Pushing the docs to dev/ for branch: main, commit d4e7158bcaa6f91a42e8afba21b7803bf82c3813

Author: sklearn-ci

dev/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip

@@ -47,8 +47,8 @@ def generate_data(n_samples, n_features):
     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=None).fit(X, y)
+        clf2 = LinearDiscriminantAnalysis(solver="lsqr", shrinkage="auto").fit(X, y)
         oa = OAS(store_precision=False, assume_centered=False)
         clf3 = LinearDiscriminantAnalysis(solver="lsqr", covariance_estimator=oa).fit(
             X, y
@@ -69,36 +69,37 @@ def generate_data(n_samples, n_features):
     features_samples_ratio,
     acc_clf1,
     linewidth=2,
-    label="Linear Discriminant Analysis with Ledoit Wolf",
-    color="navy",
-    linestyle="dashed",
+    label="LDA",
+    color="gold",
+    linestyle="solid",
 )
 plt.plot(
     features_samples_ratio,
     acc_clf2,
     linewidth=2,
-    label="Linear Discriminant Analysis",
-    color="gold",
-    linestyle="solid",
+    label="LDA with Ledoit Wolf",
+    color="navy",
+    linestyle="dashed",
 )
 plt.plot(
     features_samples_ratio,
     acc_clf3,
     linewidth=2,
-    label="Linear Discriminant Analysis with OAS",
+    label="LDA with OAS",
     color="red",
     linestyle="dotted",
 )
 
 plt.xlabel("n_features / n_samples")
 plt.ylabel("Classification accuracy")
 
-plt.legend(loc=3, prop={"size": 12})
+plt.legend(loc="lower left")
+plt.ylim((0.65, 1.0))
 plt.suptitle(
-    "Linear Discriminant Analysis vs. "
+    "LDA (Linear Discriminant Analysis) vs. "
     + "\n"
-    + "Shrinkage Linear Discriminant Analysis vs. "
+    + "LDA with Ledoit Wolf vs. "
     + "\n"
-    + "OAS Linear Discriminant Analysis (1 discriminative feature)"
+    + "LDA with OAS (1 discriminative feature)"
 )
 plt.show()

dev/_downloads/14f620cd922ca2c9a39ae5784034dd0d/plot_lda.py

@@ -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\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\", shrinkage=\"auto\").fit(X, y)\n        clf2 = LinearDiscriminantAnalysis(solver=\"lsqr\", shrinkage=None).fit(X, y)\n        oa = OAS(store_precision=False, assume_centered=False)\n        clf3 = LinearDiscriminantAnalysis(solver=\"lsqr\", covariance_estimator=oa).fit(\n            X, y\n        )\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(\n    features_samples_ratio,\n    acc_clf1,\n    linewidth=2,\n    label=\"Linear Discriminant Analysis with Ledoit Wolf\",\n    color=\"navy\",\n    linestyle=\"dashed\",\n)\nplt.plot(\n    features_samples_ratio,\n    acc_clf2,\n    linewidth=2,\n    label=\"Linear Discriminant Analysis\",\n    color=\"gold\",\n    linestyle=\"solid\",\n)\nplt.plot(\n    features_samples_ratio,\n    acc_clf3,\n    linewidth=2,\n    label=\"Linear Discriminant Analysis with OAS\",\n    color=\"red\",\n    linestyle=\"dotted\",\n)\n\nplt.xlabel(\"n_features / n_samples\")\nplt.ylabel(\"Classification accuracy\")\n\nplt.legend(loc=3, prop={\"size\": 12})\nplt.suptitle(\n    \"Linear Discriminant Analysis vs. \"\n    + \"\\n\"\n    + \"Shrinkage Linear Discriminant Analysis vs. \"\n    + \"\\n\"\n    + \"OAS Linear Discriminant Analysis (1 discriminative feature)\"\n)\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\", shrinkage=None).fit(X, y)\n        clf2 = LinearDiscriminantAnalysis(solver=\"lsqr\", shrinkage=\"auto\").fit(X, y)\n        oa = OAS(store_precision=False, assume_centered=False)\n        clf3 = LinearDiscriminantAnalysis(solver=\"lsqr\", covariance_estimator=oa).fit(\n            X, y\n        )\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(\n    features_samples_ratio,\n    acc_clf1,\n    linewidth=2,\n    label=\"LDA\",\n    color=\"gold\",\n    linestyle=\"solid\",\n)\nplt.plot(\n    features_samples_ratio,\n    acc_clf2,\n    linewidth=2,\n    label=\"LDA with Ledoit Wolf\",\n    color=\"navy\",\n    linestyle=\"dashed\",\n)\nplt.plot(\n    features_samples_ratio,\n    acc_clf3,\n    linewidth=2,\n    label=\"LDA with OAS\",\n    color=\"red\",\n    linestyle=\"dotted\",\n)\n\nplt.xlabel(\"n_features / n_samples\")\nplt.ylabel(\"Classification accuracy\")\n\nplt.legend(loc=\"lower left\")\nplt.ylim((0.65, 1.0))\nplt.suptitle(\n    \"LDA (Linear Discriminant Analysis) vs. \"\n    + \"\\n\"\n    + \"LDA with Ledoit Wolf vs. \"\n    + \"\\n\"\n    + \"LDA with OAS (1 discriminative feature)\"\n)\nplt.show()"
       ]
     }
   ],