Pushing the docs to dev/ for branch: main, commit d1a72af8a6d6c4350ed5bb027af794a8141a251b

Author: sklearn-ci

dev/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip

@@ -45,7 +45,7 @@
 from sklearn.kernel_ridge import KernelRidge
 import matplotlib.pyplot as plt
 
-rng = np.random.RandomState(0)
+rng = np.random.RandomState(42)
 
 # #############################################################################
 # Generate sample data
@@ -128,10 +128,10 @@
 X = 5 * rng.rand(10000, 1)
 y = np.sin(X).ravel()
 y[::5] += 3 * (0.5 - rng.rand(X.shape[0] // 5))
-sizes = np.logspace(1, 4, 7).astype(int)
+sizes = np.logspace(1, 3.8, 7).astype(int)
 for name, estimator in {
-    "KRR": KernelRidge(kernel="rbf", alpha=0.1, gamma=10),
-    "SVR": SVR(kernel="rbf", C=1e1, gamma=10),
+    "KRR": KernelRidge(kernel="rbf", alpha=0.01, gamma=10),
+    "SVR": SVR(kernel="rbf", C=1e2, gamma=10),
 }.items():
     train_time = []
     test_time = []

dev/_downloads/1dcd684ce26b8c407ec2c2d2101c5c73/plot_kernel_ridge_regression.py

@@ -24,14 +24,12 @@
 
 """
 
+# %%
+# Generate simulated data with Gaussian weights
+# ---------------------------------------------
 import numpy as np
-import matplotlib.pyplot as plt
 from scipy import stats
 
-from sklearn.linear_model import BayesianRidge, LinearRegression
-
-# #############################################################################
-# Generating simulated data with Gaussian weights
 np.random.seed(0)
 n_samples, n_features = 100, 100
 X = np.random.randn(n_samples, n_features)  # Create Gaussian data
@@ -40,6 +38,7 @@
 w = np.zeros(n_features)
 # Only keep 10 weights of interest
 relevant_features = np.random.randint(0, n_features, 10)
+
 for i in relevant_features:
     w[i] = stats.norm.rvs(loc=0, scale=1.0 / np.sqrt(lambda_))
 # Create noise with a precision alpha of 50.
@@ -48,17 +47,22 @@
 # Create the target
 y = np.dot(X, w) + noise
 
-# #############################################################################
+# %%
 # Fit the Bayesian Ridge Regression and an OLS for comparison
+# -----------------------------------------------------------
+from sklearn.linear_model import BayesianRidge, LinearRegression
+
 clf = BayesianRidge(compute_score=True)
 clf.fit(X, y)
 
 ols = LinearRegression()
 ols.fit(X, y)
 
-# #############################################################################
-# Plot true weights, estimated weights, histogram of the weights, and
-# predictions with standard deviations
+# %%
+# Plot true weights and estimated weights
+# ---------------------------------------
+import matplotlib.pyplot as plt
+
 lw = 2
 plt.figure(figsize=(6, 5))
 plt.title("Weights of the model")
@@ -67,7 +71,11 @@
 plt.plot(ols.coef_, color="navy", linestyle="--", label="OLS estimate")
 plt.xlabel("Features")
 plt.ylabel("Values of the weights")
-plt.legend(loc="best", prop=dict(size=12))
+_ = plt.legend(loc="best", prop=dict(size=12))
+
+# %%
+# Plot histogram of the weights
+# -----------------------------
 
 plt.figure(figsize=(6, 5))
 plt.title("Histogram of the weights")
@@ -80,16 +88,23 @@
 )
 plt.ylabel("Features")
 plt.xlabel("Values of the weights")
-plt.legend(loc="upper left")
+_ = plt.legend(loc="upper left")
+
+# %%
+# Plot marginal log-likelihood
+# ----------------------------
 
 plt.figure(figsize=(6, 5))
 plt.title("Marginal log-likelihood")
 plt.plot(clf.scores_, color="navy", linewidth=lw)
 plt.ylabel("Score")
-plt.xlabel("Iterations")
+_ = plt.xlabel("Iterations")
+
+# %%
+# Plot some predictions for polynomial regression with standard deviations
+# ------------------------------------------------------------------------
 
