Update user guides

SelfExplainML · May 18, 2023 · c1bf14d · c1bf14d
1 parent 5347534
commit c1bf14d
Show file tree

Hide file tree

Showing 151 changed files with 4,565 additions and 1,606 deletions.
diff --git a/docs/_build/doctrees/auto_examples/data/plot_0_data_loader.doctree b/docs/_build/doctrees/auto_examples/data/plot_0_data_loader.doctree
diff --git a/docs/_build/doctrees/auto_examples/data/plot_1_data_summary.doctree b/docs/_build/doctrees/auto_examples/data/plot_1_data_summary.doctree
diff --git a/docs/_build/doctrees/auto_examples/data/plot_2_data_eda.doctree b/docs/_build/doctrees/auto_examples/data/plot_2_data_eda.doctree
diff --git a/docs/_build/doctrees/auto_examples/data/plot_3_data_prepare.doctree b/docs/_build/doctrees/auto_examples/data/plot_3_data_prepare.doctree
diff --git a/docs/_build/doctrees/auto_examples/data/sg_execution_times.doctree b/docs/_build/doctrees/auto_examples/data/sg_execution_times.doctree
diff --git a/docs/_build/doctrees/environment.pickle b/docs/_build/doctrees/environment.pickle
diff --git a/docs/_build/doctrees/guides/data/data_eda.doctree b/docs/_build/doctrees/guides/data/data_eda.doctree
diff --git a/docs/_build/doctrees/guides/data/data_prepare.doctree b/docs/_build/doctrees/guides/data/data_prepare.doctree
diff --git a/docs/_build/doctrees/guides/data/data_quality.doctree b/docs/_build/doctrees/guides/data/data_quality.doctree
diff --git a/docs/_build/doctrees/guides/data/data_summary.doctree b/docs/_build/doctrees/guides/data/data_summary.doctree
diff --git a/docs/_build/doctrees/guides/data/feature_select.doctree b/docs/_build/doctrees/guides/data/feature_select.doctree
diff --git a/docs/_build/doctrees/guides/data/twosample_test.doctree b/docs/_build/doctrees/guides/data/twosample_test.doctree
diff --git a/docs/_build/doctrees/install.doctree b/docs/_build/doctrees/install.doctree
diff --git a/docs/_build/doctrees/modules/generated/piml.Experiment.doctree b/docs/_build/doctrees/modules/generated/piml.Experiment.doctree
diff --git a/docs/_build/html/_downloads/040e1bcb780cb69207e79163836035dc/plot_1_data_summary.ipynb b/docs/_build/html/_downloads/040e1bcb780cb69207e79163836035dc/plot_1_data_summary.ipynb
@@ -1,5 +1,16 @@
 {
   "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "collapsed": false
+      },
+      "outputs": [],
+      "source": [
+        "%matplotlib inline"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -22,7 +33,43 @@
       },
       "outputs": [],
       "source": [
-        "from piml import Experiment\n\nexp = Experiment()\nexp.data_loader(data=\"BikeSharing\", silent=True)\n\nexp.data_summary(feature_type={},feature_exclude=[])"
+        "from piml import Experiment\n\nexp = Experiment(highcode_only=True)\nexp.data_loader(data=\"BikeSharing\", silent=True)\n\nexp.data_summary(feature_type={}, feature_exclude=[])"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Feature removal\n\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "collapsed": false
+      },
+      "outputs": [],
+      "source": [
+        "exp.data_summary(feature_exclude=[\"yr\", \"mnth\", \"temp\"])"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Change feature types\n\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "collapsed": false
+      },
+      "outputs": [],
+      "source": [
+        "exp.data_summary(feature_type={\"weekday\": \"categorical\"})"
       ]
     }
   ],
@@ -42,7 +89,7 @@
       "name": "python",
       "nbconvert_exporter": "python",
       "pygments_lexer": "ipython3",
-      "version": "3.10.11"
+      "version": "3.9.12"
     }
   },
   "nbformat": 4,

diff --git a/docs/_build/html/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip b/docs/_build/html/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip
diff --git a/docs/_build/html/_downloads/268cd7ccf05ba3db4bb927f170b68f8b/plot_2_data_eda.py b/docs/_build/html/_downloads/268cd7ccf05ba3db4bb927f170b68f8b/plot_2_data_eda.py
@@ -36,8 +36,8 @@
 
