Pushing the docs to 1.1/ for branch: 1.1.X, commit 6cb2c52375a812ff509c00f4eed1da232e7a8932

Author: sklearn-ci

1.1/.buildinfo

@@ -1,4 +1,4 @@
 # Sphinx build info version 1
 # This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done.
-config: 0eaf86448214f705bb4019609544b7b3
+config: 8c6ff21e847d280e934fd16d253894de
 tags: 645f666f9bcd5a90fca523b33c5a78b7

1.1/_downloads/02a1306a494b46cc56c930ceec6e8c4a/plot_species_kde.py

@@ -19,7 +19,7 @@
 The two species are:
 
  - `"Bradypus variegatus"
-   <http://www.iucnredlist.org/apps/redlist/details/3038/0>`_ ,
+   <https://www.iucnredlist.org/species/3038/47437046>`_ ,
    the Brown-throated Sloth.
 
  - `"Microryzomys minutus"

1.1/_downloads/06cfc926acb27652fb2aa5bfc583e7cb/plot_hashing_vs_dict_vectorizer.ipynb

@@ -29,7 +29,7 @@
 
 # fit the model
 plt.figure(figsize=(10, 5))
-kernels = [1.0 * RBF(length_scale=1.0), 1.0 * DotProduct(sigma_0=1.0) ** 2]
+kernels = [1.0 * RBF(length_scale=1.15), 1.0 * DotProduct(sigma_0=1.0) ** 2]
 for i, kernel in enumerate(kernels):
     clf = GaussianProcessClassifier(kernel=kernel, warm_start=True).fit(X, Y)
 

1.1/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip

@@ -71,20 +71,23 @@ def generate_data(n_samples, n_features):
     linewidth=2,
     label="Linear Discriminant Analysis with Ledoit Wolf",
     color="navy",
+    linestyle="dashed",
 )
 plt.plot(
     features_samples_ratio,
     acc_clf2,
     linewidth=2,
     label="Linear Discriminant Analysis",
     color="gold",
+    linestyle="solid",
 )
 plt.plot(
     features_samples_ratio,
     acc_clf3,
     linewidth=2,
     label="Linear Discriminant Analysis with OAS",
     color="red",
+    linestyle="dotted",
 )
 
 plt.xlabel("n_features / n_samples")

1.1/_downloads/08fc4f471ae40388eb535678346dc9d1/plot_gpc_xor.py

@@ -158,7 +158,7 @@ def plot_gpr_samples(gpr_model, n_samples, ax):
 )
 
 # %%
-# Periodic kernel
+# Exp-Sine-Squared kernel
 # ...............
 from sklearn.gaussian_process.kernels import ExpSineSquared
 
@@ -183,7 +183,7 @@ def plot_gpr_samples(gpr_model, n_samples, ax):
 axs[1].legend(bbox_to_anchor=(1.05, 1.5), loc="upper left")
 axs[1].set_title("Samples from posterior distribution")
 
-fig.suptitle("Periodic kernel", fontsize=18)
+fig.suptitle("Exp-Sine-Squared kernel", fontsize=18)
 plt.tight_layout()
 
 # %%
@@ -194,7 +194,7 @@ def plot_gpr_samples(gpr_model, n_samples, ax):
 )
 
 # %%
-# Dot product kernel
+# Dot-product kernel
 # ..................
 from sklearn.gaussian_process.kernels import ConstantKernel, DotProduct
 
@@ -216,7 +216,7 @@ def plot_gpr_samples(gpr_model, n_samples, ax):
 axs[1].legend(bbox_to_anchor=(1.05, 1.5), loc="upper left")
 axs[1].set_title("Samples from posterior distribution")
 
-fig.suptitle("Dot product kernel", fontsize=18)
+fig.suptitle("Dot-product kernel", fontsize=18)
 plt.tight_layout()
 
 # %%
@@ -227,7 +227,7 @@ def plot_gpr_samples(gpr_model, n_samples, ax):
 )
 
 # %%
-# Mattern kernel
+# Matérn kernel
 # ..............
 from sklearn.gaussian_process.kernels import Matern
 
@@ -247,7 +247,7 @@ def plot_gpr_samples(gpr_model, n_samples, ax):
 axs[1].legend(bbox_to_anchor=(1.05, 1.5), loc="upper left")
 axs[1].set_title("Samples from posterior distribution")
 
-fig.suptitle("Mattern kernel", fontsize=18)
+fig.suptitle("Matérn kernel", fontsize=18)
 plt.tight_layout()
 
