Pushing the docs to dev/ for branch: master, commit 890e65289877db32c0c440cadaa2b2ef2ef7a384

Author: sklearn-ci

dev/.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: 1399f4416aa025e3557a0b67b941a0dc
+config: 2f3607c03aecd81fb813dba1dd2f3017
 tags: 645f666f9bcd5a90fca523b33c5a78b7

dev/_downloads/auto_examples_jupyter.zip

@@ -15,7 +15,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "\n# Topic extraction with Non-negative Matrix Factorizationand 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_topics) 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\n"
+        "\n# Topic extraction with Non-negative Matrix Factorizationand 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\n"
       ]
     },
     {
@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "# Author: Olivier Grisel <[email protected]>\n#         Lars Buitinck\n#         Chyi-Kwei Yau <[email protected]>\n# License: BSD 3 clause\n\nfrom __future__ import print_function\nfrom time import time\n\nfrom sklearn.feature_extraction.text import TfidfVectorizer, CountVectorizer\nfrom sklearn.decomposition import NMF, LatentDirichletAllocation\nfrom sklearn.datasets import fetch_20newsgroups\n\nn_samples = 2000\nn_features = 1000\nn_topics = 10\nn_top_words = 20\n\n\ndef print_top_words(model, feature_names, n_top_words):\n    for topic_idx, topic in enumerate(model.components_):\n        message = \"Topic #%d: \" % topic_idx\n        message += \" \".join([feature_names[i]\n                             for i in topic.argsort()[:-n_top_words - 1:-1]])\n        print(message)\n    print()\n\n\n# Load the 20 newsgroups dataset and vectorize it. We use a few heuristics\n# to filter out useless terms early on: the posts are stripped of headers,\n# footers and quoted replies, and common English words, words occurring in\n# only one document or in at least 95% of the documents are removed.\n\nprint(\"Loading dataset...\")\nt0 = time()\ndataset = fetch_20newsgroups(shuffle=True, random_state=1,\n                             remove=('headers', 'footers', 'quotes'))\ndata_samples = dataset.data[:n_samples]\nprint(\"done in %0.3fs.\" % (time() - t0))\n\n# Use tf-idf features for NMF.\nprint(\"Extracting tf-idf features for NMF...\")\ntfidf_vectorizer = TfidfVectorizer(max_df=0.95, min_df=2,\n                                   max_features=n_features,\n                                   stop_words='english')\nt0 = time()\ntfidf = tfidf_vectorizer.fit_transform(data_samples)\nprint(\"done in %0.3fs.\" % (time() - t0))\n\n# Use tf (raw term count) features for LDA.\nprint(\"Extracting tf features for LDA...\")\ntf_vectorizer = CountVectorizer(max_df=0.95, min_df=2,\n                                max_features=n_features,\n                                stop_words='english')\nt0 = time()\ntf = tf_vectorizer.fit_transform(data_samples)\nprint(\"done in %0.3fs.\" % (time() - t0))\nprint()\n\n# Fit the NMF model\nprint(\"Fitting the NMF model (Frobenius norm) with tf-idf features, \"\n      \"n_samples=%d and n_features=%d...\"\n      % (n_samples, n_features))\nt0 = time()\nnmf = NMF(n_components=n_topics, random_state=1,\n          alpha=.1, l1_ratio=.5).fit(tfidf)\nprint(\"done in %0.3fs.\" % (time() - t0))\n\nprint(\"\\nTopics in NMF model (Frobenius norm):\")\ntfidf_feature_names = tfidf_vectorizer.get_feature_names()\nprint_top_words(nmf, tfidf_feature_names, n_top_words)\n\n# Fit the NMF model\nprint(\"Fitting the NMF model (generalized Kullback-Leibler divergence) with \"\n      \"tf-idf features, n_samples=%d and n_features=%d...\"\n      % (n_samples, n_features))\nt0 = time()\nnmf = NMF(n_components=n_topics, random_state=1, beta_loss='kullback-leibler',\n          solver='mu', max_iter=1000, alpha=.1, l1_ratio=.5).fit(tfidf)\nprint(\"done in %0.3fs.\" % (time() - t0))\n\nprint(\"\\nTopics in NMF model (generalized Kullback-Leibler divergence):\")\ntfidf_feature_names = tfidf_vectorizer.get_feature_names()\nprint_top_words(nmf, tfidf_feature_names, n_top_words)\n\nprint(\"Fitting LDA models with tf features, \"\n      \"n_samples=%d and n_features=%d...\"\n      % (n_samples, n_features))\nlda = LatentDirichletAllocation(n_topics=n_topics, max_iter=5,\n                                learning_method='online',\n                                learning_offset=50.,\n                                random_state=0)\nt0 = time()\nlda.fit(tf)\nprint(\"done in %0.3fs.\" % (time() - t0))\n\nprint(\"\\nTopics in LDA model:\")\ntf_feature_names = tf_vectorizer.get_feature_names()\nprint_top_words(lda, tf_feature_names, n_top_words)"
+        "# Author: Olivier Grisel <[email protected]>\n#         Lars Buitinck\n#         Chyi-Kwei Yau <[email protected]>\n# License: BSD 3 clause\n\nfrom __future__ import print_function\nfrom time import time\n\nfrom sklearn.feature_extraction.text import TfidfVectorizer, CountVectorizer\nfrom sklearn.decomposition import NMF, LatentDirichletAllocation\nfrom sklearn.datasets import fetch_20newsgroups\n\nn_samples = 2000\nn_features = 1000\nn_components = 10\nn_top_words = 20\n\n\ndef print_top_words(model, feature_names, n_top_words):\n    for topic_idx, topic in enumerate(model.components_):\n        message = \"Topic #%d: \" % topic_idx\n        message += \" \".join([feature_names[i]\n                             for i in topic.argsort()[:-n_top_words - 1:-1]])\n        print(message)\n    print()\n\n\n# Load the 20 newsgroups dataset and vectorize it. We use a few heuristics\n# to filter out useless terms early on: the posts are stripped of headers,\n# footers and quoted replies, and common English words, words occurring in\n# only one document or in at least 95% of the documents are removed.\n\nprint(\"Loading dataset...\")\nt0 = time()\ndataset = fetch_20newsgroups(shuffle=True, random_state=1,\n                             remove=('headers', 'footers', 'quotes'))\ndata_samples = dataset.data[:n_samples]\nprint(\"done in %0.3fs.\" % (time() - t0))\n\n# Use tf-idf features for NMF.\nprint(\"Extracting tf-idf features for NMF...\")\ntfidf_vectorizer = TfidfVectorizer(max_df=0.95, min_df=2,\n                                   max_features=n_features,\n                                   stop_words='english')\nt0 = time()\ntfidf = tfidf_vectorizer.fit_transform(data_samples)\nprint(\"done in %0.3fs.\" % (time() - t0))\n\n# Use tf (raw term count) features for LDA.\nprint(\"Extracting tf features for LDA...\")\ntf_vectorizer = CountVectorizer(max_df=0.95, min_df=2,\n                                max_features=n_features,\n                                stop_words='english')\nt0 = time()\ntf = tf_vectorizer.fit_transform(data_samples)\nprint(\"done in %0.3fs.\" % (time() - t0))\nprint()\n\n# Fit the NMF model\nprint(\"Fitting the NMF model (Frobenius norm) with tf-idf features, \"\n      \"n_samples=%d and n_features=%d...\"\n      % (n_samples, n_features))\nt0 = time()\nnmf = NMF(n_components=n_components, random_state=1,\n          alpha=.1, l1_ratio=.5).fit(tfidf)\nprint(\"done in %0.3fs.\" % (time() - t0))\n\nprint(\"\\nTopics in NMF model (Frobenius norm):\")\ntfidf_feature_names = tfidf_vectorizer.get_feature_names()\nprint_top_words(nmf, tfidf_feature_names, n_top_words)\n\n# Fit the NMF model\nprint(\"Fitting the NMF model (generalized Kullback-Leibler divergence) with \"\n      \"tf-idf features, n_samples=%d and n_features=%d...\"\n      % (n_samples, n_features))\nt0 = time()\nnmf = NMF(n_components=n_components, random_state=1, beta_loss='kullback-leibler',\n          solver='mu', max_iter=1000, alpha=.1, l1_ratio=.5).fit(tfidf)\nprint(\"done in %0.3fs.\" % (time() - t0))\n\nprint(\"\\nTopics in NMF model (generalized Kullback-Leibler divergence):\")\ntfidf_feature_names = tfidf_vectorizer.get_feature_names()\nprint_top_words(nmf, tfidf_feature_names, n_top_words)\n\nprint(\"Fitting LDA models with tf features, \"\n      \"n_samples=%d and n_features=%d...\"\n      % (n_samples, n_features))\nlda = LatentDirichletAllocation(n_components=n_components, max_iter=5,\n                                learning_method='online',\n                                learning_offset=50.,\n                                random_state=0)\nt0 = time()\nlda.fit(tf)\nprint(\"done in %0.3fs.\" % (time() - t0))\n\nprint(\"\\nTopics in LDA model:\")\ntf_feature_names = tf_vectorizer.get_feature_names()\nprint_top_words(lda, tf_feature_names, n_top_words)"
       ]
     }
   ],

