Pushing the docs to dev/ for branch: master, commit 774f1aa0e767824c37b332e989146c8d6a3ee7a2

Author: sklearn-ci

dev/_downloads/auto_examples_jupyter.zip

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "print(__doc__)\n\n# Author: Adam Kleczewski\n# License: BSD 3 clause\n\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom sklearn.multioutput import ClassifierChain\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.multiclass import OneVsRestClassifier\nfrom sklearn.metrics import jaccard_similarity_score\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn.datasets import fetch_mldata\n\n# Load a multi-label dataset\nyeast = fetch_mldata('yeast')\nX = yeast['data']\nY = yeast['target'].transpose().toarray()\nX_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=.2,\n                                                    random_state=0)\n\n# Fit an independent logistic regression model for each class using the\n# OneVsRestClassifier wrapper.\novr = OneVsRestClassifier(LogisticRegression())\novr.fit(X_train, Y_train)\nY_pred_ovr = ovr.predict(X_test)\novr_jaccard_score = jaccard_similarity_score(Y_test, Y_pred_ovr)\n\n# Fit an ensemble of logistic regression classifier chains and take the\n# take the average prediction of all the chains.\nchains = [ClassifierChain(LogisticRegression(), order='random', random_state=i)\n          for i in range(10)]\nfor chain in chains:\n    chain.fit(X_train, Y_train)\n\nY_pred_chains = np.array([chain.predict(X_test) for chain in\n                          chains])\nchain_jaccard_scores = [jaccard_similarity_score(Y_test, Y_pred_chain >= .5)\n                        for Y_pred_chain in Y_pred_chains]\n\nY_pred_ensemble = Y_pred_chains.mean(axis=0)\nensemble_jaccard_score = jaccard_similarity_score(Y_test,\n                                                  Y_pred_ensemble >= .5)\n\nmodel_scores = [ovr_jaccard_score] + chain_jaccard_scores\nmodel_scores.append(ensemble_jaccard_score)\n\nmodel_names = ('Independent',\n               'Chain 1',\n               'Chain 2',\n               'Chain 3',\n               'Chain 4',\n               'Chain 5',\n               'Chain 6',\n               'Chain 7',\n               'Chain 8',\n               'Chain 9',\n               'Chain 10',\n               'Ensemble')\n\nx_pos = np.arange(len(model_names))\n\n# Plot the Jaccard similarity scores for the independent model, each of the\n# chains, and the ensemble (note that the vertical axis on this plot does\n# not begin at 0).\n\nfig, ax = plt.subplots(figsize=(7, 4))\nax.grid(True)\nax.set_title('Classifier Chain Ensemble Performance Comparison')\nax.set_xticks(x_pos)\nax.set_xticklabels(model_names, rotation='vertical')\nax.set_ylabel('Jaccard Similarity Score')\nax.set_ylim([min(model_scores) * .9, max(model_scores) * 1.1])\ncolors = ['r'] + ['b'] * len(chain_jaccard_scores) + ['g']\nax.bar(x_pos, model_scores, alpha=0.5, color=colors)\nplt.tight_layout()\nplt.show()"
+        "# Author: Adam Kleczewski\n# License: BSD 3 clause\n\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom sklearn.datasets import fetch_openml\nfrom sklearn.multioutput import ClassifierChain\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.multiclass import OneVsRestClassifier\nfrom sklearn.metrics import jaccard_similarity_score\nfrom sklearn.linear_model import LogisticRegression\n\nprint(__doc__)\n\n# Load a multi-label dataset from https://www.openml.org/d/40597\nX, Y = fetch_openml('yeast', version=4, return_X_y=True)\nY = Y == 'TRUE'\nX_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=.2,\n                                                    random_state=0)\n\n# Fit an independent logistic regression model for each class using the\n# OneVsRestClassifier wrapper.\novr = OneVsRestClassifier(LogisticRegression())\novr.fit(X_train, Y_train)\nY_pred_ovr = ovr.predict(X_test)\novr_jaccard_score = jaccard_similarity_score(Y_test, Y_pred_ovr)\n\n# Fit an ensemble of logistic regression classifier chains and take the\n# take the average prediction of all the chains.\nchains = [ClassifierChain(LogisticRegression(), order='random', random_state=i)\n          for i in range(10)]\nfor chain in chains:\n    chain.fit(X_train, Y_train)\n\nY_pred_chains = np.array([chain.predict(X_test) for chain in\n                          chains])\nchain_jaccard_scores = [jaccard_similarity_score(Y_test, Y_pred_chain >= .5)\n                        for Y_pred_chain in Y_pred_chains]\n\nY_pred_ensemble = Y_pred_chains.mean(axis=0)\nensemble_jaccard_score = jaccard_similarity_score(Y_test,\n                                                  Y_pred_ensemble >= .5)\n\nmodel_scores = [ovr_jaccard_score] + chain_jaccard_scores\nmodel_scores.append(ensemble_jaccard_score)\n\nmodel_names = ('Independent',\n               'Chain 1',\n               'Chain 2',\n               'Chain 3',\n               'Chain 4',\n               'Chain 5',\n               'Chain 6',\n               'Chain 7',\n               'Chain 8',\n               'Chain 9',\n               'Chain 10',\n               'Ensemble')\n\nx_pos = np.arange(len(model_names))\n\n# Plot the Jaccard similarity scores for the independent model, each of the\n# chains, and the ensemble (note that the vertical axis on this plot does\n# not begin at 0).\n\nfig, ax = plt.subplots(figsize=(7, 4))\nax.grid(True)\nax.set_title('Classifier Chain Ensemble Performance Comparison')\nax.set_xticks(x_pos)\nax.set_xticklabels(model_names, rotation='vertical')\nax.set_ylabel('Jaccard Similarity Score')\nax.set_ylim([min(model_scores) * .9, max(model_scores) * 1.1])\ncolors = ['r'] + ['b'] * len(chain_jaccard_scores) + ['g']\nax.bar(x_pos, model_scores, alpha=0.5, color=colors)\nplt.tight_layout()\nplt.show()"
       ]
     }
   ],

