import pandas as pd
df = pd.read_csv('http://bit.ly/kaggletrain')
cols = ['Pclass', 'Fare']
X = df[cols]
y = df['Survived']
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import plot_confusion_matrix
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)
clf = LogisticRegression()
clf.fit(X_train, y_train);
# pass it a trained model: it makes predictions for X_test and compares them to y_test
disp = plot_confusion_matrix(clf, X_test, y_test, cmap='Blues', values_format='d')
# print the "normal" confusion matrix
disp.confusion_matrix
array([[122, 17], [ 48, 36]])
© 2020 Data School. All rights reserved.