pandas归一化某一列_pandas 数据归一化以及行删除例程的方法

#coding:utf8

import pandas as pd

import numpy as np

from pandas import Series,DataFrame

# 如果有id列，则需先删除id列再进行对应操作，最后再补上

# 统计的时候不需要用到id列,删除的时候需要考虑

# delete row

def row_del(df, num_percent, label_len = 0):

#print list(df.count(axis=1))

col_num = len(list(list(df.values)[1])) - label_len # -1为考虑带标签

if col_num<0:

print 'Error'

#print int(col_num*num_percent)

return df.dropna(axis=0, how='any', thresh=int(col_num*num_percent))

# 如果有字符串类型，则报错

# data normalization -1 to 1

# label_col: 不需考虑的类标，可以为字符串或字符串列表

# 数值类型统一到float64

def data_normalization(df, label_col = []):

lab_len = len(label_col)

print label_col

if lab_len>0:

df_temp = df.drop(label_col, axis = 1)

df_lab