数据挖掘作业：财政收入影响因素分析及预测

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
inputfile = 'D:/anaconda/data/data.csv'
data = pd.read_csv(inputfile)
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：\n',np.round(description,2))

corr = data.corr(method = 'pearson')
print('相关系数矩阵为：\n',np.round(corr,2))
plt.rcParams['font.sans-serif'] = 'SimHei'
plt.subplots(figsize = (10,10))
sns.heatmap(corr,annot = True,vmax = 1,square = True,cmap = 'Greens')
plt.title('学号2020310143040')
plt.show()
plt.close

运行结果：

 

 1 import numpy as np
 2 import pandas as pd
 3 from sklearn.linear_model import Lasso
 4 
 5 inputfile = 'D:/anaconda/data/data.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
mask = np.append(mask,True)
print('相关系数是否为零：',mask)
outputfile = 'D:/anaconda/data/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)

运行结果：

 

 

 

# 代码6-5

import sys
sys.path.append('D:/anaconda/Scripts')  # 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 = 'D:/anaconda/data/new_reg_data.csv'  # 输入的数据文件
inputfile2 = 'D:/anaconda/data/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
l = ['x1', 'x3', 'x4', 'x5', 'x6', 'x7', 'x8', 'x13']
for i in l:
  f = GM11(new_reg_data.loc[range(1994, 2014),i].values)[0]
  new_reg_data.loc[2014,i] = f(len(new_reg_data)-1)  # 2014年预测结果
  new_reg_data.loc[2015,i] = f(len(new_reg_data))  # 2015年预测结果
  new_reg_data[i] = new_reg_data[i].round(2)  # 保留两位小数
outputfile = 'D:/anaconda/data/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])
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[2014:2015,:])  # 预测结果展示



# 代码6-6
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.svm import LinearSVR

inputfile = 'D:/anaconda/data/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:/anaconda/data/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('学号2020310143040')
plt.show()

运行结果：