[Python知识库]pandas表操作

# -*- coding:utf-8
import pandas as pd
import numpy as np
import datetime
from pylab import *
#设置界面显示的最大行列数据量
from pandas.tests.plotting.test_converter import dates

pd.options.display.max_colums = 10
#读取数据
df = pd.read_csv("*.csv")
#查看数据量、数据指标和数据维度
print(df.shape)
#查看数据的尺寸大小
print(df.size)
#查看前N条数据
df.head()

#对缺失值的处理
df1 = df.reindex(index=dates[:4],columns=["ABCD"]+["G"])
df1.loc[dates[0]:dates[1],"G"] = 1
print(df1)
print(df1.dropna())
print(df1.fillna(value=2))

#statistic
print(df.mean)
print(df.var())
s = pd.Series([1,2,4,np.nan,5,7,9,10],index = dates)

print(s)
print(s.shift(2))
print(s.diff())
print(df.apply(np.cumsum))
print(df.apply(lambda x:x.max()-x.min()))

#Concat
pieces = [df[:3],df[-3:]]
print(pd.concat(pieces))
left = pd.DataFrame({"key":["x","y"],"value":[1,2]})
right = pd.DataFrame({"key":["x","z"],"value":[3,4]})
print("LEFT",left)
print("RIGHT",right)
print(pd.merge(left,right,on="key",how="left"))#how="inner"
df3 = pd.DataFrame({"A",["a","b","c","d"],"B":list(range(4))})
print(df3.groupby("A").sum())

#Reshape   交叉分析中起注释作用
df4 = pd.DataFrame({'A':['one','one','two','three']*6,
                    'B':['a','b','c']*8
                    'C':['foo','foo','bar','bar','bar','bar'] * 4,
                    'D':np.random.randn(24),
                    'E':np.random.randn(24),
                    'F':[datetime.datetime(2017,i,1) for i in range(1,13)]+
                        [datetime.datetime(2017,i,15) for i in range(1,13)]})
#做透视表
print(pd.pivot_table(df4,values="D",index=["A","B"],columns=["C"]))

# Time Series 时间序列
t_txam = pd.date_range("20170301",periods=10,freq="S")
print(t_txam)

#Graph 画图
ts = pd.Series(np.random.randn(1000),index = pd.date_range("20170301",periods=1000))
ts = ts.cumsum()
ts.plot()
show()
#File 文件操作