dev/_downloads/auto_examples_python.zip

@@ -32,24 +32,23 @@
 with randomly ordered chains).
 """
 
-print(__doc__)
-
 # Author: Adam Kleczewski
 # License: BSD 3 clause
 
 import numpy as np
 import matplotlib.pyplot as plt
+from sklearn.datasets import fetch_openml
 from sklearn.multioutput import ClassifierChain
 from sklearn.model_selection import train_test_split
 from sklearn.multiclass import OneVsRestClassifier
 from sklearn.metrics import jaccard_similarity_score
 from sklearn.linear_model import LogisticRegression
-from sklearn.datasets import fetch_mldata
 
-# Load a multi-label dataset
-yeast = fetch_mldata('yeast')
-X = yeast['data']
-Y = yeast['target'].transpose().toarray()
+print(__doc__)
+
+# Load a multi-label dataset from https://www.openml.org/d/40597
+X, Y = fetch_openml('yeast', version=4, return_X_y=True)
+Y = Y == 'TRUE'
 X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=.2,
                                                     random_state=0)
 

dev/_downloads/plot_classifier_chain_yeast.ipynb

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "# Authors: Robert Layton <[email protected]>\n#          Olivier Grisel <[email protected]>\n#          Mathieu Blondel <[email protected]>\n#\n# License: BSD 3 clause\n\nprint(__doc__)\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom sklearn.cluster import KMeans\nfrom sklearn.metrics import pairwise_distances_argmin\nfrom sklearn.datasets import load_sample_image\nfrom sklearn.utils import shuffle\nfrom time import time\n\nn_colors = 64\n\n# Load the Summer Palace photo\nchina = load_sample_image(\"china.jpg\")\n\n# Convert to floats instead of the default 8 bits integer coding. Dividing by\n# 255 is important so that plt.imshow behaves works well on float data (need to\n# be in the range [0-1])\nchina = np.array(china, dtype=np.float64) / 255\n\n# Load Image and transform to a 2D numpy array.\nw, h, d = original_shape = tuple(china.shape)\nassert d == 3\nimage_array = np.reshape(china, (w * h, d))\n\nprint(\"Fitting model on a small sub-sample of the data\")\nt0 = time()\nimage_array_sample = shuffle(image_array, random_state=0)[:1000]\nkmeans = KMeans(n_clusters=n_colors, random_state=0).fit(image_array_sample)\nprint(\"done in %0.3fs.\" % (time() - t0))\n\n# Get labels for all points\nprint(\"Predicting color indices on the full image (k-means)\")\nt0 = time()\nlabels = kmeans.predict(image_array)\nprint(\"done in %0.3fs.\" % (time() - t0))\n\n\ncodebook_random = shuffle(image_array, random_state=0)[:n_colors + 1]\nprint(\"Predicting color indices on the full image (random)\")\nt0 = time()\nlabels_random = pairwise_distances_argmin(codebook_random,\n                                          image_array,\n                                          axis=0)\nprint(\"done in %0.3fs.\" % (time() - t0))\n\n\ndef recreate_image(codebook, labels, w, h):\n    \"\"\"Recreate the (compressed) image from the code book & labels\"\"\"\n    d = codebook.shape[1]\n    image = np.zeros((w, h, d))\n    label_idx = 0\n    for i in range(w):\n        for j in range(h):\n            image[i][j] = codebook[labels[label_idx]]\n            label_idx += 1\n    return image\n\n# Display all results, alongside original image\nplt.figure(1)\nplt.clf()\nplt.axis('off')\nplt.title('Original image (96,615 colors)')\nplt.imshow(china)\n\nplt.figure(2)\nplt.clf()\nplt.axis('off')\nplt.title('Quantized image (64 colors, K-Means)')\nplt.imshow(recreate_image(kmeans.cluster_centers_, labels, w, h))\n\nplt.figure(3)\nplt.clf()\nplt.axis('off')\nplt.title('Quantized image (64 colors, Random)')\nplt.imshow(recreate_image(codebook_random, labels_random, w, h))\nplt.show()"
