MNT Speed up of plot_face_recognition.py example (#21725)

pramodatre · web-flow · commit f853e78b0aa0 · 2021-12-15T11:05:48.000+01:00
diff --git a/examples/applications/plot_face_recognition.py b/examples/applications/plot_face_recognition.py
@@ -10,42 +10,23 @@
 
 .. _LFW: http://vis-www.cs.umass.edu/lfw/
 
-Expected results for the top 5 most represented people in the dataset:
-
-================== ============ ======= ========== =======
-                   precision    recall  f1-score   support
-================== ============ ======= ========== =======
-     Ariel Sharon       0.67      0.92      0.77        13
-     Colin Powell       0.75      0.78      0.76        60
-  Donald Rumsfeld       0.78      0.67      0.72        27
-    George W Bush       0.86      0.86      0.86       146
-Gerhard Schroeder       0.76      0.76      0.76        25
-      Hugo Chavez       0.67      0.67      0.67        15
-       Tony Blair       0.81      0.69      0.75        36
-
-      avg / total       0.80      0.80      0.80       322
-================== ============ ======= ========== =======
-
 """
-
+# %%
 from time import time
-import logging
 import matplotlib.pyplot as plt
 
 from sklearn.model_selection import train_test_split
-from sklearn.model_selection import GridSearchCV
+from sklearn.model_selection import RandomizedSearchCV
 from sklearn.datasets import fetch_lfw_people
 from sklearn.metrics import classification_report
-from sklearn.metrics import confusion_matrix
+from sklearn.metrics import ConfusionMatrixDisplay
+from sklearn.preprocessing import StandardScaler
 from sklearn.decomposition import PCA
 from sklearn.svm import SVC
+from sklearn.utils.fixes import loguniform
 
 
-# Display progress logs on stdout
-logging.basicConfig(level=logging.INFO, format="%(asctime)s %(message)s")
-
-
-# #############################################################################
+# %%
 # Download the data, if not already on disk and load it as numpy arrays
 
 lfw_people = fetch_lfw_people(min_faces_per_person=70, resize=0.4)
@@ -69,18 +50,21 @@
 print("n_classes: %d" % n_classes)
 
 
-# #############################################################################
-# Split into a training set and a test set using a stratified k fold
+# %%
+# Split into a training set and a test and keep 25% of the data for testing.
 
-# split into a training and testing set
 X_train, X_test, y_train, y_test = train_test_split(
     X, y, test_size=0.25, random_state=42
 )
 
+scaler = StandardScaler()
+X_train = scaler.fit_transform(X_train)
+X_test = scaler.transform(X_test)
 
-# #############################################################################
+# %%
 # Compute a PCA (eigenfaces) on the face dataset (treated as unlabeled
 # dataset): unsupervised feature extraction / dimensionality reduction
+
 n_components = 150
 
 print(
@@ -99,23 +83,25 @@
 print("done in %0.3fs" % (time() - t0))
 
 
-# #############################################################################
+# %%
 # Train a SVM classification model
 
 print("Fitting the classifier to the training set")
 t0 = time()
 param_grid = {
-    "C": [1e3, 5e3, 1e4, 5e4, 1e5],
-    "gamma": [0.0001, 0.0005, 0.001, 0.005, 0.01, 0.1],
+    "C": loguniform(1e3, 1e5),
+    "gamma": loguniform(1e-4, 1e-1),
 }
-clf = GridSearchCV(SVC(kernel="rbf", class_weight="balanced"), param_grid)
+clf = RandomizedSearchCV(
+    SVC(kernel="rbf", class_weight="balanced"), param_grid, n_iter=10
+)
 clf = clf.fit(X_train_pca, y_train)
 print("done in %0.3fs" % (time() - t0))
 print("Best estimator found by grid search:")
 print(clf.best_estimator_)
 
 
-# #############################################################################
+# %%
 # Quantitative evaluation of the model quality on the test set
 
 print("Predicting people's names on the test set")
@@ -124,10 +110,14 @@
 print("done in %0.3fs" % (time() - t0))
 
 print(classification_report(y_test, y_pred, target_names=target_names))
-print(confusion_matrix(y_test, y_pred, labels=range(n_classes)))
+ConfusionMatrixDisplay.from_estimator(
+    clf, X_test_pca, y_test, display_labels=target_names, xticks_rotation="vertical"
+)
+plt.tight_layout()
+plt.show()
 
 
-# #############################################################################
+# %%
 # Qualitative evaluation of the predictions using matplotlib
 
 
@@ -143,6 +133,7 @@ def plot_gallery(images, titles, h, w, n_row=3, n_col=4):
         plt.yticks(())
 
 
+# %%
 # plot the result of the prediction on a portion of the test set
 
 
@@ -157,10 +148,16 @@ def title(y_pred, y_test, target_names, i):
 ]
 
 plot_gallery(X_test, prediction_titles, h, w)
-
+# %%
 # plot the gallery of the most significative eigenfaces
 
 eigenface_titles = ["eigenface %d" % i for i in range(eigenfaces.shape[0])]
 plot_gallery(eigenfaces, eigenface_titles, h, w)
 
 plt.show()
+
+# %%
+# Face recognition problem would be much more effectively solved by training
+# convolutional neural networks but this family of models is outside of the scope of
+# the scikit-learn library. Interested readers should instead try to use pytorch or
+# tensorflow to implement such models.
