Pushing the docs to dev/ for branch: master, commit 4a95e33e6344e15a197f33ddc2f8f786a0a45df0

Author: sklearn-ci

dev/_downloads/0256e8c73ba2281b77ba23f17e7d1549/plot_species_kde.py

@@ -42,7 +42,6 @@
 import numpy as np
 import matplotlib.pyplot as plt
 from sklearn.datasets import fetch_species_distributions
-from sklearn.datasets.species_distributions import construct_grids
 from sklearn.neighbors import KernelDensity
 
 # if basemap is available, we'll use it.
@@ -53,6 +52,34 @@
 except ImportError:
     basemap = False
 
+
+def construct_grids(batch):
+    """Construct the map grid from the batch object
+
+    Parameters
+    ----------
+    batch : Batch object
+        The object returned by :func:`fetch_species_distributions`
+
+    Returns
+    -------
+    (xgrid, ygrid) : 1-D arrays
+        The grid corresponding to the values in batch.coverages
+    """
+    # x,y coordinates for corner cells
+    xmin = batch.x_left_lower_corner + batch.grid_size
+    xmax = xmin + (batch.Nx * batch.grid_size)
+    ymin = batch.y_left_lower_corner + batch.grid_size
+    ymax = ymin + (batch.Ny * batch.grid_size)
+
+    # x coordinates of the grid cells
+    xgrid = np.arange(xmin, xmax, batch.grid_size)
+    # y coordinates of the grid cells
+    ygrid = np.arange(ymin, ymax, batch.grid_size)
+
+    return (xgrid, ygrid)
+
+
 # Get matrices/arrays of species IDs and locations
 data = fetch_species_distributions()
 species_names = ['Bradypus Variegatus', 'Microryzomys Minutus']

dev/_downloads/06d1bf4510bd82b665c44c2bd2c364ae/plot_feature_selection_pipeline.ipynb

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "from sklearn import svm\nfrom sklearn.datasets import samples_generator\nfrom sklearn.feature_selection import SelectKBest, f_regression\nfrom sklearn.pipeline import make_pipeline\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import classification_report\n\nprint(__doc__)\n\n# import some data to play with\nX, y = samples_generator.make_classification(\n    n_features=20, n_informative=3, n_redundant=0, n_classes=4,\n    n_clusters_per_class=2)\n\nX_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42)\n\n# ANOVA SVM-C\n# 1) anova filter, take 3 best ranked features\nanova_filter = SelectKBest(f_regression, k=3)\n# 2) svm\nclf = svm.LinearSVC()\n\nanova_svm = make_pipeline(anova_filter, clf)\nanova_svm.fit(X_train, y_train)\ny_pred = anova_svm.predict(X_test)\nprint(classification_report(y_test, y_pred))\n\ncoef = anova_svm[:-1].inverse_transform(anova_svm['linearsvc'].coef_)\nprint(coef)"
+        "from sklearn import svm\nfrom sklearn.datasets import make_classification\nfrom sklearn.feature_selection import SelectKBest, f_regression\nfrom sklearn.pipeline import make_pipeline\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import classification_report\n\nprint(__doc__)\n\n# import some data to play with\nX, y = make_classification(\n    n_features=20, n_informative=3, n_redundant=0, n_classes=4,\n    n_clusters_per_class=2)\n\nX_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42)\n\n# ANOVA SVM-C\n# 1) anova filter, take 3 best ranked features\nanova_filter = SelectKBest(f_regression, k=3)\n# 2) svm\nclf = svm.LinearSVC()\n\nanova_svm = make_pipeline(anova_filter, clf)\nanova_svm.fit(X_train, y_train)\ny_pred = anova_svm.predict(X_test)\nprint(classification_report(y_test, y_pred))\n\ncoef = anova_svm[:-1].inverse_transform(anova_svm['linearsvc'].coef_)\nprint(coef)"
       ]
     }
   ],