 # %%

1.1/_downloads/14f620cd922ca2c9a39ae5784034dd0d/plot_lda.py

@@ -15,7 +15,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "\n# Kernel Density Estimate of Species Distributions\nThis shows an example of a neighbors-based query (in particular a kernel\ndensity estimate) on geospatial data, using a Ball Tree built upon the\nHaversine distance metric -- i.e. distances over points in latitude/longitude.\nThe dataset is provided by Phillips et. al. (2006).\nIf available, the example uses\n`basemap <https://matplotlib.org/basemap/>`_\nto plot the coast lines and national boundaries of South America.\n\nThis example does not perform any learning over the data\n(see `sphx_glr_auto_examples_applications_plot_species_distribution_modeling.py` for\nan example of classification based on the attributes in this dataset).  It\nsimply shows the kernel density estimate of observed data points in\ngeospatial coordinates.\n\nThe two species are:\n\n - `\"Bradypus variegatus\"\n   <http://www.iucnredlist.org/apps/redlist/details/3038/0>`_ ,\n   the Brown-throated Sloth.\n\n - `\"Microryzomys minutus\"\n   <http://www.iucnredlist.org/details/13408/0>`_ ,\n   also known as the Forest Small Rice Rat, a rodent that lives in Peru,\n   Colombia, Ecuador, Peru, and Venezuela.\n\n## References\n\n * `\"Maximum entropy modeling of species geographic distributions\"\n   <http://rob.schapire.net/papers/ecolmod.pdf>`_\n   S. J. Phillips, R. P. Anderson, R. E. Schapire - Ecological Modelling,\n   190:231-259, 2006.\n"
+        "\n# Kernel Density Estimate of Species Distributions\nThis shows an example of a neighbors-based query (in particular a kernel\ndensity estimate) on geospatial data, using a Ball Tree built upon the\nHaversine distance metric -- i.e. distances over points in latitude/longitude.\nThe dataset is provided by Phillips et. al. (2006).\nIf available, the example uses\n`basemap <https://matplotlib.org/basemap/>`_\nto plot the coast lines and national boundaries of South America.\n\nThis example does not perform any learning over the data\n(see `sphx_glr_auto_examples_applications_plot_species_distribution_modeling.py` for\nan example of classification based on the attributes in this dataset).  It\nsimply shows the kernel density estimate of observed data points in\ngeospatial coordinates.\n\nThe two species are:\n\n - `\"Bradypus variegatus\"\n   <https://www.iucnredlist.org/species/3038/47437046>`_ ,\n   the Brown-throated Sloth.\n\n - `\"Microryzomys minutus\"\n   <http://www.iucnredlist.org/details/13408/0>`_ ,\n   also known as the Forest Small Rice Rat, a rodent that lives in Peru,\n   Colombia, Ecuador, Peru, and Venezuela.\n\n## References\n\n * `\"Maximum entropy modeling of species geographic distributions\"\n   <http://rob.schapire.net/papers/ecolmod.pdf>`_\n   S. J. Phillips, R. P. Anderson, R. E. Schapire - Ecological Modelling,\n   190:231-259, 2006.\n"
       ]
     },
     {

1.1/_downloads/1bcb2039afa126da41f1cea42b4a5866/plot_gpr_prior_posterior.py

@@ -324,7 +324,7 @@ def make_plot(item_idx):
 #
 # Unlike the previous scalers, the centering and scaling statistics of
 # :class:`~sklearn.preprocessing.RobustScaler`
-# is based on percentiles and are therefore not influenced by a few
+# are based on percentiles and are therefore not influenced by a small
 # number of very large marginal outliers. Consequently, the resulting range of
 # the transformed feature values is larger than for the previous scalers and,
 # more importantly, are approximately similar: for both features most of the

1.1/_downloads/1c4a422dfa5bd721501d19a2b7e2499b/plot_species_kde.ipynb

@@ -72,6 +72,11 @@ def f(x):
     all_models["q %1.2f" % alpha] = gbr.fit(X_train, y_train)
 
 # %%
+# Notice that :class:`~sklearn.ensemble.HistGradientBoostingRegressor` is much
+# faster than :class:`~sklearn.ensemble.GradientBoostingRegressor` starting with
+# intermediate datasets (`n_samples >= 10_000`), which is not the case of the
+# present example.
+#
 # For the sake of comparison, we also fit a baseline model trained with the
 # usual (mean) squared error (MSE).
 gbr_ls = GradientBoostingRegressor(loss="squared_error", **common_params)