Pushing the docs to dev/ for branch: main, commit f6d6929f32e3eb7206719c4abde8addddd8a8f08

Author: sklearn-ci

dev/_downloads/02a1306a494b46cc56c930ceec6e8c4a/plot_species_kde.py

@@ -18,22 +18,22 @@
 
 The two species are:
 
- - `"Bradypus variegatus"
-   <https://www.iucnredlist.org/species/3038/47437046>`_ ,
-   the Brown-throated Sloth.
+- `"Bradypus variegatus"
+  <https://www.iucnredlist.org/species/3038/47437046>`_ ,
+  the Brown-throated Sloth.
 
- - `"Microryzomys minutus"
-   <http://www.iucnredlist.org/details/13408/0>`_ ,
-   also known as the Forest Small Rice Rat, a rodent that lives in Peru,
-   Colombia, Ecuador, Peru, and Venezuela.
+- `"Microryzomys minutus"
+  <http://www.iucnredlist.org/details/13408/0>`_ ,
+  also known as the Forest Small Rice Rat, a rodent that lives in Peru,
+  Colombia, Ecuador, Peru, and Venezuela.
 
 References
 ----------
 
- * `"Maximum entropy modeling of species geographic distributions"
-   <http://rob.schapire.net/papers/ecolmod.pdf>`_
-   S. J. Phillips, R. P. Anderson, R. E. Schapire - Ecological Modelling,
-   190:231-259, 2006.
+- `"Maximum entropy modeling of species geographic distributions"
+  <http://rob.schapire.net/papers/ecolmod.pdf>`_
+  S. J. Phillips, R. P. Anderson, R. E. Schapire - Ecological Modelling,
+  190:231-259, 2006.
 """  # noqa: E501
 
 # Authors: The scikit-learn developers

dev/_downloads/02fe21a1f5d14bd1ebbe34aa905d9bf6/plot_multilabel.zip

@@ -4,7 +4,7 @@
       "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\"](https://www.iucnredlist.org/species/3038/47437046) ,\n   the Brown-throated Sloth.\n\n - [\"Microryzomys minutus\"](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\"](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\"](https://www.iucnredlist.org/species/3038/47437046) ,\n  the Brown-throated Sloth.\n\n- [\"Microryzomys minutus\"](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\"](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"
       ]
     },
     {

dev/_downloads/0358b1921962fd7c6f5a94c5abc91476/plot_hashing_vs_dict_vectorizer.zip

@@ -4,7 +4,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "\n# Scaling the regularization parameter for SVCs\n\nThe following example illustrates the effect of scaling the regularization\nparameter when using `svm` for `classification <svm_classification>`.\nFor SVC classification, we are interested in a risk minimization for the\nequation:\n\n\n\\begin{align}C \\sum_{i=1, n} \\mathcal{L} (f(x_i), y_i) + \\Omega (w)\\end{align}\n\nwhere\n\n    - $C$ is used to set the amount of regularization\n    - $\\mathcal{L}$ is a `loss` function of our samples\n      and our model parameters.\n    - $\\Omega$ is a `penalty` function of our model parameters\n\nIf we consider the loss function to be the individual error per sample, then the\ndata-fit term, or the sum of the error for each sample, increases as we add more\nsamples. The penalization term, however, does not increase.\n\nWhen using, for example, `cross validation <cross_validation>`, to set the\namount of regularization with `C`, there would be a different amount of samples\nbetween the main problem and the smaller problems within the folds of the cross\nvalidation.\n\nSince the loss function dependens on the amount of samples, the latter\ninfluences the selected value of `C`. The question that arises is \"How do we\noptimally adjust C to account for the different amount of training samples?\"\n"
+        "\n# Scaling the regularization parameter for SVCs\n\nThe following example illustrates the effect of scaling the regularization\nparameter when using `svm` for `classification <svm_classification>`.\nFor SVC classification, we are interested in a risk minimization for the\nequation:\n\n\n\\begin{align}C \\sum_{i=1, n} \\mathcal{L} (f(x_i), y_i) + \\Omega (w)\\end{align}\n\nwhere\n\n- $C$ is used to set the amount of regularization\n- $\\mathcal{L}$ is a `loss` function of our samples and our model parameters.\n- $\\Omega$ is a `penalty` function of our model parameters\n\nIf we consider the loss function to be the individual error per sample, then the\ndata-fit term, or the sum of the error for each sample, increases as we add more\nsamples. The penalization term, however, does not increase.\n\nWhen using, for example, `cross validation <cross_validation>`, to set the\namount of regularization with `C`, there would be a different amount of samples\nbetween the main problem and the smaller problems within the folds of the cross\nvalidation.\n\nSince the loss function dependens on the amount of samples, the latter\ninfluences the selected value of `C`. The question that arises is \"How do we\noptimally adjust C to account for the different amount of training samples?\"\n"
       ]
     },
     {

