cha5
# coding: utf-8
# In[1]:
import pandas as pd
from pandas import Series , DataFrame
# In[2]:
obj = Series([4,7,-5,3])
# In[3]:
obj
# In[4]:
obj.values
# In[5]:
obj.index
# In[8]:
obj2=Series(data=[4,7,-5,3],index=['d','b','a','c'])
# In[9]:
obj2
# In[10]:
'b' in obj2
# In[11]:
#或者如果有Dictionary,我们也可以通过Dictionary来创建Series:
sdata = {'Ohio':350,"Texas":700,"Oregon":160}
obj3=Series(sdata)
obj3
# In[13]:
#通常说来,Series最重要的功能是,它在算数运算中,会自动对齐不同索引的数据
import numpy as np
data = DataFrame(np.arange(16).reshape((4,4)),
index=['Ohio','Colorando','Utah','New York'],
columns=['one','two','three','four'])
# In[14]:
data
# In[15]:
data<6
# In[16]:
data.ix[['Colorando'],[3,0,1]]
cha7
# coding: utf-8
# In[1]:
import pandas as pd
import numpy as np
# In[4]:
df1 = pd.DataFrame({'key':['b','b','a','c','a','a','b'],
'data1':range(7)})
# In[5]:
df1
# In[6]:
df2 = pd.DataFrame({'key':['a','b','d'],
'data2':range(3)})
# In[7]:
df2
# In[9]:
pd.merge(df1,df2)
# In[10]:
pd.merge(df1,df2,on='key')
# In[14]:
#默认情况下,merge是内连接,结果的并集
#当我们规定了how='outer'后,就是外连接,取并集
pd.merge(df1,df2,how='outer')
# In[16]:
#轴向连接
arr = np.arange(12).reshape((3,4))
arr
# In[17]:
np.concatenate([arr,arr],axis=1)
# In[18]:
np.concatenate([arr,arr],axis=0)
# In[20]:
#重塑层次化索引
data = pd.DataFrame(np.arange(6).reshape((2,3)),
index = pd.Index(['Ohio','Colorado'],name='state'),
columns = pd.Index(['One','Two','Three'],name='number'))
data
# In[22]:
result = data.stack()
result
# In[23]:
result.unstack()
# In[25]:
data= pd.Series([1,-999,2,-999,-1000,3])
data
# In[26]:
data.replace([-999,-1000],[np.nan,0])
# In[27]:
#检测和过滤异常值
np.random.seed(12345)
# In[28]:
data = pd.DataFrame(np.random.randn(1000,3))
# In[29]:
data.describe()