Pushing the docs to dev/ for branch: main, commit e3b4b9ce6fbe96f5e4166ead0f45d755f1759291

Author: sklearn-ci

dev/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "from sklearn.model_selection import (\n    TimeSeriesSplit,\n    KFold,\n    ShuffleSplit,\n    StratifiedKFold,\n    GroupShuffleSplit,\n    GroupKFold,\n    StratifiedShuffleSplit,\n    StratifiedGroupKFold,\n)\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom matplotlib.patches import Patch\n\nnp.random.seed(1338)\ncmap_data = plt.cm.Paired\ncmap_cv = plt.cm.coolwarm\nn_splits = 4"
+        "from sklearn.model_selection import (\n    TimeSeriesSplit,\n    KFold,\n    ShuffleSplit,\n    StratifiedKFold,\n    GroupShuffleSplit,\n    GroupKFold,\n    StratifiedShuffleSplit,\n    StratifiedGroupKFold,\n)\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom matplotlib.patches import Patch\n\nrng = np.random.RandomState(1338)\ncmap_data = plt.cm.Paired\ncmap_cv = plt.cm.coolwarm\nn_splits = 4"
       ]
     },
     {
@@ -44,7 +44,7 @@
       },
       "outputs": [],
       "source": [
-        "# Generate the class/group data\nn_points = 100\nX = np.random.randn(100, 10)\n\npercentiles_classes = [0.1, 0.3, 0.6]\ny = np.hstack([[ii] * int(100 * perc) for ii, perc in enumerate(percentiles_classes)])\n\n# Evenly spaced groups repeated once\ngroups = np.hstack([[ii] * 10 for ii in range(10)])\n\n\ndef visualize_groups(classes, groups, name):\n    # Visualize dataset groups\n    fig, ax = plt.subplots()\n    ax.scatter(\n        range(len(groups)),\n        [0.5] * len(groups),\n        c=groups,\n        marker=\"_\",\n        lw=50,\n        cmap=cmap_data,\n    )\n    ax.scatter(\n        range(len(groups)),\n        [3.5] * len(groups),\n        c=classes,\n        marker=\"_\",\n        lw=50,\n        cmap=cmap_data,\n    )\n    ax.set(\n        ylim=[-1, 5],\n        yticks=[0.5, 3.5],\n        yticklabels=[\"Data\\ngroup\", \"Data\\nclass\"],\n        xlabel=\"Sample index\",\n    )\n\n\nvisualize_groups(y, groups, \"no groups\")"
+        "# Generate the class/group data\nn_points = 100\nX = rng.randn(100, 10)\n\npercentiles_classes = [0.1, 0.3, 0.6]\ny = np.hstack([[ii] * int(100 * perc) for ii, perc in enumerate(percentiles_classes)])\n\n# Generate uneven groups\ngroup_prior = rng.dirichlet([2] * 10)\ngroups = np.repeat(np.arange(10), rng.multinomial(100, group_prior))\n\n\ndef visualize_groups(classes, groups, name):\n    # Visualize dataset groups\n    fig, ax = plt.subplots()\n    ax.scatter(\n        range(len(groups)),\n        [0.5] * len(groups),\n        c=groups,\n        marker=\"_\",\n        lw=50,\n        cmap=cmap_data,\n    )\n    ax.scatter(\n        range(len(groups)),\n        [3.5] * len(groups),\n        c=classes,\n        marker=\"_\",\n        lw=50,\n        cmap=cmap_data,\n    )\n    ax.set(\n        ylim=[-1, 5],\n        yticks=[0.5, 3.5],\n        yticklabels=[\"Data\\ngroup\", \"Data\\nclass\"],\n        xlabel=\"Sample index\",\n    )\n\n\nvisualize_groups(y, groups, \"no groups\")"
       ]
     },
     {
@@ -98,7 +98,7 @@
       },
       "outputs": [],
       "source": [
-        "# To better demonstrate the difference, we will assign samples to groups\n# unevenly:\n\nuneven_groups = np.sort(np.random.randint(0, 10, n_points))\n\ncvs = [StratifiedKFold, GroupKFold, StratifiedGroupKFold]\n\nfor cv in cvs:\n    fig, ax = plt.subplots(figsize=(6, 3))\n    plot_cv_indices(cv(n_splits), X, y, uneven_groups, ax, n_splits)\n    ax.legend(\n        [Patch(color=cmap_cv(0.8)), Patch(color=cmap_cv(0.02))],\n        [\"Testing set\", \"Training set\"],\n        loc=(1.02, 0.8),\n    )\n    # Make the legend fit\n    plt.tight_layout()\n    fig.subplots_adjust(right=0.7)"
+        "cvs = [StratifiedKFold, GroupKFold, StratifiedGroupKFold]\n\nfor cv in cvs:\n    fig, ax = plt.subplots(figsize=(6, 3))\n    plot_cv_indices(cv(n_splits), X, y, groups, ax, n_splits)\n    ax.legend(\n        [Patch(color=cmap_cv(0.8)), Patch(color=cmap_cv(0.02))],\n        [\"Testing set\", \"Training set\"],\n        loc=(1.02, 0.8),\n    )\n    # Make the legend fit\n    plt.tight_layout()\n    fig.subplots_adjust(right=0.7)"
       ]
     },
     {

dev/_downloads/49cd91d05440a1c88b074430761aeb76/plot_cv_indices.ipynb

@@ -26,7 +26,7 @@
 import matplotlib.pyplot as plt
 from matplotlib.patches import Patch
 
-np.random.seed(1338)
+rng = np.random.RandomState(1338)
 cmap_data = plt.cm.Paired
 cmap_cv = plt.cm.coolwarm
 n_splits = 4
@@ -47,13 +47,14 @@
 
 # Generate the class/group data
 n_points = 100
-X = np.random.randn(100, 10)
+X = rng.randn(100, 10)
 
 percentiles_classes = [0.1, 0.3, 0.6]
 y = np.hstack([[ii] * int(100 * perc) for ii, perc in enumerate(percentiles_classes)])
 
-# Evenly spaced groups repeated once
-groups = np.hstack([[ii] * 10 for ii in range(10)])
+# Generate uneven groups
+group_prior = rng.dirichlet([2] * 10)
+groups = np.repeat(np.arange(10), rng.multinomial(100, group_prior))
 
 
 def visualize_groups(classes, groups, name):
@@ -158,17 +159,11 @@ def plot_cv_indices(cv, X, y, group, ax, n_splits, lw=10):
 #   different folds.
 # - ``StratifiedGroupKFold`` to keep the constraint of ``GroupKFold`` while
 #   attempting to return stratified folds.
-
-# To better demonstrate the difference, we will assign samples to groups
-# unevenly:
-
-uneven_groups = np.sort(np.random.randint(0, 10, n_points))
-
 cvs = [StratifiedKFold, GroupKFold, StratifiedGroupKFold]
 
 for cv in cvs:
     fig, ax = plt.subplots(figsize=(6, 3))
-    plot_cv_indices(cv(n_splits), X, y, uneven_groups, ax, n_splits)
+    plot_cv_indices(cv(n_splits), X, y, groups, ax, n_splits)
     ax.legend(
         [Patch(color=cmap_cv(0.8)), Patch(color=cmap_cv(0.02))],
         ["Testing set", "Training set"],