Pushing the docs to dev/ for branch: master, commit adddf00433a961dc1186f91d791a11230f38840e

Author: sklearn-ci

dev/_downloads/auto_examples_jupyter.zip

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "print(__doc__)\n\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom scipy import stats\n\nfrom sklearn.linear_model import ARDRegression, LinearRegression\n\n# #############################################################################\n# Generating simulated data with Gaussian weights\n\n# Parameters of the example\nnp.random.seed(0)\nn_samples, n_features = 100, 100\n# Create Gaussian data\nX = np.random.randn(n_samples, n_features)\n# Create weights with a precision lambda_ of 4.\nlambda_ = 4.\nw = np.zeros(n_features)\n# Only keep 10 weights of interest\nrelevant_features = np.random.randint(0, n_features, 10)\nfor i in relevant_features:\n    w[i] = stats.norm.rvs(loc=0, scale=1. / np.sqrt(lambda_))\n# Create noise with a precision alpha of 50.\nalpha_ = 50.\nnoise = stats.norm.rvs(loc=0, scale=1. / np.sqrt(alpha_), size=n_samples)\n# Create the target\ny = np.dot(X, w) + noise\n\n# #############################################################################\n# Fit the ARD Regression\nclf = ARDRegression(compute_score=True)\nclf.fit(X, y)\n\nols = LinearRegression()\nols.fit(X, y)\n\n# #############################################################################\n# Plot the true weights, the estimated weights, the histogram of the\n# weights, and predictions with standard deviations\nplt.figure(figsize=(6, 5))\nplt.title(\"Weights of the model\")\nplt.plot(clf.coef_, color='darkblue', linestyle='-', linewidth=2,\n         label=\"ARD estimate\")\nplt.plot(ols.coef_, color='yellowgreen', linestyle=':', linewidth=2,\n         label=\"OLS estimate\")\nplt.plot(w, color='orange', linestyle='-', linewidth=2, label=\"Ground truth\")\nplt.xlabel(\"Features\")\nplt.ylabel(\"Values of the weights\")\nplt.legend(loc=1)\n\nplt.figure(figsize=(6, 5))\nplt.title(\"Histogram of the weights\")\nplt.hist(clf.coef_, bins=n_features, color='navy', log=True)\nplt.scatter(clf.coef_[relevant_features], 5 * np.ones(len(relevant_features)),\n            color='gold', marker='o', label=\"Relevant features\")\nplt.ylabel(\"Features\")\nplt.xlabel(\"Values of the weights\")\nplt.legend(loc=1)\n\nplt.figure(figsize=(6, 5))\nplt.title(\"Marginal log-likelihood\")\nplt.plot(clf.scores_, color='navy', linewidth=2)\nplt.ylabel(\"Score\")\nplt.xlabel(\"Iterations\")\n\n\n# Plotting some predictions for polynomial regression\ndef f(x, noise_amount):\n    y = np.sqrt(x) * np.sin(x)\n    noise = np.random.normal(0, 1, len(x))\n    return y + noise_amount * noise\n\n\ndegree = 10\nX = np.linspace(0, 10, 100)\ny = f(X, noise_amount=1)\nclf_poly = ARDRegression(threshold_lambda=1e5)\nclf_poly.fit(np.vander(X, degree), y)\n\nX_plot = np.linspace(0, 11, 25)\ny_plot = f(X_plot, noise_amount=0)\ny_mean, y_std = clf_poly.predict(np.vander(X_plot, degree), return_std=True)\nplt.figure(figsize=(6, 5))\nplt.errorbar(X_plot, y_mean, y_std, color='navy',\n             label=\"Polynomial ARD\", linewidth=2)\nplt.plot(X_plot, y_plot, color='gold', linewidth=2,\n         label=\"Ground Truth\")\nplt.ylabel(\"Output y\")\nplt.xlabel(\"Feature X\")\nplt.legend(loc=\"lower left\")\nplt.show()"