dev/_downloads/038d1885eb5f5ea53aca42da3031fe38/plot_document_clustering.zip

@@ -59,20 +59,17 @@
 #
 # Among these arrays, we have:
 #
-#   - ``children_left[i]``: id of the left child of node ``i`` or -1 if leaf
-#     node
-#   - ``children_right[i]``: id of the right child of node ``i`` or -1 if leaf
-#     node
-#   - ``feature[i]``: feature used for splitting node ``i``
-#   - ``threshold[i]``: threshold value at node ``i``
-#   - ``n_node_samples[i]``: the number of training samples reaching node
-#     ``i``
-#   - ``impurity[i]``: the impurity at node ``i``
-#   - ``weighted_n_node_samples[i]``: the weighted number of training samples
-#     reaching node ``i``
-#   - ``value[i, j, k]``: the summary of the training samples that reached node i for
-#     output j and class k (for regression tree, class is set to 1). See below
-#     for more information about ``value``.
+# - ``children_left[i]``: id of the left child of node ``i`` or -1 if leaf node
+# - ``children_right[i]``: id of the right child of node ``i`` or -1 if leaf node
+# - ``feature[i]``: feature used for splitting node ``i``
+# - ``threshold[i]``: threshold value at node ``i``
+# - ``n_node_samples[i]``: the number of training samples reaching node ``i``
+# - ``impurity[i]``: the impurity at node ``i``
+# - ``weighted_n_node_samples[i]``: the weighted number of training samples
+#   reaching node ``i``
+# - ``value[i, j, k]``: the summary of the training samples that reached node i for
+#   output j and class k (for regression tree, class is set to 1). See below
+#   for more information about ``value``.
 #
 # Using the arrays, we can traverse the tree structure to compute various
 # properties. Below, we will compute the depth of each node and whether or not

dev/_downloads/03c018a16384c69f3a89e473650d57ee/plot_svm_margin.zip

@@ -4,7 +4,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "\n# Faces recognition example using eigenfaces and SVMs\n\nThe dataset used in this example is a preprocessed excerpt of the\n\"Labeled Faces in the Wild\", aka LFW_:\n\n  http://vis-www.cs.umass.edu/lfw/lfw-funneled.tgz (233MB)\n\n"
+        "\n# Faces recognition example using eigenfaces and SVMs\n\nThe dataset used in this example is a preprocessed excerpt of the\n\"Labeled Faces in the Wild\", aka LFW_:\nhttp://vis-www.cs.umass.edu/lfw/lfw-funneled.tgz (233MB)\n\n"
       ]
     },
     {

dev/_downloads/041e98b4797bb4ddc34c0045e5886c3e/plot_digits_classification_exercise.zip