dev/_downloads/auto_examples_python.zip

@@ -14,7 +14,7 @@
 functions: the Frobenius norm, and the generalized Kullback-Leibler divergence.
 The latter is equivalent to Probabilistic Latent Semantic Indexing.
 
-The default parameters (n_samples / n_features / n_topics) should make
+The default parameters (n_samples / n_features / n_components) should make
 the example runnable in a couple of tens of seconds. You can try to
 increase the dimensions of the problem, but be aware that the time
 complexity is polynomial in NMF. In LDA, the time complexity is
@@ -36,7 +36,7 @@
 
 n_samples = 2000
 n_features = 1000
-n_topics = 10
+n_components = 10
 n_top_words = 20
 
 
@@ -85,7 +85,7 @@ def print_top_words(model, feature_names, n_top_words):
       "n_samples=%d and n_features=%d..."
       % (n_samples, n_features))
 t0 = time()
-nmf = NMF(n_components=n_topics, random_state=1,
+nmf = NMF(n_components=n_components, random_state=1,
           alpha=.1, l1_ratio=.5).fit(tfidf)
 print("done in %0.3fs." % (time() - t0))
 
@@ -98,7 +98,7 @@ def print_top_words(model, feature_names, n_top_words):
       "tf-idf features, n_samples=%d and n_features=%d..."
       % (n_samples, n_features))
 t0 = time()
-nmf = NMF(n_components=n_topics, random_state=1, beta_loss='kullback-leibler',
+nmf = NMF(n_components=n_components, random_state=1, beta_loss='kullback-leibler',
           solver='mu', max_iter=1000, alpha=.1, l1_ratio=.5).fit(tfidf)
 print("done in %0.3fs." % (time() - t0))
 
@@ -109,7 +109,7 @@ def print_top_words(model, feature_names, n_top_words):
 print("Fitting LDA models with tf features, "
       "n_samples=%d and n_features=%d..."
       % (n_samples, n_features))
-lda = LatentDirichletAllocation(n_topics=n_topics, max_iter=5,
+lda = LatentDirichletAllocation(n_components=n_components, max_iter=5,
                                 learning_method='online',
                                 learning_offset=50.,
                                 random_state=0)