Pushing the docs to dev/ for branch: main, commit 696ca3de57d210ffa1fdf14c50b7d1bd6a482396

Author: sklearn-ci

dev/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip

@@ -44,7 +44,7 @@
       },
       "outputs": [],
       "source": [
-        "import pandas as pd\nfrom sklearn.datasets import fetch_california_housing\nfrom sklearn.model_selection import train_test_split\n\ncal_housing = fetch_california_housing()\nX = pd.DataFrame(cal_housing.data, columns=cal_housing.feature_names)\ny = cal_housing.target\n\ny -= y.mean()\n\nX_train, X_test, y_train, y_test = train_test_split(\n    X, y, test_size=0.1, random_state=0\n)"
+        "import pandas as pd\nfrom sklearn.datasets import fetch_california_housing\nfrom sklearn.model_selection import train_test_split\n\ncal_housing = fetch_california_housing()\nX = pd.DataFrame(cal_housing.data, columns=cal_housing.feature_names)\ny = cal_housing.target\n\ny -= y.mean()\n\nX_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.1, random_state=0)"
       ]
     },
     {
@@ -62,7 +62,7 @@
       },
       "outputs": [],
       "source": [
-        "from time import time\nfrom sklearn.pipeline import make_pipeline\nfrom sklearn.preprocessing import QuantileTransformer\nfrom sklearn.neural_network import MLPRegressor\n\nprint(\"Training MLPRegressor...\")\ntic = time()\nest = make_pipeline(QuantileTransformer(),\n                    MLPRegressor(hidden_layer_sizes=(50, 50),\n                                 learning_rate_init=0.01,\n                                 early_stopping=True))\nest.fit(X_train, y_train)\nprint(f\"done in {time() - tic:.3f}s\")\nprint(f\"Test R2 score: {est.score(X_test, y_test):.2f}\")"
+        "from time import time\nfrom sklearn.pipeline import make_pipeline\nfrom sklearn.preprocessing import QuantileTransformer\nfrom sklearn.neural_network import MLPRegressor\n\nprint(\"Training MLPRegressor...\")\ntic = time()\nest = make_pipeline(\n    QuantileTransformer(),\n    MLPRegressor(\n        hidden_layer_sizes=(50, 50), learning_rate_init=0.01, early_stopping=True\n    ),\n)\nest.fit(X_train, y_train)\nprint(f\"done in {time() - tic:.3f}s\")\nprint(f\"Test R2 score: {est.score(X_test, y_test):.2f}\")"
       ]
     },
     {
@@ -80,7 +80,7 @@
       },
       "outputs": [],
       "source": [
-        "import matplotlib.pyplot as plt\nfrom sklearn.inspection import partial_dependence\nfrom sklearn.inspection import plot_partial_dependence\n\nprint('Computing partial dependence plots...')\ntic = time()\nfeatures = ['MedInc', 'AveOccup', 'HouseAge', 'AveRooms']\ndisplay = plot_partial_dependence(\n       est, X_train, features, kind=\"both\", subsample=50,\n       n_jobs=3, grid_resolution=20, random_state=0\n)\nprint(f\"done in {time() - tic:.3f}s\")\ndisplay.figure_.suptitle(\n    'Partial dependence of house value on non-___location features\\n'\n    'for the California housing dataset, with MLPRegressor'\n)\ndisplay.figure_.subplots_adjust(hspace=0.3)"
+        "import matplotlib.pyplot as plt\nfrom sklearn.inspection import partial_dependence\nfrom sklearn.inspection import plot_partial_dependence\n\nprint(\"Computing partial dependence plots...\")\ntic = time()\nfeatures = [\"MedInc\", \"AveOccup\", \"HouseAge\", \"AveRooms\"]\ndisplay = plot_partial_dependence(\n    est,\n    X_train,\n    features,\n    kind=\"both\",\n    subsample=50,\n    n_jobs=3,\n    grid_resolution=20,\n    random_state=0,\n    ice_lines_kw={\"color\": \"tab:blue\", \"alpha\": 0.2, \"linewidth\": 0.5},\n    pd_line_kw={\"color\": \"tab:orange\", \"linestyle\": \"--\"},\n)\nprint(f\"done in {time() - tic:.3f}s\")\ndisplay.figure_.suptitle(\n    \"Partial dependence of house value on non-___location features\\n\"\n    \"for the California housing dataset, with MLPRegressor\"\n)\ndisplay.figure_.subplots_adjust(hspace=0.3)"
       ]
     },
     {
@@ -116,7 +116,7 @@
       },
       "outputs": [],
       "source": [
