数据预处理练习 等频分箱、one_hot(独热编码)、数据归一化 #python

1.输入：一列数值型数据，输出:与输入等长的一列数据，每一项是输入数据在整列中的排序序号。如，输入：0.1 0.8 0.25，输出1 3 2
2.求给定一组数值型数据的均值、方差
3.给定两列数值型数据，求其和，积，差，商，输出数据列和输入等长，每一项为输入数据相应位置数据的和、积、差、商
4.给定一组数值型数据，将其归一化，（两种方式，最大最小归一化，Z-score标准化）
5.给定一组数值型数据以及一个预先给定的整数，将该组数据进行装箱
6.给定一组标称型数据，利用one-hot编码方法将其转换为多组01值数据

listOne=[1,2,3,4,5,6,7,8,9,10,11,12,13]
name   =['steven','robin','obama']
action =['playing','eating','sleeping']
local  =['home','school','playground']
mixList=[name,action,local]

#taskOne
def indexList(list):
return map(lambda x:sorted(list).index(x)+1,list)

#taskTwo
from numpy import average,std
def aveStd(list):
return average(list),std(list)

#taskThree
def opreList(list_1,list_2,operation='add'):
func=lambda L:L[0]+L[1]
if(operation=='sub'):
func=lambda L:L[0]-L[1]
if(operation=='multi'):
func=lambda L:L[0]*L[1]
if(operation=='div'):
func=lambda L:L[0]*1.0/L[1]
innerList=map(func,zip(list_1,list_2))
return innerList

#taskFour
from numpy import array
from sklearn import preprocessing
def normalization(list,method='z_score',feature_range=(0,1)):
x=x_scaled=array(list)*1.0
if(method=='z_score'):
x_scaled=preprocessing.scale(x)
return x_scaled
if(method=='MaxMin'):
Scaler=preprocessing.MinMaxScaler(feature_range).fit(x)#get scale_,min_
x_scaled=Scaler.transform(x)
return x_scaled

#taskFive Create an equifrequence box
def binning_depth(list,depth):
head=tail=0 #recorded the local of each box

8f19
counter=0
for index1 in range(len(list)):
counter+=1
if(index1+2*depth>len(list)):
if(len(list)-index1-depth<0.5*depth):
head=len(list)
ave=average(list[tail:head])
while(tail!=head):
list[tail]=ave
tail+=1
return list
if(counter==depth or index1==len(list)-1):
head=index1+1
ave=average(list[tail:head])
while(tail!=head):
list[tail]=ave
tail+=1
counter=0
return list

#taskSix
import numpy as np
def one_hot(referenceList,transformList):
newRrefence=[]
for list in referenceList:
newRrefence+=list
code=np.zeros(len(newRrefence))
for elemt in transformList:
code[newRrefence.index(elemt)]=1
return code

if __name__=='__main__':
print 'taskOne:'
print indexList(listOne)
print 'taskTwo:'
print aveStd(listOne)
print 'taskThree:'
print opreList(listOne,listOne,'add')
print 'taskFour:MaxMin:'
print normalization(listOne,method='MaxMin',feature_range=(0,1))
print 'taskFour:z_score:'
print normalization(listOne,method='z_score')
print 'taskFive:'
print binning_depth(listOne,3)
print 'taskSix:'
print one_hot(mixList,['steven','playing','home'])