Pushing the docs to dev/ for branch: master, commit 465f29f4f6f839ec12c75ea80056041e5a87189c

Author: sklearn-ci

dev/_downloads/2b2bebba7f9fb4d03b9c12d63c8b44ad/plot_topics_extraction_with_nmf_lda.py

@@ -3,8 +3,8 @@
 Topic extraction with Non-negative Matrix Factorization and Latent Dirichlet Allocation
 =======================================================================================
 
-This is an example of applying :class:`sklearn.decomposition.NMF` and
-:class:`sklearn.decomposition.LatentDirichletAllocation` on a corpus
+This is an example of applying :class:`~sklearn.decomposition.NMF` and
+:class:`~sklearn.decomposition.LatentDirichletAllocation` on a corpus
 of documents and extract additive models of the topic structure of the
 corpus.  The output is a list of topics, each represented as a list of
 terms (weights are not shown).

dev/_downloads/3409d9766d352cc9f9b169d4a799a87a/auto_examples_python.zip

@@ -15,7 +15,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "\n======================================================================\nCompressive sensing: tomography reconstruction with L1 prior (Lasso)\n======================================================================\n\nThis example shows the reconstruction of an image from a set of parallel\nprojections, acquired along different angles. Such a dataset is acquired in\n**computed tomography** (CT).\n\nWithout any prior information on the sample, the number of projections\nrequired to reconstruct the image is of the order of the linear size\n``l`` of the image (in pixels). For simplicity we consider here a sparse\nimage, where only pixels on the boundary of objects have a non-zero\nvalue. Such data could correspond for example to a cellular material.\nNote however that most images are sparse in a different basis, such as\nthe Haar wavelets. Only ``l/7`` projections are acquired, therefore it is\nnecessary to use prior information available on the sample (its\nsparsity): this is an example of **compressive sensing**.\n\nThe tomography projection operation is a linear transformation. In\naddition to the data-fidelity term corresponding to a linear regression,\nwe penalize the L1 norm of the image to account for its sparsity. The\nresulting optimization problem is called the `lasso`. We use the\nclass :class:`sklearn.linear_model.Lasso`, that uses the coordinate descent\nalgorithm. Importantly, this implementation is more computationally efficient\non a sparse matrix, than the projection operator used here.\n\nThe reconstruction with L1 penalization gives a result with zero error\n(all pixels are successfully labeled with 0 or 1), even if noise was\nadded to the projections. In comparison, an L2 penalization\n(:class:`sklearn.linear_model.Ridge`) produces a large number of labeling\nerrors for the pixels. Important artifacts are observed on the\nreconstructed image, contrary to the L1 penalization. Note in particular\nthe circular artifact separating the pixels in the corners, that have\ncontributed to fewer projections than the central disk.\n"
+        "\n======================================================================\nCompressive sensing: tomography reconstruction with L1 prior (Lasso)\n======================================================================\n\nThis example shows the reconstruction of an image from a set of parallel\nprojections, acquired along different angles. Such a dataset is acquired in\n**computed tomography** (CT).\n\nWithout any prior information on the sample, the number of projections\nrequired to reconstruct the image is of the order of the linear size\n``l`` of the image (in pixels). For simplicity we consider here a sparse\nimage, where only pixels on the boundary of objects have a non-zero\nvalue. Such data could correspond for example to a cellular material.\nNote however that most images are sparse in a different basis, such as\nthe Haar wavelets. Only ``l/7`` projections are acquired, therefore it is\nnecessary to use prior information available on the sample (its\nsparsity): this is an example of **compressive sensing**.\n\nThe tomography projection operation is a linear transformation. In\naddition to the data-fidelity term corresponding to a linear regression,\nwe penalize the L1 norm of the image to account for its sparsity. The\nresulting optimization problem is called the `lasso`. We use the\nclass :class:`~sklearn.linear_model.Lasso`, that uses the coordinate descent\nalgorithm. Importantly, this implementation is more computationally efficient\non a sparse matrix, than the projection operator used here.\n\nThe reconstruction with L1 penalization gives a result with zero error\n(all pixels are successfully labeled with 0 or 1), even if noise was\nadded to the projections. In comparison, an L2 penalization\n(:class:`~sklearn.linear_model.Ridge`) produces a large number of labeling\nerrors for the pixels. Important artifacts are observed on the\nreconstructed image, contrary to the L1 penalization. Note in particular\nthe circular artifact separating the pixels in the corners, that have\ncontributed to fewer projections than the central disk.\n"
       ]
     },
     {

dev/_downloads/3daf4e9ab9d86061e19a11d997a09779/plot_tomography_l1_reconstruction.ipynb

