if __name__ == '__main__':
if len(sys.argv) == 1:
data = load_data.load_data()
# Set up datasets for cross validation
rs = cross_validation.ShuffleSplit(150000, n_iterations=3, test_fraction=.30)
C, train_results, cv_results = prepare_params(100, 10000, 10)
# Run through the cross validation iterations
for train_index, cv_index in rs:
train_data, cv_data = split_data(data[1], train_index, cv_index)
model = Logistic_ComplexI_Model()
train_X, train_y = model.load_train_data(train_data)
cv_X, cv_y = model.load_data(cv_data)
for c in C:
print c
model.train_model(train_X, train_y, {'c':c})
train_probs = model.run_model(train_X)
train_results[c].append(calc_score(train_probs, train_y))
cv_probs = model.run_model(cv_X)
cv_results[c].append(calc_score(cv_probs, cv_y))
if __name__ == '__main__':
if len(sys.argv) == 1:
data = load_data.load_data()
# Set up datasets for cross validation
rs = cross_validation.ShuffleSplit(150000, n_iterations=3, test_fraction=.30)
C, train_results, cv_results = prepare_params(0.0000001, 1000, 50)
# Run through the cross validation iterations
for train_index, cv_index in rs:
train_data, cv_data = split_data(data[1], train_index, cv_index)
model = Logistic_Inverse_Model()
train_X, train_y = model.load_train_data(train_data)
cv_X, cv_y = model.load_data(cv_data)
for c in C:
print c
model.train_model(train_X, train_y, {'c':c})
train_probs = model.run_model(train_X)
train_results[c].append(calc_score(train_probs, train_y))
cv_probs = model.run_model(cv_X)
cv_results[c].append(calc_score(cv_probs, cv_y))
# probs = self.clf.predict_proba(X)
# return probs[:,1]
if __name__ == '__main__':
if len(sys.argv) == 1:
data = load_data.load_data()
# Set up datasets for cross validation
rs = cross_validation.ShuffleSplit(150000,
n_iterations=3,
test_fraction=.30)
C, train_results, cv_results = prepare_params(0.0000000001, 0.0001, 10)
# Run through the cross validation iterations
for train_index, cv_index in rs:
train_data, cv_data = split_data(data[1], train_index, cv_index)
model = Logistic_Pca_Model()
train_X, train_y = model.load_train_data(train_data)
cv_X, cv_y = model.load_data(cv_data)
for c in C:
print c
model.train_model(train_X, train_y, {'c': c})
train_probs = model.run_model(train_X)
train_results[c].append(calc_score(train_probs, train_y))
cv_probs = model.run_model(cv_X)
cv_results[c].append(calc_score(cv_probs, cv_y))
# cv_test_data = self.pcan.execute(X)
return (X, y)
if __name__ == '__main__':
if len(sys.argv) == 1:
data = load_data.load_data()
# Set up datasets for cross validation
rs = cross_validation.ShuffleSplit(150000,
n_iterations=3,
test_fraction=.30)
C, train_results, cv_results = prepare_params(100, 10000, 10)
# Run through the cross validation iterations
for train_index, cv_index in rs:
train_data, cv_data = split_data(data[1], train_index, cv_index)
model = Logistic_ComplexI_Model()
train_X, train_y = model.load_train_data(train_data)
cv_X, cv_y = model.load_data(cv_data)
for c in C:
print c
model.train_model(train_X, train_y, {'c': c})
train_probs = model.run_model(train_X)
train_results[c].append(calc_score(train_probs, train_y))
cv_probs = model.run_model(cv_X)
cv_results[c].append(calc_score(cv_probs, cv_y))
