Python数据分析库pandas基本操作 Python数据分析库pandas基本操作方法

import numpy as np 
import pandas as pd 
 
s_data = pd.Series([1,3,5,7,np.NaN,9,11])#pandas中生产序列的函数，类似于我们平时说的数组 
print s_data 

import numpy as np 
import pandas as pd 
 
#以20170220为基点向后生产时间点 
dates = pd.date_range('20170220',periods=6) 
#DataFrame生成函数，行索引为时间点，列索引为ABCD 
data = pd.DataFrame(np.random.randn(6,4),index=dates,columns=list('ABCD')) 
print data 
print 
print data.shape 
print 
print data.values 

import numpy as np
import pandas as pd
#设计一个字典
d_data = {'A':1,'B':pd.Timestamp('20170220'),'C':range(4),'D':np.arange(4)}
print d_data
#使用字典生成一个DataFrame
df_data = pd.DataFrame(d_data)
print df_data
#DataFrame中每一列的类型
print df_data.dtypes
#打印A列
print df_data.A
#打印B列
print df_data.B
#B列的类型
print type(df_data.B)

import numpy as np 
import pandas as pd 
 
dates = pd.date_range('20170220',periods=6) 
data = pd.DataFrame(np.random.randn(6,4),index=dates,columns=list('ABCD')) 
print data 
print 
#输出DataFrame头部数据，默认为前5行 
print data.head() 
#输出输出DataFrame第一行数据 
print data.head(1) 
#输出DataFrame尾部数据，默认为后5行 
print data.tail() 
#输出输出DataFrame最后一行数据 
print data.tail(1) 
#输出行索引 
print data.index 
#输出列索引 
print data.columns 
#输出DataFrame数据值 
print data.values 
#输出DataFrame详细信息 
print data.describe() 

import numpy as np 
import pandas as pd 
 
dates = pd.date_range('20170220',periods=6) 
data = pd.DataFrame(np.random.randn(6,4),index=dates,columns=list('ABCD')) 
print data 
print 
#转置 
print data.T 
#输出维度信息 
print data.shape 
#转置后的维度信息 
print data.T.shape 
#将列索引排序 
print data.sort_index(axis = 1) 
#将列索引排序，降序排列 
print data.sort_index(axis = 1,ascending=False) 
#将行索引排序，降序排列 
print data.sort_index(axis = 0,ascending=False) 
#按照A列的值进行升序排列 
print data.sort_values(by='A') 

import numpy as np 
import pandas as pd 
 
dates = pd.date_range('20170220',periods=6) 
data = pd.DataFrame(np.random.randn(6,4),index=dates,columns=list('ABCD')) 
print data 
#输出A列 
print data.A 
#输出A列 
print data['A'] 
#输出3,4行 
print data[2:4] 
#输出3，4行 
print data['20170222':'20170223'] 
#输出3,4行 
print data.loc['20170222':'20170223'] 
#输出3,4行 
print data.iloc[2:4] 
输出B,C两列 
print data.loc[:,['B','C']] 

import numpy as np 
import pandas as pd 
 
dates = pd.date_range('20170220',periods=6) 
data = pd.DataFrame(np.random.randn(6,4),index=dates,columns=list('ABCD')) 
print data 
#输出A列中大于0的行 
print data[data.A > 0] 
#输出大于0的数据，小于等于0的用NaN补位 
print data[data > 0] 
#拷贝data 
data2 = data.copy() 
print data2 
tag = ['a'] * 2 + ['b'] * 2 + ['c'] * 2 
#在data2中增加TAG列用tag赋值 
data2['TAG'] = tag 
print data2 
#打印TAG列中为a,c的行 
print data2[data2.TAG.isin(['a','c'])] 

import numpy as np 
import pandas as pd 
 
dates = pd.date_range('20170220',periods=6) 
data = pd.DataFrame(np.random.randn(6,4),index=dates,columns=list('ABCD')) 
print data 
#将第一行第一列元素赋值为100 
data.iat[0,0] = 100 
print data 
#将A列元素用range(6)赋值 
data.A = range(6) 
print data 
#将B列元素赋值为200 
data.B = 200 
print data 
#将3,4列元素赋值为1000 
data.iloc[:,2:5] = 1000 
print data 