dev/_downloads/0855ac0efd714397341de370a68cf6f3/plot_mean_shift.ipynb

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "print(__doc__)\n\nimport numpy as np\nfrom sklearn.cluster import MeanShift, estimate_bandwidth\nfrom sklearn.datasets.samples_generator import make_blobs\n\n# #############################################################################\n# Generate sample data\ncenters = [[1, 1], [-1, -1], [1, -1]]\nX, _ = make_blobs(n_samples=10000, centers=centers, cluster_std=0.6)\n\n# #############################################################################\n# Compute clustering with MeanShift\n\n# The following bandwidth can be automatically detected using\nbandwidth = estimate_bandwidth(X, quantile=0.2, n_samples=500)\n\nms = MeanShift(bandwidth=bandwidth, bin_seeding=True)\nms.fit(X)\nlabels = ms.labels_\ncluster_centers = ms.cluster_centers_\n\nlabels_unique = np.unique(labels)\nn_clusters_ = len(labels_unique)\n\nprint(\"number of estimated clusters : %d\" % n_clusters_)\n\n# #############################################################################\n# Plot result\nimport matplotlib.pyplot as plt\nfrom itertools import cycle\n\nplt.figure(1)\nplt.clf()\n\ncolors = cycle('bgrcmykbgrcmykbgrcmykbgrcmyk')\nfor k, col in zip(range(n_clusters_), colors):\n    my_members = labels == k\n    cluster_center = cluster_centers[k]\n    plt.plot(X[my_members, 0], X[my_members, 1], col + '.')\n    plt.plot(cluster_center[0], cluster_center[1], 'o', markerfacecolor=col,\n             markeredgecolor='k', markersize=14)\nplt.title('Estimated number of clusters: %d' % n_clusters_)\nplt.show()"
+        "print(__doc__)\n\nimport numpy as np\nfrom sklearn.cluster import MeanShift, estimate_bandwidth\nfrom sklearn.datasets import make_blobs\n\n# #############################################################################\n# Generate sample data\ncenters = [[1, 1], [-1, -1], [1, -1]]\nX, _ = make_blobs(n_samples=10000, centers=centers, cluster_std=0.6)\n\n# #############################################################################\n# Compute clustering with MeanShift\n\n# The following bandwidth can be automatically detected using\nbandwidth = estimate_bandwidth(X, quantile=0.2, n_samples=500)\n\nms = MeanShift(bandwidth=bandwidth, bin_seeding=True)\nms.fit(X)\nlabels = ms.labels_\ncluster_centers = ms.cluster_centers_\n\nlabels_unique = np.unique(labels)\nn_clusters_ = len(labels_unique)\n\nprint(\"number of estimated clusters : %d\" % n_clusters_)\n\n# #############################################################################\n# Plot result\nimport matplotlib.pyplot as plt\nfrom itertools import cycle\n\nplt.figure(1)\nplt.clf()\n\ncolors = cycle('bgrcmykbgrcmykbgrcmykbgrcmyk')\nfor k, col in zip(range(n_clusters_), colors):\n    my_members = labels == k\n    cluster_center = cluster_centers[k]\n    plt.plot(X[my_members, 0], X[my_members, 1], col + '.')\n    plt.plot(cluster_center[0], cluster_center[1], 'o', markerfacecolor=col,\n             markeredgecolor='k', markersize=14)\nplt.title('Estimated number of clusters: %d' % n_clusters_)\nplt.show()"
       ]
     }
   ],

dev/_downloads/18e2721d4cbbd390f886d71f471ce223/plot_species_distribution_modeling.py

@@ -45,9 +45,8 @@
 import numpy as np
 import matplotlib.pyplot as plt
 
-from sklearn.datasets.base import Bunch
+from sklearn.utils import Bunch
 from sklearn.datasets import fetch_species_distributions
-from sklearn.datasets.species_distributions import construct_grids
 from sklearn import svm, metrics
 
