Plot Confusion Matrix
- ds_utils.metrics.confusion_matrix.plot_confusion_matrix(y_test: ndarray, y_pred: ndarray, labels: List[str | int], sample_weight: List[float] | None = None, annot_kws: Dict | None = None, cbar: bool = True, cbar_kws: Dict | None = None, **kwargs) Axes[source]
Compute and plot confusion matrix with classification metrics.
Computes and plots confusion matrix, False Positive Rate, False Negative Rate, Accuracy, and F1 score of a classification. Before plotting, it validates that the unique values in y_test, y_pred, and labels are identical.
- Parameters:
y_test – array, shape = [n_samples]. Ground truth (correct) target values.
y_pred – array, shape = [n_samples]. Estimated targets as returned by a classifier.
labels – List of labels (strings or integers) used to index the matrix, corresponding to n_classes.
sample_weight – array-like of shape = [n_samples], optional. Optional sample weights for weighting the samples.
annot_kws – dict of key, value mappings, optional. Keyword arguments for
ax.text.cbar – boolean, optional. Whether to draw a colorbar.
cbar_kws – dict of key, value mappings, optional. Keyword arguments for
figure.colorbar.kwargs – other keyword arguments. All other keyword arguments are passed to
matplotlib.axes.Axes.pcolormesh().
- Returns:
Returns the Axes object with the matrix drawn onto it.
- Raises:
ValueError – If number of labels is lower than 2, or if there is a mismatch between the unique values in y_test, y_pred, and labels.
Code Examples
In the following examples, we are going to use the iris dataset from scikit-learn. First, let’s import it:
import numpy as np
from sklearn import datasets
IRIS = datasets.load_iris()
RANDOM_STATE = np.random.RandomState(0)
Next, we’ll add a small function to add noise:
def _add_noisy_features(x, random_state):
n_samples, n_features = x.shape
return numpy.c_[x, random_state.randn(n_samples, 200 * n_features)]
Binary Classification
We’ll use only the first two classes in the iris dataset, build an SVM classifier and evaluate it:
from matplotlib import pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn import svm
from ds_utils.metrics.confusion_matrix import plot_confusion_matrix
# Load and prepare the data
features = IRIS.data
labels = IRIS.target
# Add noisy features to make the problem harder
features = _add_noisy_features(features, RANDOM_STATE)
# Limit to the two first classes, and split into training and test
X_train, X_test, y_train, y_test = train_test_split(features[labels < 2], labels[labels < 2],
test_size=.5, random_state=RANDOM_STATE)
# Create a simple classifier
classifier = svm.LinearSVC(random_state=RANDOM_STATE)
classifier.fit(X_train, y_train)
y_pred = classifier.predict(X_test)
plot_confusion_matrix(y_test, y_pred, [1, 0])
plt.show()
And the following image will be shown:
Multi-Label Classification
This time, we’ll train on all the classes and plot an evaluation:
from matplotlib import pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.multiclass import OneVsRestClassifier
from sklearn import svm
from ds_utils.metrics.confusion_matrix import plot_confusion_matrix
# Load and prepare the data
features = IRIS.data
labels = IRIS.target
# Add noisy features to make the problem harder
features = _add_noisy_features(features, RANDOM_STATE)
X_train, X_test, y_train, y_test = train_test_split(features, labels, test_size=.5, random_state=RANDOM_STATE)
# Create a simple classifier
# OneVsRestClassifier is used for multi-class classification
classifier = OneVsRestClassifier(svm.LinearSVC(random_state=RANDOM_STATE))
classifier.fit(X_train, y_train)
y_pred = classifier.predict(X_test)
plot_confusion_matrix(y_test, y_pred, [0, 1, 2])
plt.show()
And the following image will be shown:
