版权声明：https://blog.csdn.net/thfyshz版权所有 https://blog.csdn.net/thfyshz/article/details/83744533
选择数据
dataframes
> df = pd.DataFrame(
....: {'AAA' : [4,5,6,7], 'BBB' : [10,20,30,40],'CCC' : [100,50,-30,-50]}); df
AAA BBB CCC
0 4 10 100
1 5 20 50
2 6 30 -30
3 7 40 -50
#设定两个“或”条件筛选数据
> df[(df.AAA > 5) | (df.index.isin([0, 2]))]
AAA BBB CCC
0 4 10 100
2 6 30 -30
3 7 40 -50
#使用~表示“非”，注意书写是全非还是部分非
#下面是一个部分非的例子
> df[~(df.AAA > 5) & (df.index.isin([0, 2, 4]))]
AAA BBB CCC
0 4 10 100
df.loc的方法已经比较熟练，不再赘述。
面板数据
# 可能会报错：panel将在未来的版本里弃用。不影响使用
# 三个时间序列数据组成了面板数据
> rng = pd.date_range('1/1/2013',periods=100,freq='D')
> data = np.random.randn(100, 4)
> cols = ['A','B','C','D']
> df1, df2, df3 = pd.DataFrame(data, rng, cols), pd.DataFrame(data, rng, cols), pd.DataFrame(data, rng, cols)
> pf = pd.Panel({'df1':df1,'df2':df2,'df3':df3});pf
<class 'pandas.core.panel.Panel'>
Dimensions: 3 (items) x 100 (major_axis) x 4 (minor_axis)
Items axis: df1 to df3
Major_axis axis: 2013-01-01 00:00:00 to 2013-04-10 00:00:00
Minor_axis axis: A to D
> pf.loc[:,:,'F'] = pd.DataFrame(data, rng, cols);pf
<class 'pandas.core.panel.Panel'>
Dimensions: 3 (items) x 100 (major_axis) x 5 (minor_axis)
Items axis: df1 to df3
Major_axis axis: 2013-01-01 00:00:00 to 2013-04-10 00:00:00
Minor_axis axis: A to F
> pf['df3']
A B C D F
2013-01-01 -0.321314 -1.264130 -0.701352 -0.097620 NaN
2013-01-02 -0.798209 0.767679 0.073943 -1.692146 NaN
2013-01-03 0.927847 0.555940 0.590923 0.350158 NaN
2013-01-04 -0.042397 -1.003914 0.952686 -0.911484 NaN
生成新列
> df = pd.DataFrame(
....: {'AAA' : [1,2,1,3], 'BBB' : [1,1,2,2], 'CCC' : [2,1,3,1]}); df
AAA BBB CCC
0 1 1 2
1 2 1 1
2 1 2 3
3 3 2 1
> source_cols = df.columns
> new_cols = [str(x) + "_cat" for x in source_cols]
> categories = {1 : 'Alpha', 2 : 'Beta', 3 : 'Charlie' }
> df[new_cols] = df[source_cols].applymap(categories.get);df
AAA BBB CCC AAA_cat BBB_cat CCC_cat
0 1 1 2 Alpha Alpha Beta
1 2 1 1 Beta Alpha Alpha
2 1 2 3 Alpha Beta Charlie
3 3 2 1 Charlie Beta Alpha
> df = pd.DataFrame(
....: {'AAA' : [1,1,1,2,2,2,3,3], 'BBB' : [2,1,3,4,5,1,2,3]}); df
AAA BBB
0 1 2
1 1 1
2 1 3
3 2 4
4 2 5
5 2 1
6 3 2
7 3 3
#按AAA分组并找出每组中对应BBB的最小值的索引值
> df.loc[df.groupby("AAA")["BBB"].idxmin()]
AAA BBB
1 1 1
5 2 1
6 3 2
#另一种方法：
> df.sort_values(by="BBB").groupby("AAA", as_index=False).first()
AAA BBB
0 1 1
1 2 1
2 3 2