python基础篇之pandas常用基本函数汇总

df.describe()

#运行截图
	Height	Weight
count	183.000000	189.000000
mean	163.218033	55.015873
std	8.608879	12.824294
min	145.400000	34.000000
25%	157.150000	46.000000
50%	161.900000	51.000000
75%	167.500000	65.000000
max	193.900000	89.000000

df_demo = df[['Height', 'Weight']]
df_demo.mean()

df_demo.mean(axis=1).head()

#原本的数据样例
df_demo = df[['Gender','Transfer','Name']]
df_demo

    Gender    Transfer    Name
0    Female    N    Gaopeng Yang
1    Male    N    Changqiang You
2    Male    N    Mei Sun
3    Female    N    Xiaojuan Sun
4    Male    N    Gaojuan You
...    ...    ...    ...
195    Female    N    Xiaojuan Sun
196    Female    N    Li Zhao
197    Female    N    Chengqiang Chu
198    Male    N    Chengmei Shen
199    Male    N    Chunpeng Lv
200 rows × 3 columns

#现给Gender,Transfer两列去重
df_demo.drop_duplicates(['Gender','Transfer'])

    Gender    Transfer    Name
0    Female    N    Gaopeng Yang
1    Male    N    Changqiang You
12    Female    NaN    Peng You
21    Male    NaN    Xiaopeng Shen
36    Male    Y    Xiaojuan Qin
43    Female    Y    Gaoli Feng

df_demo.drop_duplicates(['Gender', 'Transfer'], keep='last')

    Gender    Transfer    Name
147    Male    NaN    Juan You
150    Male    Y    Chengpeng You
169    Female    Y    Chengquan Qin
194    Female    NaN    Yanmei Qian
197    Female    N    Chengqiang Chu
199    Male    N    Chunpeng Lv

#原本的数据
df_demo = df[['Gender','Transfer','Name']]
df_demo

    Gender    Transfer    Name
0    Female    N    Gaopeng Yang
1    Male    N    Changqiang You
2    Male    N    Mei Sun
3    Female    N    Xiaojuan Sun
4    Male    N    Gaojuan You
...    ...    ...    ...
195    Female    N    Xiaojuan Sun
196    Female    N    Li Zhao
197    Female    N    Chengqiang Chu
198    Male    N    Chengmei Shen
199    Male    N    Chunpeng Lv
200 rows × 3 columns

#替换Gender，女替换为0，男替换为1
df['Gender'].replace({'Female':0, 'Male':1}).head()

0    0
1    1
2    1
3    0
4    1
Name: Gender, dtype: int64

s = pd.Series([-1, 1.2345, 100, -50])
s.where(s<0)

0    -1.0
1     NaN
2     NaN
3   -50.0
dtype: float64

s.where(s<0, 100)

0     -1.0
1    100.0
2    100.0
3    -50.0
dtype: float64

s.mask(s<0)

0         NaN
1      1.2345
2    100.0000
3         NaN
dtype: float64