 
-# Plotting some predictions for polynomial regression
 def f(x, noise_amount):
     y = np.sqrt(x) * np.sin(x)
     noise = np.random.normal(0, 1, len(x))
@@ -117,5 +132,4 @@ def f(x, noise_amount):
 plt.plot(X_plot, y_plot, color="gold", linewidth=lw, label="Ground Truth")
 plt.ylabel("Output y")
 plt.xlabel("Feature X")
-plt.legend(loc="lower left")
-plt.show()
+_ = plt.legend(loc="lower left")

dev/_downloads/6f1e7a639e0699d6164445b55e6c116d/auto_examples_jupyter.zip

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "# Authors: Jan Hendrik Metzen <[email protected]>\n# License: BSD 3 clause\n\nimport time\n\nimport numpy as np\n\nfrom sklearn.svm import SVR\nfrom sklearn.model_selection import GridSearchCV\nfrom sklearn.model_selection import learning_curve\nfrom sklearn.kernel_ridge import KernelRidge\nimport matplotlib.pyplot as plt\n\nrng = np.random.RandomState(0)\n\n# #############################################################################\n# Generate sample data\nX = 5 * rng.rand(10000, 1)\ny = np.sin(X).ravel()\n\n# Add noise to targets\ny[::5] += 3 * (0.5 - rng.rand(X.shape[0] // 5))\n\nX_plot = np.linspace(0, 5, 100000)[:, None]\n\n# #############################################################################\n# Fit regression model\ntrain_size = 100\nsvr = GridSearchCV(\n    SVR(kernel=\"rbf\", gamma=0.1),\n    param_grid={\"C\": [1e0, 1e1, 1e2, 1e3], \"gamma\": np.logspace(-2, 2, 5)},\n)\n\nkr = GridSearchCV(\n    KernelRidge(kernel=\"rbf\", gamma=0.1),\n    param_grid={\"alpha\": [1e0, 0.1, 1e-2, 1e-3], \"gamma\": np.logspace(-2, 2, 5)},\n)\n\nt0 = time.time()\nsvr.fit(X[:train_size], y[:train_size])\nsvr_fit = time.time() - t0\nprint(\"SVR complexity and bandwidth selected and model fitted in %.3f s\" % svr_fit)\n\nt0 = time.time()\nkr.fit(X[:train_size], y[:train_size])\nkr_fit = time.time() - t0\nprint(\"KRR complexity and bandwidth selected and model fitted in %.3f s\" % kr_fit)\n\nsv_ratio = svr.best_estimator_.support_.shape[0] / train_size\nprint(\"Support vector ratio: %.3f\" % sv_ratio)\n\nt0 = time.time()\ny_svr = svr.predict(X_plot)\nsvr_predict = time.time() - t0\nprint(\"SVR prediction for %d inputs in %.3f s\" % (X_plot.shape[0], svr_predict))\n\nt0 = time.time()\ny_kr = kr.predict(X_plot)\nkr_predict = time.time() - t0\nprint(\"KRR prediction for %d inputs in %.3f s\" % (X_plot.shape[0], kr_predict))\n\n\n# #############################################################################\n# Look at the results\nsv_ind = svr.best_estimator_.support_\nplt.scatter(\n    X[sv_ind],\n    y[sv_ind],\n    c=\"r\",\n    s=50,\n    label=\"SVR support vectors\",\n    zorder=2,\n    edgecolors=(0, 0, 0),\n)\nplt.scatter(X[:100], y[:100], c=\"k\", label=\"data\", zorder=1, edgecolors=(0, 0, 0))\nplt.plot(\n    X_plot,\n    y_svr,\n    c=\"r\",\n    label=\"SVR (fit: %.3fs, predict: %.3fs)\" % (svr_fit, svr_predict),\n)\nplt.plot(\n    X_plot, y_kr, c=\"g\", label=\"KRR (fit: %.3fs, predict: %.3fs)\" % (kr_fit, kr_predict)\n)\nplt.xlabel(\"data\")\nplt.ylabel(\"target\")\nplt.title(\"SVR versus Kernel Ridge\")\nplt.legend()\n\n# Visualize training and prediction time\nplt.figure()\n\n# Generate sample data\nX = 5 * rng.rand(10000, 1)\ny = np.sin(X).ravel()\ny[::5] += 3 * (0.5 - rng.rand(X.shape[0] // 