From 46ea28a49d7d61a356e96ae6a25e12af3563de21 Mon Sep 17 00:00:00 2001
From: Dipak Nidhi <nidhi73dipak@gmail.com>
Date: Wed, 11 Oct 2023 13:48:36 +0300
Subject: [PATCH] added my notbook

---
 notebooks/Final_LR_feature_importance.ipynb  | 194 +++++++++++++++++++
 notebooks/Final_MLP_feature_importance.ipynb | 184 ++++++++++++++++++
 2 files changed, 378 insertions(+)
 create mode 100644 notebooks/Final_LR_feature_importance.ipynb
 create mode 100644 notebooks/Final_MLP_feature_importance.ipynb

diff --git a/notebooks/Final_LR_feature_importance.ipynb b/notebooks/Final_LR_feature_importance.ipynb
new file mode 100644
index 00000000..9f519f54
--- /dev/null
+++ b/notebooks/Final_LR_feature_importance.ipynb
@@ -0,0 +1,194 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "2df65bbd",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.linear_model import LogisticRegression\n",
+    "from sklearn.metrics import accuracy_score\n",
+    "from sklearn.inspection import permutation_importance\n",
+    "import matplotlib.pyplot as plt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def load_data(x_res_path='X_res.csv', y_res_path='y_res.csv'):\n",
+    "    \"\"\"\n",
+    "    Load resampled data from CSV files.\n",
+    "\n",
+    "    Parameters:\n",
+    "        x_res_path (str): Path to the CSV file containing feature data.\n",
+    "        y_res_path (str): Path to the CSV file containing target data.\n",
+    "\n",
+    "    Returns:\n",
+    "        pd.DataFrame: Feature and target data.\n",
+    "    \"\"\"\n",
+    "    X_res = pd.read_csv(x_res_path)\n",
+    "    y_res = pd.read_csv(y_res_path)\n",
+    "    return X_res, y_res\n",
+    "\n",
+    "def train_model(X_train, y_train):\n",
+    "    \"\"\"\n",
+    "    Train a Logistic Regression model.\n",
+    "\n",
+    "    Parameters:\n",
+    "        X_train (pd.DataFrame): Training feature data.\n",
+    "        y_train (pd.DataFrame): Training target data.\n",
+    "\n",
+    "    Returns:\n",
+    "        LogisticRegression: Trained Logistic Regression model.\n",
+    "    \"\"\"\n",
+    "    model = LogisticRegression()\n",
+    "    model.fit(X_train, y_train.values.ravel())\n",
+    "    return model\n",
+    "\n",
+    "def evaluate_model(model, X_test, y_test):\n",
+    "    \"\"\"\n",
+    "    Evaluate model accuracy and display feature importances.\n",
+    "\n",
+    "    Parameters:\n",
+    "        model (LogisticRegression): Trained Logistic Regression model.\n",
+    "        X_test (pd.DataFrame): Testing feature data.\n",
+    "        y_test (pd.DataFrame): Testing target data.\n",
+    "    \"\"\"\n",
+    "    y_pred = model.predict(X_test)\n",
+    "    base_accuracy = accuracy_score(y_test, y_pred)\n",
+    "    print(\"Accuracy:\", base_accuracy)\n",
+    "    \n",
+    "    result = permutation_importance(model, X_test, y_test.values.ravel(), n_repeats=50, random_state=0)\n",
+    "\n",
+    "    feature_importance = pd.DataFrame({'Feature': X_test.columns,\n",
+    "                                       'Importance': result.importances_mean})\n",
+    "    feature_importance['Importance'] = feature_importance['Importance'] * 100\n",
+    "    feature_importance = feature_importance.sort_values(by='Importance', ascending=False)\n",
+    "    feature_importance['Importance'] = feature_importance['Importance'].apply(lambda x: '{:.6f}%'.format(x))\n",
+    "    print(feature_importance)\n",
+    "    \n",
+    "    plot_feature_importance(result.importances_mean, X_test.columns)\n",
+    "\n",
+    "def plot_feature_importance(importances, feature_names):\n",
+    "    \"\"\"\n",
+    "    Plot feature importances.\n",
+    "\n",
+    "    Parameters:\n",
+    "        importances (np.array): Array of feature importances.\n",
+    "        feature_names (list): List of feature names.\n",
+    "    \"\"\"\n",
+    "    imp = pd.Series(importances*100, index=feature_names).sort_values(ascending=True)\n",
+    "    ax = imp.plot.barh()\n",
+    "    ax.set_title(f\"LR permutation_importance\")\n",
+    "    ax.figure.tight_layout()\n",
+    "    plt.xlabel('Importance (%)')\n",
+    "    plt.grid(axis='x', linestyle='--', alpha=0.6)\n",
+    "    plt.ylabel('Feature')\n",
+    "    plt.title('Logistic Regression Permutation Feature Importance')\n",
+    "    for i, v in enumerate(imp):\n",
