均一化

df = pd.read_excel('桃園全區實價登錄資料_20190430修改後_轉數字_lite.xls',0)

#全部的空白
df=df.fillna(-1)

print(df.head())
print(df.columns)
print(df.index)
print(df.columns)

columnsName=['鄉鎮市區_Code','交易標的_Code','土地區段位置建物區段門牌_Code']
dfX=df[columnsName]
dfY=df["總價元"]

dfX = (dfX - dfX.min()) / (dfX.max() - dfX.min())

dfY = (dfY - dfY2.min()) / (dfY2.max() - dfY2.min())  # 均一化

X=dfX.to_numpy()
Y=dfY.to_numpy()
X_train ,X_test ,Y_train ,Y_test = train_test_split(X,Y,test_size=0.01)