读取特定的column

report_headers_arr = ['a', 'b']
pd.read_csv(REPORT_PATH, sep='\t', usecols=report_headers_arr)

保存dataframe到sqlite是数据库

import sqlite3

  
conn = sqlite3.connect('example.db')
df.to_sql('report', conn, if_exists='replace')
conn.commit()
conn.close()

从sqlite数据库表中读取dataframe

import pandas as pd

# Connect to the SQLite database
conn = sqlite3.connect('example.db')
# Read the data from the SQLite database
df = pd.read_sql('SELECT * FROM report', conn)
# Close the connection
conn.close()

通过groupby实现针对某一列数据得分类

In [62]: grouped = df.groupby('A')

In [63]: for name, group in grouped:
   ....:     print(name)
   ....:     print(group)
   ....: 
bar
     A      B         C         D
1  bar    one  0.254161  1.511763
3  bar  three  0.215897 -0.990582
5  bar    two -0.077118  1.211526
foo
     A      B         C         D
0  foo    one -0.575247  1.346061
2  foo    two -1.143704  1.627081
4  foo    two  1.193555 -0.441652
6  foo    one -0.408530  0.268520
7  foo  three -0.862495  0.024580