for i in C:
for j in penalty:
clf = LogisticRegression(C=i, penalty=j, solver='saga',
max_iter=100).fit(X_train, y_train)
scoring = []
accuracyScore = []
for train_index, test_index in tscv.split(X):
print("TRAIN:", train_index, "TEST:", test_index)
X_train, X_test = X[train_index], X[test_index]
y_train, y_test = y[train_index], y[test_index]
clf.fit(X_train, y_train)
test_predictions = clf.predict_proba(X_test).T[1]
test_score = clf.score(X_test, y_test)
testAcScore = clf.accuracy_score(X_test, y_test)
scoring.append(test_score)
accuracyScore.append(testAcScore)
#prediction = clf.predict()
print(test_score)
print('i: ', i)
print('j: ', j)
plt.plot(scoring)
plt.plot(accuracyScore)
plt.show()
'''
clf = linear_model.LogisticRegression(C=1e5)
clf.fit(X, y)
plot_feature_importance(forest.feature_importances_, X.columns,
'RANDOM FOREST CLASSIFIER')
# In[12]:
#logistic Regression
from sklearn.linear_model import LogisticRegression
logistic_regression = LogisticRegression()
logistic_regression.fit(X_train, y_train)
# In[14]:
y_pred = logistic_regression.predict(X_test)
accuracy = logistic_regression.accuracy_score(y_test, y_pred)
accuracy_percentage = 100 * accuracy
accuracy_percentage
# In[ ]:
from sklearn.linear_model import LogisticRegressionCV
import numpy as np
import matplotlib.pyplot as plt
# get importance
importance = logistic_regression.coef_[0]
# summarize feature importance
for i, v in enumerate(importance):
print('Feature: %0d, Score: %.5f' % (i, v))
# plot feature importance