5))\nsizes = np.logspace(1, 4, 7).astype(int)\nfor name, estimator in {\n    \"KRR\": KernelRidge(kernel=\"rbf\", alpha=0.1, gamma=10),\n    \"SVR\": SVR(kernel=\"rbf\", C=1e1, gamma=10),\n}.items():\n    train_time = []\n    test_time = []\n    for train_test_size in sizes:\n        t0 = time.time()\n        estimator.fit(X[:train_test_size], y[:train_test_size])\n        train_time.append(time.time() - t0)\n\n        t0 = time.time()\n        estimator.predict(X_plot[:1000])\n        test_time.append(time.time() - t0)\n\n    plt.plot(\n        sizes,\n        train_time,\n        \"o-\",\n        color=\"r\" if name == \"SVR\" else \"g\",\n        label=\"%s (train)\" % name,\n    )\n    plt.plot(\n        sizes,\n        test_time,\n        \"o--\",\n        color=\"r\" if name == \"SVR\" else \"g\",\n        label=\"%s (test)\" % name,\n    )\n\nplt.xscale(\"log\")\nplt.yscale(\"log\")\nplt.xlabel(\"Train size\")\nplt.ylabel(\"Time (seconds)\")\nplt.title(\"Execution Time\")\nplt.legend(loc=\"best\")\n\n# Visualize learning curves\nplt.figure()\n\nsvr = SVR(kernel=\"rbf\", C=1e1, gamma=0.1)\nkr = KernelRidge(kernel=\"rbf\", alpha=0.1, gamma=0.1)\ntrain_sizes, train_scores_svr, test_scores_svr = learning_curve(\n    svr,\n    X[:100],\n    y[:100],\n    train_sizes=np.linspace(0.1, 1, 10),\n    scoring=\"neg_mean_squared_error\",\n    cv=10,\n)\ntrain_sizes_abs, train_scores_kr, test_scores_kr = learning_curve(\n    kr,\n    X[:100],\n    y[:100],\n    train_sizes=np.linspace(0.1, 1, 10),\n    scoring=\"neg_mean_squared_error\",\n    cv=10,\n)\n\nplt.plot(train_sizes, -test_scores_svr.mean(1), \"o-\", color=\"r\", label=\"SVR\")\nplt.plot(train_sizes, -test_scores_kr.mean(1), \"o-\", color=\"g\", label=\"KRR\")\nplt.xlabel(\"Train size\")\nplt.ylabel(\"Mean Squared Error\")\nplt.title(\"Learning curves\")\nplt.legend(loc=\"best\")\n\nplt.show()"
+        "# Authors: Jan Hendrik Metzen <[email protected]>\n# License: BSD 3 clause\n\nimport time\n\nimport numpy as np\n\nfrom sklearn.svm import SVR\nfrom sklearn.model_selection import GridSearchCV\nfrom sklearn.model_selection import learning_curve\nfrom sklearn.kernel_ridge import KernelRidge\nimport matplotlib.pyplot as plt\n\nrng = np.random.RandomState(42)\n\n# #############################################################################\n# Generate sample data\nX = 5 * rng.rand(10000, 1)\ny = np.sin(X).ravel()\n\n# Add noise to targets\ny[::5] += 3 * (0.5 - rng.rand(X.shape[0] // 5))\n\nX_plot = np.linspace(0, 5, 100000)[:, None]\n\n# #############################################################################\n# Fit regression model\ntrain_size = 100\nsvr = GridSearchCV(\n    SVR(kernel=\"rbf\", gamma=0.1),\n    param_grid={\"C\": [1e0, 1e1, 1e2, 1e3], \"gamma\": np.logspace(-2, 2, 5)},\n)\n\nkr = GridSearchCV(\n    KernelRidge(kernel=\"rbf\", gamma=0.1),\n    param_grid={\"alpha\": [1e0, 0.1, 1e-2, 1e-3], \"gamma\": np.logspace(-2, 2, 5)},\n)\n\nt0 = time.time()\nsvr.fit(X[:train_size], y[:train_size])\nsvr_fit = time.time() - t0\nprint(\"SVR complexity and bandwidth selected and model fitted in %.3f s\" % svr_fit)\n\nt0 = time.time()\nkr.fit(X[:train_size], y[:train_size])\nkr_fit = time.time() - t0\nprint(\"KRR complexity and bandwidth selected and model