import numpy as np 
import pandas as pd 
 
dates = pd.date_range('20170220',periods = 6) 
df = pd.DataFrame(np.random.randn(6,4) , index = dates , columns = list('ABCD')) 
print df 
#重定义索引，并添加E列 
dfl = df.reindex(index = dates[0:4],columns = list(df.columns)+['E']) 
print dfl 
#将E列中的2,3行赋值为2 
dfl.loc[dates[1:3],'E'] = 2 
print dfl 
#去掉存在NaN元素的行 
print dfl.dropna() 
#将NaN元素赋值为5 
print dfl.fillna(5) 
#判断每个元素是否为NaN 
print pd.isnull(dfl) 
#求列平均值 
print dfl.mean() 
#对每列进行累加 
print dfl.cumsum() 

import numpy as np 
import pandas as pd 
dates = pd.date_range('20170220',periods = 6) 
df = pd.DataFrame(np.random.randn(6,4) , index = dates , columns = list('ABCD')) 
print df 
dfl = df.reindex(index = dates[0:4],columns = list(df.columns)+['E']) 
print dfl 
#针对行求平均值 
print dfl.mean(axis=1) 
#生成序列并向右平移两位 
s = pd.Series([1,3,5,np.nan,6,8],index = dates).shift(2) 
print s 
#df与s做减法运算 
print df.sub(s,axis = 'index') 
#每列进行累加运算 
print df.apply(np.cumsum) 
#每列的最大值减去最小值 
print df.apply(lambda x: x.max() - x.min()) 

import numpy as np 
import pandas as pd 
dates = pd.date_range('20170220',periods = 6) 
df = pd.DataFrame(np.random.randn(6,4) , index = dates , columns = list('ABCD')) 
print df 
#定义一个函数 
def _sum(x): 
 print(type(x)) 
 return x.sum() 
#apply函数可以接受一个函数作为参数 
print df.apply(_sum) 
s = pd.Series(np.random.randint(10,20,size = 15)) 
print s 
#统计序列中每个元素出现的次数 
print s.value_counts() 
#返回出现次数最多的元素 
print s.mode() 

import numpy as np 
import pandas as pd 
 
df = pd.DataFrame(np.random.randn(10,4) , columns = list('ABCD')) 
print df 
#合并函数 
dfl = pd.concat([df.iloc[:3],df.iloc[3:7],df.iloc[7:]]) 
print dfl 
#判断两个DataFrame中元素是否相等 
print df == dfl 

import numpy as np
import pandas as pd

df = pd.DataFrame(np.random.randn(10,4) , columns = list('ABCD'))
print df
left = pd.DataFrame({'key':['foo','foo'],'lval':[1,2]})
right = pd.DataFrame({'key':['foo','foo'],'rval':[4,5]})
print left
print right
#通过key来合并数据
print pd.merge(left,right,on='key')
s = pd.Series(np.random.randint(1,5,size = 4),index = list('ABCD'))
print s
#通过序列添加一行
print df.append(s,ignore_index = True)

import numpy as np 
import pandas as pd 
df = pd.DataFrame({'A': ['foo','bar','foo','bar', 
       'foo','bar','foo','bar'], 
     'B': ['one','one','two','three', 
       'two','two','one','three'], 
     'C': np.random.randn(8), 
     'D': np.random.randn(8)}) 
print df 
print 
#根据A列的索引求和 
print df.groupby('A').sum() 
print 
#先根据A列的索引，在根据B列的索引求和 
print df.groupby(['A','B']).sum() 
print 
#先根据B列的索引，在根据A列的索引求和 
print df.groupby(['B','A']).sum() 

