Pushing the docs to dev/ for branch: main, commit e4fbc3735c51018a9b30c5d6c749249f83d37132

Author: sklearn-ci

dev/_downloads/00ae629d652473137a3905a5e08ea815/plot_iris_dtc.py

@@ -63,7 +63,7 @@
 
     # Plot the training points
     for i, color in zip(range(n_classes), plot_colors):
-        idx = np.where(y == i)
+        idx = np.asarray(y == i).nonzero()
         plt.scatter(
             X[idx, 0],
             X[idx, 1],

dev/_downloads/02192f99342d6d1323161978b6c80bfc/plot_ols_ridge.zip

@@ -31,7 +31,7 @@
     # decision_function = np.dot(X, clf.coef_[0]) + clf.intercept_[0]
     # The support vectors are the samples that lie within the margin
     # boundaries, whose size is conventionally constrained to 1
-    support_vector_indices = np.where(np.abs(decision_function) <= 1 + 1e-15)[0]
+    support_vector_indices = (np.abs(decision_function) <= 1 + 1e-15).nonzero()[0]
     support_vectors = X[support_vector_indices]
 
     plt.subplot(1, 2, i + 1)

dev/_downloads/02fe21a1f5d14bd1ebbe34aa905d9bf6/plot_multilabel.zip

@@ -108,7 +108,7 @@
             sub.axis("off")
 
         # labeling 5 points, remote from labeled set
-        (delete_index,) = np.where(unlabeled_indices == image_index)
+        (delete_index,) = (unlabeled_indices == image_index).nonzero()
         delete_indices = np.concatenate((delete_indices, delete_index))
 
     unlabeled_indices = np.delete(unlabeled_indices, delete_indices)

dev/_downloads/0358b1921962fd7c6f5a94c5abc91476/plot_hashing_vs_dict_vectorizer.zip

@@ -15,7 +15,7 @@
       },
       "outputs": [],
       "source": [
-        "# Authors: The scikit-learn developers\n# SPDX-License-Identifier: BSD-3-Clause\n\nimport matplotlib.pyplot as plt\nimport numpy as np\n\nfrom sklearn.datasets import make_blobs\nfrom sklearn.inspection import DecisionBoundaryDisplay\nfrom sklearn.svm import LinearSVC\n\nX, y = make_blobs(n_samples=40, centers=2, random_state=0)\n\nplt.figure(figsize=(10, 5))\nfor i, C in enumerate([1, 100]):\n    # \"hinge\" is the standard SVM loss\n    clf = LinearSVC(C=C, loss=\"hinge\", random_state=42).fit(X, y)\n    # obtain the support vectors through the decision function\n    decision_function = clf.decision_function(X)\n    # we can also calculate the decision function manually\n    # decision_function = np.dot(X, clf.coef_[0]) + clf.intercept_[0]\n    # The support vectors are the samples that lie within the margin\n    # boundaries, whose size is conventionally constrained to 1\n    support_vector_indices = np.where(np.abs(decision_function) <= 1 + 1e-15)[0]\n    support_vectors = X[support_vector_indices]\n\n    plt.subplot(1, 2, i + 1)\n    plt.scatter(X[:, 0], X[:, 1], c=y, s=30, cmap=plt.cm.Paired)\n    ax = plt.gca()\n    DecisionBoundaryDisplay.from_estimator(\n        clf,\n        X,\n        ax=ax,\n        grid_resolution=50,\n        plot_method=\"contour\",\n        colors=\"k\",\n        levels=[-1, 0, 1],\n        alpha=0.5,\n        linestyles=[\"--\", \"-\", \"--\"],\n    )\n    plt.scatter(\n        support_vectors[:, 0],\n        support_vectors[:, 1],\n        s=100,\n        linewidth=1,\n        facecolors=\"none\",\n        edgecolors=\"k\",\n    )\n    plt.title(\"C=\" + str(C))\nplt.tight_layout()\nplt.show()"
+        "# Authors: The scikit-learn developers\n# SPDX-License-Identifier: BSD-3-Clause\n\nimport matplotlib.pyplot as plt\nimport numpy as np\n\nfrom sklearn.datasets import make_blobs\nfrom sklearn.inspection import DecisionBoundaryDisplay\nfrom sklearn.svm import LinearSVC\n\nX, y = make_blobs(n_samples=40, centers=2, random_state=0)\n\nplt.figure(figsize=(10, 5))\nfor i, C in enumerate([1, 100]):\n    # \"hinge\" is the standard SVM loss\n    clf = LinearSVC(C=C, loss=\"hinge\", random_state=42).fit(X, y)\n    # obtain the support vectors through the decision function\n    decision_function = clf.decision_function(X)\n    # we can also calculate the decision function manually\n    # decision_function = np.dot(X, clf.coef_[0]) + clf.intercept_[0]\n    # The support vectors are the samples that lie within the margin\n    # boundaries, whose size is conventionally constrained to 1\n    support_vector_indices = (np.abs(decision_function) <= 1 + 1e-15).nonzero()[0]\n    support_vectors = X[support_vector_indices]\n\n    plt.subplot(1, 2, i + 1)\n    plt.scatter(X[:, 0], X[:, 1], c=y, s=30, cmap=plt.cm.Paired)\n    ax = plt.gca()\n    DecisionBoundaryDisplay.from_estimator(\n        clf,\n        X,\n        ax=ax,\n        grid_resolution=50,\n        plot_method=\"contour\",\n        colors=\"k\",\n        levels=[-1, 0, 1],\n        alpha=0.5,\n        linestyles=[\"--\", \"-\", \"--\"],\n    )\n    plt.scatter(\n        support_vectors[:, 0],\n        support_vectors[:, 1],\n        s=100,\n        linewidth=1,\n        facecolors=\"none\",\n        edgecolors=\"k\",\n    )\n    plt.title(\"C=\" + str(C))\nplt.tight_layout()\nplt.show()"
       ]
     }
   ],