 # if basemap is available, we'll use it.
@@ -61,6 +60,33 @@
 print(__doc__)
 
 
+def construct_grids(batch):
+    """Construct the map grid from the batch object
+
+    Parameters
+    ----------
+    batch : Batch object
+        The object returned by :func:`fetch_species_distributions`
+
+    Returns
+    -------
+    (xgrid, ygrid) : 1-D arrays
+        The grid corresponding to the values in batch.coverages
+    """
+    # x,y coordinates for corner cells
+    xmin = batch.x_left_lower_corner + batch.grid_size
+    xmax = xmin + (batch.Nx * batch.grid_size)
+    ymin = batch.y_left_lower_corner + batch.grid_size
+    ymax = ymin + (batch.Ny * batch.grid_size)
+
+    # x coordinates of the grid cells
+    xgrid = np.arange(xmin, xmax, batch.grid_size)
+    # y coordinates of the grid cells
+    ygrid = np.arange(ymin, ymax, batch.grid_size)
+
+    return (xgrid, ygrid)
+
+
 def create_species_bunch(species_name, train, test, coverages, xgrid, ygrid):
     """Create a bunch with information about a particular organism
 

dev/_downloads/27375e56cec22d4d2650b24abbf811d2/plot_lasso_dense_vs_sparse_data.py

@@ -13,7 +13,7 @@
 from scipy import sparse
 from scipy import linalg
 
-from sklearn.datasets.samples_generator import make_regression
+from sklearn.datasets import make_regression
 from sklearn.linear_model import Lasso
 
 

dev/_downloads/275c1a8902428a3a52b079bb6f13591a/plot_sgd_separating_hyperplane.py

@@ -12,7 +12,7 @@
 import numpy as np
 import matplotlib.pyplot as plt
 from sklearn.linear_model import SGDClassifier
-from sklearn.datasets.samples_generator import make_blobs
+from sklearn.datasets import make_blobs
 
