1 import numpy as np
2 import pandas as pd
3 df = pd.read_csv(‘table.csv‘,index_col=‘ID‘) #用来指定表格的索引值
4 ?
5 df.head(2)

1 df.loc[1103]

School          S_1
Class           C_1
Gender            M
Address    street_2
Height          186
Weight           82
Math           87.2
Physics          B+
Name: 1103, dtype: object

1 df.loc[[1101,1105,1204,1301]]

1 df.loc[1103:1203]

1 df.loc[:,‘Weight‘].head(3)

ID
1101    63
1102    73
1103    82
Name: Weight, dtype: int64

1 df.loc[:,[‘Address‘,‘Height‘,‘Math‘]].head()

1 df.loc[1102:2301,[‘Address‘,‘Height‘,‘Math‘]].head()

1 df.head(9)

1 df.iloc[2]

School          S_1
Class           C_1
Gender            M
Address    street_2
Height          186
Weight           82
Math           87.2
Physics          B+
Name: 1103, dtype: object

1 df.iloc[2:6]

1 df.iloc[:,4].head(3)

ID
1101    173
1102    192
1103    186
Name: Height, dtype: int64

1 df.iloc[:,7::-2].head(3)

1 df.iloc[2:6,7::-2].head(3)

1 df.head()

1 df[‘Gender‘].unique()
2 array([‘M‘, ‘F‘], dtype=object)
3 df.where(df[‘Gender‘]==‘M‘).head()

1 aa = df.where(df[‘Gender‘]==‘M‘).dropna().head()
2 #意思是：在通过以上的操作，删除掉单元格中不满足条件的行，或提取出筛选后的新数组
3 #mask对条件为True的单元进行填充
4 aa