+    "        ax.text(v, i, str(round(v,1)), color='blue', fontweight='bold', fontsize=8)\n",
+    "    plt.show()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "03ac820b",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/dipak/anaconda3/envs/bayesian/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:460: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
+      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
+      "\n",
+      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
+      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
+      "Please also refer to the documentation for alternative solver options:\n",
+      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
+      "  n_iter_i = _check_optimize_result(\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Accuracy: 0.92803597387663\n",
+      "     Feature  Importance\n",
+      "1     Mag_AS  35.580138%\n",
+      "4      DRC45  10.715426%\n",
+      "19   EM_Inph  10.640861%\n",
+      "3     DRC180   8.077947%\n",
+      "17  EM_Ap_rs   3.590553%\n",
+      "8   Mag_Xdrv   2.568186%\n",
+      "10  Mag_Zdrv   1.804696%\n",
+      "18     Em_Qd   1.705564%\n",
+      "9   mag_Ydrv   1.231072%\n",
+      "5      DRC90   0.658129%\n",
+      "0    Mag_TMI   0.440647%\n",
+      "12      Rd_U   0.172251%\n",
+      "15      Rd_K   0.125618%\n",
+      "2     DRC135   0.125163%\n",
+      "6     Mag_TD   0.034602%\n",
+      "11  Pseu_Grv   0.002194%\n",
+      "7      HDTDR   0.000000%\n",
+      "14     Rd_Th  -0.023804%\n",
+      "16  EM_ratio  -0.080453%\n",
+      "13     Rd_TC  -0.223372%\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Example usage:\n",
+    "X_res, y_res = load_data('/home/dipak/Desktop/codes/SMOTE/X_res.csv', '/home/dipak/Desktop/codes/SMOTE/y_res.csv')\n",
+    "X_train, X_test, y_train, y_test = train_test_split(X_res, y_res, test_size=0.2, random_state=0)\n",
+    "\n",
+    "model = train_model(X_train, y_train)\n",
+    "evaluate_model(model, X_test, y_test)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "maati",
+   "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": "3.9.16"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "82066b0237e4b3d286efffd3c9285d2f9ccb2657b1585d54bb3129443d417e32"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/notebooks/Final_MLP_feature_importance.ipynb b/notebooks/Final_MLP_feature_importance.ipynb
new file mode 100644
index 00000000..29731edf
--- /dev/null
+++ b/notebooks/Final_MLP_feature_importance.ipynb
@@ -0,0 +1,184 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "from sklearn.neural_network import MLPClassifier\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.preprocessing import StandardScaler\n",
+    "import matplotlib.pyplot as plt\n",
+    "from sklearn.inspection import permutation_importance\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def load_and_scale_data(x_path, y_path):\n",
+    "    \"\"\"\n",
+    "    Load and scale feature and target data from specified paths.\n",
+    "\n",
+    "    Parameters:\n",
+    "        x_path (str): Path to the CSV file containing feature data.\n",
+    "        y_path (str): Path to the CSV file containing target data.\n",
+    "\n",
+    "    Returns:\n",
+    "        np.ndarray, pd.DataFrame: Scaled feature data and target data.\n",
+    "    \"\"\"\n",
+    "    X = pd.read_csv(x_path)\n",
+    "    X_scaled = StandardScaler().fit_transform(X)\n",
+    "    y = pd.read_csv(y_path)\n",
+    "    return X_scaled, y\n",
+    "\n",
+    "def split_data(X, y, test_size=0.25):\n",
+    "    \"\"\"\n",
+    "    Split data into training and testing sets.\n",
+    "\n",
+    "    Parameters:\n",
+    "        X (np.ndarray): Feature data.\n",
+    "        y (pd.DataFrame): Target data.\n",
+    "        test_size (float): Proportion of dataset to include in the test split.\n",
+    "\n",
+    "    Returns:\n",
+    "        np.ndarray, np.ndarray, pd.DataFrame, pd.DataFrame: Training and testing data for features and target.\n",
+    "    \"\"\"\n",
+    "    return train_test_split(X, y, test_size=test_size)\n",
+    "\n",
+    "def train_classifier(X_train, y_train, solver='adam', alpha=0.001, hidden_layer_sizes=(16, 2), random_state=1):\n",
+    "    \"\"\"\n",
+    "    Train a Multi-Layer Perceptron classifier and return the model.\n",
