预测模型利用

import numpy as np
import pandas as pd
from sklearn.linear_model import Lasso

inputfile ='datayc.csv'
data = pd.read_csv(inputfile)
lasso = Lasso(1000)
lasso.fit(data.iloc[:,0:13],data['y'])
print('相关系数为:',np.round(lasso.coef_,5))
print('相关系数非零个数为:',np.sum(lasso.coef_ != 0))

mask = lasso.coef_ != 0

print('相关系数是否为零:',mask)

outputfile ='new_reg_data.csv'
mask = np.append(mask,True)
new_reg_data = data.iloc[:, mask]

new_reg_data.to_csv(outputfile)

print('输出数据的维度为:',new_reg_data.shape)

 找到相关系数不为零的数据

建立灰度预测模型

import numpy as np
import pandas as pd
from GM11 import GM11
inputfile1 = 'new_reg_data.csv'
inputfile2 = 'datayc.csv'
new_reg_data = pd.read_csv(inputfile1)
data = pd.read_csv(inputfile2)
new_reg_data.index = range(1994,2014)
new_reg_data.loc[2014] = None
new_reg_data.loc[2015] = None
cols =  ['x1','x3','x4','x5','x6','x7','x8','x13','y']
for i in cols:
    f = GM11(new_reg_data.loc[range(1994,2014),i].values)[0]
    new_reg_data.loc[2014,i] = f(len(new_reg_data)-1)
    new_reg_data.loc[2015,i] = f(len(new_reg_data))
    new_reg_data[i] = new_reg_data[i].round(2)
outputfile = 'new_reg_data_GM11.xls'
y = list(data['y'].values)
y.extend([np.nan,np.nan])
new_reg_data['y'] = y
new_reg_data.to_excel(outputfile)
print('预测结果为：\n',new_reg_data.loc[2014:2015,:])

 进行预测

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.svm import LinearSVR

inputfile = "new_reg_data_GM11.xls"  # 灰色预测后保存的路径
data = pd.read_excel(inputfile)  # 读取数据
feature = ['x1', 'x3', 'x4', 'x5', 'x6', 'x7', 'x8', 'x13']  # 属性所在列

data.index = range(1994, 2016)
data_train = data.loc[range(1994, 2014)].copy()  # 取2014年前的数据建模
data_mean = data_train.mean()
data_std = data_train.std()
data_train = (data_train - data_mean)/data_std  # 数据标准化
x_train = data_train[feature].to_numpy()  # 属性数据
y_train = data_train['y'].to_numpy()  # 标签数据

linearsvr = LinearSVR()  # 调用LinearSVR()函数
linearsvr.fit(x_train,y_train)
x = ((data[feature] - data_mean[feature])/data_std[feature]).to_numpy()  # 预测，并还原结果。
data['y_pred'] = linearsvr.predict(x) * data_std['y'] + data_mean['y']
outputfile ="new_reg_data_GM11_revenue.xls"  # SVR预测后保存的结果
data.to_excel(outputfile)

print('真实值与预测值分别为：\n',data[['y','y_pred']])

fig = data[['y','y_pred']].plot(subplots = True, style=['b-o','r-*'])  # 画出预测结果图
plt.rcParams['font.sans-serif'] = ['SimHei'] # 添加这条可以让图形显示中文
plt.title('学号3106')
plt.show()