Pushing the docs to dev/ for branch: main, commit 835904a7642b6d14b230b11b7038de07d1f9b29f

Author: sklearn-ci

dev/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip

@@ -26,7 +26,61 @@
       },
       "outputs": [],
       "source": [
-        "# Author: Alexandre Gramfort <alexandre.gramfort@inria.fr>\n# License: BSD 3 clause\n\nimport numpy as np\nfrom sklearn import linear_model\n\n# #############################################################################\n# Generate sample data\nn_samples_train, n_samples_test, n_features = 75, 150, 500\nnp.random.seed(0)\ncoef = np.random.randn(n_features)\ncoef[50:] = 0.0  # only the top 10 features are impacting the model\nX = np.random.randn(n_samples_train + n_samples_test, n_features)\ny = np.dot(X, coef)\n\n# Split train and test data\nX_train, X_test = X[:n_samples_train], X[n_samples_train:]\ny_train, y_test = y[:n_samples_train], y[n_samples_train:]\n\n# #############################################################################\n# Compute train and test errors\nalphas = np.logspace(-5, 1, 60)\nenet = linear_model.ElasticNet(l1_ratio=0.7, max_iter=10000)\ntrain_errors = list()\ntest_errors = list()\nfor alpha in alphas:\n    enet.set_params(alpha=alpha)\n    enet.fit(X_train, y_train)\n    train_errors.append(enet.score(X_train, y_train))\n    test_errors.append(enet.score(X_test, y_test))\n\ni_alpha_optim = np.argmax(test_errors)\nalpha_optim = alphas[i_alpha_optim]\nprint(\"Optimal regularization parameter : %s\" % alpha_optim)\n\n# Estimate the coef_ on full data with optimal regularization parameter\nenet.set_params(alpha=alpha_optim)\ncoef_ = enet.fit(X, y).coef_\n\n# #############################################################################\n# Plot results functions\n\nimport matplotlib.pyplot as plt\n\nplt.subplot(2, 1, 1)\nplt.semilogx(alphas, train_errors, label=\"Train\")\nplt.semilogx(alphas, test_errors, label=\"Test\")\nplt.vlines(\n    alpha_optim,\n    plt.ylim()[0],\n    np.max(test_errors),\n    color=\"k\",\n    linewidth=3,\n    label=\"Optimum on test\",\n)\nplt.legend(loc=\"lower left\")\nplt.ylim([0, 1.2])\nplt.xlabel(\"Regularization parameter\")\nplt.ylabel(\"Performance\")\n\n# Show estimated coef_ vs true coef\nplt.subplot(2, 1, 2)\nplt.plot(coef, label=\"True coef\")\nplt.plot(coef_, label=\"Estimated coef\")\nplt.legend()\nplt.subplots_adjust(0.09, 0.04, 0.94, 0.94, 0.26, 0.26)\nplt.show()"
+        "# Author: Alexandre Gramfort <alexandre.gramfort@inria.fr>\n# License: BSD 3 clause"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Generate sample data\n\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "collapsed": false
+      },
+      "outputs": [],
+      "source": [
+        "import numpy as np\nfrom sklearn import linear_model\nfrom sklearn.datasets import make_regression\nfrom sklearn.model_selection import train_test_split\n\nn_samples_train, n_samples_test, n_features = 75, 150, 500\nX, y, coef = make_regression(\n    n_samples=n_samples_train + n_samples_test,\n    n_features=n_features,\n    n_informative=50,\n    shuffle=False,\n    noise=1.0,\n    coef=True,\n)\nX_train, X_test, y_train, y_test = train_test_split(\n    X, y, train_size=n_samples_train, test_size=n_samples_test, shuffle=False\n)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Compute train and test errors\n\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "collapsed": false
+      },
+      "outputs": [],
+      "source": [
+        "alphas = np.logspace(-5, 1, 60)\nenet = linear_model.ElasticNet(l1_ratio=0.7, max_iter=10000)\ntrain_errors = list()\ntest_errors = list()\nfor alpha in alphas:\n    enet.set_params(alpha=alpha)\n    enet.fit(X_train, y_train)\n    train_errors.append(enet.score(X_train, y_train))\n    test_errors.append(enet.score(X_test, y_test))\n\ni_alpha_optim = np.argmax(test_errors)\nalpha_optim = alphas[i_alpha_optim]\nprint(\"Optimal regularization parameter : %s\" % alpha_optim)\n\n# Estimate the coef_ on full data with optimal regularization parameter\nenet.set_params(alpha=alpha_optim)\ncoef_ = enet.fit(X, y).coef_"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Plot results functions\n\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "collapsed": false
+      },
+      "outputs": [],
+      "source": [
+        "import matplotlib.pyplot as plt\n\nplt.subplot(2, 1, 1)\nplt.semilogx(alphas, train_errors, label=\"Train\")\nplt.semilogx(alphas, test_errors, label=\"Test\")\nplt.vlines(\n    alpha_optim,\n    plt.ylim()[0],\n    np.max(test_errors),\n    color=\"k\",\n    linewidth=3,\n    label=\"Optimum on test\",\n)\nplt.legend(loc=\"lower left\")\nplt.ylim([0, 1.2])\nplt.xlabel(\"Regularization parameter\")\nplt.ylabel(\"Performance\")\n\n# Show estimated coef_ vs true coef\nplt.subplot(2, 1, 2)\nplt.plot(coef, label=\"True coef\")\nplt.plot(coef_, label=\"Estimated coef\")\nplt.legend()\nplt.subplots_adjust(0.09, 0.04, 0.94, 0.94, 0.26, 0.26)\nplt.show()"
       ]
     }
   ],

dev/_downloads/6f1e7a639e0699d6164445b55e6c116d/auto_examples_jupyter.zip

@@ -15,24 +15,29 @@
 # Author: Alexandre Gramfort <alexandre.gramfort@inria.fr>
 # License: BSD 3 clause
 
+# %%
+# Generate sample data
+# --------------------
 import numpy as np
 from sklearn import linear_model
+from sklearn.datasets import make_regression
+from sklearn.model_selection import train_test_split
 
-# #############################################################################
-# Generate sample data
 n_samples_train, n_samples_test, n_features = 75, 150, 500
-np.random.seed(0)
-coef = np.random.randn(n_features)
-coef[50:] = 0.0  # only the top 10 features are impacting the model
-X = np.random.randn(n_samples_train + n_samples_test, n_features)
-y = np.dot(X, coef)
-
-# Split train and test data
-X_train, X_test = X[:n_samples_train], X[n_samples_train:]
-y_train, y_test = y[:n_samples_train], y[n_samples_train:]
-
-# #############################################################################
+X, y, coef = make_regression(
+    n_samples=n_samples_train + n_samples_test,
+    n_features=n_features,
+    n_informative=50,
+    shuffle=False,
+    noise=1.0,
+    coef=True,
+)
+X_train, X_test, y_train, y_test = train_test_split(
+    X, y, train_size=n_samples_train, test_size=n_samples_test, shuffle=False
+)
+# %%
 # Compute train and test errors
+# -----------------------------
 alphas = np.logspace(-5, 1, 60)
 enet = linear_model.ElasticNet(l1_ratio=0.7, max_iter=10000)
 train_errors = list()
@@ -51,8 +56,9 @@
 enet.set_params(alpha=alpha_optim)
 coef_ = enet.fit(X, y).coef_
 
-# #############################################################################
+# %%
 # Plot results functions
+# ----------------------
 
 import matplotlib.pyplot as plt