fitted in %.3f s\" % kr_fit)\n\nsv_ratio = svr.best_estimator_.support_.shape[0] / train_size\nprint(\"Support vector ratio: %.3f\" % sv_ratio)\n\nt0 = time.time()\ny_svr = svr.predict(X_plot)\nsvr_predict = time.time() - t0\nprint(\"SVR prediction for %d inputs in %.3f s\" % (X_plot.shape[0], svr_predict))\n\nt0 = time.time()\ny_kr = kr.predict(X_plot)\nkr_predict = time.time() - t0\nprint(\"KRR prediction for %d inputs in %.3f s\" % (X_plot.shape[0], kr_predict))\n\n\n# #############################################################################\n# Look at the results\nsv_ind = svr.best_estimator_.support_\nplt.scatter(\n    X[sv_ind],\n    y[sv_ind],\n    c=\"r\",\n    s=50,\n    label=\"SVR support vectors\",\n    zorder=2,\n    edgecolors=(0, 0, 0),\n)\nplt.scatter(X[:100], y[:100], c=\"k\", label=\"data\", zorder=1, edgecolors=(0, 0, 0))\nplt.plot(\n    X_plot,\n    y_svr,\n    c=\"r\",\n    label=\"SVR (fit: %.3fs, predict: %.3fs)\" % (svr_fit, svr_predict),\n)\nplt.plot(\n    X_plot, y_kr, c=\"g\", label=\"KRR (fit: %.3fs, predict: %.3fs)\" % (kr_fit, kr_predict)\n)\nplt.xlabel(\"data\")\nplt.ylabel(\"target\")\nplt.title(\"SVR versus Kernel Ridge\")\nplt.legend()\n\n# Visualize training and prediction time\nplt.figure()\n\n# Generate sample data\nX = 5 * rng.rand(10000, 1)\ny = np.sin(X).ravel()\ny[::5] += 3 * (0.5 - rng.rand(X.shape[0] // 5))\nsizes = np.logspace(1, 3.8, 7).astype(int)\nfor name, estimator in {\n    \"KRR\": KernelRidge(kernel=\"rbf\", alpha=0.01, gamma=10),\n    \"SVR\": SVR(kernel=\"rbf\", C=1e2, gamma=10),\n}.items():\n    train_time = []\n    test_time = []\n    for train_test_size in sizes:\n        t0 = time.time()\n        estimator.fit(X[:train_test_size], y[:train_test_size])\n        train_time.append(time.time() - t0)\n\n        t0 = time.time()\n        estimator.predict(X_plot[:1000])\n        test_time.append(time.time() - t0)\n\n    plt.plot(\n        sizes,\n        train_time,\n        \"o-\",\n        color=\"r\" if name == \"SVR\" else \"g\",\n        label=\"%s (train)\" % name,\n    )\n    plt.plot(\n        sizes,\n        test_time,\n        \"o--\",\n        color=\"r\" if name == \"SVR\" else \"g\",\n        label=\"%s (test)\" % name,\n    )\n\nplt.xscale(\"log\")\nplt.yscale(\"log\")\nplt.xlabel(\"Train size\")\nplt.ylabel(\"Time (seconds)\")\nplt.title(\"Execution Time\")\nplt.legend(loc=\"best\")\n\n# Visualize learning curves\nplt.figure()\n\nsvr = SVR(kernel=\"rbf\", C=1e1, gamma=0.1)\nkr = KernelRidge(kernel=\"rbf\", alpha=0.1, gamma=0.1)\ntrain_sizes, train_scores_svr, test_scores_svr = learning_curve(\n    svr,\n    X[:100],\n    y[:100],\n    train_sizes=np.linspace(0.1, 1, 10),\n    scoring=\"neg_mean_squared_error\",\n    cv=10,\n)\ntrain_sizes_abs, train_scores_kr, test_scores_kr = learning_curve(\n    kr,\n    X[:100],\n    y[:100],\n    train_sizes=np.linspace(0.1, 1, 10),\n    scoring=\"neg_mean_squared_error\",\n    cv=10,\n)\n\nplt.plot(train_sizes, -test_scores_svr.mean(1), \"o-\", color=\"r\", label=\"SVR\")\nplt.plot(train_sizes, -test_scores_kr.mean(1), \"o-\", color=\"g\", label=\"KRR\")\nplt.xlabel(\"Train size\")\nplt.ylabel(\"Mean Squared Error\")\nplt.title(\"Learning curves\")\nplt.legend(loc=\"best\")\n\nplt.show()"
       ]
     }
   ],