python学习14---pandas中Series与DataFrame的初步认识

import numpy as np
import pandas as pd
import sys
from pandas import Series,DataFrame

###pandas
#Series
obj = Series([4,7,-5,3])
print(obj)

# 真值
print(obj.values)
# 索引值
print(obj.index)

# 可以自己构建索引参数
obj2 = Series([4,7,-5,3],index= ['a','b','c','d'])
print(obj2)
# 选取单个
print(obj2['b'])
obj2['b'] = -9
# 选取需要的索引元素
print(obj2[['a','b','c']])

# 选取其中大于0的元素
print(obj2[obj2>0])

print(obj2*2)

print(np.exp(obj2))

print('b' in obj2)
print('e' in obj2)

# 可以通过字典直接船舰Series
sdata = {'onhi':3500,'faf':432,'fa8':876}
obj3 = Series(sdata)
print(obj3)

states = ['faf','onhi','fdffe']
obj4 = Series(sdata,states)
print(obj4)
# 返回是否缺失
print(pd.isnull(obj4))
print(obj4.isnull())

# 根据索引两数组相加
print(obj3+obj4)

# Series中都有一个name属性
obj4.name = 'population'
obj4.index.name = 'state'
print(obj4)

# 整体修改索引值
obj.index = ['Bob','Steve','Jeff','Ryan']
print(obj)

# Dataframe 表格型数据结构 ---行索引，列索引

data = {'state':['ohio','ohio','nevada','nevadas'],
        'year':[2000,2001,2001,2002],
        'pop':[1.5,1.7,3.6,2.9]}
frame = DataFrame(data)

print (frame)

frame2 = DataFrame(data,columns=['year','state','pop','debt'],index= ['one','two','three','four'])

print(frame2)

# 通过索引可以返回一列(相当于返回Series)
print(frame2['state'])



# 返回行
print(frame2.ix['three'])

frame2['debt'] = np.arange(4) # 注意长度相匹配
print(frame2)
# 转置
print(frame2.T)

arr = np.zeros((3,3))
arr[2,1] = 23
print(arr)

# 索引对象
obj = Series(range(3),index=['a','b','c'])
# 返回的是一个对象类，注意：不可修改，不可修改！！！
index = obj.index

print(index)