dev/_downloads/036b9372e2e7802453cbb994da7a6786/plot_linearsvc_support_vectors.py

@@ -105,7 +105,7 @@
       },
       "outputs": [],
       "source": [
-        "import matplotlib.pyplot as plt\nfrom matplotlib.collections import LineCollection\n\nplt.figure(1, facecolor=\"w\", figsize=(10, 8))\nplt.clf()\nax = plt.axes([0.0, 0.0, 1.0, 1.0])\nplt.axis(\"off\")\n\n# Plot the graph of partial correlations\npartial_correlations = edge_model.precision_.copy()\nd = 1 / np.sqrt(np.diag(partial_correlations))\npartial_correlations *= d\npartial_correlations *= d[:, np.newaxis]\nnon_zero = np.abs(np.triu(partial_correlations, k=1)) > 0.02\n\n# Plot the nodes using the coordinates of our embedding\nplt.scatter(\n    embedding[0], embedding[1], s=100 * d**2, c=labels, cmap=plt.cm.nipy_spectral\n)\n\n# Plot the edges\nstart_idx, end_idx = np.where(non_zero)\n# a sequence of (*line0*, *line1*, *line2*), where::\n#            linen = (x0, y0), (x1, y1), ... (xm, ym)\nsegments = [\n    [embedding[:, start], embedding[:, stop]] for start, stop in zip(start_idx, end_idx)\n]\nvalues = np.abs(partial_correlations[non_zero])\nlc = LineCollection(\n    segments, zorder=0, cmap=plt.cm.hot_r, norm=plt.Normalize(0, 0.7 * values.max())\n)\nlc.set_array(values)\nlc.set_linewidths(15 * values)\nax.add_collection(lc)\n\n# Add a label to each node. The challenge here is that we want to\n# position the labels to avoid overlap with other labels\nfor index, (name, label, (x, y)) in enumerate(zip(names, labels, embedding.T)):\n    dx = x - embedding[0]\n    dx[index] = 1\n    dy = y - embedding[1]\n    dy[index] = 1\n    this_dx = dx[np.argmin(np.abs(dy))]\n    this_dy = dy[np.argmin(np.abs(dx))]\n    if this_dx > 0:\n        horizontalalignment = \"left\"\n        x = x + 0.002\n    else:\n        horizontalalignment = \"right\"\n        x = x - 0.002\n    if this_dy > 0:\n        verticalalignment = \"bottom\"\n        y = y + 0.002\n    else:\n        verticalalignment = \"top\"\n        y = y - 0.002\n    plt.text(\n        x,\n        y,\n        name,\n        size=10,\n        horizontalalignment=horizontalalignment,\n        verticalalignment=verticalalignment,\n        bbox=dict(\n            facecolor=\"w\",\n            edgecolor=plt.cm.nipy_spectral(label / float(n_labels)),\n            alpha=0.6,\n        ),\n    )\n\nplt.xlim(\n    embedding[0].min() - 0.15 * np.ptp(embedding[0]),\n    embedding[0].max() + 0.10 * np.ptp(embedding[0]),\n)\nplt.ylim(\n    embedding[1].min() - 0.03 * np.ptp(embedding[1]),\n    embedding[1].max() + 0.03 * np.ptp(embedding[1]),\n)\n\nplt.show()"
