财政相关性分析

#数据分析

import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
inputfile = './data.csv'
data = pd.read_csv(inputfile)
describe = data.describe() #describe()函数能算出数据集的八个统计量
print(describe)

 

 

 2.相关性分析

corr = data.corr(method = 'pearson')
pd.options.display.float_format = '{:,.2f}'.format ## 指定小数位数
data.corr()
# print(np.round(corr,2))

 

 

3.绘制热力图

import matplotlib.pyplot as plt
import seaborn as sns
plt.subplots(figsize=(10,10))
sns.heatmap(corr,annot = True,vmax = 1,square = True,cmap = "Accent")
plt.rcParams['font.sans-serif'] = ['SimHei']  # 用来正常显示中文标签
plt.title('相关性热力图')
plt.show()
plt.close

 

 4.Lasso回归

from sklearn.linear_model import Lasso
inputfile = './data.csv'
data = pd.read_csv(inputfile)
lasso = Lasso(1000)
lasso.fit(data.iloc[:,0:14],data['y'])
print(np.round(lasso.coef_,5))
print(np.sum(lasso.coef_ != 0))

mask = lasso.coef_ != 0
print(mask)

outputfile = './new_reg_data.csv'
new_reg_data = data.iloc[:,mask]
new_reg_data.to_csv(outputfile)
print(new_reg_data.shape)

 

5.灰色预测模型

 

import sys
sys.path.append('./code')  # 设置路径
import numpy as np
import pandas as pd
from GM11 import GM11  # 引入自编的灰色预测函数

inputfile1 = './new_reg_data.csv'  # 输入的数据文件
inputfile2 = './data.csv'  # 输入的数据文件
new_reg_data = pd.read_csv(inputfile1)  # 读取经过特征选择后的数据
data = pd.read_csv(inputfile2)  # 读取总的数据
new_reg_data.index = range(1994, 2014)
new_reg_data.loc[2014] = None
new_reg_data.loc[2015] = None
new_reg_data.loc[2016] = None
l = ['x1', 'x4', 'x5', 'x6', 'x7', 'x8']
for i in l:
    f = GM11(new_reg_data.loc[range(1994, 2014),i].to_numpy())[0]
    new_reg_data.loc[2014,i] = f(len(new_reg_data)-1)  # 2014年预测结果
    print(new_reg_data.loc[2014,i])
    new_reg_data.loc[2015,i] = f(len(new_reg_data))  # 2015年预测结果
    print(new_reg_data.loc[2015,i])
    new_reg_data.loc[2016,i] = f(len(new_reg_data)+1)  # 2016年预测结果
    print(new_reg_data.loc[2016,i])
    new_reg_data[i] = new_reg_data[i].round(3)  # 保留两位小数
    print("*"*50)
outputfile = './new_reg_data_GM11.xls'  # 灰色预测后保存的路径
y = list(data['y'].values)  # 提取财政收入列，合并至新数据框中
y.extend([np.nan,np.nan,np.nan])
new_reg_data['y'] = y
new_reg_data.to_excel(outputfile)  # 结果输出
print('预测结果为：\n',new_reg_data.loc[2015:2016,:])  # 预测结果展示