@@ -9,7 +9,7 @@
 mammals given past observations and 14 environmental
 variables. Since we have only positive examples (there are
 no unsuccessful observations), we cast this problem as a
-density estimation problem and use the :class:`sklearn.svm.OneClassSVM`
+density estimation problem and use the :class:`~sklearn.svm.OneClassSVM`
 as our modeling tool. The dataset is provided by Phillips et. al. (2006).
 If available, the example uses
 `basemap <https://matplotlib.org/basemap/>`_

dev/_downloads/69878e8e2864920aa874c5a68cecf1d3/plot_species_distribution_modeling.py

@@ -15,7 +15,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "\n# Topic extraction with Non-negative Matrix Factorization and Latent Dirichlet Allocation\n\n\nThis is an example of applying :class:`sklearn.decomposition.NMF` and\n:class:`sklearn.decomposition.LatentDirichletAllocation` on a corpus\nof documents and extract additive models of the topic structure of the\ncorpus.  The output is a list of topics, each represented as a list of\nterms (weights are not shown).\n\nNon-negative Matrix Factorization is applied with two different objective\nfunctions: the Frobenius norm, and the generalized Kullback-Leibler divergence.\nThe latter is equivalent to Probabilistic Latent Semantic Indexing.\n\nThe default parameters (n_samples / n_features / n_components) should make\nthe example runnable in a couple of tens of seconds. You can try to\nincrease the dimensions of the problem, but be aware that the time\ncomplexity is polynomial in NMF. In LDA, the time complexity is\nproportional to (n_samples * iterations).\n"
+        "\n# Topic extraction with Non-negative Matrix Factorization and Latent Dirichlet Allocation\n\n\nThis is an example of applying :class:`~sklearn.decomposition.NMF` and\n:class:`~sklearn.decomposition.LatentDirichletAllocation` on a corpus\nof documents and extract additive models of the topic structure of the\ncorpus.  The output is a list of topics, each represented as a list of\nterms (weights are not shown).\n\nNon-negative Matrix Factorization is applied with two different objective\nfunctions: the Frobenius norm, and the generalized Kullback-Leibler divergence.\nThe latter is equivalent to Probabilistic Latent Semantic Indexing.\n\nThe default parameters (n_samples / n_features / n_components) should make\nthe example runnable in a couple of tens of seconds. You can try to\nincrease the dimensions of the problem, but be aware that the time\ncomplexity is polynomial in NMF. In LDA, the time complexity is\nproportional to (n_samples * iterations).\n"
       ]
     },
     {

dev/_downloads/b26574ccf9c31e12ab2afd8d683f3279/plot_topics_extraction_with_nmf_lda.ipynb

@@ -15,7 +15,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "\n# Species distribution modeling\n\n\nModeling species' geographic distributions is an important\nproblem in conservation biology. In this example we\nmodel the geographic distribution of two south american\nmammals given past observations and 14 environmental\nvariables. Since we have only positive examples (there are\nno unsuccessful observations), we cast this problem as a\ndensity estimation problem and use the :class:`sklearn.svm.OneClassSVM`\nas our modeling tool. The 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\nThe two species are:\n\n - `\"Bradypus variegatus\"\n   <http://www.iucnredlist.org/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\nReferences\n----------\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# Species distribution modeling\n\n\nModeling species' geographic distributions is an important\nproblem in conservation biology. In this example we\nmodel the geographic distribution of two south american\nmammals given past observations and 14 environmental\nvariables. Since we have only positive examples (there are\nno unsuccessful observations), we cast this problem as a\ndensity estimation problem and use the :class:`~sklearn.svm.OneClassSVM`\nas our modeling tool. The 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\nThe two species are:\n\n - `\"Bradypus variegatus\"\n   <http://www.iucnredlist.org/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\nReferences\n----------\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"
       ]
     },
     {

dev/_downloads/b5d1ec88ae06ced89813c50d00effe51/plot_species_distribution_modeling.ipynb

@@ -21,14 +21,14 @@
 addition to the data-fidelity term corresponding to a linear regression,
 we penalize the L1 norm of the image to account for its sparsity. The
 resulting optimization problem is called the :ref:`lasso`. We use the
-class :class:`sklearn.linear_model.Lasso`, that uses the coordinate descent
+class :class:`~sklearn.linear_model.Lasso`, that uses the coordinate descent
 algorithm. Importantly, this implementation is more computationally efficient
 on a sparse matrix, than the projection operator used here.
 
 The reconstruction with L1 penalization gives a result with zero error
 (all pixels are successfully labeled with 0 or 1), even if noise was
 added to the projections. In comparison, an L2 penalization
-(:class:`sklearn.linear_model.Ridge`) produces a large number of labeling
+(:class:`~sklearn.linear_model.Ridge`) produces a large number of labeling
 errors for the pixels. Important artifacts are observed on the
 reconstructed image, contrary to the L1 penalization. Note in particular
 the circular artifact separating the pixels in the corners, that have