+        "import matplotlib.pyplot as plt\nfrom matplotlib.collections import LineCollection\n\nplt.figure(1, facecolor=\"w\", figsize=(10, 8))\nplt.clf()\nax = plt.axes([0.0, 0.0, 1.0, 1.0])\nplt.axis(\"off\")\n\n# Plot the graph of partial correlations\npartial_correlations = edge_model.precision_.copy()\nd = 1 / np.sqrt(np.diag(partial_correlations))\npartial_correlations *= d\npartial_correlations *= d[:, np.newaxis]\nnon_zero = np.abs(np.triu(partial_correlations, k=1)) > 0.02\n\n# Plot the nodes using the coordinates of our embedding\nplt.scatter(\n    embedding[0], embedding[1], s=100 * d**2, c=labels, cmap=plt.cm.nipy_spectral\n)\n\n# Plot the edges\nstart_idx, end_idx = non_zero.nonzero()\n# a sequence of (*line0*, *line1*, *line2*), where::\n#            linen = (x0, y0), (x1, y1), ... (xm, ym)\nsegments = [\n    [embedding[:, start], embedding[:, stop]] for start, stop in zip(start_idx, end_idx)\n]\nvalues = np.abs(partial_correlations[non_zero])\nlc = LineCollection(\n    segments, zorder=0, cmap=plt.cm.hot_r, norm=plt.Normalize(0, 0.7 * values.max())\n)\nlc.set_array(values)\nlc.set_linewidths(15 * values)\nax.add_collection(lc)\n\n# Add a label to each node. The challenge here is that we want to\n# position the labels to avoid overlap with other labels\nfor index, (name, label, (x, y)) in enumerate(zip(names, labels, embedding.T)):\n    dx = x - embedding[0]\n    dx[index] = 1\n    dy = y - embedding[1]\n    dy[index] = 1\n    this_dx = dx[np.argmin(np.abs(dy))]\n    this_dy = dy[np.argmin(np.abs(dx))]\n    if this_dx > 0:\n        horizontalalignment = \"left\"\n        x = x + 0.002\n    else:\n        horizontalalignment = \"right\"\n        x = x - 0.002\n    if this_dy > 0:\n        verticalalignment = \"bottom\"\n        y = y + 0.002\n    else:\n        verticalalignment = \"top\"\n        y = y - 0.002\n    plt.text(\n        x,\n        y,\n        name,\n        size=10,\n        horizontalalignment=horizontalalignment,\n        verticalalignment=verticalalignment,\n        bbox=dict(\n            facecolor=\"w\",\n            edgecolor=plt.cm.nipy_spectral(label / float(n_labels)),\n            alpha=0.6,\n        ),\n    )\n\nplt.xlim(\n    embedding[0].min() - 0.15 * np.ptp(embedding[0]),\n    embedding[0].max() + 0.10 * np.ptp(embedding[0]),\n)\nplt.ylim(\n    embedding[1].min() - 0.03 * np.ptp(embedding[1]),\n    embedding[1].max() + 0.03 * np.ptp(embedding[1]),\n)\n\nplt.show()"
       ]
     }
   ],