@@ -22,7 +22,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Download the dataset\n\n We will use the `Ames Housing`_ dataset which was first compiled by Dean De Cock\n and became better known after it was used in Kaggle challenge. It is a set\n of 1460 residential homes in Ames, Iowa, each described by 80 features. We\n will use it to predict the final logarithmic price of the houses. In this\n example we will use only 20 most interesting features chosen using\n GradientBoostingRegressor() and limit number of entries (here we won't go\n into the details on how to select the most interesting features).\n\n The Ames housing dataset is not shipped with scikit-learn and therefore we\n will fetch it from `OpenML`_.\n\n\n"
+        "## Download the dataset\n\nWe will use the `Ames Housing`_ dataset which was first compiled by Dean De Cock\nand became better known after it was used in Kaggle challenge. It is a set\nof 1460 residential homes in Ames, Iowa, each described by 80 features. We\nwill use it to predict the final logarithmic price of the houses. In this\nexample we will use only 20 most interesting features chosen using\nGradientBoostingRegressor() and limit number of entries (here we won't go\ninto the details on how to select the most interesting features).\n\nThe Ames housing dataset is not shipped with scikit-learn and therefore we\nwill fetch it from `OpenML`_.\n\n\n"
       ]
     },
     {
@@ -40,7 +40,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Make pipeline to preprocess the data\n\n Before we can use Ames dataset we still need to do some preprocessing.\n First, we will select the categorical and numerical columns of the dataset to\n construct the first step of the pipeline.\n\n"
+        "## Make pipeline to preprocess the data\n\nBefore we can use Ames dataset we still need to do some preprocessing.\nFirst, we will select the categorical and numerical columns of the dataset to\nconstruct the first step of the pipeline.\n\n"
       ]
     },
     {
@@ -105,7 +105,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Stack of predictors on a single data set\n\n It is sometimes tedious to find the model which will best perform on a given\n dataset. Stacking provide an alternative by combining the outputs of several\n learners, without the need to choose a model specifically. The performance of\n stacking is usually close to the best model and sometimes it can outperform\n the prediction performance of each individual model.\n\n Here, we combine 3 learners (linear and non-linear) and use a ridge regressor\n to combine their outputs together.\n\n .. note::\n    Although we will make new pipelines with the processors which we wrote in\n    the previous section for the 3 learners, the final estimator\n    :class:`~sklearn.linear_model.RidgeCV()` does not need preprocessing of\n    the data as it will be fed with the already preprocessed output from the 3\n    learners.\n\n"
+        "## Stack of predictors on a single data set\n\nIt is sometimes tedious to find the model which will best perform on a given\ndataset. Stacking provide an alternative by combining the outputs of several\nlearners, without the need to choose a model specifically. The performance of\nstacking is usually close to the best model and sometimes it can outperform\nthe prediction performance of each individual model.\n\nHere, we combine 3 learners (linear and non-linear) and use a ridge regressor\nto combine their outputs together.\n\n<div class=\"alert alert-info\"><h4>Note</h4><p>Although we will make new pipelines with the processors which we wrote in\n   the previous section for the 3 learners, the final estimator\n   :class:`~sklearn.linear_model.RidgeCV()` does not need preprocessing of\n   the data as it will be fed with the already preprocessed output from the 3\n   learners.</p></div>\n\n"
       ]
     },
     {
@@ -156,7 +156,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Measure and plot the results\n\n Now we can use Ames Housing dataset to make the predictions. We check the\n performance of each individual predictor as well as of the stack of the\n regressors.\n\n"
+        "## Measure and plot the results\n\nNow we can use Ames Housing dataset to make the predictions. We check the\nperformance of each individual predictor as well as of the stack of the\nregressors.\n\n"
       ]
     },
     {

dev/_downloads/04b9a7769df5b331f4d94e1d065b4311/plot_voting_decision_regions.zip

@@ -7,9 +7,9 @@
 signal obtained from sparse and correlated features that are further corrupted
 with additive gaussian noise:
 
- - a :ref:`lasso`;
- - an :ref:`automatic_relevance_determination`;
- - an :ref:`elastic_net`.
+- a :ref:`lasso`;
+- an :ref:`automatic_relevance_determination`;
+- an :ref:`elastic_net`.
 
 It is known that the Lasso estimates turn to be close to the model selection
 estimates when the data dimensions grow, given that the irrelevant variables are
@@ -244,6 +244,6 @@
 # References
 # ----------
 #
-#   .. [1] :doi:`"Lasso-type recovery of sparse representations for
+# .. [1] :doi:`"Lasso-type recovery of sparse representations for
 #    high-dimensional data" N. Meinshausen, B. Yu - The Annals of Statistics
 #    2009, Vol. 37, No. 1, 246-270 <10.1214/07-AOS582>`

dev/_downloads/053b58bbfc8177072856c743b2c93424/plot_varimax_fa.zip

@@ -6,10 +6,7 @@
 A classical way to assert the relative importance of vertices in a
 graph is to compute the principal eigenvector of the adjacency matrix
 so as to assign to each vertex the values of the components of the first
-eigenvector as a centrality score:
-
-    https://en.wikipedia.org/wiki/Eigenvector_centrality
-
+eigenvector as a centrality score: https://en.wikipedia.org/wiki/Eigenvector_centrality.
 On the graph of webpages and links those values are called the PageRank
 scores by Google.
 
@@ -18,10 +15,7 @@
 this eigenvector centrality.
 
