Pushing the docs to dev/ for branch: master, commit 269afa3a77972e883aa1d64081b8f25d1819d5ac

Author: sklearn-ci

dev/_downloads/3409d9766d352cc9f9b169d4a799a87a/auto_examples_python.zip

@@ -15,7 +15,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "\n# Visualization of MLP weights on MNIST\n\n\nSometimes looking at the learned coefficients of a neural network can provide\ninsight into the learning behavior. For example if weights look unstructured,\nmaybe some were not used at all, or if very large coefficients exist, maybe\nregularization was too low or the learning rate too high.\n\nThis example shows how to plot some of the first layer weights in a\nMLPClassifier trained on the MNIST dataset.\n\nThe input data consists of 28x28 pixel handwritten digits, leading to 784\nfeatures in the dataset. Therefore the first layer weight matrix have the shape\n(784, hidden_layer_sizes[0]).  We can therefore visualize a single column of\nthe weight matrix as a 28x28 pixel image.\n\nTo make the example run faster, we use very few hidden units, and train only\nfor a very short time. Training longer would result in weights with a much\nsmoother spatial appearance.\n"
+        "\n# Visualization of MLP weights on MNIST\n\n\nSometimes looking at the learned coefficients of a neural network can provide\ninsight into the learning behavior. For example if weights look unstructured,\nmaybe some were not used at all, or if very large coefficients exist, maybe\nregularization was too low or the learning rate too high.\n\nThis example shows how to plot some of the first layer weights in a\nMLPClassifier trained on the MNIST dataset.\n\nThe input data consists of 28x28 pixel handwritten digits, leading to 784\nfeatures in the dataset. Therefore the first layer weight matrix have the shape\n(784, hidden_layer_sizes[0]).  We can therefore visualize a single column of\nthe weight matrix as a 28x28 pixel image.\n\nTo make the example run faster, we use very few hidden units, and train only\nfor a very short time. Training longer would result in weights with a much\nsmoother spatial appearance. The example will throw a warning because it\ndoesn't converge, in this case this is what we want because of CI's time\nconstraints.\n"
       ]
     },
     {
@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "import matplotlib.pyplot as plt\nfrom sklearn.datasets import fetch_openml\nfrom sklearn.neural_network import MLPClassifier\n\nprint(__doc__)\n\n# Load data from https://www.openml.org/d/554\nX, y = fetch_openml('mnist_784', version=1, return_X_y=True)\nX = X / 255.\n\n# rescale the data, use the traditional train/test split\nX_train, X_test = X[:60000], X[60000:]\ny_train, y_test = y[:60000], y[60000:]\n\nmlp = MLPClassifier(hidden_layer_sizes=(50,), max_iter=10, alpha=1e-4,\n                    solver='sgd', verbose=10, random_state=1,\n                    learning_rate_init=.1)\n\nmlp.fit(X_train, y_train)\nprint(\"Training set score: %f\" % mlp.score(X_train, y_train))\nprint(\"Test set score: %f\" % mlp.score(X_test, y_test))\n\nfig, axes = plt.subplots(4, 4)\n# use global min / max to ensure all weights are shown on the same scale\nvmin, vmax = mlp.coefs_[0].min(), mlp.coefs_[0].max()\nfor coef, ax in zip(mlp.coefs_[0].T, axes.ravel()):\n    ax.matshow(coef.reshape(28, 28), cmap=plt.cm.gray, vmin=.5 * vmin,\n               vmax=.5 * vmax)\n    ax.set_xticks(())\n    ax.set_yticks(())\n\nplt.show()"
+        "import warnings\n\nimport matplotlib.pyplot as plt\nfrom sklearn.datasets import fetch_openml\nfrom sklearn.exceptions import ConvergenceWarning\nfrom sklearn.neural_network import MLPClassifier\n\nprint(__doc__)\n\n# Load data from https://www.openml.org/d/554\nX, y = fetch_openml('mnist_784', version=1, return_X_y=True)\nX = X / 255.\n\n# rescale the data, use the traditional train/test split\nX_train, X_test = X[:60000], X[60000:]\ny_train, y_test = y[:60000], y[60000:]\n\nmlp = MLPClassifier(hidden_layer_sizes=(50,), max_iter=10, alpha=1e-4,\n                    solver='sgd', verbose=10, random_state=1,\n                    learning_rate_init=.1)\n\n# this example won't converge because of CI's time constraints, so we catch the\n# warning and are ignore it here\nwith warnings.catch_warnings():\n    warnings.filterwarnings(\"ignore\", category=ConvergenceWarning,\n                            module=\"sklearn\")\n    mlp.fit(X_train, y_train)\n\nprint(\"Training set score: %f\" % mlp.score(X_train, y_train))\nprint(\"Test set score: %f\" % mlp.score(X_test, y_test))\n\nfig, axes = plt.subplots(4, 4)\n# use global min / max to ensure all weights are shown on the same scale\nvmin, vmax = mlp.coefs_[0].min(), mlp.coefs_[0].max()\nfor coef, ax in zip(mlp.coefs_[0].T, axes.ravel()):\n    ax.matshow(coef.reshape(28, 28), cmap=plt.cm.gray, vmin=.5 * vmin,\n               vmax=.5 * vmax)\n    ax.set_xticks(())\n    ax.set_yticks(())\n\nplt.show()"
       ]
     }
   ],

dev/_downloads/64866fb2a9398ff657578febcb91d430/plot_mnist_filters.ipynb

@@ -18,10 +18,16 @@
 
 To make the example run faster, we use very few hidden units, and train only
 for a very short time. Training longer would result in weights with a much
-smoother spatial appearance.
+smoother spatial appearance. The example will throw a warning because it
+doesn't converge, in this case this is what we want because of CI's time
+constraints.
 """
+
+import warnings
+
 import matplotlib.pyplot as plt
 from sklearn.datasets import fetch_openml
+from sklearn.exceptions import ConvergenceWarning
 from sklearn.neural_network import MLPClassifier
 
 print(__doc__)
@@ -38,7 +44,13 @@
                     solver='sgd', verbose=10, random_state=1,
                     learning_rate_init=.1)
 
-mlp.fit(X_train, y_train)
+# this example won't converge because of CI's time constraints, so we catch the
+# warning and are ignore it here
+with warnings.catch_warnings():
+    warnings.filterwarnings("ignore", category=ConvergenceWarning,
+                            module="sklearn")
+    mlp.fit(X_train, y_train)
+
 print("Training set score: %f" % mlp.score(X_train, y_train))
 print("Test set score: %f" % mlp.score(X_test, y_test))