怎么使用pandas模塊實(shí)現(xiàn)數(shù)據(jù)標(biāo)準(zhǔn)化操作？

import pandas as pd
import numpy as np
def three_sigma(se):
    """
    自實(shí)現(xiàn)3σ原則，進(jìn)行數(shù)據(jù)過濾
    :param se:傳進(jìn)來(lái)的series結(jié)構(gòu)數(shù)據(jù)
    :return:去除異常值之后的series數(shù)據(jù)
    """
    bool_id=((se.mean()-3*se.std())<se) & (se<(se.mean()+3*se.std()))
    print(bool_id)
    return se[bool_id]
 
#加載數(shù)據(jù)
detail=pd.read_excel('./meal_order_detail.xlsx')
#進(jìn)行異常值處理
res=three_sigma(detail['amounts'])
print(detail.shape)
print(res.shape)

(x-min)/(max-min)

import pandas as pd
import numpy as np
 
def minmax_sca(data):
    """
    離差標(biāo)準(zhǔn)化
    param data:傳入的數(shù)據(jù)
    return:標(biāo)準(zhǔn)化之后的數(shù)據(jù)
    """
    new_data=(data-data.min())/(data.max()-data.min())
    return new_data
 
#加載數(shù)據(jù)
detail=pd.read_excel('./meal_order_detail.xlsx')
res=minmax_sca(detail[['amounts','counts']])
print(res)
data=res
bool_id=data.loc[:,'count']==1
print(data.loc[bool_id],'counts')

import pandas as pd
import numpy as np
def stand_sca(data):
    """
    標(biāo)準(zhǔn)差標(biāo)準(zhǔn)化
    :param data:傳入的數(shù)據(jù)
    :return:標(biāo)準(zhǔn)化之后的數(shù)據(jù)
    """
    new_data=(data-data.mean())/data.std()
    return new_data
 
#加載數(shù)據(jù)
detail=pd.read_excel('./meal_order_detail.xlsx')
res=stand_sca(detail[['amounts','counts']])
print(res)
print('res的均值：',res.mean())
print('res的標(biāo)準(zhǔn)差：',res.std())

x/(10^k)
k=math.ceil(log10(max(|x|)))

import pandas as pd
import numpy as np
def deci_sca(data):
    """
    自實(shí)現(xiàn)小數(shù)定標(biāo)標(biāo)準(zhǔn)化
    :param data: 傳入的數(shù)據(jù)
    :return: 標(biāo)準(zhǔn)化之后的數(shù)據(jù)
    """
    new_data=data/(10**(np.ceil(np.log10(data.abs().max()))))
    return new_data
#加載數(shù)據(jù)
detail = pd.read_excel('./meal_order_detail.xlsx')
res = deci_sca(detail[['amounts', 'counts']])
print(res)

from sklearn import preprocessing
# 獲取數(shù)據(jù)
cols = ['OverallQual','GrLivArea', 'GarageCars','TotalBsmtSF', 'FullBath', 'TotRmsAbvGrd', 'YearBuilt'] ##選取列
x = data_train[cols].values
y = data_train['SalePrice'].values  
x_scaled = preprocessing.StandardScaler().fit_transform(x) ##進(jìn)行歸一化
y_scaled = preprocessing.StandardScaler().fit_transform(y.reshape(-1,1))##先將y轉(zhuǎn)換成一列，再進(jìn)行歸一
 

# 先將數(shù)據(jù)標(biāo)準(zhǔn)化
from sklearn.preprocessing import StandardScaler
ss = StandardScaler() ##
#用測(cè)試集訓(xùn)練并標(biāo)準(zhǔn)化
ss.fit(missing_age_X_train)##首先f(wàn)it
missing_age_X_train = ss.transform(missing_age_X_train) #進(jìn)行transform
missing_age_X_test = ss.transform(missing_age_X_test)

from sklearn import preprocessing
f_names = ['CentralAir', 'Neighborhood'] ##需要處理的數(shù)據(jù)標(biāo)簽 
for x in f_names:
    label = preprocessing.LabelEncoder()
    data_train[x] = label.fit_transform(data_train[x]) ##數(shù)據(jù)標(biāo)準(zhǔn)化

title_mapping = {"Mr": 1, "Miss": 2, "Mrs": 3, "Master": 4, "Rare": 5}#將標(biāo)簽對(duì)應(yīng)數(shù)值
train_df['Title'] = train_df['Title'].map(title_mapping)#處理數(shù)據(jù)
train_df['Title'] = train_df['Title'].fillna(0)##將其余標(biāo)簽填充為0值

train_test.loc[train_test["Age"].isnull() ,"age_nan"] = 1 ##將標(biāo)簽轉(zhuǎn)換成1
train_test.loc[train_test["Age"].notnull() ,"age_nan"] = 0##將此標(biāo)簽成為0
train_test = pd.get_dummies(train_test,columns=['age_nan']) ##columns決定哪幾行分列處理，prefix參數(shù)是每列前綴