ML算法——线性回归随笔【机器学习】【六一创作】

from sklearn.linear_model import LinearRegression
from sklearn import preprocessing

lr = LinearRegression()
lr.fit(X_train, y_train)
lr.score(X_test, y_test) # 使用绝对系数 R^2 

Forecast = lr.predict(X_Predict)

import numpy as np 
import pandas as pd 
import matplotlib.pyplot as plt
from datetime import datetime as dt

import tushare as ts

df = ts.get_hist_data('000001') #平安银行代码 000001
df.to_csv('000001.csv')
df = pd.read_csv('./000001.csv') 

df['date'] = pd.to_datetime(df['date'])
df = df.set_index('date')
# 按照时间升序排列
df.sort_values(by=['date'], inplace=True, ascending=True)

df.dropna(axis=0 , inplace=True)
df.isna().sum()

Min_date = df.index.min()
Max_date = df.index.max()
print ("First date is",Min_date)
print ("Last date is",Max_date)
print (Max_date - Min_date)

from plotly import tools
from plotly.graph_objs import *
from plotly.offline import init_notebook_mode, iplot, iplot_mpl
init_notebook_mode()
import plotly.plotly as py
import plotly.graph_objs as go

trace = go.Ohlc(x=df.index, open=df['open'], high=df['high'], low=df['low'], close=df['close'])
data = [trace]
iplot(data, filename='simple_ohlc')

from sklearn.linear_model import LinearRegression
from sklearn import preprocessing

num = 5 # 预测5天后的情况
df['label'] = df['close'].shift(-num) # 预测值

Data = df.drop(['label', 'price_change', 'p_change'],axis=1)


X = Data.values
X = preprocessing.scale(X)
X = X[:-num]

df.dropna(inplace=True)#去掉缺失值所在的行
Target = df.label
y = Target.values

X_train, y_train = X[0:550, :], y[0:550]
X_test, y_test = X[550:, -51:], y[550:606]

lr = LinearRegression()
lr.fit(X_train, y_train)
lr.score(X_test, y_test) #训练好的lr 投喂 X_test得到 pred_test 与 y_test 做评估，越大越好
# 预测
X_Predict = X[-num:] #取最后 num 条数据
Forecast = lr.predict(X_Predict)

trange = pd.date_range('2019-05-13', periods=num, freq='d')

Predict_df = pd.DataFrame(Forecast, index=trange)
Predict_df.columns = ['forecast']

df = pd.read_csv('./000001.csv') 
df['date'] = pd.to_datetime(df['date'])
df = df.set_index('date')

df.sort_values(by=['date'], inplace=True, ascending=True)
df_concat = pd.concat([df, Predict_df], axis=1)

df_concat = df_concat[df_concat.index.isin(Predict_df.index)]
df_concat.tail(num)

df_concat['close'].plot(color='green', linewidth=1)
df_concat['forecast'].plot(color='orange', linewidth=3)
plt.xlabel('Time')
plt.ylabel('Price')
plt.show()

for idx, col_name in enumerate(['open', 'high', 'close', 'low', 'volume', 'ma5', 'ma10', 'ma20', 'v_ma5', 'v_ma10', 'v_ma20']):
    print("The coefficient for {} is {}".format(col_name, lr.coef_[idx]))