import pandas as pd 
import numpy as np 
#zip函数可以打包成一个个tuple 
tuples = list(zip(*[['bar', 'bar', 'baz', 'baz', 
      'foo', 'foo', 'qux', 'qux'], 
     ['one', 'two', 'one', 'two', 
      'one', 'two', 'one', 'two']])) 
print tuples 
#生成一个多层索引 
index = pd.MultiIndex.from_tuples(tuples, names=['first', 'second']) 
print index 
print 
df = pd.DataFrame(np.random.randn(8, 2), index=index, columns=['A', 'B']) 
print df 
print 
#将列索引变成行索引 
print df.stack() 

import pandas as pd 
import numpy as np 
 
tuples = list(zip(*[['bar', 'bar', 'baz', 'baz', 
      'foo', 'foo', 'qux', 'qux'], 
     ['one', 'two', 'one', 'two', 
      'one', 'two', 'one', 'two']])) 
index = pd.MultiIndex.from_tuples(tuples, names=['first', 'second']) 
df = pd.DataFrame(np.random.randn(8, 2), index=index, columns=['A', 'B']) 
print df 
print 
stacked = df.stack() 
print stacked 
#将行索引转换为列索引 
print stacked.unstack() 
#转换两次 
print stacked.unstack().unstack() 

import pandas as pd 
import numpy as np 
df = pd.DataFrame({'A' : ['one', 'one', 'two', 'three'] * 3, 
     'B' : ['A', 'B', 'C'] * 4, 
     'C' : ['foo', 'foo', 'foo', 'bar', 'bar', 'bar'] * 2, 
     'D' : np.random.randn(12), 
     'E' : np.random.randn(12)}) 
print df 
#根据A，B索引为行，C的索引为列处理D的值 
print pd.pivot_table(df, values='D', index=['A', 'B'], columns=['C']) 
#感觉A列等于one为索引，根据C列组合的平均值 
print df[df.A=='one'].groupby('C').mean() 

import pandas as pd 
import numpy as np 
 
#创建一个以20170220为基准的以秒为单位的向前推进600个的时间序列 
rng = pd.date_range('20170220', periods=600, freq='s') 
print rng 
#以时间序列为索引的序列 
print pd.Series(np.random.randint(0, 500, len(rng)), index=rng) 

import pandas as pd 
import numpy as np 
 
rng = pd.date_range('20170220', periods=600, freq='s') 
ts = pd.Series(np.random.randint(0, 500, len(rng)), index=rng) 
#重采样，以2分钟为单位进行加和采样 
print ts.resample('2Min', how='sum') 
#列出2011年1季度到2017年1季度 
rng1 = pd.period_range('2011Q1','2017Q1',freq='Q') 
print rng1 
#转换成时间戳形式 
print rng1.to_timestamp() 
#时间加减法 
print pd.Timestamp('20170220') - pd.Timestamp('20170112') 
print pd.Timestamp('20170220') + pd.Timedelta(days=12) 

import pandas as pd 
import numpy as np 
 
df = pd.DataFrame({"id":[1,2,3,4,5,6], "raw_grade":['a', 'b', 'b', 'a', 'a', 'e']}) 
print df 
#添加类别数据，以raw_grade的值为类别基础 
df["grade"] = df["raw_grade"].astype("category") 
print df 
#打印类别 
print df["grade"].cat.categories 
#更改类别 
df["grade"].cat.categories = ["very good", "good", "very bad"] 
print df 
#根据grade的值排序 
print df.sort_values(by='grade', ascending=True) 
#根据grade排序显示数量 
print df.groupby("grade").size() 

import pandas as pd 
import numpy as np 
import matplotlib.pyplot as plt 
 
ts = pd.Series(np.random.randn(1000), index=pd.date_range('20170220', periods=1000)) 
ts = ts.cumsum() 
print ts 
ts.plot() 
plt.show() 

import pandas as pd 
import numpy as np 
 
df = pd.DataFrame(np.random.randn(10, 4), columns=list('ABCD')) 
#数据保存，相对路径 
df.to_csv('data.csv') 
#数据读取 
print pd.read_csv('data.csv', index_col=0)