Created
August 8, 2017 20:59
-
-
Save ratchetwrench/d80ac70067c7cb0ada97f9c8a99f88dc to your computer and use it in GitHub Desktop.
sklearn confusion matrix
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import itertools | |
import numpy as np | |
import matplotlib.pyplot as plt | |
from sklearn import svm, datasets | |
from sklearn.model_selection import train_test_split | |
from sklearn.metrics import confusion_matrix | |
# import some data to play with | |
iris = datasets.load_iris() | |
X = iris.data | |
y = iris.target | |
class_names = iris.target_names | |
# Split the data into a training set and a test set | |
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0) | |
# Run classifier, using a model that is too regularized (C too low) to see | |
# the impact on the results | |
classifier = svm.SVC(kernel='linear', C=0.01) | |
y_pred = classifier.fit(X_train, y_train).predict(X_test) | |
def plot_confusion_matrix(cm, classes, | |
normalize=False, | |
title='Confusion matrix', | |
cmap=plt.cm.Blues): | |
""" | |
This function prints and plots the confusion matrix. | |
Normalization can be applied by setting `normalize=True`. | |
""" | |
plt.imshow(cm, interpolation='nearest', cmap=cmap) | |
plt.title(title) | |
plt.colorbar() | |
tick_marks = np.arange(len(classes)) | |
plt.xticks(tick_marks, classes, rotation=45) | |
plt.yticks(tick_marks, classes) | |
if normalize: | |
cm = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis] | |
print("Normalized confusion matrix") | |
else: | |
print('Confusion matrix, without normalization') | |
print(cm) | |
thresh = cm.max() / 2. | |
for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])): | |
plt.text(j, i, cm[i, j], | |
horizontalalignment="center", | |
color="white" if cm[i, j] > thresh else "black") | |
plt.tight_layout() | |
plt.ylabel('True label') | |
plt.xlabel('Predicted label') | |
# Compute confusion matrix | |
cnf_matrix = confusion_matrix(y_test, y_pred) | |
np.set_printoptions(precision=2) | |
# Plot non-normalized confusion matrix | |
plt.figure() | |
plot_confusion_matrix(cnf_matrix, classes=class_names, | |
title='Confusion matrix, without normalization') | |
# Plot normalized confusion matrix | |
plt.figure() | |
plot_confusion_matrix(cnf_matrix, classes=class_names, normalize=True, | |
title='Normalized confusion matrix') | |
plt.show() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment