Pushing the docs to dev/ for branch: main, commit adb47e7c142ce6d699cc5927925d448cb2c1ab91

Author: sklearn-ci

dev/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip

@@ -69,7 +69,7 @@
       },
       "outputs": [],
       "source": [
-        "from sklearn.inspection import PartialDependenceDisplay\n\ncommon_params = {\"subsample\": 50, \"n_jobs\": 2, \"grid_resolution\": 20, \"random_state\": 0}\n\nprint(\"Computing partial dependence plots...\")\ntic = time()\ndisplay = PartialDependenceDisplay.from_estimator(\n    est,\n    X_train,\n    features=[\"MedInc\", \"AveOccup\", \"HouseAge\", \"AveRooms\"],\n    kind=\"both\",\n    **common_params,\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)"
+        "from sklearn.inspection import PartialDependenceDisplay\n\ncommon_params = {\n    \"subsample\": 50,\n    \"n_jobs\": 2,\n    \"grid_resolution\": 20,\n    \"centered\": True,\n    \"random_state\": 0,\n}\n\nprint(\"Computing partial dependence plots...\")\ntic = time()\ndisplay = PartialDependenceDisplay.from_estimator(\n    est,\n    X_train,\n    features=[\"MedInc\", \"AveOccup\", \"HouseAge\", \"AveRooms\"],\n    kind=\"both\",\n    **common_params,\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)"
       ]
     },
     {
@@ -112,7 +112,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "### Analysis of the plots\n\nWe can clearly see on the PDPs (dashed orange line) that the median house price\nshows a linear relationship with the median income (top left) and that the\nhouse price drops when the average occupants per household increases (top\nmiddle). The top right plot shows that the house age in a district does not\nhave a strong influence on the (median) house price; so does the average\nrooms per household.\n\nThe ICE curves (light blue lines) complement the analysis: we can see that\nthere are some exceptions, where the house price remain constant with median\nincome and average occupants. On the other hand, while the house age (top\nright) does not have a strong influence on the median house price on average,\nthere seems to be a number of exceptions where the house price increase when\nbetween the ages 15-25. Similar exceptions can be observed for the average\nnumber of rooms (bottom left). Therefore, ICE plots show some individual\neffect which are attenuated by taking the averages.\n\nIn all plots, the tick marks on the x-axis represent the deciles of the\nfeature values in the training data.\n\nWe also observe that :class:`~sklearn.neural_network.MLPRegressor` has much\nsmoother predictions than\n:class:`~sklearn.ensemble.HistGradientBoostingRegressor`.\n\nHowever, it is worth noting that we are creating potential meaningless\nsynthetic samples if features are correlated.\n\n"
+        "### Analysis of the plots\n\nWe can clearly see on the PDPs (dashed orange line) that the median house price\nshows a linear relationship with the median income (top left) and that the\nhouse price drops when the average occupants per household increases (top\nmiddle). The top right plot shows that the house age in a district does not\nhave a strong influence on the (median) house price; so does the average\nrooms per household.\n\nThe ICE curves (light blue lines) complement the analysis: we can see that\nthere are some exceptions (which are better highlighted with the option\n`centered=True`), where the house price remains constant with respect to\nmedian income and average occupants variations.\nOn the other hand, while the house age (top right) does not have a strong\ninfluence on the median house price on average, there seems to be a number\nof exceptions where the house price increases when\nbetween the ages 15-25. Similar exceptions can be observed for the average\nnumber of rooms (bottom left). Therefore, ICE plots show some individual\neffect which are attenuated by taking the averages.\n\nIn all plots, the tick marks on the x-axis represent the deciles of the\nfeature values in the training data.\n\nWe also observe that :class:`~sklearn.neural_network.MLPRegressor` has much\nsmoother predictions than\n:class:`~sklearn.ensemble.HistGradientBoostingRegressor`.\n\nHowever, it is worth noting that we are creating potential meaningless\nsynthetic samples if features are correlated.\n\n"
       ]
     },
     {

dev/_downloads/21b82d82985712b5de6347f382c77c86/plot_partial_dependence.ipynb

@@ -113,7 +113,13 @@
 
 from sklearn.inspection import PartialDependenceDisplay
 
-common_params = {"subsample": 50, "n_jobs": 2, "grid_resolution": 20, "random_state": 0}
+common_params = {
+    "subsample": 50,
+    "n_jobs": 2,
+    "grid_resolution": 20,
+    "centered": True,
+    "random_state": 0,
+}
 
 print("Computing partial dependence plots...")
 tic = time()
@@ -188,10 +194,12 @@
 # rooms per household.
 #
 # The ICE curves (light blue lines) complement the analysis: we can see that
-# there are some exceptions, where the house price remain constant with median
-# income and average occupants. On the other hand, while the house age (top
-# right) does not have a strong influence on the median house price on average,
-# there seems to be a number of exceptions where the house price increase when
+# there are some exceptions (which are better highlighted with the option
+# `centered=True`), where the house price remains constant with respect to
+# median income and average occupants variations.
+# On the other hand, while the house age (top right) does not have a strong
+# influence on the median house price on average, there seems to be a number
+# of exceptions where the house price increases when
 # between the ages 15-25. Similar exceptions can be observed for the average
 # number of rooms (bottom left). Therefore, ICE plots show some individual
 # effect which are attenuated by taking the averages.