财政收入相关分析

数据描述

import pandas as pd
import numpy as np

data=pd.read_csv("D:\Python\数据处理\data.csv")
description = [data.min(),data.max(),data.mean(),data.std()]
description = pd.DataFrame(description,index=['Min','Max','Mean','STD']).T
print('描述性统计结果3152：\n',np.round(description,2))

 

 

相关性分析

corr = data.corr(method = 'pearson')
print('相关系数矩阵为3152：\n',np.round(corr,2))

 

 相关性热力图

import matplotlib.pyplot as plt
import seaborn as sns
plt.rcParams['font.sans-serif'] = ['SimHei']  # 用来正常显示中文标签
plt.rcParams['axes.unicode_minus'] = False  # 用来正常显示负号
plt.subplots(figsize=(10,10))
sns.heatmap(corr,annot=True,vmax=1,square=True,cmap="Blues")
plt.title('相关性热力图3152',fontsize=20)
plt.show()
plt.close

 

 

import pandas as pd
import numpy as np
from sklearn.linear_model import Lasso #sklearn中的线性模型

data=pd.read_csv("D:\Python\数据处理\data.csv")
lasso = Lasso(1000)
lasso.fit(data.iloc[:,0:13],data['y'])
data = data.iloc[:,0:13]
print('相关系数为：',np.round(lasso.coef_,5)) #..保留五位小数
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='D:\Python\数据处理/new_reg_data.csv'
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)

 

 

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

inputfile = 'D:\Python\数据处理/new_reg_data_GM11.xls'  # 灰色预测后保存的路径
data = pd.read_excel((inputfile),index_col = 0,header = 0)  # 读取数据
feature = ['x1', 'x3', 'x4', 'x5', 'x6', 'x7', 'x8', 'x13']  # 属性所在列
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].values  # 属性数据
y_train = data_train['y'].values  # 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]).values  # 预测，并还原结果。
data['y_pred'] = linearsvr.predict(x) * data_std['y'] + data_mean['y']
outputfile = 'D:\Python\数据处理/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']])
plt.rcParams['font.sans-serif'] = 'SimHei'
fig = data[['y','y_pred']].plot(subplots = True, style=['b-o','r-*'])  # 画出预测结果图
plt.title('3152',fontsize=20)
plt.show()