 # %%
 # correlation heatmap
-exp.eda(show='multivariate', multi_type='correlation_heatmap', figsize=(5, 4))
+exp.eda(show='multivariate', multi_type='correlation_heatmap', figsize=(6, 5))
 
 # %%
 # correlation graph
-exp.eda(show='multivariate', multi_type='correlation_graph', figsize=(5, 4))
+exp.eda(show='multivariate', multi_type='correlation_graph', figsize=(6, 5))
diff --git a/docs/_build/html/_downloads/6f1e7a639e0699d6164445b55e6c116d/auto_examples_jupyter.zip b/docs/_build/html/_downloads/6f1e7a639e0699d6164445b55e6c116d/auto_examples_jupyter.zip
diff --git a/docs/_build/html/_downloads/88c585f5be3189c21b7b64f94b7d4c1d/plot_1_data_summary.py b/docs/_build/html/_downloads/88c585f5be3189c21b7b64f94b7d4c1d/plot_1_data_summary.py
@@ -10,7 +10,15 @@
 # Experiment initialization and data preparation
 from piml import Experiment
 
-exp = Experiment()
+exp = Experiment(highcode_only=True)
 exp.data_loader(data="BikeSharing", silent=True)
 
-exp.data_summary(feature_type={},feature_exclude=[])
+exp.data_summary(feature_type={}, feature_exclude=[])
+
+#%%
+# Feature removal
+exp.data_summary(feature_exclude=["yr", "mnth", "temp"])
+
+#%%
+# Change feature types
+exp.data_summary(feature_type={"weekday": "categorical"})
diff --git a/docs/_build/html/_downloads/a04dc4b44b4be95c12b300a8a6f20453/plot_2_data_eda.ipynb b/docs/_build/html/_downloads/a04dc4b44b4be95c12b300a8a6f20453/plot_2_data_eda.ipynb
@@ -141,7 +141,7 @@
       },
       "outputs": [],
       "source": [
-        "exp.eda(show='multivariate', multi_type='correlation_heatmap', figsize=(5, 4))"
+        "exp.eda(show='multivariate', multi_type='correlation_heatmap', figsize=(6, 5))"
       ]
     },
     {
@@ -159,7 +159,7 @@
       },
       "outputs": [],
       "source": [
-        "exp.eda(show='multivariate', multi_type='correlation_graph', figsize=(5, 4))"
+        "exp.eda(show='multivariate', multi_type='correlation_graph', figsize=(6, 5))"
       ]
     }
   ],

diff --git a/docs/_build/html/_downloads/b2ece34e3c321a03403e6d3f1e05817b/plot_0_data_loader.py b/docs/_build/html/_downloads/b2ece34e3c321a03403e6d3f1e05817b/plot_0_data_loader.py
diff --git a/docs/_build/html/_downloads/ba163cdea28be131742a4208b4eb7cde/plot_3_data_prepare.py b/docs/_build/html/_downloads/ba163cdea28be131742a4208b4eb7cde/plot_3_data_prepare.py
@@ -8,15 +8,30 @@
 
 #%%
 # Experiment initialization and data preparation
+import numpy as np
 from piml import Experiment
 
 exp = Experiment()
 exp.data_loader(data="BikeSharing", silent=True)
 
-exp.data_prepare(target='cnt', task_type='Regression', sample_weight=None,
+#%%
+# Random split
+exp.data_prepare(target='cnt', task_type='regression', sample_weight=None,
                        split_method='random', test_ratio=0.2, random_state=0)
 