+        "print(__doc__)\n\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom scipy import stats\n\nfrom sklearn.linear_model import ARDRegression, LinearRegression\n\n# #############################################################################\n# Generating simulated data with Gaussian weights\n\n# Parameters of the example\nnp.random.seed(0)\nn_samples, n_features = 100, 100\n# Create Gaussian data\nX = np.random.randn(n_samples, n_features)\n# Create weights with a precision lambda_ of 4.\nlambda_ = 4.\nw = np.zeros(n_features)\n# Only keep 10 weights of interest\nrelevant_features = np.random.randint(0, n_features, 10)\nfor i in relevant_features:\n    w[i] = stats.norm.rvs(loc=0, scale=1. / np.sqrt(lambda_))\n# Create noise with a precision alpha of 50.\nalpha_ = 50.\nnoise = stats.norm.rvs(loc=0, scale=1. / np.sqrt(alpha_), size=n_samples)\n# Create the target\ny = np.dot(X, w) + noise\n\n# #############################################################################\n# Fit the ARD Regression\nclf = ARDRegression(compute_score=True)\nclf.fit(X, y)\n\nols = LinearRegression()\nols.fit(X, y)\n\n# #############################################################################\n# Plot the true weights, the estimated weights, the histogram of the\n# weights, and predictions with standard deviations\nplt.figure(figsize=(6, 5))\nplt.title(\"Weights of the model\")\nplt.plot(clf.coef_, color='darkblue', linestyle='-', linewidth=2,\n         label=\"ARD estimate\")\nplt.plot(ols.coef_, color='yellowgreen', linestyle=':', linewidth=2,\n         label=\"OLS estimate\")\nplt.plot(w, color='orange', linestyle='-', linewidth=2, label=\"Ground truth\")\nplt.xlabel(\"Features\")\nplt.ylabel(\"Values of the weights\")\nplt.legend(loc=1)\n\nplt.figure(figsize=(6, 5))\nplt.title(\"Histogram of the weights\")\nplt.hist(clf.coef_, bins=n_features, color='navy', log=True)\nplt.scatter(clf.coef_[relevant_features], np.full(len(relevant_features), 5.),\n            color='gold', marker='o', label=\"Relevant features\")\nplt.ylabel(\"Features\")\nplt.xlabel(\"Values of the weights\")\nplt.legend(loc=1)\n\nplt.figure(figsize=(6, 5))\nplt.title(\"Marginal log-likelihood\")\nplt.plot(clf.scores_, color='navy', linewidth=2)\nplt.ylabel(\"Score\")\nplt.xlabel(\"Iterations\")\n\n\n# Plotting some predictions for polynomial regression\ndef f(x, noise_amount):\n    y = np.sqrt(x) * np.sin(x)\n    noise = np.random.normal(0, 1, len(x))\n    return y + noise_amount * noise\n\n\ndegree = 10\nX = np.linspace(0, 10, 100)\ny = f(X, noise_amount=1)\nclf_poly = ARDRegression(threshold_lambda=1e5)\nclf_poly.fit(np.vander(X, degree), y)\n\nX_plot = np.linspace(0, 11, 25)\ny_plot = f(X_plot, noise_amount=0)\ny_mean, y_std = clf_poly.predict(np.vander(X_plot, degree), return_std=True)\nplt.figure(figsize=(6, 5))\nplt.errorbar(X_plot, y_mean, y_std, color='navy',\n             label=\"Polynomial ARD\", linewidth=2)\nplt.plot(X_plot, y_plot, color='gold', linewidth=2,\n         label=\"Ground Truth\")\nplt.ylabel(\"Output y\")\nplt.xlabel(\"Feature X\")\nplt.legend(loc=\"lower left\")\nplt.show()"
       ]
     }
   ],