-        "print('Computing partial dependence plots...')\ntic = time()\ndisplay = plot_partial_dependence(\n    est, X_train, features, kind=\"both\", subsample=50,\n    n_jobs=3, grid_resolution=20, random_state=0\n)\nprint(f\"done in {time() - tic:.3f}s\")\ndisplay.figure_.suptitle(\n    'Partial dependence of house value on non-___location features\\n'\n    'for the California housing dataset, with Gradient Boosting'\n)\ndisplay.figure_.subplots_adjust(wspace=0.4, hspace=0.3)"
+        "print(\"Computing partial dependence plots...\")\ntic = time()\ndisplay = plot_partial_dependence(\n    est,\n    X_train,\n    features,\n    kind=\"both\",\n    subsample=50,\n    n_jobs=3,\n    grid_resolution=20,\n    random_state=0,\n    ice_lines_kw={\"color\": \"tab:blue\", \"alpha\": 0.2, \"linewidth\": 0.5},\n    pd_line_kw={\"color\": \"tab:orange\", \"linestyle\": \"--\"},\n)\nprint(f\"done in {time() - tic:.3f}s\")\ndisplay.figure_.suptitle(\n    \"Partial dependence of house value on non-___location features\\n\"\n    \"for the California housing dataset, with Gradient Boosting\"\n)\ndisplay.figure_.subplots_adjust(wspace=0.4, hspace=0.3)"
       ]
     },
     {
@@ -141,7 +141,7 @@
       },
       "outputs": [],
       "source": [
-        "features = ['AveOccup', 'HouseAge', ('AveOccup', 'HouseAge')]\nprint('Computing partial dependence plots...')\ntic = time()\n_, ax = plt.subplots(ncols=3, figsize=(9, 4))\ndisplay = plot_partial_dependence(\n    est, X_train, features, kind='average', n_jobs=3, grid_resolution=20,\n    ax=ax,\n)\nprint(f\"done in {time() - tic:.3f}s\")\ndisplay.figure_.suptitle(\n    'Partial dependence of house value on non-___location features\\n'\n    'for the California housing dataset, with Gradient Boosting'\n)\ndisplay.figure_.subplots_adjust(wspace=0.4, hspace=0.3)"
+        "features = [\"AveOccup\", \"HouseAge\", (\"AveOccup\", \"HouseAge\")]\nprint(\"Computing partial dependence plots...\")\ntic = time()\n_, ax = plt.subplots(ncols=3, figsize=(9, 4))\ndisplay = plot_partial_dependence(\n    est,\n    X_train,\n    features,\n    kind=\"average\",\n    n_jobs=3,\n    grid_resolution=20,\n    ax=ax,\n)\nprint(f\"done in {time() - tic:.3f}s\")\ndisplay.figure_.suptitle(\n    \"Partial dependence of house value on non-___location features\\n\"\n    \"for the California housing dataset, with Gradient Boosting\"\n)\ndisplay.figure_.subplots_adjust(wspace=0.4, hspace=0.3)"
       ]
     },
     {
@@ -159,7 +159,7 @@
       },
       "outputs": [],
       "source": [
-        "import numpy as np\nfrom mpl_toolkits.mplot3d import Axes3D\nfig = plt.figure()\n\nfeatures = ('AveOccup', 'HouseAge')\npdp = partial_dependence(\n    est, X_train, features=features, kind='average', grid_resolution=20\n)\nXX, YY = np.meshgrid(pdp[\"values\"][0], pdp[\"values\"][1])\nZ = pdp.average[0].T\nax = Axes3D(fig)\nsurf = ax.plot_surface(XX, YY, Z, rstride=1, cstride=1,\n                       cmap=plt.cm.BuPu, edgecolor='k')\nax.set_xlabel(features[0])\nax.set_ylabel(features[1])\nax.set_zlabel('Partial dependence')\n# pretty init view\nax.view_init(elev=22, azim=122)\nplt.colorbar(surf)\nplt.suptitle('Partial dependence of house value on median\\n'\n             'age and average occupancy, with Gradient Boosting')\nplt.subplots_adjust(top=0.9)\nplt.show()"
+        "import numpy as np\nfrom mpl_toolkits.mplot3d import Axes3D\n\nfig = plt.figure()\n\nfeatures = (\"AveOccup\", \"HouseAge\")\npdp = partial_dependence(\n    est, X_train, features=features, kind=\"average\", grid_resolution=20\n)\nXX, YY = np.meshgrid(pdp[\"values\"][0], pdp[\"values\"][1])\nZ = pdp.average[0].T\nax = Axes3D(fig)\nfig.add_axes(ax)\nsurf = ax.plot_surface(XX, YY, Z, rstride=1, cstride=1, cmap=plt.cm.BuPu, edgecolor=\"k\")\nax.set_xlabel(features[0])\nax.set_ylabel(features[1])\nax.set_zlabel(\"Partial dependence\")\n# pretty init view\nax.view_init(elev=22, azim=122)\nplt.colorbar(surf)\nplt.suptitle(\n    \"Partial dependence of house value on median\\n\"\n    \"age and average occupancy, with Gradient Boosting\"\n)\nplt.subplots_adjust(top=0.9)\nplt.show()"
       ]
     }
   ],

