from matplotlib import pyplot as plt
from sklearn import linear_model
from sklearn.model_selection import train_test_split
import numpy as np
import pandas as pd
plt.rcparams['font.sans-serif'] = ['kaiti']
data_path1 = 'housing_true.xls'
hd1 = pd.read_excel(data_path1)
data_ = hd1.drop(['medv'],axis=1)
y1 = hd1['medv']
y = np.reshape(y1,len(y1),1)
#將資料集7:3比例分割
x_train, x_test, y_train, y_test =train_test_split(data_,y,test_size=0.3,random_state=1)
#訓練lr = linear_model.linearregression()
lr.fit(x_train,y_train)
score_test = lr.score(x_test,y_test)
print(score_test)
#print(lr.coef_)#斜率
#plt.plot(lr.coef_)#斜率視覺化
test_pre = lr.predict(x_test)
#print(test_pre)
#print(y_test)
dev = y_test-test_pre #偏差
#print(dev)
rmse = np.sum(np.sqrt(dev*dev))/152#共152資料
print(rmse)#均方根誤差
x_data = range(0,len(x_test))
y_data1 = y_test
#print(len(y_data1))
y_data2 = test_pre
plt.figure(figsize=(20,8),dpi=80)
plt.plot(x_data,y_data1,label='實際值')
plt.plot(x_data,y_data2,label='**值')
plt.grid(alpha = 0.3)#網格，alpha為透明度
plt.ylabel("房價")
plt.legend()
plt.show()
##儲存**的值
#result =
#result_file = pd.dataframe(result)
#result_file.head()
#result_file.to_csv('test_pre_housing_true.csv')#儲存**的值
波士頓房價資料集視覺化
將所有屬性與房價之間的關係視覺化 import matplotlib.pyplot as plt import numpy as np import tensorflow as tf plt.rcparams font.sans serif microsoft yahei 指定預設字型 plt.rc...
Python 波士頓房價資料主成分PCA分析降維
import pandas as pd import matplotlib.pyplot as plt import numpy as np from sklearn import datasets,metrics from sklearn.linear model import linearreg...
使用sklearn載入波士頓房價資料集
使用sklearn載入波士頓房價資料集 從sklearn匯入資料集 from sklearn.datasets import load boston載入資料 boston load boston x為輸入，y為輸出 x boston.data y boston.target檢視資料有哪些字段 載入的...