Pandas数据去重和对重复数据分类、求和，得到未…

import pandas as pd
import numpy as np

data = {"number":[1,1,np.nan,np.nan,2,2,1,2,2],
        "letter":['a','b',np.nan,np.nan,'c','d','b','c','d'],
        "label":[1,1,9,9,2,2,1,2,2]}
dataset1 = pd.DataFrame(data) #初始化DataFrame 得到数据集dataset1
print(dataset1)

dataset = dataset1.fillna("NULL")
print(dataset)

duplicate_row = dataset.duplicated(subset=['letter',' number '],keep=False) 
print(duplicate_row)

duplicate_data = dataset.loc[duplicate_row,:]
print(duplicate_data)

duplicate_data_sum = duplicate_data.groupby(by=['letter',' number ']).agg({' label ':sum}).reset_index(drop=True)
Print(duplicate_data_sum)

duplicate_data _one= duplicate_data.drop_duplicates(subset=['letter',' number '] ,keep="first").reset_index(drop=True)
Print(duplicate_data)

no_duplicate = dataset.drop_duplicates(subset=['letter',' number ',' label '] ,keep=False)
Print(no_duplicate)

duplicate_data _one ["label"] = duplicate_data_sum ['label']  #前面需要重置索引
print(duplicate_data_one)

Result = pd.concat([no_duplicate,duplicate_data _one])
Print(result)