Pushing the docs to dev/ for branch: main, commit 4f70d8585ba4107a190ccadae7f20adbc4e47e46

Author: sklearn-ci

dev/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip

@@ -30,7 +30,7 @@
 
 from sklearn.linear_model import ARDRegression, LinearRegression
 
-# #############################################################################
+# %%
 # Generating simulated data with Gaussian weights
 
 # Parameters of the example
@@ -51,15 +51,15 @@
 # Create the target
 y = np.dot(X, w) + noise
 
-# #############################################################################
+# %%
 # Fit the ARD Regression
 clf = ARDRegression(compute_score=True)
 clf.fit(X, y)
 
 ols = LinearRegression()
 ols.fit(X, y)
 
-# #############################################################################
+# %%
 # Plot the true weights, the estimated weights, the histogram of the
 # weights, and predictions with standard deviations
 plt.figure(figsize=(6, 5))

dev/_downloads/6f1e7a639e0699d6164445b55e6c116d/auto_examples_jupyter.zip

@@ -26,7 +26,61 @@
       },
       "outputs": [],
       "source": [
-        "import 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_ = 4.0\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=1.0 / np.sqrt(lambda_))\n# Create noise with a precision alpha of 50.\nalpha_ = 50.0\nnoise = stats.norm.rvs(loc=0, scale=1.0 / 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, label=\"ARD estimate\")\nplt.plot(\n    ols.coef_, color=\"yellowgreen\", linestyle=\":\", linewidth=2, label=\"OLS estimate\"\n)\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(\n    clf.coef_[relevant_features],\n    np.full(len(relevant_features), 5.0),\n    color=\"gold\",\n    marker=\"o\",\n    label=\"Relevant features\",\n)\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\", label=\"Polynomial ARD\", linewidth=2)\nplt.plot(X_plot, y_plot, color=\"gold\", linewidth=2, label=\"Ground Truth\")\nplt.ylabel(\"Output y\")\nplt.xlabel(\"Feature X\")\nplt.legend(loc=\"lower left\")\nplt.show()"
+        "import numpy as np\nimport matplotlib.pyplot as plt\nfrom scipy import stats\n\nfrom sklearn.linear_model import ARDRegression, LinearRegression"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Generating simulated data with Gaussian weights\n\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "collapsed": false
+      },
+      "outputs": [],
+      "source": [
+        "# 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_ = 4.0\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=1.0 / np.sqrt(lambda_))\n# Create noise with a precision alpha of 50.\nalpha_ = 50.0\nnoise = stats.norm.rvs(loc=0, scale=1.0 / np.sqrt(alpha_), size=n_samples)\n# Create the target\ny = np.dot(X, w) + noise"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Fit the ARD Regression\n\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "collapsed": false
+      },
+      "outputs": [],
+      "source": [
+        "clf = ARDRegression(compute_score=True)\nclf.fit(X, y)\n\nols = LinearRegression()\nols.fit(X, y)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Plot the true weights, the estimated weights, the histogram of the\nweights, and predictions with standard deviations\n\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "collapsed": false
+      },
+      "outputs": [],
+      "source": [
+        "plt.figure(figsize=(6, 5))\nplt.title(\"Weights of the model\")\nplt.plot(clf.coef_, color=\"darkblue\", linestyle=\"-\", linewidth=2, label=\"ARD estimate\")\nplt.plot(\n    ols.coef_, color=\"yellowgreen\", linestyle=\":\", linewidth=2, label=\"OLS estimate\"\n)\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(\n    clf.coef_[relevant_features],\n    np.full(len(relevant_features), 5.0),\n    color=\"gold\",\n    marker=\"o\",\n    label=\"Relevant features\",\n)\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\", label=\"Polynomial ARD\", linewidth=2)\nplt.plot(X_plot, y_plot, color=\"gold\", linewidth=2, label=\"Ground Truth\")\nplt.ylabel(\"Output y\")\nplt.xlabel(\"Feature X\")\nplt.legend(loc=\"lower left\")\nplt.show()"
       ]
     }
   ],