Pushing the docs to dev/ for branch: main, commit bac46762be1d2926663f99de306d9794e63e1fb2

Author: sklearn-ci

dev/_downloads/02fe21a1f5d14bd1ebbe34aa905d9bf6/plot_multilabel.zip

@@ -33,7 +33,25 @@
       },
       "outputs": [],
       "source": [
-        "from sklearn import datasets\n\niris = datasets.load_iris()\nX = iris.data\ny = iris.target\n\nX = X[y != 2]\ny = y[y != 2]\n\nX /= X.max()  # Normalize X to speed-up convergence"
+        "from sklearn import datasets\n\niris = datasets.load_iris()\nX = iris.data\ny = iris.target\nfeature_names = iris.feature_names"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Here we remove the third class to make the problem a binary classification\n\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "collapsed": false
+      },
+      "outputs": [],
+      "source": [
+        "X = X[y != 2]\ny = y[y != 2]"
       ]
     },
     {
@@ -51,7 +69,25 @@
       },
       "outputs": [],
       "source": [
-        "import numpy as np\n\nfrom sklearn import linear_model\nfrom sklearn.svm import l1_min_c\n\ncs = l1_min_c(X, y, loss=\"log\") * np.logspace(0, 10, 16)\n\nclf = linear_model.LogisticRegression(\n    penalty=\"l1\",\n    solver=\"liblinear\",\n    tol=1e-6,\n    max_iter=int(1e6),\n    warm_start=True,\n    intercept_scaling=10000.0,\n)\ncoefs_ = []\nfor c in cs:\n    clf.set_params(C=c)\n    clf.fit(X, y)\n    coefs_.append(clf.coef_.ravel().copy())\n\ncoefs_ = np.array(coefs_)"
+        "import numpy as np\n\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn.pipeline import make_pipeline\nfrom sklearn.preprocessing import StandardScaler\nfrom sklearn.svm import l1_min_c\n\ncs = l1_min_c(X, y, loss=\"log\") * np.logspace(0, 1, 16)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Create a pipeline with `StandardScaler` and `LogisticRegression`, to normalize\nthe data before fitting a linear model, in order to speed-up convergence and\nmake the coefficients comparable. Also, as a side effect, since the data is now\ncentered around 0, we don't need to fit an intercept.\n\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "collapsed": false
+      },
+      "outputs": [],
+      "source": [
+        "clf = make_pipeline(\n    StandardScaler(),\n    LogisticRegression(\n        penalty=\"l1\",\n        solver=\"liblinear\",\n        tol=1e-6,\n        max_iter=int(1e6),\n        warm_start=True,\n        fit_intercept=False,\n    ),\n)\ncoefs_ = []\nfor c in cs:\n    clf.set_params(logisticregression__C=c)\n    clf.fit(X, y)\n    coefs_.append(clf[\"logisticregression\"].coef_.ravel().copy())\n\ncoefs_ = np.array(coefs_)"
       ]
     },
     {
@@ -69,7 +105,7 @@
       },
       "outputs": [],
       "source": [
-        "import matplotlib.pyplot as plt\n\nplt.plot(np.log10(cs), coefs_, marker=\"o\")\nymin, ymax = plt.ylim()\nplt.xlabel(\"log(C)\")\nplt.ylabel(\"Coefficients\")\nplt.title(\"Logistic Regression Path\")\nplt.axis(\"tight\")\nplt.show()"
+        "import matplotlib.pyplot as plt\n\n# Colorblind-friendly palette (IBM Color Blind Safe palette)\ncolors = [\"#648FFF\", \"#785EF0\", \"#DC267F\", \"#FE6100\"]\n\nplt.figure(figsize=(10, 6))\nfor i in range(coefs_.shape[1]):\n    plt.semilogx(cs, coefs_[:, i], marker=\"o\", color=colors[i], label=feature_names[i])\n\nymin, ymax = plt.ylim()\nplt.xlabel(\"C\")\nplt.ylabel(\"Coefficients\")\nplt.title(\"Logistic Regression Path\")\nplt.legend()\nplt.axis(\"tight\")\nplt.show()"
       ]
     }
   ],

dev/_downloads/0358b1921962fd7c6f5a94c5abc91476/plot_hashing_vs_dict_vectorizer.zip

@@ -37,36 +37,47 @@
 iris = datasets.load_iris()
 X = iris.data
 y = iris.target
+feature_names = iris.feature_names
 
+# %%
+# Here we remove the third class to make the problem a binary classification
 X = X[y != 2]
 y = y[y != 2]
 
-X /= X.max()  # Normalize X to speed-up convergence
-
 # %%
 # Compute regularization path
 # ---------------------------
 
 import numpy as np
 
-from sklearn import linear_model
+from sklearn.linear_model import LogisticRegression
+from sklearn.pipeline import make_pipeline
+from sklearn.preprocessing import StandardScaler
 from sklearn.svm import l1_min_c
 
-cs = l1_min_c(X, y, loss="log") * np.logspace(0, 10, 16)
+cs = l1_min_c(X, y, loss="log") * np.logspace(0, 1, 16)
 
-clf = linear_model.LogisticRegression(
-    penalty="l1",
-    solver="liblinear",
-    tol=1e-6,
-    max_iter=int(1e6),
-    warm_start=True,
-    intercept_scaling=10000.0,
+# %%
+# Create a pipeline with `StandardScaler` and `LogisticRegression`, to normalize
+# the data before fitting a linear model, in order to speed-up convergence and
+# make the coefficients comparable. Also, as a side effect, since the data is now
+# centered around 0, we don't need to fit an intercept.
+clf = make_pipeline(
+    StandardScaler(),
+    LogisticRegression(
+        penalty="l1",
+        solver="liblinear",
+        tol=1e-6,
+        max_iter=int(1e6),
+        warm_start=True,
+        fit_intercept=False,
+    ),
 )
 coefs_ = []
 for c in cs:
-    clf.set_params(C=c)
+    clf.set_params(logisticregression__C=c)
     clf.fit(X, y)
-    coefs_.append(clf.coef_.ravel().copy())
+    coefs_.append(clf["logisticregression"].coef_.ravel().copy())
 
 coefs_ = np.array(coefs_)
 
@@ -76,10 +87,17 @@
 
 import matplotlib.pyplot as plt
 
-plt.plot(np.log10(cs), coefs_, marker="o")
+# Colorblind-friendly palette (IBM Color Blind Safe palette)
+colors = ["#648FFF", "#785EF0", "#DC267F", "#FE6100"]
+
+plt.figure(figsize=(10, 6))
+for i in range(coefs_.shape[1]):
+    plt.semilogx(cs, coefs_[:, i], marker="o", color=colors[i], label=feature_names[i])
+
 ymin, ymax = plt.ylim()
-plt.xlabel("log(C)")
+plt.xlabel("C")
 plt.ylabel("Coefficients")
 plt.title("Logistic Regression Path")
+plt.legend()
 plt.axis("tight")
 plt.show()