numpy-pandas 使用

#coding=utf-8
import numpy as np
import pandas as pd
from collections import Counter
#python 基本字符串处理
str = "ABCdefg"
# print("转化为小写",str.lower())
# print("转化为大写",str.upper())
# print(str[2])
str = "a v b b b\tvv"
#print("删除首尾空格",str.strip())
#print("以空格分割字符串",str.split(" "))
# print ("以逗号链接字符串",",".join(str.split(" ")))
# print("计算b在字符串中出现的次数"，str.count('b'))
# print(str.find('b'))


####列表集合字典
str = "abddhed" #字符串是一个列表
#print (list(set(str))) #集合不是序列所以无法索引，只能转化为列表。
# print (dict(enumerate(str)))
# key = ['a','b','c','d','e','f','g']
# print (dict(zip(key,str)))
# str = Counter(str)
# print(str.most_common())
# print(dict(str.most_common()))


#numpy
'''
print("3行4列的单位阵",np.ones([3,4],dtype=np.int16))
print("2行4列的零阵",np.zeros([2,4],dtype=np.int16).astype(np.float64))
print(np.zeros([2,4]).dtype)
 
a = np.array([[1,2,3,4],[5,6,7,8]])
print(np.min(a,axis=1))
print(a[:,1:3])
print((a>2)&(a<7))
print((a<2)|(a>7))
print(np.greater(a[0],a[1]))  #比较后一个是否比前一个大

a = a.astype(np.float16)
a[0][1] = np.nan
print(np.isnan(a))

str = "AAaavvbbasdsds"
str = np.array(list(str))
print(np.unique(str))
str1 = "vafaeafafafa"
print(set(str)&set(str1)) #集合交集
print(set(str)|set(str1)) #集合并集
'''


#pandas
a = pd.Series([1.0,2,7,5,4,5,79,63,7,8])
print(a)
print(a.values)
print(a.index.values)
a = pd.Series(dict(zip(['a','b','c','d'],[2,5,8,9])))
print(a)

a = pd.DataFrame([[1,2,3,4],[5,6,7,8],[9,10,11,12]],columns=['a','b','c','d'],index=['a1','b1','c1'])
print(a)
print(a.columns)
print(a.index)
print(a.head())
a['total']=a.sum(axis=1)
print(a)
print(a.set_index(a['a']))
print(a.iloc[:,2:4])#获取滴2-3行
print(a.iloc[1:2])#获取第1列

b = pd.DataFrame([[11,22,33,44],[55,66,77,88],[99,10,11,12]],columns=['a11','b11','c11','d11'],index=['b1','a1','c1'])
print(pd.merge(a.reset_index(),b.reset_index()).set_index(a.index))
print(pd.concat([a,b],axis=1))
print(b.iloc[[1,2],[1]])
print(b.loc[['a1','b1'],['b11']])