逻辑回归模型_RF模型

import sys
import numpy as np

from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression

def load_data():
       input_data = datasets.load_iris()
       x_train, x_test, y_train, y_test = train_test_split(input_data.data, input_data.target, test_size = 0.2, random_state = 0)
       return x_train, x_test, y_train, y_test


def main():
        print("---------")
        x_train, x_test, y_train, y_test = load_data()
        model = LogisticRegression()
        model.fit(x_train, y_train)

        print("w: ", model.coef_)
        print("b: ", model.intercept_)
        print("precision: ", model.score(x_test, y_test))
        print("MSE: ", np.mean((model.predict(x_test) - y_test) ** 2))

if __name__ == '__main__':
        main()

import sys
import numpy as np
from scipy.sparse import csr_matrix
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
#外部输入数据集
data_in = sys.argv[1]
#重写数据集加载函数
def load_data():
#特征的行号
fea_row_list = []
#特征的列号
fea_col_list = []
#标签列表
target_list = []
#特征对应的评分
data_list = []
#行索引
row_index = 0
#最大的特征编号
max_col = 0
#一行行读数据并解析
with open(data_in, 'r') as fd:
for line in fd:
ss = line.strip().split(' ')
label = ss[0]
fea = ss[1:]
target_list.append(int(label))
for fea_score in fea:
sss = fea_score.strip().split(':')
if len(sss) != 2:
continue
feature, score = sss
fea_row_list.append(row_index)
fea_col_list.append(int(feature))
data_list.append(float(score))
if int(feature) > max_col:
max_col = int(feature)
row_index += 1
row = np.array(fea_row_list)
col = np.array(fea_col_list)
data = np.array(data_list)
fea_datasets = csr_matrix((data, (row, col)), shape=(row_index, max_col+1)).toarray()
#当特征维度过大时，选下面这种方式（加toarray（）和不加都是对的），内存不容易爆掉
#fea_datasets = csr_matrix((data, (row, col)), shape=(row_index, max_col+1))
x_train, x_test, y_train, y_test = train_test_split(fea_datasets, target_list, test_size = 0.2, random_state = 0)
return x_train, x_test, y_train, y_test
#自带iris数据集加载函数
#def load_data():
#       input_data = datasets.load_iris()
#
#       x_train, x_test, y_train, y_test = train_test_split(input_data.data, input_data.target, test_size = 0.2, random_state = 0)
#
#       return x_train, x_test, y_train, y_test
def main():
print("---------")
x_train, x_test, y_train, y_test = load_data()
model = LogisticRegression()
model.fit(x_train, y_train)
print("w: ", model.coef_)
print("b: ", model.intercept_)
print("precision: ", model.score(x_test, y_test))
print("MSE: ", np.mean((model.predict(x_test) - y_test) ** 2))
if __name__ == '__main__':
main()