Pushing the docs to dev/ for branch: master, commit 5e193ec655d2b7634e35733e2fa0e5bef5e63d45

Author: sklearn-ci

dev/_downloads/3409d9766d352cc9f9b169d4a799a87a/auto_examples_python.zip

@@ -0,0 +1,108 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "collapsed": false
+      },
+      "outputs": [],
+      "source": [
+        "%matplotlib inline"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "\n===============================================================\nFactor Analysis (with rotation) to visualize patterns\n===============================================================\n\nInvestigating the Iris dataset, we see that sepal length, petal\nlength and petal width are highly correlated. Sepal width is\nless redundant. Matrix decomposition techniques can uncover\nthese latent patterns. Applying rotations to the resulting\ncomponents does not inherently improve the predictve value\nof the derived latent space, but can help visualise their\nstructure; here, for example, the varimax rotation, which\nis found by maximizing the squared variances of the weights,\nfinds a structure where the second component only loads\npositively on sepal width.\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "collapsed": false
+      },
+      "outputs": [],
+      "source": [
+        "# Authors: Jona Sassenhagen\n# License: BSD 3 clause\n\nimport matplotlib.pyplot as plt\nimport numpy as np\n\nfrom sklearn.decomposition import FactorAnalysis, PCA\nfrom sklearn.preprocessing import StandardScaler\nfrom sklearn.datasets import load_iris\n\nprint(__doc__)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Load Iris data\n\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "collapsed": false
+      },
+      "outputs": [],
+      "source": [
+        "data = load_iris()\nX = StandardScaler().fit_transform(data[\"data\"])\nfeature_names = data[\"feature_names\"]"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Plot covariance of Iris features\n\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "collapsed": false
+      },
+      "outputs": [],
+      "source": [
+        "ax = plt.axes()\n\nim = ax.imshow(np.corrcoef(X.T), cmap=\"RdBu_r\", vmin=-1, vmax=1)\n\nax.set_xticks([0, 1, 2, 3])\nax.set_xticklabels(list(feature_names), rotation=90)\nax.set_yticks([0, 1, 2, 3])\nax.set_yticklabels(list(feature_names))\n\nplt.colorbar(im).ax.set_ylabel(\"$r$\", rotation=0)\nax.set_title(\"Iris feature correlation matrix\")\nplt.tight_layout()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Run factor analysis with Varimax rotation\n\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "collapsed": false
+      },
+      "outputs": [],
+      "source": [
+        "n_comps = 2\n\nmethods = [('PCA', PCA()),\n           ('Unrotated FA', FactorAnalysis()),\n           ('Varimax FA', FactorAnalysis(rotation='varimax'))]\nfig, axes = plt.subplots(ncols=len(methods), figsize=(10, 8))\n\nfor ax, (method, fa) in zip(axes, methods):\n    fa.set_params(n_components=n_comps)\n    fa.fit(X)\n\n    components = fa.components_.T\n    print(\"\\n\\n %s :\\n\" % method)\n    print(components)\n\n    vmax = np.abs(components).max()\n    ax.imshow(components, cmap=\"RdBu_r\", vmax=vmax, vmin=-vmax)\n    ax.set_yticks(np.arange(len(feature_names)))\n    if ax.is_first_col():\n        ax.set_yticklabels(feature_names)\n    else:\n        ax.set_yticklabels([])\n    ax.set_title(str(method))\n    ax.set_xticks([0, 1])\n    ax.set_xticklabels([\"Comp. 1\", \"Comp. 2\"])\nfig.suptitle(\"Factors\")\nplt.tight_layout()\nplt.show()"
+      ]
+    }
+  ],
+  "metadata": {
+    "kernelspec": {
+      "display_name": "Python 3",
+      "language": "python",
+      "name": "python3"
+    },
+    "language_info": {
+      "codemirror_mode": {
+        "name": "ipython",
+        "version": 3
+      },
+      "file_extension": ".py",
+      "mimetype": "text/x-python",
+      "name": "python",
+      "nbconvert_exporter": "python",
+      "pygments_lexer": "ipython3",
+      "version": "3.8.3"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

dev/_downloads/7716523ca12b85a020d7a525dff641cc/plot_varimax_fa.ipynb

@@ -0,0 +1,80 @@
+"""
+===============================================================
+Factor Analysis (with rotation) to visualize patterns
+===============================================================
+
+Investigating the Iris dataset, we see that sepal length, petal
+length and petal width are highly correlated. Sepal width is
+less redundant. Matrix decomposition techniques can uncover
+these latent patterns. Applying rotations to the resulting
+components does not inherently improve the predictve value
+of the derived latent space, but can help visualise their
+structure; here, for example, the varimax rotation, which
+is found by maximizing the squared variances of the weights,
+finds a structure where the second component only loads
+positively on sepal width.
+"""
+
+# Authors: Jona Sassenhagen
+# License: BSD 3 clause
+
+import matplotlib.pyplot as plt
+import numpy as np
+
+from sklearn.decomposition import FactorAnalysis, PCA
+from sklearn.preprocessing import StandardScaler
+from sklearn.datasets import load_iris
+
+print(__doc__)
+
+# %%
+# Load Iris data
+data = load_iris()
+X = StandardScaler().fit_transform(data["data"])
+feature_names = data["feature_names"]
+
+# %%
+# Plot covariance of Iris features
+ax = plt.axes()
+
+im = ax.imshow(np.corrcoef(X.T), cmap="RdBu_r", vmin=-1, vmax=1)
+
+ax.set_xticks([0, 1, 2, 3])
+ax.set_xticklabels(list(feature_names), rotation=90)
+ax.set_yticks([0, 1, 2, 3])
+ax.set_yticklabels(list(feature_names))
+
+plt.colorbar(im).ax.set_ylabel("$r$", rotation=0)
+ax.set_title("Iris feature correlation matrix")
+plt.tight_layout()
+
+# %%
+# Run factor analysis with Varimax rotation
+n_comps = 2
+
+methods = [('PCA', PCA()),
+           ('Unrotated FA', FactorAnalysis()),
+           ('Varimax FA', FactorAnalysis(rotation='varimax'))]
+fig, axes = plt.subplots(ncols=len(methods), figsize=(10, 8))
+
+for ax, (method, fa) in zip(axes, methods):
+    fa.set_params(n_components=n_comps)
+    fa.fit(X)
+
+    components = fa.components_.T
+    print("\n\n %s :\n" % method)
+    print(components)
+
+    vmax = np.abs(components).max()
+    ax.imshow(components, cmap="RdBu_r", vmax=vmax, vmin=-vmax)
+    ax.set_yticks(np.arange(len(feature_names)))
+    if ax.is_first_col():
+        ax.set_yticklabels(feature_names)
+    else:
+        ax.set_yticklabels([])
+    ax.set_title(str(method))
+    ax.set_xticks([0, 1])
+    ax.set_xticklabels(["Comp. 1", "Comp. 2"])
+fig.suptitle("Factors")
+plt.tight_layout()
+plt.show()