dev/_downloads/auto_examples_python.zip

@@ -76,7 +76,7 @@
 plt.figure(figsize=(6, 5))
 plt.title("Histogram of the weights")
 plt.hist(clf.coef_, bins=n_features, color='navy', log=True)
-plt.scatter(clf.coef_[relevant_features], 5 * np.ones(len(relevant_features)),
+plt.scatter(clf.coef_[relevant_features], np.full(len(relevant_features), 5.),
             color='gold', marker='o', label="Relevant features")
 plt.ylabel("Features")
 plt.xlabel("Values of the weights")

dev/_downloads/plot_ard.ipynb

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "print(__doc__)\n\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom scipy import stats\n\nfrom sklearn.linear_model import BayesianRidge, LinearRegression\n\n# #############################################################################\n# Generating simulated data with Gaussian weights\nnp.random.seed(0)\nn_samples, n_features = 100, 100\nX = np.random.randn(n_samples, n_features)  # Create Gaussian data\n# Create weights with a precision lambda_ of 4.\nlambda_ = 4.\nw = np.zeros(n_features)\n# Only keep 10 weights of interest\nrelevant_features = np.random.randint(0, n_features, 10)\nfor i in relevant_features:\n    w[i] = stats.norm.rvs(loc=0, scale=1. / np.sqrt(lambda_))\n# Create noise with a precision alpha of 50.\nalpha_ = 50.\nnoise = stats.norm.rvs(loc=0, scale=1. / np.sqrt(alpha_), size=n_samples)\n# Create the target\ny = np.dot(X, w) + noise\n\n# #############################################################################\n# Fit the Bayesian Ridge Regression and an OLS for comparison\nclf = BayesianRidge(compute_score=True)\nclf.fit(X, y)\n\nols = LinearRegression()\nols.fit(X, y)\n\n# #############################################################################\n# Plot true weights, estimated weights, histogram of the weights, and\n# predictions with standard deviations\nlw = 2\nplt.figure(figsize=(6, 5))\nplt.title(\"Weights of the model\")\nplt.plot(clf.coef_, color='lightgreen', linewidth=lw,\n         label=\"Bayesian Ridge estimate\")\nplt.plot(w, color='gold', linewidth=lw, label=\"Ground truth\")\nplt.plot(ols.coef_, color='navy', linestyle='--', label=\"OLS estimate\")\nplt.xlabel(\"Features\")\nplt.ylabel(\"Values of the weights\")\nplt.legend(loc=\"best\", prop=dict(size=12))\n\nplt.figure(figsize=(6, 5))\nplt.title(\"Histogram of the weights\")\nplt.hist(clf.coef_, bins=n_features, color='gold', log=True,\n         edgecolor='black')\nplt.scatter(clf.coef_[relevant_features], 5 * np.ones(len(relevant_features)),\n            color='navy', label=\"Relevant features\")\nplt.ylabel(\"Features\")\nplt.xlabel(\"Values of the weights\")\nplt.legend(loc=\"upper left\")\n\nplt.figure(figsize=(6, 5))\nplt.title(\"Marginal log-likelihood\")\nplt.plot(clf.scores_, color='navy', linewidth=lw)\nplt.ylabel(\"Score\")\nplt.xlabel(\"Iterations\")\n\n\n# Plotting some predictions for polynomial regression\ndef f(x, noise_amount):\n    y = np.sqrt(x) * np.sin(x)\n    noise = np.random.normal(0, 1, len(x))\n    return y + noise_amount * noise\n\n\ndegree = 10\nX = np.linspace(0, 10, 100)\ny = f(X, noise_amount=0.1)\nclf_poly = BayesianRidge()\nclf_poly.fit(np.vander(X, degree), y)\n\nX_plot = np.linspace(0, 11, 25)\ny_plot = f(X_plot, noise_amount=0)\ny_mean, y_std = clf_poly.predict(np.vander(X_plot, degree), return_std=True)\nplt.figure(figsize=(6, 5))\nplt.errorbar(X_plot, y_mean, y_std, color='navy',\n             label=\"Polynomial Bayesian Ridge Regression\", linewidth=lw)\nplt.plot(X_plot, y_plot, color='gold', linewidth=lw,\n         label=\"Ground Truth\")\nplt.ylabel(\"Output y\")\nplt.xlabel(\"Feature X\")\nplt.legend(loc=\"lower left\")\nplt.show()"
