python pandas 笔记2

 

1. CSV操作 

1.1 pd.read_csv() 

df = pd.read_csv('olympics.csv')
df.head()

 

 

# index_col =0 ，从0列开始读取， 并跳过第一行
df = pd.read_csv('olympics.csv', index_col = 0, skiprows=1)
df.head()

1.2 rename() 方法。

for col in df.columns:
    if col[:2]=='01':
        df.rename(columns={col:'Gold' + col[4:]}, inplace=True)
    if col[:2]=='02':
        df.rename(columns={col:'Silver' + col[4:]}, inplace=True)
    if col[:2]=='03':
        df.rename(columns={col:'Bronze' + col[4:]}, inplace=True)
    if col[:1]=='№':
        df.rename(columns={col:'#' + col[1:]}, inplace=True) 

df.head()

 2. 查询 DataFrame

only_gold = df.where(df['Gold'] > 0)
only_gold.head()

2.1 删除NAN这行

only_gold = only_gold.dropna()
only_gold.head()

drop()方法

print(df.drop(df[df['Quantity'] == 0].index).rename(columns={'Weight': 'Weight (oz.)'}))

2.3 或者直接用两次[]

only_gold = df[df['Gold'] > 0]
only_gold.head()
#df[(df['Gold.1'] > 0) & (df['Gold'] == 0)]

 3. 索引设置

df.head()

#索引设置
df['country'] = df.index
df = df.set_index('Gold')
df.head()

df = df.reset_index()
df.head()

3.1 unique()方法，找独一无二的元素。

df['SUMLEV'].unique()
# array([40, 50])

df=df[df['SUMLEV'] == 50]
df.head()

3.2 保留指定列

columns_to_keep = ['STNAME',
                   'CTYNAME',
                   'BIRTHS2010',
                   'BIRTHS2011',
                   'BIRTHS2012',
                   'BIRTHS2013',
                   'BIRTHS2014',
                   'BIRTHS2015',
                   'POPESTIMATE2010',
                   'POPESTIMATE2011',
                   'POPESTIMATE2012',
                   'POPESTIMATE2013',
                   'POPESTIMATE2014',
                   'POPESTIMATE2015']
df = df[columns_to_keep]
df.head()

3.3 设置两个索引值

df = df.set_index(['STNAME', 'CTYNAME'])
df.head()

3.4 loc()方法

df.loc['Michigan', 'Washtenaw County']
"""
BIRTHS2010            977
BIRTHS2011           3826
BIRTHS2012           3780
BIRTHS2013           3662
BIRTHS2014           3683
BIRTHS2015           3709
POPESTIMATE2010    345563
POPESTIMATE2011    349048
POPESTIMATE2012    351213
POPESTIMATE2013    354289
POPESTIMATE2014    357029
POPESTIMATE2015    358880
Name: (Michigan, Washtenaw County), dtype: int64
"""

df.loc[ [('Michigan', 'Washtenaw County'),
         ('Michigan', 'Wayne County')] ]

4. 丢失值的处理

df = pd.read_csv('log.csv')
df

4.1 重新设置索引

df = df.set_index('time')
df = df.sort_index()
df

df = df.reset_index()
df = df.set_index(['time', 'user'])
df

4.2 向上填充fillna方法

df = df.fillna(method='ffill')
df.head()

5. 返回最大值的索引

参考：http://pandas.pydata.org/pandas-docs/stable/generated/pandas.Series.argmax.html

 

#example 
>>> s = pd.Series(data=[1, None, 4, 3, 4],
...               index=['A', 'B', 'C', 'D', 'E'])
>>> s
A    1.0
B    NaN
C    4.0
D    3.0
E    4.0
dtype: float64

>>> s.idxmax()
'C'