Python 中的重复数据删除

Dedupe in Python

在查看 Python 中用于记录重复数据删除的 Dedupe 库示例时,我发现它在输出中创建了一个 Cluster Id 列文件,根据文档指示哪些记录相互引用。虽然我无法找出 Cluster Id 之间的任何关系,但这对查找重复记录有何帮助。如果有人对此有所了解,请向我解释一下。这是去重的代码。

# This can run either as a python2 or python3 code
from future.builtins import next

import os
import csv
import re
import logging
import optparse

import dedupe
from unidecode import  unidecode


input_file = 'data/csv_example_input_with_true_ids.csv'
output_file = 'data/csv_example_output1.csv'
settings_file = 'data/csv_example_learned_settings'
training_file = 'data/csv_example_training.json'

# Clean or process the data


def preProcess(column):

    try:
        column = column.decode('utf-8')
    except AttributeError:
        pass
    column = unidecode(column)
    column = re.sub(' +', ' ', column)
    column = re.sub('\n', ' ', column)
    column = column.strip().strip('"').strip("'").lower().strip()

    if not column:
        column = None
    return column


# Read in the data from CSV file:


def readData(filename):

    data_d = {}
    with open(filename) as f:
        reader = csv.DictReader(f)
        for row in reader:
            clean_row = [(k, preProcess(v)) for (k, v) in row.items()]
            row_id = int(row['Id'])
            data_d[row_id] = dict(clean_row)

    return data_d

print('importing data ...')
data_d = readData(input_file)

if os.path.exists(settings_file):
    print('reading from', settings_file)
    with open(settings_file, 'rb') as f:
        deduper = dedupe.StaticDedupe(f)
else:
    fields = [
        {'field' : 'Site name', 'type': 'String'},
        {'field' : 'Address', 'type': 'String'},
        {'field' : 'Zip', 'type': 'Exact', 'has missing' : True},
        {'field' : 'Phone', 'type': 'String', 'has missing' : True},
        ]
    deduper = dedupe.Dedupe(fields)
    deduper.sample(data_d, 15000)

    if os.path.exists(training_file):
        print('reading labeled examples from ', training_file)
        with open(training_file, 'rb') as f:
            deduper.readTraining(f)

    print('starting active labeling...')

    dedupe.consoleLabel(deduper)

    deduper.train()

    with open(training_file, 'w') as tf:
        deduper.writeTraining(tf)

    with open(settings_file, 'wb') as sf:
        deduper.writeSettings(sf)

threshold = deduper.threshold(data_d, recall_weight=1)

print('clustering...')
clustered_dupes = deduper.match(data_d, threshold)

print('# duplicate sets', len(clustered_dupes))


cluster_membership = {}
cluster_id = 0
for (cluster_id, cluster) in enumerate(clustered_dupes):
    id_set, scores = cluster
    cluster_d = [data_d[c] for c in id_set]
    canonical_rep = dedupe.canonicalize(cluster_d)
    for record_id, score in zip(id_set, scores):
        cluster_membership[record_id] = {
            "cluster id" : cluster_id,
            "canonical representation" : canonical_rep,
            "confidence": score
        }

singleton_id = cluster_id + 1

with open(output_file, 'w') as f_output, open(input_file) as f_input:
    writer = csv.writer(f_output)
    reader = csv.reader(f_input)

    heading_row = next(reader)
    heading_row.insert(0, 'confidence_score')
    heading_row.insert(0, 'Cluster ID')
    canonical_keys = canonical_rep.keys()
    for key in canonical_keys:
        heading_row.append('canonical_' + key)

    writer.writerow(heading_row)

    for row in reader:
        row_id = int(row[0])
        if row_id in cluster_membership:
            cluster_id = cluster_membership[row_id]["cluster id"]
            canonical_rep = cluster_membership[row_id]["canonical representation"]
            row.insert(0, cluster_membership[row_id]['confidence'])
            row.insert(0, cluster_id)
            for key in canonical_keys:
                row.append(canonical_rep[key].encode('utf8'))
        else:
            row.insert(0, None)
            row.insert(0, singleton_id)
            singleton_id += 1
            for key in canonical_keys:
                row.append(None)
        writer.writerow(row)

提前致谢

你说得对,Cluster ID 没有任何用途。

您应该将 Cluster ID 视为重复数据删除执行的输出。 Dedupe 对合并您的记录不感兴趣。它的核心重点是尝试识别可能相似的记录。

它通过分配它认为相似的行来做到这一点 Cluster ID

作为软件工程师,您的工作就是以智能方式使用该数据并决定您希望如何合并该数据(如果有的话)。

如果我的输入如下:

我的输出将类似于以下内容:

因此,请记住,您的输入记录数应始终与重复数据删除输出记录数相匹配。区别仅在于您有一个新列 "Cluster ID",您现在可以使用它来 "group" 您可能的重复项。