 # we create 50 separable points
 X, Y = make_blobs(n_samples=50, centers=2, random_state=0, cluster_std=0.60)

dev/_downloads/2c18712ac7ff7f791c5400c9935d733d/plot_species_kde.ipynb

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "# Author: Jake Vanderplas <[email protected]>\n#\n# License: BSD 3 clause\n\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom sklearn.datasets import fetch_species_distributions\nfrom sklearn.datasets.species_distributions import construct_grids\nfrom sklearn.neighbors import KernelDensity\n\n# if basemap is available, we'll use it.\n# otherwise, we'll improvise later...\ntry:\n    from mpl_toolkits.basemap import Basemap\n    basemap = True\nexcept ImportError:\n    basemap = False\n\n# Get matrices/arrays of species IDs and locations\ndata = fetch_species_distributions()\nspecies_names = ['Bradypus Variegatus', 'Microryzomys Minutus']\n\nXtrain = np.vstack([data['train']['dd lat'],\n                    data['train']['dd long']]).T\nytrain = np.array([d.decode('ascii').startswith('micro')\n                  for d in data['train']['species']], dtype='int')\nXtrain *= np.pi / 180.  # Convert lat/long to radians\n\n# Set up the data grid for the contour plot\nxgrid, ygrid = construct_grids(data)\nX, Y = np.meshgrid(xgrid[::5], ygrid[::5][::-1])\nland_reference = data.coverages[6][::5, ::5]\nland_mask = (land_reference > -9999).ravel()\n\nxy = np.vstack([Y.ravel(), X.ravel()]).T\nxy = xy[land_mask]\nxy *= np.pi / 180.\n\n# Plot map of South America with distributions of each species\nfig = plt.figure()\nfig.subplots_adjust(left=0.05, right=0.95, wspace=0.05)\n\nfor i in range(2):\n    plt.subplot(1, 2, i + 1)\n\n    # construct a kernel density estimate of the distribution\n    print(\" - computing KDE in spherical coordinates\")\n    kde = KernelDensity(bandwidth=0.04, metric='haversine',\n                        kernel='gaussian', algorithm='ball_tree')\n    kde.fit(Xtrain[ytrain == i])\n\n    # evaluate only on the land: -9999 indicates ocean\n    Z = np.full(land_mask.shape[0], -9999, dtype='int')\n    Z[land_mask] = np.exp(kde.score_samples(xy))\n    Z = Z.reshape(X.shape)\n\n    # plot contours of the density\n    levels = np.linspace(0, Z.max(), 25)\n    plt.contourf(X, Y, Z, levels=levels, cmap=plt.cm.Reds)\n\n    if basemap:\n        print(\" - plot coastlines using basemap\")\n        m = Basemap(projection='cyl', llcrnrlat=Y.min(),\n                    urcrnrlat=Y.max(), llcrnrlon=X.min(),\n                    urcrnrlon=X.max(), resolution='c')\n        m.drawcoastlines()\n        m.drawcountries()\n    else:\n        print(\" - plot coastlines from coverage\")\n        plt.contour(X, Y, land_reference,\n                    levels=[-9998], colors=\"k\",\n                    linestyles=\"solid\")\n        plt.xticks([])\n        plt.yticks([])\n\n    plt.title(species_names[i])\n\nplt.show()"
+        "# Author: Jake Vanderplas <[email protected]>\n#\n# License: BSD 3 clause\n\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom sklearn.datasets import fetch_species_distributions\nfrom sklearn.neighbors import KernelDensity\n\n# if basemap is available, we'll use it.\n# otherwise, we'll improvise later...\ntry:\n    from mpl_toolkits.basemap import Basemap\n    basemap = True\nexcept ImportError:\n    basemap = False\n\n\ndef construct_grids(batch):\n    \"\"\"Construct the map grid from the batch object\n\n    Parameters\n    ----------\n    batch : Batch object\n        The object returned by :func:`fetch_species_distributions`\n\n    Returns\n    -------\n    (xgrid, ygrid) : 1-D arrays\n        The grid corresponding to the values in batch.coverages\n    \"\"\"\n    # x,y coordinates for corner cells\n    xmin = batch.x_left_lower_corner + batch.grid_size\n    xmax = xmin + (batch.Nx * batch.grid_size)\n    ymin = batch.y_left_lower_corner + batch.grid_size\n    ymax = ymin + (batch.Ny * batch.grid_size)\n\n    # x coordinates of the grid cells\n    xgrid = np.arange(xmin, xmax, batch.grid_size)\n    # y coordinates of the grid cells\n    ygrid = np.arange(ymin, ymax, batch.grid_size)\n\n    return (xgrid, ygrid)\n\n\n# Get matrices/arrays of species IDs and locations\ndata = fetch_species_distributions()\nspecies_names = ['Bradypus Variegatus', 'Microryzomys Minutus']\n\nXtrain = np.vstack([data['train']['dd lat'],\n                    data['train']['dd long']]).T\nytrain = np.array([d.decode('ascii').startswith('micro')\n                  for d in data['train']['species']], dtype='int')\nXtrain *= np.pi / 180.  # Convert lat/long to radians\n\n# Set up the data grid for the contour plot\nxgrid, ygrid = construct_grids(data)\nX, Y = np.meshgrid(xgrid[::5], ygrid[::5][::-1])\nland_reference = data.coverages[6][::5, ::5]\nland_mask = (land_reference > -9999).ravel()\n\nxy = np.vstack([Y.ravel(), X.ravel()]).T\nxy = xy[land_mask]\nxy *= np.pi / 180.\n\n# Plot map of South America with distributions of each species\nfig = plt.figure()\nfig.subplots_adjust(left=0.05, right=0.95, wspace=0.05)\n\nfor i in range(2):\n    plt.subplot(1, 2, i + 1)\n\n    # construct a kernel density estimate of the distribution\n    print(\" - computing KDE in spherical coordinates\")\n    kde = KernelDensity(bandwidth=0.04, metric='haversine',\n                        kernel='gaussian', algorithm='ball_tree')\n    kde.fit(Xtrain[ytrain == i])\n\n    # evaluate only on the land: -9999 indicates ocean\n    Z = np.full(land_mask.shape[0], -9999, dtype='int')\n    Z[land_mask] = np.exp(kde.score_samples(xy))\n    Z = Z.reshape(X.shape)\n\n    # plot contours of the density\n    levels = np.linspace(0, Z.max(), 25)\n    plt.contourf(X, Y, Z, levels=levels, cmap=plt.cm.Reds)\n\n    if basemap:\n        print(\" - plot coastlines using basemap\")\n        m = Basemap(projection='cyl', llcrnrlat=Y.min(),\n                    urcrnrlat=Y.max(), llcrnrlon=X.min(),\n                    urcrnrlon=X.max(), resolution='c')\n        m.drawcoastlines()\n        m.drawcountries()\n    else:\n        print(\" - plot coastlines from coverage\")\n        plt.contour(X, Y, land_reference,\n                    levels=[-9998], colors=\"k\",\n                    linestyles=\"solid\")\n        plt.xticks([])\n        plt.yticks([])\n\n    plt.title(species_names[i])\n\nplt.show()"
       ]
     }
   ],

