pandas 缺失值与空值处理的实现方法

df = pd.DataFrame({"name": ['Alfred', 'Batman', 'Catwoman'],
        "toy": [np.nan, 'Batmobile', 'Bullwhip'],
         "born": [pd.NaT, pd.Timestamp("1940-04-25"),pd.NaT]})
 
print df

print df.dropna()
print df

print "delete colums"
print df.dropna(axis=1) #delete col

print "所有值全为缺失值才删除"
print df.dropna(how='all')

print "至少出现过两个缺失值才删除"
print df.dropna(thresh=2)

print "删除这个subset中的含有缺失值的行或列"
print df.dropna(subset=['name', 'born'])

df = pd.DataFrame([[np.nan, 2, np.nan, 0],
         [3, 4, np.nan, 1],
         [np.nan, np.nan, np.nan, 5],
        [np.nan, 3, np.nan, 4]],
         columns=list('ABCD'))
 
print df
 
print "横向用缺失值前面的值替换缺失值"
print df.fillna(axis=1,method='ffill')
 
print "纵向用缺失值上面的值替换缺失值"
print df.fillna(axis=0,method='ffill')

print df.fillna(0)

df = pd.DataFrame([[np.nan, 2, np.nan, 0],
         [3, 4, "", 1],
         [np.nan, np.nan, np.nan, 5],
        [np.nan, 3, "", 4]],
         columns=list('ABCD'))
 
print df

clean_z = df['C'].fillna(0)
clean_z[clean_z==''] = 'hello'
df['C'] = clean_z
print df