利用python进行数据分析--pandas入门2

随书练习，第五章  pandas入门2

# coding: utf-8

# In[1]:

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

# In[2]:

obj = Series(range(5),index=['a','a','b','b','c'])

# In[3]:

obj #带有重复索引的Series

# In[4]:

obj.index.is_unique

# In[5]:

obj['a']

# In[6]:

obj['c']

# In[7]:

df = DataFrame(np.random.randn(4,3),index=['a','a','b','b'])

# In[8]:

df

# In[9]:

df.loc['b']

# In[10]:

df = DataFrame([[1.4,np.nan],[7.1,-4.5],[np.nan,np.nan],[0.75,-1.3]],index=['a','b','c','d'],columns=['one','two'])

# In[11]:

df

# In[12]:

df.sum()

# In[13]:

df.sum(axis=1) #自动忽略缺失值

# In[14]:

df.mean(axis=1,skipna=False) #禁用自动忽略缺失值功能

# In[15]:

df.idxmax() #间接统计，返回索引

# In[16]:

df.idxmax(axis=1)

# In[17]:

df.cumsum() #累计型

# In[18]:

df.describe() #数值型数据

# In[19]:

obj = Series(['a','a','b','c']*4)

# In[20]:

obj

# In[21]:

obj.describe() #非数值型数据

# In[22]:

# corr ,cov ,corrwith

# In[23]:

obj = Series(['c','a','d','a','a','b','b','c','c'])

# In[24]:

uniques = obj.unique()  #这里只是找出唯一值，不排序，numpy有一个函数unique()去重并排序

# In[25]:

uniques

# In[26]:

uniques.sort()

# In[27]:

uniques

# In[28]:

obj.value_counts() #用于计算各值出现的频数，降序排列

# In[29]:

pd.value_counts(obj.values,sort=False)

# In[30]:

mask = obj.isin(['b','c'])

# In[31]:

mask

# In[32]:

obj[mask] #布尔型索引

# In[33]:

data = DataFrame({'Qu1':[1,3,4,3,4],'Qu2':[2,3,1,2,3],'Qu3':[1,5,2,4,4]})

# In[34]:

data

# In[35]:

result = data.apply(pd.value_counts).fillna(0)

# In[36]:

result  #索引是唯一值，列是唯一值出现的次数

# In[37]:

string_data = Series(['aardvark','artichoke',np.nan,'avocado'])

# In[38]:

string_data

# In[39]:

string_data.isnull()

# In[40]:

string_data[0] = None

# In[41]:

string_data.isnull() #python内置的None值也会被当作NA值处理

# In[42]:

data = DataFrame({'Qu1':[np.nan,3,np.nan,3,4],'Qu2':[2,3,np.nan,2,3],'Qu3':[np.nan,5,np.nan,4,np.nan]})

# In[43]:

data

# In[44]:

data.dropna() #默认删除有缺失值的数据

# In[45]:

data.dropna(how='all')

# In[46]:

data.dropna(thresh=2) #缺失数量大于等于2的行删掉

# In[47]:

data.notnull() #isnull的否定式

# In[48]:

from numpy import nan as NA

# In[49]:

data = Series([1,NA,3.5,NA,7])

# In[50]:

data.dropna()

# In[51]:

data[data.notnull()] #布尔型索引

# In[52]:

data = DataFrame([[1,6.5,3],[1,NA,NA],[NA,NA,NA],[NA,6.5,3]])

# In[53]:

cleaned = data.dropna()

# In[54]:

data

# In[55]:

cleaned

# In[56]:

data[4] = NA

# In[57]:

data

# In[58]:

data.dropna(axis=1,how='all')

# In[59]:

df = DataFrame(np.random.randn(7,3))

# In[60]:

df.iloc[:4,1] = NA;df.iloc[:2,2] = NA

# In[61]:

df

# In[62]:

df.fillna(0)

# In[63]:

df.fillna({1:0.5,3:-1}) #可以对不同的列填充不同的值

# In[64]:

_ = df.fillna(0,inplace=True) #会改变原数据

# In[65]:

df

# In[66]:

df = DataFrame(np.random.randn(6,3))

# In[67]:

df.iloc[2:,1] = NA;df.iloc[4:,2] = NA

# In[68]:

df

# In[69]:

df.fillna(method='ffill')

# In[70]:

df.fillna(method='ffill',limit=2)

# In[71]:

data = Series([1,NA,3.5,NA,7])

# In[72]:

data.fillna(data.mean())

# In[73]:

df

# In[74]:

df.mean()

# In[75]:

df.fillna(df.mean()) #用平均值填充

# In[76]:

df.iloc[3,1]=5

# In[77]:

df

# In[78]:

df.interpolate() #插值法填充缺失值

# In[79]:

data = Series(np.random.randn(10),index=[['a','a','a','b','b','b','c','c','d','d'],[1,2,3,1,2,3,1,2,2,3]]) #层次化索引

# In[80]:

data

# In[81]:

data.index

# In[82]:

data['b']

# In[83]:

data['b':'c']

# In[84]:

data[['b','d']]

# In[85]:

data.loc[['b','d']]

# In[86]:

data[:,2]

# In[87]:

data.unstack()

# In[88]:

data.unstack().stack()

# In[89]:

frame = DataFrame(np.arange(12).reshape((4,3)),index=[['a','a','b','b'],[1,2,1,2]],columns=[['Ohio','Ohio','Colorado'],['Green','Red','Green']])

# In[90]:

frame

# In[91]:

frame.index.names = ['key1','key2']

# In[92]:

frame.columns.names = ['state','color']

# In[93]:

frame

# In[94]:

frame['Ohio']

# In[103]:

pd.MultiIndex.from_arrays([['Ohio','Ohio','Colorado'],['Green','Red','Green']],names=['state','color'])

# In[104]:

frame.swaplevel('key1','key2') #互换级别

# In[106]:

frame.sort_index(level=1)

# In[109]:

frame.swaplevel(0,1).sort_index(level=0)

# In[110]:

frame

# In[111]:

frame.sum(level='key2') # 根据级别进行汇总

# In[112]:

frame.sum(level='color',axis=1)

# In[113]:

frame = DataFrame({'a':range(7),'b':range(7,0,-1),'c':['one','one','one','two','two','two','two'],'d':[0,1,2,0,1,2,3]})

# In[114]:

frame

# In[115]:

frame2 = frame.set_index(['c','d']) #将一个或多个列转换为行索引

# In[116]:

frame2

# In[117]:

frame.set_index(['c','d'],drop=False)

# In[118]:

frame2

# In[119]:

frame2.reset_index()

# In[125]:

frame2

# In[124]:

frame.loc[frame.d>0]