dev/_downloads/31ed7d76091fdf7cbba173b644810790/plot_spectral_coclustering.ipynb

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "print(__doc__)\n\n# Author: Kemal Eren <[email protected]>\n# License: BSD 3 clause\n\nimport numpy as np\nfrom matplotlib import pyplot as plt\n\nfrom sklearn.datasets import make_biclusters\nfrom sklearn.datasets import samples_generator as sg\nfrom sklearn.cluster import SpectralCoclustering\nfrom sklearn.metrics import consensus_score\n\ndata, rows, columns = make_biclusters(\n    shape=(300, 300), n_clusters=5, noise=5,\n    shuffle=False, random_state=0)\n\nplt.matshow(data, cmap=plt.cm.Blues)\nplt.title(\"Original dataset\")\n\ndata, row_idx, col_idx = sg._shuffle(data, random_state=0)\nplt.matshow(data, cmap=plt.cm.Blues)\nplt.title(\"Shuffled dataset\")\n\nmodel = SpectralCoclustering(n_clusters=5, random_state=0)\nmodel.fit(data)\nscore = consensus_score(model.biclusters_,\n                        (rows[:, row_idx], columns[:, col_idx]))\n\nprint(\"consensus score: {:.3f}\".format(score))\n\nfit_data = data[np.argsort(model.row_labels_)]\nfit_data = fit_data[:, np.argsort(model.column_labels_)]\n\nplt.matshow(fit_data, cmap=plt.cm.Blues)\nplt.title(\"After biclustering; rearranged to show biclusters\")\n\nplt.show()"
+        "print(__doc__)\n\n# Author: Kemal Eren <[email protected]>\n# License: BSD 3 clause\n\nimport numpy as np\nfrom matplotlib import pyplot as plt\n\nfrom sklearn.datasets import make_biclusters\nfrom sklearn.cluster import SpectralCoclustering\nfrom sklearn.metrics import consensus_score\n\ndata, rows, columns = make_biclusters(\n    shape=(300, 300), n_clusters=5, noise=5,\n    shuffle=False, random_state=0)\n\nplt.matshow(data, cmap=plt.cm.Blues)\nplt.title(\"Original dataset\")\n\n# shuffle clusters\nrng = np.random.RandomState(0)\nrow_idx = rng.permutation(data.shape[0])\ncol_idx = rng.permutation(data.shape[1])\ndata = data[row_idx][:, col_idx]\n\nplt.matshow(data, cmap=plt.cm.Blues)\nplt.title(\"Shuffled dataset\")\n\nmodel = SpectralCoclustering(n_clusters=5, random_state=0)\nmodel.fit(data)\nscore = consensus_score(model.biclusters_,\n                        (rows[:, row_idx], columns[:, col_idx]))\n\nprint(\"consensus score: {:.3f}\".format(score))\n\nfit_data = data[np.argsort(model.row_labels_)]\nfit_data = fit_data[:, np.argsort(model.column_labels_)]\n\nplt.matshow(fit_data, cmap=plt.cm.Blues)\nplt.title(\"After biclustering; rearranged to show biclusters\")\n\nplt.show()"
       ]
     }
   ],

