#coding=utf-8 import pandas as pd import numpy as np import matplotlib.pyplot as plt

df = pd.read_csv("./team.csv") df

df.describe()

df.set_index('name',inplace=True) df.head()

df.sample(4) df.index df.columns

df[['team','Q1']]

df.loc[:,['team','Q1']]

df[df.index=='Liver']

df[0:3]

df.loc['Austin7':'Ben','Q1':'Q4']

df[df['Q1']>90]

df[(df['Q1']>90) & (df['team']=='C')]

df.sort_values(['Q1','team'],ascending=[True,False])# True升,False降

df.groupby('team').sum()

df.groupby('team').agg({ 'Q1':'sum', 'Q2':'count', 'Q3':'mean', 'Q4':'max' })

df['total'] = df.loc[:,'Q1':'Q4'].apply(lambda x:sum(x),axis=1) df['total']

df['avg'] = df['total']/4 df['avg']

df.mean(1) # 返回所有行的均值，下同 df.corr() # 返回列与列之间的相关系数 df.count() # 返回每一列中的非空值的个数 df.max() # 返回每一列的最大值 df.min() # 返回每一列的最小值 df.median() # 返回每一列的中位数 df.std() # 返回每一列的标准差 df.var() # 方差 df.mode() # 众数

df['Q1'].plot()

df.loc['Ben','Q1':'Q4'].plot()

df.loc['Ben','Q1':'Q4'].plot.bar()

df.groupby('team').sum().T.plot()

df.groupby('team').count().Q1.plot.pie()

dates = pd.date_range('20130101',periods=6) df = pd.DataFrame(np.random.randn(6,4),index=dates,columns=list(range(1,5))) df1 = df.reindex(index=dates[0:4],columns=list(df.columns)+['5']) df1.loc[dates[0]:dates[1],'5'] = 1 df1

df1.dropna(how='any')

minus = df.apply(lambda x:x.max()-x.min(),axis=1) df1.loc[:,"minus"] = minus df1

df.apply(lambda x:x.max()-x.min())

left = pd.DataFrame({'key': ['foo', 'foo'], 'lval': [1, 2]}) right = pd.DataFrame({'key': ['foo', 'foo'], 'rval': [4, 5]}) pd.merge(left,right,on='key')

rng = pd.date_range('20120101',periods=100,freq='S') ts = pd.Series(np.random.randint(0,500,len(rng)),index=rng) ts

ts.tz_localize('UTC')

ts.to_period()

ts.plot()