def cv(data, target, multivariant=False):
X_train, X_test, Y_train, Y_test = cross_validation.train_test_split(data, target, test_size=0.2,
random_state=0)
if multivariant is False:
linear_regression(X_train, X_test, Y_train, Y_test, plot=False)
else:
linear_regression_multivariant(X_train, X_test, Y_train, Y_test, cost_fun='Ridge_Regression')
def cv(data, target, multivariant=False):
X_train, X_test, Y_train, Y_test = cross_validation.train_test_split(data, target, test_size=0.1, random_state=10)
if multivariant is False:
linear_regression(X_train, X_test, Y_train, Y_test, plot=False)
else:
linear_regression_multivariant(X_train, X_test, Y_train, Y_test, cost_fun="ordinary_least_squares")
linear_regression_multivariant(X_train, X_test, Y_train, Y_test, cost_fun="Ridge_Regression")
linear_regression_multivariant(X_train, X_test, Y_train, Y_test, cost_fun="Bayesian_Regression")
linear_regression_multivariant(X_train, X_test, Y_train, Y_test, cost_fun="SVR")
linear_regression_multivariant(X_train, X_test, Y_train, Y_test, cost_fun="KNN_Reg")
def avg(training_file, submission_file, output_file):
data = utilities.read_file(training_file)
train_data, cv_data = preprocess.get_train_cv_data_by_chunk(data)
targets_train, targets_cv = preprocess.get_train_cv_targets(
train_data, cv_data)
(chunk_avg, hour_avg_by_chunk, weekday_avg_by_chunk,
hour_avg, weekday_avg) = feature_extraction.get_avg_maps(train_data)
x_train_all, x_cv_all = feature_extraction.get_x_by_avg(
train_data, cv_data, chunk_avg, hour_avg_by_chunk,
weekday_avg_by_chunk, hour_avg, weekday_avg)
clfs = regression.linear_regression(
x_train_all, x_cv_all, targets_train, targets_cv)
clfs = regression.random_forest(
x_train_all, x_cv_all, targets_train, targets_cv)
print 'Filling submission file...'
sub_data = utilities.read_file(submission_file, True)
for i in range(1, len(sub_data)):
chunk_id = sub_data[i][1]
hour = sub_data[i][3]
weekday = ''
all_features = feature_extraction.get_features(
chunk_id, weekday, hour, chunk_avg, hour_avg_by_chunk,
weekday_avg_by_chunk, hour_avg, weekday_avg)
for j in range(5, len(sub_data[i])):
if sub_data[i][j] == '0':
feature = []
for f in all_features:
feature.append(f[j - 5])
sub_data[i][j] = clfs[j - 5].predict([feature])[0]
utilities.write_file(output_file, sub_data)
import regression as reg
import load_data as ld
ld.create_sample('airfoil_self_noise_.csv','new_file.csv', 10)
ld.createSets('new_file.csv', 75)
b_vector = reg.linear_regression('train_set.csv')
error = reg.test("test_set.csv", b_vector)
#print(data_list[i][0:-2]) character.append(data_list[i][:-1]) label.append(data_list[i][-1]) return np.array(character), np.array(label) if __name__ == '__main__': file_path = '/Users/yuqishi/Documents/machine_learning/data/波士顿房价数据集/housing_data.txt' split = 450 #获得训练样本和测试样本 train_data, test_data = get_Data(file_path, split) #获得训练样本的特征和标签数组 train_X, train_Y = split_data(train_data) #获得测试数组X的特征和标签数组 test_X, test_Y = split_data(test_data) #将训练集中的数据训练求得w参数值 w = linear_regression(train_X, train_Y) print(predict(test_X, test_Y, w))