+        "print(__doc__)\n\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom scipy import stats\n\nfrom sklearn.linear_model import BayesianRidge, LinearRegression\n\n# #############################################################################\n# Generating simulated data with Gaussian weights\nnp.random.seed(0)\nn_samples, n_features = 100, 100\nX = np.random.randn(n_samples, n_features)  # Create Gaussian data\n# Create weights with a precision lambda_ of 4.\nlambda_ = 4.\nw = np.zeros(n_features)\n# Only keep 10 weights of interest\nrelevant_features = np.random.randint(0, n_features, 10)\nfor i in relevant_features:\n    w[i] = stats.norm.rvs(loc=0, scale=1. / np.sqrt(lambda_))\n# Create noise with a precision alpha of 50.\nalpha_ = 50.\nnoise = stats.norm.rvs(loc=0, scale=1. / np.sqrt(alpha_), size=n_samples)\n# Create the target\ny = np.dot(X, w) + noise\n\n# #############################################################################\n# Fit the Bayesian Ridge Regression and an OLS for comparison\nclf = BayesianRidge(compute_score=True)\nclf.fit(X, y)\n\nols = LinearRegression()\nols.fit(X, y)\n\n# #############################################################################\n# Plot true weights, estimated weights, histogram of the weights, and\n# predictions with standard deviations\nlw = 2\nplt.figure(figsize=(6, 5))\nplt.title(\"Weights of the model\")\nplt.plot(clf.coef_, color='lightgreen', linewidth=lw,\n         label=\"Bayesian Ridge estimate\")\nplt.plot(w, color='gold', linewidth=lw, label=\"Ground truth\")\nplt.plot(ols.coef_, color='navy', linestyle='--', label=\"OLS estimate\")\nplt.xlabel(\"Features\")\nplt.ylabel(\"Values of the weights\")\nplt.legend(loc=\"best\", prop=dict(size=12))\n\nplt.figure(figsize=(6, 5))\nplt.title(\"Histogram of the weights\")\nplt.hist(clf.coef_, bins=n_features, color='gold', log=True,\n         edgecolor='black')\nplt.scatter(clf.coef_[relevant_features], np.full(len(relevant_features), 5.),\n            color='navy', label=\"Relevant features\")\nplt.ylabel(\"Features\")\nplt.xlabel(\"Values of the weights\")\nplt.legend(loc=\"upper left\")\n\nplt.figure(figsize=(6, 5))\nplt.title(\"Marginal log-likelihood\")\nplt.plot(clf.scores_, color='navy', linewidth=lw)\nplt.ylabel(\"Score\")\nplt.xlabel(\"Iterations\")\n\n\n# Plotting some predictions for polynomial regression\ndef f(x, noise_amount):\n    y = np.sqrt(x) * np.sin(x)\n    noise = np.random.normal(0, 1, len(x))\n    return y + noise_amount * noise\n\n\ndegree = 10\nX = np.linspace(0, 10, 100)\ny = f(X, noise_amount=0.1)\nclf_poly = BayesianRidge()\nclf_poly.fit(np.vander(X, degree), y)\n\nX_plot = np.linspace(0, 11, 25)\ny_plot = f(X_plot, noise_amount=0)\ny_mean, y_std = clf_poly.predict(np.vander(X_plot, degree), return_std=True)\nplt.figure(figsize=(6, 5))\nplt.errorbar(X_plot, y_mean, y_std, color='navy',\n             label=\"Polynomial Bayesian Ridge Regression\", linewidth=lw)\nplt.plot(X_plot, y_plot, color='gold', linewidth=lw,\n         label=\"Ground Truth\")\nplt.ylabel(\"Output y\")\nplt.xlabel(\"Feature X\")\nplt.legend(loc=\"lower left\")\nplt.show()"
       ]
     }
   ],

dev/_downloads/plot_ard.py

@@ -74,7 +74,7 @@
 plt.title("Histogram of the weights")
 plt.hist(clf.coef_, bins=n_features, color='gold', log=True,
          edgecolor='black')
-plt.scatter(clf.coef_[relevant_features], 5 * np.ones(len(relevant_features)),
+plt.scatter(clf.coef_[relevant_features], np.full(len(relevant_features), 5.),
             color='navy', label="Relevant features")
 plt.ylabel("Features")
 plt.xlabel("Values of the weights")