dev/_downloads/038d1885eb5f5ea53aca42da3031fe38/plot_document_clustering.zip

@@ -106,7 +106,7 @@ def ricker_matrix(width, resolution, n_components):
         dictionary=D, transform_algorithm="threshold", transform_alpha=20
     )
     x = coder.transform(y.reshape(1, -1))
-    _, idx = np.where(x != 0)
+    _, idx = (x != 0).nonzero()
     x[0, idx], _, _, _ = np.linalg.lstsq(D[idx, :].T, y, rcond=None)
     x = np.ravel(np.dot(x, D))
     squared_error = np.sum((y - x) ** 2)

dev/_downloads/03c018a16384c69f3a89e473650d57ee/plot_svm_margin.zip

@@ -15,7 +15,7 @@
       },
       "outputs": [],
       "source": [
-        "# Authors: The scikit-learn developers\n# SPDX-License-Identifier: BSD-3-Clause\nfrom collections import Counter\nfrom time import time\n\nimport numpy as np\n\nfrom sklearn.cluster import MiniBatchKMeans, SpectralCoclustering\nfrom sklearn.datasets import fetch_20newsgroups\nfrom sklearn.feature_extraction.text import TfidfVectorizer\nfrom sklearn.metrics.cluster import v_measure_score\n\n\ndef number_normalizer(tokens):\n    \"\"\"Map all numeric tokens to a placeholder.\n\n    For many applications, tokens that begin with a number are not directly\n    useful, but the fact that such a token exists can be relevant.  By applying\n    this form of dimensionality reduction, some methods may perform better.\n    \"\"\"\n    return (\"#NUMBER\" if token[0].isdigit() else token for token in tokens)\n\n\nclass NumberNormalizingVectorizer(TfidfVectorizer):\n    def build_tokenizer(self):\n        tokenize = super().build_tokenizer()\n        return lambda doc: list(number_normalizer(tokenize(doc)))\n\n\n# exclude 'comp.os.ms-windows.misc'\ncategories = [\n    \"alt.atheism\",\n    \"comp.graphics\",\n    \"comp.sys.ibm.pc.hardware\",\n    \"comp.sys.mac.hardware\",\n    \"comp.windows.x\",\n    \"misc.forsale\",\n    \"rec.autos\",\n    \"rec.motorcycles\",\n    \"rec.sport.baseball\",\n    \"rec.sport.hockey\",\n    \"sci.crypt\",\n    \"sci.electronics\",\n    \"sci.med\",\n    \"sci.space\",\n    \"soc.religion.christian\",\n    \"talk.politics.guns\",\n    \"talk.politics.mideast\",\n    \"talk.politics.misc\",\n    \"talk.religion.misc\",\n]\nnewsgroups = fetch_20newsgroups(categories=categories)\ny_true = newsgroups.target\n\nvectorizer = NumberNormalizingVectorizer(stop_words=\"english\", min_df=5)\ncocluster = SpectralCoclustering(\n    n_clusters=len(categories), svd_method=\"arpack\", random_state=0\n)\nkmeans = MiniBatchKMeans(\n    n_clusters=len(categories), batch_size=20000, random_state=0, n_init=3\n)\n\nprint(\"Vectorizing...\")\nX = vectorizer.fit_transform(newsgroups.data)\n\nprint(\"Coclustering...\")\nstart_time = time()\ncocluster.fit(X)\ny_cocluster = cocluster.row_labels_\nprint(\n    f\"Done in {time() - start_time:.2f}s. V-measure: \\\n{v_measure_score(y_cocluster, y_true):.4f}\"\n)\n\n\nprint(\"MiniBatchKMeans...