dev/_downloads/3409d9766d352cc9f9b169d4a799a87a/auto_examples_python.zip

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "print(__doc__)\n\nfrom time import time\nfrom scipy import sparse\nfrom scipy import linalg\n\nfrom sklearn.datasets.samples_generator import make_regression\nfrom sklearn.linear_model import Lasso\n\n\n# #############################################################################\n# The two Lasso implementations on Dense data\nprint(\"--- Dense matrices\")\n\nX, y = make_regression(n_samples=200, n_features=5000, random_state=0)\nX_sp = sparse.coo_matrix(X)\n\nalpha = 1\nsparse_lasso = Lasso(alpha=alpha, fit_intercept=False, max_iter=1000)\ndense_lasso = Lasso(alpha=alpha, fit_intercept=False, max_iter=1000)\n\nt0 = time()\nsparse_lasso.fit(X_sp, y)\nprint(\"Sparse Lasso done in %fs\" % (time() - t0))\n\nt0 = time()\ndense_lasso.fit(X, y)\nprint(\"Dense Lasso done in %fs\" % (time() - t0))\n\nprint(\"Distance between coefficients : %s\"\n      % linalg.norm(sparse_lasso.coef_ - dense_lasso.coef_))\n\n# #############################################################################\n# The two Lasso implementations on Sparse data\nprint(\"--- Sparse matrices\")\n\nXs = X.copy()\nXs[Xs < 2.5] = 0.0\nXs = sparse.coo_matrix(Xs)\nXs = Xs.tocsc()\n\nprint(\"Matrix density : %s %%\" % (Xs.nnz / float(X.size) * 100))\n\nalpha = 0.1\nsparse_lasso = Lasso(alpha=alpha, fit_intercept=False, max_iter=10000)\ndense_lasso = Lasso(alpha=alpha, fit_intercept=False, max_iter=10000)\n\nt0 = time()\nsparse_lasso.fit(Xs, y)\nprint(\"Sparse Lasso done in %fs\" % (time() - t0))\n\nt0 = time()\ndense_lasso.fit(Xs.toarray(), y)\nprint(\"Dense Lasso done in %fs\" % (time() - t0))\n\nprint(\"Distance between coefficients : %s\"\n      % linalg.norm(sparse_lasso.coef_ - dense_lasso.coef_))"
+        "print(__doc__)\n\nfrom time import time\nfrom scipy import sparse\nfrom scipy import linalg\n\nfrom sklearn.datasets import make_regression\nfrom sklearn.linear_model import Lasso\n\n\n# #############################################################################\n# The two Lasso implementations on Dense data\nprint(\"--- Dense matrices\")\n\nX, y = make_regression(n_samples=200, n_features=5000, random_state=0)\nX_sp = sparse.coo_matrix(X)\n\nalpha = 1\nsparse_lasso = Lasso(alpha=alpha, fit_intercept=False, max_iter=1000)\ndense_lasso = Lasso(alpha=alpha, fit_intercept=False, max_iter=1000)\n\nt0 = time()\nsparse_lasso.fit(X_sp, y)\nprint(\"Sparse Lasso done in %fs\" % (time() - t0))\n\nt0 = time()\ndense_lasso.fit(X, y)\nprint(\"Dense Lasso done in %fs\" % (time() - t0))\n\nprint(\"Distance between coefficients : %s\"\n      % linalg.norm(sparse_lasso.coef_ - dense_lasso.coef_))\n\n# #############################################################################\n# The two Lasso implementations on Sparse data\nprint(\"--- Sparse matrices\")\n\nXs = X.copy()\nXs[Xs < 2.5] = 0.0\nXs = sparse.coo_matrix(Xs)\nXs = Xs.tocsc()\n\nprint(\"Matrix density : %s %%\" % (Xs.nnz / float(X.size) * 100))\n\nalpha = 0.1\nsparse_lasso = Lasso(alpha=alpha, fit_intercept=False, max_iter=10000)\ndense_lasso = Lasso(alpha=alpha, fit_intercept=False, max_iter=10000)\n\nt0 = time()\nsparse_lasso.fit(Xs, y)\nprint(\"Sparse Lasso done in %fs\" % (time() - t0))\n\nt0 = time()\ndense_lasso.fit(Xs.toarray(), y)\nprint(\"Dense Lasso done in %fs\" % (time() - t0))\n\nprint(\"Distance between coefficients : %s\"\n      % linalg.norm(sparse_lasso.coef_ - dense_lasso.coef_))"
       ]
     }
   ],