DOC Changed layer number and learning rate init to make execution of …

…plot_mnist_filters.py quicker (scikit-learn#21647) * Changed layer number and learning rate init to make execution of example faster * Update plot_mnist_filters.py * Update plot_mnist_filters.py * Update plot_mnist_filters.py * Update plot_mnist_filters.py
YutongLi2024 · Nov 23, 2021 · 11222e0 · 11222e0
1 parent 4dfaaf9
commit 11222e0
Showing 1 changed file with 13 additions and 13 deletions.
diff --git a/examples/neural_networks/plot_mnist_filters.py b/examples/neural_networks/plot_mnist_filters.py
@@ -12,45 +12,45 @@
 MLPClassifier trained on the MNIST dataset.
 
 The input data consists of 28x28 pixel handwritten digits, leading to 784
-features in the dataset. Therefore the first layer weight matrix have the shape
+features in the dataset. Therefore the first layer weight matrix has the shape
 (784, hidden_layer_sizes[0]).  We can therefore visualize a single column of
 the weight matrix as a 28x28 pixel image.
 
 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. 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.
-
+doesn't converge, in this case this is what we want because of resource
+usage constraints on our Continuous Integration infrastructure that is used
+to build this documentation on a regular basis.
 """
 
 import warnings
-
 import matplotlib.pyplot as plt
 from sklearn.datasets import fetch_openml
 from sklearn.exceptions import ConvergenceWarning
 from sklearn.neural_network import MLPClassifier
+from sklearn.model_selection import train_test_split
 
 # Load data from https://www.openml.org/d/554
 X, y = fetch_openml("mnist_784", version=1, return_X_y=True)
 X = X / 255.0
 
-# rescale the data, use the traditional train/test split
-X_train, X_test = X[:60000], X[60000:]
-y_train, y_test = y[:60000], y[60000:]
+# Split data into train partition and test partition
+X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0, test_size=0.7)
 
 mlp = MLPClassifier(
-    hidden_layer_sizes=(50,),
-    max_iter=10,
+    hidden_layer_sizes=(40,),
+    max_iter=8,
     alpha=1e-4,
     solver="sgd",
     verbose=10,
     random_state=1,
-    learning_rate_init=0.1,
+    learning_rate_init=0.2,
 )
 
-# this example won't converge because of CI's time constraints, so we catch the
-# warning and are ignore it here
+# this example won't converge because of resource usage constraints on
+# our Continuous Integration infrastructure, so we catch the warning and
+# ignore it here
 with warnings.catch_warnings():
     warnings.filterwarnings("ignore", category=ConvergenceWarning, module="sklearn")
     mlp.fit(X_train, y_train)