from sklearn.linear_model import LogisticRegression
import numpy as np
data = np.loadtxt("output.txt", delimiter=',')
data = data[7:,]
x = data[:,6]
lists = []
for xx in x:
tmp = []
tmp.append(xx)
lists.append(tmp)
y = data[:,4]
clf = LogisticRegression(C=1e5)
clf.fit(lists ,y)
LogisticRegression(C=100000.0, class_weight=None, dual=False, fit_intercept=True, intercept_scaling=1, penalty='l2', random_state=None, tol=0.0001)
print (np.exp(clf.intercept_),np.exp(clf.coef_.ravel()))
(array([ 1.45966822e+38]), array([ 0.91710845]))
def lr_model(clf,x):
return 1/ ( 1+np.exp(-(clf.intercept_ + clf.coef_ * x)))
import matplotlib.pyplot as plt
plt.clf()
<matplotlib.figure.Figure at 0x107a58790>
plt.scatter(lists, y, color='black', zorder=20)
<matplotlib.collections.PathCollection at 0x105823350>
plt.clf()
plt.scatter(lists, y, color='black', zorder=20)
X_test = np.linspace(1000, 1030, 100)
def model(x):
return 1 / (1 + np.exp(-x))
loss = model(X_test * clf.coef_ + clf.intercept_).ravel()
plt.plot(X_test, loss, color='blue', linewidth=3)
[<matplotlib.lines.Line2D at 0x107ac0fd0>]
lr_model(clf,1020)
array([[ 0.40523615]])
clf.predict_proba(1020)
array([[ 0.59476385, 0.40523615]])