Pushing the docs to dev/ for branch: master, commit 370e5452b52a90cb137513159d3d9559d77bc71d

Author: sklearn-ci

dev/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip

@@ -1,15 +1,17 @@
 """
-====================================================================
-Normal and Shrinkage Linear Discriminant Analysis for classification
-====================================================================
+===========================================================================
+Normal, Ledoit-Wolf and OAS Linear Discriminant Analysis for classification
+===========================================================================
 
-Shows how shrinkage improves classification.
+This example illustrates how the Ledoit-Wolf and Oracle Shrinkage
+Approximating (OAS) estimators of covariance can improve classification.
 """
 import numpy as np
 import matplotlib.pyplot as plt
 
 from sklearn.datasets import make_blobs
 from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
+from sklearn.covariance import OAS
 
 
 n_train = 20  # samples for training
@@ -35,34 +37,45 @@ def generate_data(n_samples, n_features):
         X = np.hstack([X, np.random.randn(n_samples, n_features - 1)])
     return X, y
 
-acc_clf1, acc_clf2 = [], []
+
+acc_clf1, acc_clf2, acc_clf3 = [], [], []
 n_features_range = range(1, n_features_max + 1, step)
 for n_features in n_features_range:
-    score_clf1, score_clf2 = 0, 0
+    score_clf1, score_clf2, score_clf3 = 0, 0, 0
     for _ in range(n_averages):
         X, y = generate_data(n_train, n_features)
 
-        clf1 = LinearDiscriminantAnalysis(solver='lsqr', shrinkage='auto').fit(X, y)
-        clf2 = LinearDiscriminantAnalysis(solver='lsqr', shrinkage=None).fit(X, y)
+        clf1 = LinearDiscriminantAnalysis(solver='lsqr',
+                                          shrinkage='auto').fit(X, y)
+        clf2 = LinearDiscriminantAnalysis(solver='lsqr',
+                                          shrinkage=None).fit(X, y)
+        oa = OAS(store_precision=False, assume_centered=False)
+        clf3 = LinearDiscriminantAnalysis(solver='lsqr',
+                                          covariance_estimator=oa).fit(X, y)
 
         X, y = generate_data(n_test, n_features)
         score_clf1 += clf1.score(X, y)
         score_clf2 += clf2.score(X, y)
+        score_clf3 += clf3.score(X, y)
 
     acc_clf1.append(score_clf1 / n_averages)
     acc_clf2.append(score_clf2 / n_averages)
+    acc_clf3.append(score_clf3 / n_averages)
 
 features_samples_ratio = np.array(n_features_range) / n_train
 
 plt.plot(features_samples_ratio, acc_clf1, linewidth=2,
-         label="Linear Discriminant Analysis with shrinkage", color='navy')
+         label="Linear Discriminant Analysis with Ledoit Wolf", color='navy')
 plt.plot(features_samples_ratio, acc_clf2, linewidth=2,
          label="Linear Discriminant Analysis", color='gold')
+plt.plot(features_samples_ratio, acc_clf3, linewidth=2,
+         label="Linear Discriminant Analysis with OAS", color='red')
 
 plt.xlabel('n_features / n_samples')
 plt.ylabel('Classification accuracy')
 
-plt.legend(loc=1, prop={'size': 12})
-plt.suptitle('Linear Discriminant Analysis vs. \
-shrinkage Linear Discriminant Analysis (1 discriminative feature)')
+plt.legend(loc=3, prop={'size': 12})
+plt.suptitle('Linear Discriminant Analysis vs. ' + '\n'
+             + 'Shrinkage Linear Discriminant Analysis vs. ' + '\n'
+             + 'OAS Linear Discriminant Analysis (1 discriminative feature)')
 plt.show()