\")\nstart_time = time()\ny_kmeans = kmeans.fit_predict(X)\nprint(\n    f\"Done in {time() - start_time:.2f}s. V-measure: \\\n{v_measure_score(y_kmeans, y_true):.4f}\"\n)\n\n\nfeature_names = vectorizer.get_feature_names_out()\ndocument_names = list(newsgroups.target_names[i] for i in newsgroups.target)\n\n\ndef bicluster_ncut(i):\n    rows, cols = cocluster.get_indices(i)\n    if not (np.any(rows) and np.any(cols)):\n        import sys\n\n        return sys.float_info.max\n    row_complement = np.nonzero(np.logical_not(cocluster.rows_[i]))[0]\n    col_complement = np.nonzero(np.logical_not(cocluster.columns_[i]))[0]\n    # Note: the following is identical to X[rows[:, np.newaxis],\n    # cols].sum() but much faster in scipy <= 0.16\n    weight = X[rows][:, cols].sum()\n    cut = X[row_complement][:, cols].sum() + X[rows][:, col_complement].sum()\n    return cut / weight\n\n\nbicluster_ncuts = list(bicluster_ncut(i) for i in range(len(newsgroups.target_names)))\nbest_idx = np.argsort(bicluster_ncuts)[:5]\n\nprint()\nprint(\"Best biclusters:\")\nprint(\"----------------\")\nfor idx, cluster in enumerate(best_idx):\n    n_rows, n_cols = cocluster.get_shape(cluster)\n    cluster_docs, cluster_words = cocluster.get_indices(cluster)\n    if not len(cluster_docs) or not len(cluster_words):\n        continue\n\n    # categories\n    counter = Counter(document_names[doc] for doc in cluster_docs)\n\n    cat_string = \", \".join(\n        f\"{(c / n_rows * 100):.0f}% {name}\" for name, c in counter.most_common(3)\n    )\n\n    # words\n    out_of_cluster_docs = cocluster.row_labels_ != cluster\n    out_of_cluster_docs = np.where(out_of_cluster_docs)[0]\n    word_col = X[:, cluster_words]\n    word_scores = np.array(\n        word_col[cluster_docs, :].sum(axis=0)\n        - word_col[out_of_cluster_docs, :].sum(axis=0)\n    )\n    word_scores = word_scores.ravel()\n    important_words = list(\n        feature_names[cluster_words[i]] for i in word_scores.argsort()[:-11:-1]\n    )\n\n    print(f\"bicluster {idx} : {n_rows} documents, {n_cols} words\")\n    print(f\"categories   : {cat_string}\")\n    print(f\"words        : {', '.join(important_words)}\\n\")"
+        "# Authors: The scikit-learn developers\n# SPDX-License-Identifier: BSD-3-Clause\nfrom collections import Counter\nfrom time import time\n\nimport numpy as np\n\nfrom sklearn.cluster import MiniBatchKMeans, SpectralCoclustering\nfrom sklearn.datasets import fetch_20newsgroups\nfrom sklearn.feature_extraction.text import TfidfVectorizer\nfrom sklearn.metrics.cluster import v_measure_score\n\n\ndef number_normalizer(tokens):\n    \"\"\"Map all numeric tokens to a placeholder.\n\n    For many applications, tokens that begin with a number are not directly\n    useful, but the fact that such a token exists can be relevant.  By applying\n    this form of dimensionality reduction, some methods may perform better.\n    \"\"\"\n    return (\"#NUMBER\" if token[0].isdigit() else token for token in tokens)\n\n\nclass NumberNormalizingVectorizer(TfidfVectorizer):\n    def build_tokenizer(self):\n        tokenize = super().build_tokenizer()\n        return lambda doc: list(number_normalizer(tokenize(doc)))\n\n\n# exclude 'comp.os.ms-windows.misc'\ncategories = [\n    \"alt.atheism\",\n    \"comp.graphics\",\n    \"comp.sys.ibm.pc.hardware\",\n    \"comp.sys.mac.hardware\",\n    \"comp.windows.x\",\n    \"misc.forsale\",\n    \"rec.autos\",\n    \"rec.motorcycles\",\n    \"rec.sport.baseball\",\n    \"rec.sport.hockey\",\n    \"sci.crypt\",\n    \"sci.electronics\",\n    \"sci.med\",\n    \"sci.space\",\n    \"soc.religion.christian\",\n    \"talk.politics.guns\",\n    \"talk.politics.mideast\",\n    \"talk.politics.misc\",\n    \"talk.religion.misc\",\n]\nnewsgroups = fetch_20newsgroups(categories=categories)\ny_true = newsgroups.target\n\nvectorizer = NumberNormalizingVectorizer(stop_words=\"english\", min_df=5)\ncocluster = SpectralCoclustering(\n    n_clusters=len(categories), svd_method=\"arpack\", random_state=0\n)\nkmeans = MiniBatchKMeans(\n    n_clusters=len(categories), batch_size=20000, random_state=0, n_init=3\n)\n\nprint(\"Vectorizing...\")\nX = vectorizer.fit_transform(newsgroups.data)\n\nprint(\"Coclustering...\")\nstart_time = time()\ncocluster.fit(X)\ny_cocluster = cocluster.row_labels_\nprint(\n    f\"Done in {time() - start_time:.2f}s. V-measure: \\\n{v_measure_score(y_cocluster, y_true):.4f}\"\n)\n\n\nprint(\"MiniBatchKMeans...\")\nstart_time = time()\ny_kmeans = kmeans.fit_predict(X)\nprint(\n    f\"Done in {time() - start_time:.2f}s. V-measure: \\\n{v_measure_score(y_kmeans, y_true):.4f}\"\n)\n\n\nfeature_names = vectorizer.get_feature_names_out()\ndocument_names = list(newsgroups.target_names[i] for i in newsgroups.target)\n\n\ndef bicluster_ncut(i):\n    rows, cols = cocluster.get_indices(i)\n    if not (np.any(rows) and np.any(cols)):\n        import sys\n\n        return sys.float_info.max\n    row_complement = np.nonzero(np.logical_not(cocluster.rows_[i]))[0]\n    col_complement = np.nonzero(np.logical_not(cocluster.columns_[i]))[0]\n    # Note: the following is identical to X[rows[:, np.newaxis],\n    # cols].sum() but much faster in scipy <= 0.16\n    weight = X[rows][:, cols].sum()\n    cut = X[row_complement][:, cols].sum() + X[rows][:, col_complement].sum()\n    return cut / weight\n\n\nbicluster_ncuts = list(bicluster_ncut(i) for i in range(len(newsgroups.target_names)))\nbest_idx = np.argsort(bicluster_ncuts)[:5]\n\nprint()\nprint(\"Best biclusters:\")\nprint(\"----------------\")\nfor idx, cluster in enumerate(best_idx):\n    n_rows, n_cols = cocluster.get_shape(cluster)\n    cluster_docs, cluster_words = cocluster.get_indices(cluster)\n    if not len(cluster_docs) or not len(cluster_words):\n        continue\n\n    # categories\n    counter = Counter(document_names[doc] for doc in cluster_docs)\n\n    cat_string = \", \".join(\n        f\"{(c / n_rows * 100):.0f}% {name}\" for name, c in counter.most_common(3)\n    )\n\n    # words\n    out_of_cluster_docs = cocluster.row_labels_ != cluster\n    out_of_cluster_docs = out_of_cluster_docs.nonzero()[0]\n    word_col = X[:, cluster_words]\n    word_scores = np.array(\n        word_col[cluster_docs, :].sum(axis=0)\n        - word_col[out_of_cluster_docs, :].sum(axis=0)\n    )\n    word_scores = word_scores.ravel()\n    important_words = list(\n        feature_names[cluster_words[i]] for i in word_scores.argsort()[:-11:-1]\n    )\n\n    print(f\"bicluster {idx} : {n_rows} documents, {n_cols} words\")\n    print(f\"categories   : {cat_string}\")\n    print(f\"words        : {', '.join(important_words)}\\n\")"
       ]
     }
   ],