+    "\n",
+    "    Parameters:\n",
+    "        X_train (np.ndarray): Training feature data.\n",
+    "        y_train (pd.DataFrame): Training target data.\n",
+    "        solver (str): Solver for weight optimization.\n",
+    "        alpha (float): L2 penalty parameter.\n",
+    "        hidden_layer_sizes (tuple): The ith element represents the number of neurons in the ith hidden layer.\n",
+    "        random_state (int): Determines random number generation for weights and bias initialization.\n",
+    "\n",
+    "    Returns:\n",
+    "        MLPClassifier: Trained classifier.\n",
+    "    \"\"\"\n",
+    "    clf = MLPClassifier(solver=solver, alpha=alpha, hidden_layer_sizes=hidden_layer_sizes, random_state=random_state)\n",
+    "    clf.fit(X_train, y_train.values.ravel())\n",
+    "    return clf\n",
+    "\n",
+    "def evaluate_and_display_importance(clf, X_test, y_test, feature_names):\n",
+    "    \"\"\"\n",
+    "    Evaluate classifier, display accuracy and plot feature importances.\n",
+    "\n",
+    "    Parameters:\n",
+    "        clf (MLPClassifier): Trained classifier.\n",
+    "        X_test (np.ndarray): Testing feature data.\n",
+    "        y_test (pd.DataFrame): Testing target data.\n",
+    "        feature_names (list): Names of the feature columns.\n",
+    "    \"\"\"\n",
+    "    print(\"Accuracy:\", clf.score(X_test, y_test))\n",
+    "    \n",
+    "    result = permutation_importance(clf, X_test, y_test.values.ravel(), n_repeats=50, random_state=0)\n",
+    "\n",
+    "    feature_importance = pd.DataFrame({'Feature': feature_names,\n",
+    "                                       'Importance': result.importances_mean})\n",
+    "    feature_importance['Importance'] = feature_importance['Importance']*100\n",
+    "    feature_importance = feature_importance.sort_values(by='Importance', ascending=False)\n",
+    "    feature_importance['Importance'] = feature_importance['Importance'].apply(lambda x: '{:.6f}%'.format(x))\n",
+    "    print(feature_importance)\n",
+    "\n",
+    "    imp = pd.Series(result.importances_mean*100, index=feature_names).sort_values(ascending=True)\n",
+    "    ax = imp.plot.barh()\n",
+    "    ax.set_title(\"MLP Permutation Importance\")\n",
+    "    ax.figure.tight_layout()\n",
+    "    plt.xlabel('Importance (%)')\n",
+    "    plt.grid(axis='x', linestyle='--', alpha=0.6)\n",
+    "    plt.ylabel('Feature')\n",
+    "    for i, v in enumerate(imp):\n",
+    "        ax.text(v, i, f\"{v:.1f}\", color='blue', fontweight='bold', fontsize=8)\n",
+    "    plt.show()\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Accuracy: 0.9999468419796481\n",
+      "     Feature  Importance\n",
+      "1     Mag_AS  35.750235%\n",
+      "3     DRC180  27.303263%\n",
+      "11  Pseu_Grv  25.969288%\n",
+      "9   mag_Ydrv  22.786641%\n",
+      "5      DRC90  22.534069%\n",
+      "18     Em_Qd  19.747638%\n",
+      "7      HDTDR  17.318675%\n",
+      "19   EM_Inph  17.076689%\n",
+      "17  EM_Ap_rs  16.363408%\n",
+      "6     Mag_TD  14.967083%\n",
+      "8   Mag_Xdrv  14.550342%\n",
+      "10  Mag_Zdrv  14.373907%\n",
+      "4      DRC45  13.481301%\n",
+      "2     DRC135  10.828382%\n",
+      "0    Mag_TMI   8.320356%\n",
+      "16  EM_ratio   0.012758%\n",
+      "13     Rd_TC   0.004268%\n",
+      "14     Rd_Th   0.004042%\n",
+      "12      Rd_U   0.004001%\n",
+      "15      Rd_K   0.003975%\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Example usage:\n",
+    "feature_names = [\"Mag_TMI\",\"Mag_AS\",\"DRC135\",\"DRC180\",\"DRC45\",\"DRC90\",\"Mag_TD\",\"HDTDR\",\"Mag_Xdrv\",\"mag_Ydrv\",\n",
+    "                 \"Mag_Zdrv\",\"Pseu_Grv\",\"Rd_U\",\"Rd_TC\",\"Rd_Th\",\"Rd_K\",\"EM_ratio\",\"EM_Ap_rs\",\"Em_Qd\",\"EM_Inph\"]\n",
+    "\n",
+    "X, y = load_and_scale_data('/home/dipak/Desktop/Wine_datasets/X_res.csv', '/home/dipak/Desktop/Wine_datasets/y_res.csv')\n",
+    "X_train, X_test, y_train, y_test = split_data(X, y, test_size=0.25)\n",
+    "clf = train_classifier(X_train, y_train)\n",
+    "evaluate_and_display_importance(clf, X_test, y_test, feature_names)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "bayesian",
+   "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": "3.9.16"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}