dev/_downloads/14f620cd922ca2c9a39ae5784034dd0d/plot_lda.py

@@ -15,7 +15,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "\n# Normal and Shrinkage Linear Discriminant Analysis for classification\n\nShows how shrinkage improves classification.\n"
+        "\n# Normal, Ledoit-Wolf and OAS Linear Discriminant Analysis for classification\n\nThis example illustrates how the Ledoit-Wolf and Oracle Shrinkage\nApproximating (OAS) estimators of covariance can improve classification.\n"
       ]
     },
     {
@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "import numpy as np\nimport matplotlib.pyplot as plt\n\nfrom sklearn.datasets import make_blobs\nfrom sklearn.discriminant_analysis import LinearDiscriminantAnalysis\n\n\nn_train = 20  # samples for training\nn_test = 200  # samples for testing\nn_averages = 50  # how often to repeat classification\nn_features_max = 75  # maximum number of features\nstep = 4  # step size for the calculation\n\n\ndef generate_data(n_samples, n_features):\n    \"\"\"Generate random blob-ish data with noisy features.\n\n    This returns an array of input data with shape `(n_samples, n_features)`\n    and an array of `n_samples` target labels.\n\n    Only one feature contains discriminative information, the other features\n    contain only noise.\n    \"\"\"\n    X, y = make_blobs(n_samples=n_samples, n_features=1, centers=[[-2], [2]])\n\n    # add non-discriminative features\n    if n_features > 1:\n        X = np.hstack([X, np.random.randn(n_samples, n_features - 1)])\n    return X, y\n\nacc_clf1, acc_clf2 = [], []\nn_features_range = range(1, n_features_max + 1, step)\nfor n_features in n_features_range:\n    score_clf1, score_clf2 = 0, 0\n    for _ in range(n_averages):\n        X, y = generate_data(n_train, n_features)\n\n        clf1 = LinearDiscriminantAnalysis(solver='lsqr', shrinkage='auto').fit(X, y)\n        clf2 = LinearDiscriminantAnalysis(solver='lsqr', shrinkage=None).fit(X, y)\n\n        X, y = generate_data(n_test, n_features)\n        score_clf1 += clf1.score(X, y)\n        score_clf2 += clf2.score(X, y)\n\n    acc_clf1.append(score_clf1 / n_averages)\n    acc_clf2.append(score_clf2 / n_averages)\n\nfeatures_samples_ratio = np.array(n_features_range) / n_train\n\nplt.plot(features_samples_ratio, acc_clf1, linewidth=2,\n         label=\"Linear Discriminant Analysis with shrinkage\", color='navy')\nplt.plot(features_samples_ratio, acc_clf2, linewidth=2,\n         label=\"Linear Discriminant Analysis\", color='gold')\n\nplt.xlabel('n_features / n_samples')\nplt.ylabel('Classification accuracy')\n\nplt.legend(loc=1, prop={'size': 12})\nplt.suptitle('Linear Discriminant Analysis vs. \\\nshrinkage Linear Discriminant Analysis (1 discriminative feature)')\nplt.show()"
+        "import numpy as np\nimport matplotlib.pyplot as plt\n\nfrom sklearn.datasets import make_blobs\nfrom sklearn.discriminant_analysis import LinearDiscriminantAnalysis\nfrom sklearn.covariance import OAS\n\n\nn_train = 20  # samples for training\nn_test = 200  # samples for testing\nn_averages = 50  # how often to repeat classification\nn_features_max = 75  # maximum number of features\nstep = 4  # step size for the calculation\n\n\ndef generate_data(n_samples, n_features):\n    \"\"\"Generate random blob-ish data with noisy features.\n\n    This returns an array of input data with shape `(n_samples, n_features)`\n    and an array of `n_samples` target labels.\n\n    Only one feature contains discriminative information, the other features\n    contain only noise.\n    \"\"\"\n    X, y = make_blobs(n_samples=n_samples, n_features=1, centers=[[-2], [2]])\n\n    # add non-discriminative features\n    if n_features > 1:\n        X = np.hstack([X, np.random.randn(n_samples, n_features - 1)])\n    return X, y\n\n\nacc_clf1, acc_clf2, acc_clf3 = [], [], []\nn_features_range = range(1, n_features_max + 1, step)\nfor n_features in n_features_range:\n    score_clf1, score_clf2, score_clf3 = 0, 0, 0\n    for _ in range(n_averages):\n        X, y = generate_data(n_train, n_features)\n\n        clf1 = LinearDiscriminantAnalysis(solver='lsqr',\n                                          shrinkage='auto').fit(X, y)\n        clf2 = LinearDiscriminantAnalysis(solver='lsqr',\n                                          shrinkage=None).fit(X, y)\n        oa = OAS(store_precision=False, assume_centered=False)\n        clf3 = LinearDiscriminantAnalysis(solver='lsqr',\n                                          covariance_estimator=oa).fit(X, y)\n\n        X, y = generate_data(n_test, n_features)\n        score_clf1 += clf1.score(X, y)\n        score_clf2 += clf2.score(X, y)\n        score_clf3 += clf3.score(X, y)\n\n    acc_clf1.append(score_clf1 / n_averages)\n    acc_clf2.append(score_clf2 / n_averages)\n    acc_clf3.append(score_clf3 / n_averages)\n\nfeatures_samples_ratio = np.array(n_features_range) / n_train\n\nplt.plot(features_samples_ratio, acc_clf1, linewidth=2,\n         label=\"Linear Discriminant Analysis with Ledoit Wolf\", color='navy')\nplt.plot(features_samples_ratio, acc_clf2, linewidth=2,\n         label=\"Linear Discriminant Analysis\", color='gold')\nplt.plot(features_samples_ratio, acc_clf3, linewidth=2,\n         label=\"Linear Discriminant Analysis with OAS\", color='red')\n\nplt.xlabel('n_features / n_samples')\nplt.ylabel('Classification accuracy')\n\nplt.legend(loc=3, prop={'size': 12})\nplt.suptitle('Linear Discriminant Analysis vs. ' + '\\n'\n             + 'Shrinkage Linear Discriminant Analysis vs. ' + '\\n'\n             + 'OAS Linear Discriminant Analysis (1 discriminative feature)')\nplt.show()"
       ]
     }
   ],