Pushing the docs to dev/ for branch: main, commit c3bfe86b45577a9405a4680d9971efa9594a0657

Author: sklearn-ci

dev/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip

@@ -202,7 +202,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## 1-way partial dependence with different models\n\nIn this section, we will compute 1-way partial dependence with two different\nmachine-learning models: (i) a multi-layer perceptron and (ii) a\ngradient-boosting model. With these two models, we illustrate how to compute and\ninterpret both partial dependence plot (PDP) for both numerical and categorical\nfeatures and individual conditional expectation (ICE).\n\n#### Multi-layer perceptron\n\nLet's fit a :class:`~sklearn.neural_network.MLPRegressor` and compute\nsingle-variable partial dependence plots.\n\n"
+        "## 1-way partial dependence with different models\n\nIn this section, we will compute 1-way partial dependence with two different\nmachine-learning models: (i) a multi-layer perceptron and (ii) a\ngradient-boosting model. With these two models, we illustrate how to compute and\ninterpret both partial dependence plot (PDP) for both numerical and categorical\nfeatures and individual conditional expectation (ICE).\n\n### Multi-layer perceptron\n\nLet's fit a :class:`~sklearn.neural_network.MLPRegressor` and compute\nsingle-variable partial dependence plots.\n\n"
       ]
     },
     {
@@ -238,7 +238,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "#### Gradient boosting\n\nLet's now fit a :class:`~sklearn.ensemble.HistGradientBoostingRegressor` and\ncompute the partial dependence on the same features. We also use the\nspecific preprocessor we created for this model.\n\n"
+        "### Gradient boosting\n\nLet's now fit a :class:`~sklearn.ensemble.HistGradientBoostingRegressor` and\ncompute the partial dependence on the same features. We also use the\nspecific preprocessor we created for this model.\n\n"
       ]
     },
     {
@@ -274,7 +274,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "#### Analysis of the plots\n\nWe will first look at the PDPs for the numerical features. For both models, the\ngeneral trend of the PDP of the temperature is that the number of bike rentals is\nincreasing with temperature. We can make a similar analysis but with the opposite\ntrend for the humidity features. The number of bike rentals is decreasing when the\nhumidity increases. Finally, we see the same trend for the wind speed feature. The\nnumber of bike rentals is decreasing when the wind speed is increasing for both\nmodels. We also observe that :class:`~sklearn.neural_network.MLPRegressor` has much\nsmoother predictions than :class:`~sklearn.ensemble.HistGradientBoostingRegressor`.\n\nNow, we will look at the partial dependence plots for the categorical features.\n\nWe observe that the spring season is the lowest bar for the season feature. With the\nweather feature, the rain category is the lowest bar. Regarding the hour feature,\nwe see two peaks around the 7 am and 6 pm. These findings are in line with the\nthe observations we made earlier on the dataset.\n\nHowever, it is worth noting that we are creating potential meaningless\nsynthetic samples if features are correlated.\n\n#### ICE vs. PDP\nPDP is an average of the marginal effects of the features. We are averaging the\nresponse of all samples of the provided set. Thus, some effects could be hidden. In\nthis regard, it is possible to plot each individual response. This representation is\ncalled the Individual Effect Plot (ICE). In the plot below, we plot 50 randomly\nselected ICEs for the temperature and humidity features.\n\n"
+        "### Analysis of the plots\n\nWe will first look at the PDPs for the numerical features. For both models, the\ngeneral trend of the PDP of the temperature is that the number of bike rentals is\nincreasing with temperature. We can make a similar analysis but with the opposite\ntrend for the humidity features. The number of bike rentals is decreasing when the\nhumidity increases. Finally, we see the same trend for the wind speed feature. The\nnumber of bike rentals is decreasing when the wind speed is increasing for both\nmodels. We also observe that :class:`~sklearn.neural_network.MLPRegressor` has much\nsmoother predictions than :class:`~sklearn.ensemble.HistGradientBoostingRegressor`.\n\nNow, we will look at the partial dependence plots for the categorical features.\n\nWe observe that the spring season is the lowest bar for the season feature. With the\nweather feature, the rain category is the lowest bar. Regarding the hour feature,\nwe see two peaks around the 7 am and 6 pm. These findings are in line with the\nthe observations we made earlier on the dataset.\n\nHowever, it is worth noting that we are creating potential meaningless\nsynthetic samples if features are correlated.\n\n### ICE vs. PDP\nPDP is an average of the marginal effects of the features. We are averaging the\nresponse of all samples of the provided set. Thus, some effects could be hidden. In\nthis regard, it is possible to plot each individual response. This representation is\ncalled the Individual Effect Plot (ICE). In the plot below, we plot 50 randomly\nselected ICEs for the temperature and humidity features.\n\n"
       ]
     },
     {
@@ -375,7 +375,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "#### 3D representation\n\nLet's make the same partial dependence plot for the 2 features interaction,\nthis time in 3 dimensions.\n\n"
+        "### 3D representation\n\nLet's make the same partial dependence plot for the 2 features interaction,\nthis time in 3 dimensions.\n\n"
       ]
     },
     {

dev/_downloads/21b82d82985712b5de6347f382c77c86/plot_partial_dependence.ipynb

@@ -198,7 +198,7 @@
 # features and individual conditional expectation (ICE).
 #
 # Multi-layer perceptron
-# """"""""""""""""""""""
+# ~~~~~~~~~~~~~~~~~~~~~~
 #
 # Let's fit a :class:`~sklearn.neural_network.MLPRegressor` and compute
 # single-variable partial dependence plots.
@@ -278,7 +278,7 @@
 
 # %%
 # Gradient boosting
-# """""""""""""""""
+# ~~~~~~~~~~~~~~~~~
 #
 # Let's now fit a :class:`~sklearn.ensemble.HistGradientBoostingRegressor` and
 # compute the partial dependence on the same features. We also use the
@@ -330,7 +330,7 @@
 
 # %%
 # Analysis of the plots
-# """""""""""""""""""""
+# ~~~~~~~~~~~~~~~~~~~~~
 #
 # We will first look at the PDPs for the numerical features. For both models, the
 # general trend of the PDP of the temperature is that the number of bike rentals is
@@ -352,7 +352,7 @@
 # synthetic samples if features are correlated.
 #
 # ICE vs. PDP
-# """""""""""
+# ~~~~~~~~~~~
 # PDP is an average of the marginal effects of the features. We are averaging the
 # response of all samples of the provided set. Thus, some effects could be hidden. In
 # this regard, it is possible to plot each individual response. This representation is
@@ -521,7 +521,7 @@
 
 # %%
 # 3D representation
-# """""""""""""""""
+# ~~~~~~~~~~~~~~~~~
 #
 # Let's make the same partial dependence plot for the 2 features interaction,
 # this time in 3 dimensions.