+        "# Authors: Robert Layton <[email protected]>\n#          Olivier Grisel <[email protected]>\n#          Mathieu Blondel <[email protected]>\n#\n# License: BSD 3 clause\n\nprint(__doc__)\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom sklearn.cluster import KMeans\nfrom sklearn.metrics import pairwise_distances_argmin\nfrom sklearn.datasets import load_sample_image\nfrom sklearn.utils import shuffle\nfrom time import time\n\nn_colors = 64\n\n# Load the Summer Palace photo\nchina = load_sample_image(\"china.jpg\")\n\n# Convert to floats instead of the default 8 bits integer coding. Dividing by\n# 255 is important so that plt.imshow behaves works well on float data (need to\n# be in the range [0-1])\nchina = np.array(china, dtype=np.float64) / 255\n\n# Load Image and transform to a 2D numpy array.\nw, h, d = original_shape = tuple(china.shape)\nassert d == 3\nimage_array = np.reshape(china, (w * h, d))\n\nprint(\"Fitting model on a small sub-sample of the data\")\nt0 = time()\nimage_array_sample = shuffle(image_array, random_state=0)[:1000]\nkmeans = KMeans(n_clusters=n_colors, random_state=0).fit(image_array_sample)\nprint(\"done in %0.3fs.\" % (time() - t0))\n\n# Get labels for all points\nprint(\"Predicting color indices on the full image (k-means)\")\nt0 = time()\nlabels = kmeans.predict(image_array)\nprint(\"done in %0.3fs.\" % (time() - t0))\n\n\ncodebook_random = shuffle(image_array, random_state=0)[:n_colors]\nprint(\"Predicting color indices on the full image (random)\")\nt0 = time()\nlabels_random = pairwise_distances_argmin(codebook_random,\n                                          image_array,\n                                          axis=0)\nprint(\"done in %0.3fs.\" % (time() - t0))\n\n\ndef recreate_image(codebook, labels, w, h):\n    \"\"\"Recreate the (compressed) image from the code book & labels\"\"\"\n    d = codebook.shape[1]\n    image = np.zeros((w, h, d))\n    label_idx = 0\n    for i in range(w):\n        for j in range(h):\n            image[i][j] = codebook[labels[label_idx]]\n            label_idx += 1\n    return image\n\n# Display all results, alongside original image\nplt.figure(1)\nplt.clf()\nplt.axis('off')\nplt.title('Original image (96,615 colors)')\nplt.imshow(china)\n\nplt.figure(2)\nplt.clf()\nplt.axis('off')\nplt.title('Quantized image (64 colors, K-Means)')\nplt.imshow(recreate_image(kmeans.cluster_centers_, labels, w, h))\n\nplt.figure(3)\nplt.clf()\nplt.axis('off')\nplt.title('Quantized image (64 colors, Random)')\nplt.imshow(recreate_image(codebook_random, labels_random, w, h))\nplt.show()"
       ]
     }
   ],

dev/_downloads/plot_classifier_chain_yeast.py

@@ -61,7 +61,7 @@
 print("done in %0.3fs." % (time() - t0))
 
 
-codebook_random = shuffle(image_array, random_state=0)[:n_colors + 1]
+codebook_random = shuffle(image_array, random_state=0)[:n_colors]
 print("Predicting color indices on the full image (random)")
 t0 = time()
 labels_random = pairwise_distances_argmin(codebook_random,