In [13]:
import numpy as np
import matplotlib.pyplot as plt
In [14]:
def sigmoid(scores):
return 1 / (1 + np.exp(-scores))
In [15]:
def log_likelihood(features, target, weights):
scores = np.dot(features, weights)
ll = np.sum( target*scores - np.log(1 + np.exp(scores)) )
return ll
In [16]:
def logistic_regression(features, target, num_steps, learning_rate, add_intercept = False):
if add_intercept:
intercept = np.ones((features.shape[0], 1))
features = np.hstack((intercept, features))
weights = np.zeros(features.shape[1])
for step in range(num_steps):
scores = np.dot(features, weights)
predictions = sigmoid(scores)
# Update weights with gradient
output_error_signal = target - predictions
gradient = np.dot(features.T, output_error_signal)
weights += learning_rate * gradient
# Print log-likelihood every so often
if step % 10000 == 0:
print(log_likelihood(features, target, weights))
return weights
In [17]:
np.random.seed(12)
num_observations = 5000
x1 = np.random.multivariate_normal([0, 0], [[1, .75],[.75, 1]], num_observations)
x2 = np.random.multivariate_normal([1, 4], [[1, .75],[.75, 1]], num_observations)
simulated_separableish_features = np.vstack((x1, x2)).astype(np.float32)
simulated_labels = np.hstack((np.zeros(num_observations),
np.ones(num_observations)))
In [18]:
weights = logistic_regression(simulated_separableish_features, simulated_labels,
num_steps = 300000, learning_rate = 5e-5, add_intercept=True)
In [19]:
from sklearn.linear_model import LogisticRegression
clf = LogisticRegression(fit_intercept=True, C = 1e15)
clf.fit(simulated_separableish_features, simulated_labels)
print(clf.intercept_, clf.coef_)
print(weights)