pandas去重方法

import numpy as np
import pandas as pd
from pandas import Series, DataFrame

df = pd.read_csv(‘./demo_duplicate.csv‘)
print(df)
print(df[‘Seqno‘].unique()) # [0. 1.]

# 使用duplicated 查看 重复值
# 参数 keep 可以标记重复值 {‘first‘，‘last‘，False}
print(df[‘Seqno‘].duplicated())
‘‘‘
0    False
1     True
2     True
3     True
4    False
Name: Seqno, dtype: bool
‘‘‘

# 删除 series 重复数据
print(df[‘Seqno‘].drop_duplicates())
‘‘‘
0    0.0
4    1.0
Name: Seqno, dtype: float64
‘‘‘

# 删除 dataframe 重复数据
print(df.drop_duplicates([‘Seqno‘])) # 按照 Seqno 来 去重
‘‘‘
    Price  Seqno Symbol        time
0  1623.0    0.0   APPL  1473411962
4  1649.0    1.0   APPL  1473411963
‘‘‘
# drop_dujplicates() 第二个参数 keep 包含的值 有： first、last、False
print(df.drop_duplicates([‘Seqno‘], keep=‘last‘)) # 保存最后一个
‘‘‘
    Price  Seqno Symbol        time
3  1623.0    0.0   APPL  1473411963
4  1649.0    1.0   APPL  1473411963
‘‘‘