Reduced processing time

alteryx · Jun 30, 2023 · 313a598 · 313a598
1 parent abcd38b
commit 313a598
Show file tree

Hide file tree

Showing 4 changed files with 32 additions and 17 deletions.
diff --git a/docs/source/start.ipynb b/docs/source/start.ipynb
@@ -1,13 +1,15 @@
 {
  "cells": [
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
     "# Start"
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -26,6 +28,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -42,6 +45,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -77,6 +81,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -95,13 +100,15 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
     "__Note:__ To provide data to EvalML, it is recommended that you initialize a woodwork accessor so that you control how EvalML will treat each feature, such as as a numeric feature, a categorical feature, a text feature or other type of feature. Consult the [the Woodwork project](https://woodwork.alteryx.com/en/stable/) for help on how to do this. Here, `split_data()` returns dataframes with woodwork accessors."
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -133,6 +140,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -151,6 +159,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -170,20 +179,22 @@
     "    y_train=y_train,\n",
     "    problem_type=\"binary\",\n",
     "    objective=\"f1\",\n",
-    "    max_batches=3,\n",
+    "    max_batches=2,\n",
     "    verbose=False,\n",
     ")\n",
     "automl.search()"
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
     "We also provide a standalone `search` [method](./autoapi/evalml/automl/index.rst#evalml.automl.search) which does all of the above in a single line, and returns the `AutoMLSearch` instance and data check results. If there were data check errors, AutoML will not be run and no `AutoMLSearch` instance will be returned."
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -200,6 +211,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -216,6 +228,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -233,6 +246,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -250,6 +264,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [

diff --git a/evalml/tests/automl_tests/test_automl.py b/evalml/tests/automl_tests/test_automl.py
@@ -1861,7 +1861,7 @@ def test_pipelines_in_batch_return_none(
         X_train=X,
         y_train=y,
         problem_type="binary",
-        max_batches=3,
+        max_batches=2,
         automl_algorithm="iterative",
         allowed_component_graphs={"Name": [dummy_classifier_estimator_class]},
         n_jobs=1,
@@ -2299,7 +2299,7 @@ def test_time_series_regression_with_parameters(ts_data):
         allowed_component_graphs={"Name_0": ["Imputer", "Linear Regressor"]},
         objective="auto",
         problem_configuration=problem_configuration,
-        max_batches=3,
+        max_batches=2,
     )
     assert (
         automl.automl_algorithm.search_parameters["pipeline"] == problem_configuration
@@ -2344,7 +2344,7 @@ def test_automl_accepts_component_graphs(graph_type, X_y_binary):
         problem_type="binary",
         allowed_component_graphs={"Dummy_Name": component_graph},
         objective="auto",
-        max_batches=3,
+        max_batches=2,
     )
     for pipeline_ in automl.allowed_pipelines:
         assert isinstance(pipeline_, BinaryClassificationPipeline)
@@ -4158,7 +4158,7 @@ def test_automl_drop_unknown_columns(columns, AutoMLTestEnv, X_y_binary, caplog)
         y_train=y,
         problem_type="binary",
         optimize_thresholds=False,
-        max_batches=3,
+        max_batches=2,
         verbose=True,
     )
     env = AutoMLTestEnv("binary")
@@ -4573,7 +4573,7 @@ def test_automl_passes_known_in_advance_pipeline_parameters_to_all_pipelines(
         X_train=X,
         y_train=y,
         problem_type=problem_type,
-        max_batches=3,
+        max_batches=2,
         problem_configuration={
             "time_index": "date",
             "max_delay": 3,
@@ -4624,7 +4624,7 @@ def test_cv_ranking_scores(
         X_train=X,
         y_train=y,
         problem_type="binary",
-        max_batches=3,
+        max_batches=2,
         data_splitter=data_splitter,
         allowed_component_graphs={"Name": [dummy_classifier_estimator_class]},
         n_jobs=1,
@@ -4818,7 +4818,7 @@ def test_automl_accepts_features(
         y_train=y,
         problem_type="binary",
         optimize_thresholds=False,
-        max_batches=3,
+        max_batches=2,
         features=features,
         automl_algorithm=automl_algorithm,
     )
@@ -4862,7 +4862,7 @@ def test_automl_with_empty_features_list(
         y_train=y,
         problem_type="binary",
         optimize_thresholds=False,
-        max_batches=3,
+        max_batches=2,
         features=[],
         automl_algorithm=automl_algorithm,
     )
@@ -5075,7 +5075,7 @@ def test_default_algorithm_uses_n_jobs(X_y_binary, AutoMLTestEnv):
         X_train=X,
         y_train=y,
         problem_type="binary",
-        max_batches=3,
+        max_batches=2,
         automl_algorithm="default",
         n_jobs=2,
     )
@@ -5525,7 +5525,7 @@ def test_holdout_set_results_and_rankings(caplog, AutoMLTestEnv):
         X_train=X,
         y_train=y,
         problem_type="binary",
-        max_batches=3,
+        max_batches=2,
         automl_algorithm="default",
         verbose=True,
         holdout_set_size=0.1,

diff --git a/evalml/tests/automl_tests/test_automl_search_classification.py b/evalml/tests/automl_tests/test_automl_search_classification.py
@@ -1022,7 +1022,7 @@ def test_automl_search_dictionary_undersampler(
         optimize_thresholds=False,
         sampler_method="Undersampler",
         search_parameters=search_parameters,
-        max_batches=3,
+        max_batches=2,
     )
     # check that the sampling dict got set properly
     automl.search()
@@ -1077,7 +1077,7 @@ def test_automl_search_dictionary_oversampler(
         sampler_method="Oversampler",
         optimize_thresholds=False,
         search_parameters=search_parameters,
-        max_batches=3,
+        max_batches=2,
     )
     # check that the sampling dict got set properly
     pipelines = automl.allowed_pipelines
@@ -1122,7 +1122,7 @@ def test_automl_search_sampler_dictionary_keys(
         sampler_method=sampler,
         optimize_thresholds=False,
         search_parameters=search_parameters,
-        max_batches=3,
+        max_batches=2,
     )
     if errors:
         with pytest.raises(
@@ -1254,7 +1254,7 @@ def test_automl_passes_allow_long_running_models(
         objective="Log Loss Multiclass",
         allow_long_running_models=allow_long_running_models,
         automl_algorithm=algo,
-        max_batches=3,
+        max_batches=2,
         verbose=True,
     )
     assert (
@@ -1280,7 +1280,7 @@ def test_automl_threshold_score(fraud_100):
         X_train,
         y_train,
         problem_type="binary",
-        max_batches=3,
+        max_batches=2,
         ensembling=True,
         verbose=False,
         automl_algorithm="default",

diff --git a/evalml/tests/automl_tests/test_search.py b/evalml/tests/automl_tests/test_search.py
@@ -121,7 +121,7 @@ def test_search_args(mock_automl_search, mock_data_checks_validate, X_y_binary):
     assert automl.max_time == 42
     assert automl.patience == 3
     assert automl.tolerance == 0.5
-    assert automl.max_batches == 4
+    assert automl.max_batches == 3
     assert isinstance(automl.automl_algorithm, DefaultAlgorithm)
 
     automl, _ = search(