 The traditional way to compute the principal eigenvector is to use the
-power iteration method:
-
-    https://en.wikipedia.org/wiki/Power_iteration
-
+`power iteration method <https://en.wikipedia.org/wiki/Power_iteration>`_.
 Here the computation is achieved thanks to Martinsson's Randomized SVD
 algorithm implemented in scikit-learn.
 

dev/_downloads/0639a004b8e8cf5b7fbcc4942c47e8ba/plot_validation_curve.zip

@@ -32,11 +32,6 @@
 We will use data from the `"Current Population Survey"
 <https://www.openml.org/d/534>`_ from 1985 to predict wage as a function of
 various features such as experience, age, or education.
-
-.. contents::
-   :local:
-   :depth: 1
-
 """
 
 # Authors: The scikit-learn developers
@@ -98,7 +93,7 @@
 # at the pairwise relationships between them. Only numerical
 # variables will be used. In the following plot, each dot represents a sample.
 #
-#   .. _marginal_dependencies:
+# .. _marginal_dependencies:
 
 train_dataset = X_train.copy()
 train_dataset.insert(0, "WAGE", y_train)

dev/_downloads/06754f94d3767e38162c19499b317556/plot_digits_last_image.zip

@@ -9,17 +9,17 @@
 
 Points are labeled as follows, where Y means the class is present:
 
-    =====  =====  =====  ======
-      1      2      3    Color
-    =====  =====  =====  ======
-      Y      N      N    Red
-      N      Y      N    Blue
-      N      N      Y    Yellow
-      Y      Y      N    Purple
-      Y      N      Y    Orange
-      Y      Y      N    Green
-      Y      Y      Y    Brown
-    =====  =====  =====  ======
+=====  =====  =====  ======
+  1      2      3    Color
+=====  =====  =====  ======
+  Y      N      N    Red
+  N      Y      N    Blue
+  N      N      Y    Yellow
+  Y      Y      N    Purple
+  Y      N      Y    Orange
+  Y      Y      N    Green
+  Y      Y      Y    Brown
+=====  =====  =====  ======
 
 A star marks the expected sample for each class; its size reflects the
 probability of selecting that class label.

dev/_downloads/06c18f4675ecd124f98537d05e10abd0/plot_nca_dim_reduction.zip

@@ -4,7 +4,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "\n# Multilabel classification\n\nThis example simulates a multi-label document classification problem. The\ndataset is generated randomly based on the following process:\n\n    - pick the number of labels: n ~ Poisson(n_labels)\n    - n times, choose a class c: c ~ Multinomial(theta)\n    - pick the document length: k ~ Poisson(length)\n    - k times, choose a word: w ~ Multinomial(theta_c)\n\nIn the above process, rejection sampling is used to make sure that n is more\nthan 2, and that the document length is never zero. Likewise, we reject classes\nwhich have already been chosen.  The documents that are assigned to both\nclasses are plotted surrounded by two colored circles.\n\nThe classification is performed by projecting to the first two principal\ncomponents found by PCA and CCA for visualisation purposes, followed by using\nthe :class:`~sklearn.multiclass.OneVsRestClassifier` metaclassifier using two\nSVCs with linear kernels to learn a discriminative model for each class.\nNote that PCA is used to perform an unsupervised dimensionality reduction,\nwhile CCA is used to perform a supervised one.\n\nNote: in the plot, \"unlabeled samples\" does not mean that we don't know the\nlabels (as in semi-supervised learning) but that the samples simply do *not*\nhave a label.\n"
+        "\n# Multilabel classification\n\nThis example simulates a multi-label document classification problem. The\ndataset is generated randomly based on the following process:\n\n- pick the number of labels: n ~ Poisson(n_labels)\n- n times, choose a class c: c ~ Multinomial(theta)\n- pick the document length: k ~ Poisson(length)\n- k times, choose a word: w ~ Multinomial(theta_c)\n\nIn the above process, rejection sampling is used to make sure that n is more\nthan 2, and that the document length is never zero. Likewise, we reject classes\nwhich have already been chosen.  The documents that are assigned to both\nclasses are plotted surrounded by two colored circles.\n\nThe classification is performed by projecting to the first two principal\ncomponents found by PCA and CCA for visualisation purposes, followed by using\nthe :class:`~sklearn.multiclass.OneVsRestClassifier` metaclassifier using two\nSVCs with linear kernels to learn a discriminative model for each class.\nNote that PCA is used to perform an unsupervised dimensionality reduction,\nwhile CCA is used to perform a supervised one.\n\nNote: in the plot, \"unlabeled samples\" does not mean that we don't know the\nlabels (as in semi-supervised learning) but that the samples simply do *not*\nhave a label.\n"
       ]
     },
     {