Last active
November 14, 2017 23:14
-
-
Save lorenzoriano/bd0c95bb811b8c38d0433692a337f6b1 to your computer and use it in GitHub Desktop.
Test Linear Regression in Python
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 matplotlib.pyplot as plt | |
from sklearn.model_selection import train_test_split | |
from sklearn.linear_model import LogisticRegression | |
import numpy as np | |
intercept = -2.0 | |
beta = 5.0 | |
n_samples = 1000 | |
regularization = 1e30 | |
X = np.random.normal(size=(n_samples,1)) | |
linepred = intercept + (X*beta) | |
prob = np.exp(linepred) / (1.0 + np.exp(linepred)) | |
y = (np.random.uniform(size=X.shape) < prob).astype(np.float) | |
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2) | |
print "Percent of class 1: ", sum(y)/len(y) | |
plt.figure() | |
plt.plot(X,prob, '.', color='blue', label='model', markersize=0.5) | |
clf = LogisticRegression(solver='liblinear', tol=1e-10, max_iter=10000, C=regularization); | |
clf.fit(X_train, y_train.ravel()); | |
print "Coeff: {}, Intercept: {}".format(clf.coef_, clf.intercept_) | |
print "Score over training: ", clf.score(X_train, y_train) | |
print "Score over testing: ", clf.score(X_test, y_test) | |
plt.plot(X, clf.predict_proba(X)[:,1], '.', color='red', label='clf', markersize=0.5) | |
tot_score = clf.score(X, y) | |
plt.title("Score: {}".format(tot_score)) | |
plt.legend(loc='best'); | |
plt.show() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment