In [1]:
import pandas as pd
import numpy as np
s = pd.Series(['A','B','C','gaer','GAER',np.nan])
s
Out[1]:
In [2]:
s.str.lower()
Out[2]:
In [3]:
s.str.upper()
Out[3]:
In [4]:
s.str.len()
Out[4]:
In [5]:
index = pd.Index([' tang',' shi ','banshou '])
index
Out[5]:
In [6]:
index.str.strip()
Out[6]:
In [7]:
index.str.lstrip()
Out[7]:
In [8]:
index.str.rstrip()
Out[8]:
In [10]:
df = pd.DataFrame(np.random.randn(3,2),columns=['A a','B b'],index = range(3))
df
Out[10]:
In [13]:
df.columns = df.columns.str.replace(' ','_')
df
Out[13]:
In [14]:
s = pd.Series(['a_b_c','c_d_e','f_g_h'])
s
Out[14]:
In [15]:
s.str.split('_')
Out[15]:
In [17]:
s.str.split('_',expand = True)
Out[17]:
In [19]:
s = pd.Series(['A','Aas','Afgew','Ager','Agre','Ager'])
s
Out[19]:
In [20]:
s.str.contains('Aas')
Out[20]:
In [21]:
s = pd.Series(['a','a|b','a|c'])
s
Out[21]:
In [22]:
s.str.get_dummies(sep = '|')
Out[22]:
In [ ]: