链接 DataFrame

Python 数据清洗

Adel Nehme

VP of AI Curriculum, DataCamp

记录链接（Record linkage）

我们的 DataFrame

census_A

             given_name  surname date_of_birth         suburb state  address_1
rec_id                                                                
rec-1070-org   michaela  neumann      19151111  winston hills   nsw  stanley street 
rec-1016-org   courtney  painter      19161214      richlands   vic  pinkerton circuit 
...

census_B

               given_name  surname date_of_birth             suburb state  address_1
rec_id                                                                      
rec-561-dup-0       elton      NaN      19651013         windermere   vic  light setreet 
rec-2642-dup-0   mitchell    maxon      19390212         north ryde   nsw  edkins street 
...

我们已完成的步骤

# 导入 recordlinkage 并生成全量配对
import recordlinkage
indexer = recordlinkage.Index()
indexer.block('state')
full_pairs = indexer.index(census_A, census_B)


# 比较步骤
compare_cl = recordlinkage.Compare()
compare_cl.exact('date_of_birth', 'date_of_birth', label='date_of_birth')
compare_cl.exact('state', 'state', label='state')
compare_cl.string('surname', 'surname', threshold=0.85, label='surname')
compare_cl.string('address_1', 'address_1', threshold=0.85, label='address_1')


potential_matches = compare_cl.compute(full_pairs, census_A, census_B)

当前进度

候选匹配

potential_matches

候选匹配

potential_matches

候选匹配

potential_matches

候选匹配

potential_matches

可能匹配

matches = potential_matches[potential_matches.sum(axis = 1) >= 3]
print(matches)

可能匹配

matches = potential_matches[potential_matches.sum(axis = 1) >= 3]
print(matches)

获取索引

matches.index

MultiIndex(levels=[['rec-1007-org', 'rec-1016-org', 'rec-1054-org', 'rec-1066-org', 
'rec-1070-org', 'rec-1075-org', 'rec-1080-org', 'rec-110-org', ...

# 仅获取 census_B 的索引
duplicate_rows = matches.index.get_level_values(1)
print(census_B_index)

Index(['rec-2404-dup-0', 'rec-4178-dup-0', 'rec-1054-dup-0', 'rec-4663-dup-0',
       'rec-485-dup-0', 'rec-2950-dup-0', 'rec-1234-dup-0', ... , 'rec-299-dup-0'])

链接 DataFrame

# 在 census_B 中查找重复
densus_B_duplicates = census_B[census_B.index.isin(duplicate_rows)]


# 在 census_B 中查找新行
census_B_new = census_B[~census_B.index.isin(duplicate_rows)]

# 连接 DataFrame！
full_census = pd.concat([census_A, census_B_new])

# 导入 recordlinkage，生成配对并按列比较
...
# 生成候选匹配
potential_matches = compare_cl.compute(full_pairs, census_A, census_B)


# 保留≥3列匹配的记录
matches = potential_matches[potential_matches.sum(axis = 1) >= 3]


# 仅获取匹配到的 census_B 索引
duplicate_rows = matches.index.get_level_values(1)


# 在 census_B 中查找新行
census_B_new = census_B[~census_B.index.isin(duplicate_rows)]


# 连接 DataFrame！
full_census = pd.concat([census_A, census_B_new])

让我们练习！

Python 数据清洗