-import numpy as np
-custom_train_idx = np.arange(0,16000)
+#%%
+# Outer-sample-based split
+exp.data_prepare(target='cnt', task_type='regression', sample_weight=None,
+            split_method='outer-sample', test_ratio=0.2, random_state=0)
+
+#%%
+# KMeans-based split
+exp.data_prepare(target='cnt', task_type='regression', sample_weight=None,
+                 split_method='kmeans', test_ratio=[0.0, 1.0, 0.0], random_state=0)
+
+#%%
+# Custom split
+custom_train_idx = np.arange(0, 16000)
 custom_test_idx = np.arange(16000, 17379)
-exp.data_prepare(train_idx=custom_train_idx, test_idx=custom_test_idx)
+exp.data_prepare(target='cnt', task_type='regression', sample_weight=None, 
+                 train_idx=custom_train_idx, test_idx=custom_test_idx)
diff --git a/docs/_build/html/_downloads/e53c7505626799a26bea02da2fbd5275/plot_3_data_prepare.ipynb b/docs/_build/html/_downloads/e53c7505626799a26bea02da2fbd5275/plot_3_data_prepare.ipynb
@@ -33,7 +33,79 @@
       },
       "outputs": [],
       "source": [
-        "from piml import Experiment\n\nexp = Experiment()\nexp.data_loader(data=\"BikeSharing\", silent=True)\n\nexp.data_prepare(target='cnt', task_type='Regression', sample_weight=None,\n                       split_method='random', test_ratio=0.2, random_state=0)\n\nimport numpy as np\ncustom_train_idx = np.arange(0,16000)\ncustom_test_idx = np.arange(16000, 17379)\nexp.data_prepare(train_idx=custom_train_idx, test_idx=custom_test_idx)"
+        "import numpy as np\nfrom piml import Experiment\n\nexp = Experiment()\nexp.data_loader(data=\"BikeSharing\", silent=True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Random split\n\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "collapsed": false
+      },
+      "outputs": [],
+      "source": [
+        "exp.data_prepare(target='cnt', task_type='regression', sample_weight=None,\n                       split_method='random', test_ratio=0.2, random_state=0)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Outer-sample-based split\n\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "collapsed": false
+      },
+      "outputs": [],
+      "source": [
+        "exp.data_prepare(target='cnt', task_type='regression', sample_weight=None,\n            split_method='outer-sample', test_ratio=0.2, random_state=0)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "KMeans-based split\n\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "collapsed": false
+      },
+      "outputs": [],
+      "source": [
+        "exp.data_prepare(target='cnt', task_type='regression', sample_weight=None,\n                 split_method='kmeans', test_ratio=[0.0, 1.0, 0.0], random_state=0)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Custom split\n\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "collapsed": false
+      },
+      "outputs": [],
+      "source": [
+        "custom_train_idx = np.arange(0, 16000)\ncustom_test_idx = np.arange(16000, 17379)\nexp.data_prepare(target='cnt', task_type='regression', sample_weight=None, \n                 train_idx=custom_train_idx, test_idx=custom_test_idx)"
       ]
     }
   ],

diff --git a/docs/_build/html/_downloads/ffb06e3c98665323e482500609f6b0e9/plot_0_data_loader.ipynb b/docs/_build/html/_downloads/ffb06e3c98665323e482500609f6b0e9/plot_0_data_loader.ipynb
diff --git a/docs/_build/html/_images/sphx_glr_plot_0_data_loader_thumb.png b/docs/_build/html/_images/sphx_glr_plot_0_data_loader_thumb.png
diff --git a/docs/_build/html/_images/sphx_glr_plot_2_data_eda_006.png b/docs/_build/html/_images/sphx_glr_plot_2_data_eda_006.png
diff --git a/docs/_build/html/_images/sphx_glr_plot_2_data_eda_007.png b/docs/_build/html/_images/sphx_glr_plot_2_data_eda_007.png