    "iopub.execute_input": "2023-09-01T13:33:05.457066Z",
+                    "iopub.status.busy": "2023-09-01T13:33:05.456971Z",
+                    "iopub.status.idle": "2023-09-01T13:33:05.462186Z",
+                    "shell.execute_reply": "2023-09-01T13:33:05.461938Z"
                 },
                 "jukit_cell_id": "MHDxE0uhWH"
             },
@@ -297,7 +293,7 @@
                 "test_frac = 0.2\n",
                 "val_frac = 0.15\n",
                 "\n",
-                "X_train, X_test, y_train, y_test = train_test_split(featdf, platedf[gene_column], test_size = test_frac, random_state=0, shuffle=True)"
+                "X_train, X_test, y_train, y_test = train_test_split(featdf, platedf[gene_column], test_size = test_frac, random_state=0, shuffle=True, stratify=platedf[gene_column])"
             ]
         },
         {
@@ -314,10 +310,10 @@
             "execution_count": 10,
             "metadata": {
                 "execution": {
-                    "iopub.execute_input": "2023-08-17T16:46:34.201234Z",
-                    "iopub.status.busy": "2023-08-17T16:46:34.200985Z",
-                    "iopub.status.idle": "2023-08-17T16:46:34.315457Z",
-                    "shell.execute_reply": "2023-08-17T16:46:34.314938Z"
+                    "iopub.execute_input": "2023-09-01T13:33:05.463535Z",
+                    "iopub.status.busy": "2023-09-01T13:33:05.463437Z",
+                    "iopub.status.idle": "2023-09-01T13:33:06.143342Z",
+                    "shell.execute_reply": "2023-09-01T13:33:06.142934Z"
                 },
                 "jukit_cell_id": "EoWGvinowW"
             },
@@ -354,10 +350,10 @@
             "execution_count": 11,
             "metadata": {
                 "execution": {
-                    "iopub.execute_input": "2023-08-17T16:46:34.317478Z",
-                    "iopub.status.busy": "2023-08-17T16:46:34.317339Z",
-                    "iopub.status.idle": "2023-08-17T16:46:34.321051Z",
-                    "shell.execute_reply": "2023-08-17T16:46:34.320680Z"
+                    "iopub.execute_input": "2023-09-01T13:33:06.145331Z",
+                    "iopub.status.busy": "2023-09-01T13:33:06.145180Z",
+                    "iopub.status.idle": "2023-09-01T13:33:06.148696Z",
+                    "shell.execute_reply": "2023-09-01T13:33:06.148423Z"
                 },
                 "jukit_cell_id": "4E094VqTVl"
             },
@@ -369,9 +365,6 @@
                 "    \"l1_ratio\": uniform(loc=0, scale=1),\n",
                 "}\n",
                 "\n",
-                "# Define stratification method\n",
-                "strat_obj = StratifiedKFold(n_splits=5, shuffle=True, random_state=0)\n",
-                "\n",
                 "# Create a Logistic Regression model\n",
                 "logreg_params = {\n",
                 "    \"max_iter\": 1000,\n",
@@ -385,7 +378,7 @@
                 "    \"param_distributions\": param_dist,\n",
                 "    \"scoring\": \"precision\",\n",
                 "    \"n_iter\": 100,\n",
-                "    \"cv\": strat_obj,\n",
+                "    \"cv\": 5,\n",
                 "    \"random_state\": 0,\n",
                 "    \"n_jobs\": -1,\n",
                 "}"
@@ -405,10 +398,10 @@
             "execution_count": 12,
             "metadata": {
                 "execution": {
-                    "iopub.execute_input": "2023-08-17T16:46:34.322867Z",
-                    "iopub.status.busy": "2023-08-17T16:46:34.322625Z",
-                    "iopub.status.idle": "2023-08-17T16:53:19.476298Z",
-                    "shell.execute_reply": "2023-08-17T16:53:19.475891Z"
+                    "iopub.execute_input": "2023-09-01T13:33:06.150016Z",
+                    "iopub.status.busy": "2023-09-01T13:33:06.149817Z",
+                    "iopub.status.idle": "2023-09-01T13:39:55.805395Z",
+                    "shell.execute_reply": "2023-09-01T13:39:55.804768Z"
                 },
                 "jukit_cell_id": "YY8qaxm1l1"
             },
@@ -443,10 +436,10 @@
             "execution_count": 13,
             "metadata": {
                 "execution": {
-                    "iopub.execute_input": "2023-08-17T16:53:19.478510Z",
-                    "iopub.status.busy": "2023-08-17T16:53:19.478352Z",
-                    "iopub.status.idle": "2023-08-17T16:59:48.318350Z",
-                    "shell.execute_reply": "2023-08-17T16:59:48.317710Z"
+                    "iopub.execute_input": "2023-09-01T13:39:55.808015Z",
+                    "iopub.status.busy": "2023-09-01T13:39:55.807835Z",
+                    "iopub.status.idle": "2023-09-01T13:46:38.468473Z",
+                    "shell.execute_reply": "2023-09-01T13:46:38.468023Z"
                 },
                 "jukit_cell_id": "HoOPZ90KFZ"
             },
@@ -482,10 +475,10 @@
             "execution_count": 14,
             "metadata": {
                 "execution": {
-                    "iopub.execute_input": "2023-08-17T16:59:48.321003Z",
-                    "iopub.status.busy": "2023-08-17T16:59:48.320788Z",
-                    "iopub.status.idle": "2023-08-17T16:59:48.328672Z",
-                    "shell.execute_reply": "2023-08-17T16:59:48.328422Z"
+                    "iopub.execute_input": "2023-09-01T13:46:38.470611Z",
+                    "iopub.status.busy": "2023-09-01T13:46:38.470501Z",
+                    "iopub.status.idle": "2023-09-01T13:46:38.476534Z",
+                    "shell.execute_reply": "2023-09-01T13:46:38.476296Z"
                 },
                 "jukit_cell_id": "XmQTfarxJe"
             },
@@ -526,10 +519,10 @@
             "execution_count": 15,
             "metadata": {
                 "execution": {
-                    "iopub.execute_input": "2023-08-17T16:59:48.358203Z",
-                    "iopub.status.busy": "2023-08-17T16:59:48.358037Z",
-                    "iopub.status.idle": "2023-08-17T16:59:48.368806Z",
-                    "shell.execute_reply": "2023-08-17T16:59:48.368428Z"
+                    "iopub.execute_input": "2023-09-01T13:46:38.500321Z",
+                    "iopub.status.busy": "2023-09-01T13:46:38.500182Z",
+                    "iopub.status.idle": "2023-09-01T13:46:38.508417Z",
+                    "shell.execute_reply": "2023-09-01T13:46:38.508160Z"
                 },
                 "jukit_cell_id": "KRaXZbEIzO"
             },
@@ -553,7 +546,7 @@
     "metadata": {
         "anaconda-cloud": {},
         "kernelspec": {
-            "display_name": "Python 3 (ipykernel)",
+            "display_name": "python",
             "language": "python",
             "name": "python3"
         },