# __author__ = 'heyin'
# __date__ = '2018/11/22 9:22'
import pandas as pd
import numpy as np
from sklearn.linear_model import LogisticRegression, LogisticRegressionCV
from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import classification_report


def logic():
    column = ['Sample code number', 'Clump Thickness', 'Uniformity of Cell Size', 'Uniformity of Cell Shape',
              'Marginal Adhesion', 'Single Epithelial Cell Size', 'Bare Nuclei', 'Bland Chromatin', 'Normal Nucleoli',
              'Mitoses', 'Class']

    # 读取数据
    data = pd.read_csv('./cancer.csv', names=column)
    # 替换数据中的问号
    data.replace(to_replace='?', value=np.nan, inplace=True)
    # 然后删除nan所在的行
    data.dropna(how='any', inplace=True)

    x = data.iloc[:, 1:10]
    y = data.loc[:, 'Class']

    x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.25, random_state=1)
    sd = StandardScaler()
    x_train = sd.fit_transform(x_train)
    x_test = sd.transform(x_test)

    # lr = LogisticRegression()
    # params = {'solver': ['lbfgs'], 'penalty': ['l2'], 'C': [0.01, 0.1, 1.0, 10.0, 100.0]}
    # gv = GridSearchCV(lr, param_grid=params, cv=4)
    #
    # gv.fit(x_train, y_train)
    # y_pred = gv.predict(x_test)
    #
    # print(gv.best_score_)
    # print(gv.best_params_)
    #
    # print('训练集score：', gv.score(x_train, y_train))
    # print('测试集score：', gv.score(x_test, y_test))

    # 以下是通过上边的网格搜索得出的C值
    c = [0.01, 0.1, 1.0, 10.0, 100.0]
    for i in range(5):
        print('*' * 20, i)
        lr = LogisticRegression(C=c[i], solver='lbfgs', penalty='l2')
        lr.fit(x_train, y_train)
        y_pred = lr.predict(x_test)
        print('训练集score：', lr.score(x_train, y_train))
        print('测试集score：', lr.score(x_test, y_test))
        print(classification_report(y_test, y_pred, labels=[2, 4], target_names=['良性', '恶性']))


def l_stock():
    # 从csv文件获取数据
    df = pd.read_csv('./stockdata/sh.csv')
    df.pop('date')
    y = df.pop('up_down')
    x = df
    # 特征工程需要拆分训练集和测试集后进行
    x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.25, random_state=1)
    # 数据标准化处理
    std = StandardScaler()
    x_train = std.fit_transform(x_train)
    x_test = std.transform(x_test)
    c = [0.01, 0.1, 1.0, 10.0, 100.0]
    for i in range(5):
        print('*' * 20, i)
        lr = LogisticRegression(C=c[i])
        lr.fit(x_train, y_train)
        y_pred = lr.predict(x_test)
        print("训练集score:", lr.score(x_train, y_train))
        print("测试集score:", lr.score(x_test, y_test))
        print(classification_report(y_test, y_pred, labels=[0, 1], target_names=['跌', '涨']))


if __name__ == '__main__':
    # logic()
    l_stock()