无法输出参与者的所有行数据

Question

我目前正在研究这个数据排序问题，我应该（除了一堆其他标准）仅包含至少 3 行的参与者的数据行。

我使用的方法（第 9-16 行和第 37-40 行）似乎无法排除至少有 3 行数据的参与者的第一行数据。 这里肯定有逻辑错误，有人能找出我的想法哪里出了问题吗？非常感谢，非常感谢！

代码

import csv

def preprocessing(raw_filename, output_filename):
    data=open(raw_filename)
    new=open(output_filename, "a")
    health_write=csv.writer(new)
    reader=csv.DictReader(data)
    health_write.writerow(reader.fieldnames) 
    counting_part={}
    for row in reader:
        checker = False
        participant_id=row['participant_ID']
        if participant_id in counting_part: 
            counting_part[participant_id]+=1
        else: 
            counting_part[participant_id]=1
        x=row['timestamp'].split()[0]
        if x.split('/')[-1] in ('2023'):
            if float(row['accuracy']) <= 30:
                if len(participant_id.split('-'))==5:
                    match=[]
                    for each in participant_id.split('-'):
                        match.append(len(each))
                        if match == [8, 4, 4, 4, 12]:
                            for elm in each:
                                if elm.islower() or elm.isdigit():
                                    value_lat=float(row['double_latitude'])
                                    value_long=float(row['double_longitude'])
                                    if (value_lat >= -180 and value_lat
                                        <= 180 and value_long >= -180
                                        and value_long <=180):
                                        if 0<=float(row
                                                    ['double_altitude'])<=1000:
                                            if row['provider'] in ['gps',
                                                                   'network']:
                                                checker = True
                                                
        if checker and counting_part[participant_id] >= 3: 
            for participant_key, count in counting_part.items():
                if participant_id == participant_key:
                    health_write.writerow(row.values())

    data.close()
    new.close()

    
preprocessing("example_raw.csv", "my_output.csv")

部分数据：

row_id,timestamp,participant_ID,double_latitude,double_longitude,double_altitude,provider,accuracy
1,24/1/2023 1:05,2c9a7613-84f7-4c6d-af82,-37.80014035,144.963727,171.117,gps,41
2,24/1/2023 3:38,2c9a7613-84f7-4c6d-af82-9f54c8be2c1a,-37.80389128,144.9634838,143.159,gps,12.7445
3,24/1/2022 3:44,2c9a7613-84f7-4c6d-af82-9f54c8be2c1a,-37.80438867,144.9645387,19.95410156,gps,57.0303
4,24/1/2023 4:02,2c9a7613-84f7-4c6d-af82-9f54c8be2c1a,-37.80366035,144.9679344,56.83,gps,6.76879
5,24/1/2023 4:05,2c9a7613-84f7-4c6d-af82-9f54c8be2c1a,-37.80139125,144.9683195,55.13,gps,4.98383
6,15/7/2022 4:08,a7f3e14c-5db5-47e7-86c9-81f60e727d61,-37.80512032,144.9676758,4.723449707,gps,6.10221
7,15/7/2023 7:30,a7f3e14c-5db5-47e7-86c9-81f60e727d61,-37.80480437,144.9675091,95.83,gps,15

Answer 1

由于您在读取行并按参与者计算行的同一循环中写入输出文件，因此在到达参与者的第三行之前，您不会为参与者写入任何内容。

不要只使用计数器，而是列出每个参与者的行。然后在循环结束时，您可以遍历所有参与者，如果行数至少为 3，则写入他们的所有行。

每个参与者字典还可以包含

checker

变量，如果任何行的所有条件都为 true，则该变量设置为

True

。

from collections import defaultdict

def preprocessing(raw_filename, output_filename):
    with open(raw_filename) as data
        reader=csv.DictReader(data)

        counting_part = defaultdict(lambda: {"checker": False, "rows": []})

        for row in reader:
            participant_id=row['participant_ID']
            counting_part[participant_id]['rows'].append(row.values())

            x=row['timestamp'].split()[0]
            if x.split('/')[-1] in ('2023'):
                if float(row['accuracy']) <= 30:
                    if len(participant_id.split('-'))==5:
                        match=[]
                        for each in participant_id.split('-'):
                            match.append(len(each))
                            if match == [8, 4, 4, 4, 12]:
                                for elm in each:
                                    if elm.islower() or elm.isdigit():
                                        value_lat=float(row['double_latitude'])
                                        value_long=float(row['double_longitude'])
                                        if (value_lat >= -180 and value_lat
                                            <= 180 and value_long >= -180
                                            and value_long <=180):
                                            if 0<=float(row
                                                        ['double_altitude'])<=1000:
                                                if row['provider'] in ['gps',
                                                                       'network']:
                                                    counting_part[participant_id]['checker'] = True



    with open(output_filename, "a") as new:
        health_write=csv.writer(new)
        health_write.writerow(reader.fieldnames)

        for item in counting_part.values():
            if item['checker'] and len(item['rows']) > 3:
                for row in item['rows']:
                    health_write.writerow(row)