dev/_downloads/21b82d82985712b5de6347f382c77c86/plot_partial_dependence.ipynb

@@ -53,9 +53,7 @@
 
 y -= y.mean()
 
-X_train, X_test, y_train, y_test = train_test_split(
-    X, y, test_size=0.1, random_state=0
-)
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.1, random_state=0)
 
 # %%
 # 1-way partial dependence with different models
@@ -80,10 +78,12 @@
 
 print("Training MLPRegressor...")
 tic = time()
-est = make_pipeline(QuantileTransformer(),
-                    MLPRegressor(hidden_layer_sizes=(50, 50),
-                                 learning_rate_init=0.01,
-                                 early_stopping=True))
+est = make_pipeline(
+    QuantileTransformer(),
+    MLPRegressor(
+        hidden_layer_sizes=(50, 50), learning_rate_init=0.01, early_stopping=True
+    ),
+)
 est.fit(X_train, y_train)
 print(f"done in {time() - tic:.3f}s")
 print(f"Test R2 score: {est.score(X_test, y_test):.2f}")
@@ -113,17 +113,25 @@
 from sklearn.inspection import partial_dependence
 from sklearn.inspection import plot_partial_dependence
 
-print('Computing partial dependence plots...')
+print("Computing partial dependence plots...")
 tic = time()
-features = ['MedInc', 'AveOccup', 'HouseAge', 'AveRooms']
+features = ["MedInc", "AveOccup", "HouseAge", "AveRooms"]
 display = plot_partial_dependence(
-       est, X_train, features, kind="both", subsample=50,
-       n_jobs=3, grid_resolution=20, random_state=0
+    est,
+    X_train,
+    features,
+    kind="both",
+    subsample=50,
+    n_jobs=3,
+    grid_resolution=20,
+    random_state=0,
+    ice_lines_kw={"color": "tab:blue", "alpha": 0.2, "linewidth": 0.5},
+    pd_line_kw={"color": "tab:orange", "linestyle": "--"},
 )
 print(f"done in {time() - tic:.3f}s")
 display.figure_.suptitle(
-    'Partial dependence of house value on non-___location features\n'
-    'for the California housing dataset, with MLPRegressor'
+    "Partial dependence of house value on non-___location features\n"
+    "for the California housing dataset, with MLPRegressor"
 )
 display.figure_.subplots_adjust(hspace=0.3)
 
@@ -156,16 +164,24 @@
 # We will plot the partial dependence, both individual (ICE) and averaged one
 # (PDP). We limit to only 50 ICE curves to not overcrowd the plot.
 
