python第二周作业

import numpy as np
import pandas as pd

inputfile = 'C://Users//Administrator//Desktop//data.csv' # 输入的数据文件
data = pd.read_csv(inputfile) # 读取数据

# 描述性统计分析
description = [data.min(), data.max(), data.mean(), data.std()] # 依次计算最小值、最大值、均值、标准差
description = pd.DataFrame(description, index = ['Min', 'Max', 'Mean', 'STD']).T # 将结果存入数据框

print('描述性统计结果：\n',np.round(description, 2)) # 保留两位小数
# 代码6-2

# 相关性分析
corr = data.corr(method = 'pearson') # 计算相关系数矩阵
print('相关系数矩阵为：\n',np.round(corr, 2)) # 保留两位小数

 

# 代码6-3

# 绘制热力图
import matplotlib.pyplot as plt
import seaborn as sns
plt.subplots(figsize=(10, 10)) # 设置画面大小
sns.heatmap(corr, annot=True, vmax=1, square=True, cmap="Blues")
plt.title('相关性热力图 3022')
plt.show()
plt.close

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

inputfile ='C://Users//Administrator//Desktop//data.csv'
data = pd.read_csv(inputfile)
lasso = Lasso(1000)
lasso.fit(data.iloc[:,0:13],data['y'])
print('徐韵晴 3022')
print('相关系数为：',np.round(lasso.coef_,5))
print('相关非零个数为：',np.sum(lasso.coef_ != 0))
mask =lasso.coef_ != 0
print('相关系数是否为零：',mask)
mask = np.append(mask,True)
print('相关系数是否为零：',mask)
outputfile ='C://Users//Administrator//Desktop//tmp//new_reg_data3.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 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 = 'C://Users//Administrator//Desktop//tmp//new_reg_data3.csv' # 输入的数据文件
inputfile2 = 'C://Users//Administrator//Desktop//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', 'x3', 'x4', 'x5', 'x6', 'x7', 'x8', 'x13']
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)-2) # 2014年预测结果
new_reg_data.loc[2015,i] = f(len(new_reg_data)-1) # 2015年预测结果
new_reg_data.loc[2016,i] = f(len(new_reg_data)) # 2016年预测结果
new_reg_data[i] = new_reg_data[i].round(2) # 保留两位小数

outputfile = 'C://Users//Administrator//Desktop//te//new_reg_data_GM22.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[2014:2016,:]) # 预测结果展示

import matplotlib.pyplot as plt
from sklearn.svm import LinearSVR

inputfile = 'C://Users//Administrator//Desktop//te//new_reg_data_GM22.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_train = data.iloc[0:20,:].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 = '../te/new_reg_data_GM22_revenue.xls' #