-print('Computing partial dependence plots...')
+print("Computing partial dependence plots...")
 tic = time()
 display = plot_partial_dependence(
-    est, X_train, features, kind="both", subsample=50,
-    n_jobs=3, grid_resolution=20, random_state=0
+    est,
+    X_train,
+    features,
+    kind="both",
+    subsample=50,
+    n_jobs=3,
+    grid_resolution=20,
+    random_state=0,
+    ice_lines_kw={"color": "tab:blue", "alpha": 0.2, "linewidth": 0.5},
+    pd_line_kw={"color": "tab:orange", "linestyle": "--"},
 )
 print(f"done in {time() - tic:.3f}s")
 display.figure_.suptitle(
-    'Partial dependence of house value on non-___location features\n'
-    'for the California housing dataset, with Gradient Boosting'
+    "Partial dependence of house value on non-___location features\n"
+    "for the California housing dataset, with Gradient Boosting"
 )
 display.figure_.subplots_adjust(wspace=0.4, hspace=0.3)
 
@@ -209,18 +225,23 @@
 # the tree-based algorithm, when only PDPs are requested, they can be computed
 # on an efficient way using the `'recursion'` method.
 
-features = ['AveOccup', 'HouseAge', ('AveOccup', 'HouseAge')]
-print('Computing partial dependence plots...')
+features = ["AveOccup", "HouseAge", ("AveOccup", "HouseAge")]
+print("Computing partial dependence plots...")
 tic = time()
 _, ax = plt.subplots(ncols=3, figsize=(9, 4))
 display = plot_partial_dependence(
-    est, X_train, features, kind='average', n_jobs=3, grid_resolution=20,
+    est,
+    X_train,
+    features,
+    kind="average",
+    n_jobs=3,
+    grid_resolution=20,
     ax=ax,
 )
 print(f"done in {time() - tic:.3f}s")
 display.figure_.suptitle(
-    'Partial dependence of house value on non-___location features\n'
-    'for the California housing dataset, with Gradient Boosting'
+    "Partial dependence of house value on non-___location features\n"
+    "for the California housing dataset, with Gradient Boosting"
 )
 display.figure_.subplots_adjust(wspace=0.4, hspace=0.3)
 
@@ -240,24 +261,27 @@
 
 import numpy as np
 from mpl_toolkits.mplot3d import Axes3D
+
 fig = plt.figure()
 
-features = ('AveOccup', 'HouseAge')
+features = ("AveOccup", "HouseAge")
 pdp = partial_dependence(
-    est, X_train, features=features, kind='average', grid_resolution=20
+    est, X_train, features=features, kind="average", grid_resolution=20
 )
 XX, YY = np.meshgrid(pdp["values"][0], pdp["values"][1])
 Z = pdp.average[0].T
 ax = Axes3D(fig)
-surf = ax.plot_surface(XX, YY, Z, rstride=1, cstride=1,
-                       cmap=plt.cm.BuPu, edgecolor='k')
+fig.add_axes(ax)
+surf = ax.plot_surface(XX, YY, Z, rstride=1, cstride=1, cmap=plt.cm.BuPu, edgecolor="k")
 ax.set_xlabel(features[0])
 ax.set_ylabel(features[1])
-ax.set_zlabel('Partial dependence')
+ax.set_zlabel("Partial dependence")
 # pretty init view
 ax.view_init(elev=22, azim=122)
 plt.colorbar(surf)
-plt.suptitle('Partial dependence of house value on median\n'
-             'age and average occupancy, with Gradient Boosting')
+plt.suptitle(
+    "Partial dependence of house value on median\n"
+    "age and average occupancy, with Gradient Boosting"
+)
 plt.subplots_adjust(top=0.9)
 plt.show()