使用python按名称对数据进行分类

Question

我有一个导入到脚本中的data (小示例)。

LastName    StartTime   EndTime Duration  Period    TeamAbbrev  Position
Bouwmeester     0:00    0:37    0:37         1         STL         D
Schwartz        0:00    0:40    0:40         1         STL         W
Foligno         0:00    0:40    0:40         1         MIN         W
Pietrangelo     0:00    0:48    0:48         1         STL         D
Suter           0:00    0:40    0:40         1         MIN         D
Staal           0:00    0:40    0:40         1         MIN         C
Niederreiter    0:00    0:40    0:40         1         MIN         W
Allen           0:00    20:00   20:00        1         STL         G
Steen           0:00    0:30    0:30         1         STL         W
Tarasenko       0:30    1:27    0:57         1         STL         W
Parayko         0:37    1:43    1:06         1         STL         D

这就是脚本

import csv
from itertools import combinations, product

#Header = LastName  StartTime  EndTime  Duration Period TeamAbbrev Position

#Import Game
with open('2017020397.csv', newline='') as f:
    next(f)
    skaters = '\n'.join(' '.join(row) for row in csv.reader(f))
    data = skaters.splitlines()

def to_secs(ms):
    ''' Convert a mm:ss string to seconds '''
    m, s = map(int, ms.split(':'))
    return 60 * m + s

# Store a list of (start, end) times for each player
players = {}
for row in data:
    name, start, end = row.split(None, 3)[:3]
    times = to_secs(start), to_secs(end)
    players.setdefault(name, []).append(times)

for t in players.items():
    print(t)
print()

# Determine the amount of overlapping time for each combination of players
for p1, p2, p3 in combinations(sorted(players), 3):
    total = 0
    # Check each pair of times for this pair of players
    for t1, t2, t3 in product(players[p1], players[p2], players[p3]):
        # Compute the overlap in this pair of times and
        # add it to the total for this pair of players
        start, end = zip(t1, t2, t3)
        total += max(0, min(end) - max(start))
    if total:
        print(p1, p2, p3, total)

输出：

Allen Niederreiter Pietrangelo 5481
Allen Niederreiter Prosser 2088
Allen Niederreiter Reilly 1464

这样做的目的是看看哪个队友在一起玩。从Output中，我们可以看到来自STL的Allen与来自MIN的Niederreiter配对。我只想让像combinations这样的团队合并。TeamAbbrev是如何识别的。另一项规定是，TeamAbbrev将根据当晚的比赛情况逐场改变比赛。欢迎任何建议，谢谢！

编辑:如果int()比TeamAbbrev的str()更容易，我可以抓取teamId，它是一个数字。

Answer 1

在dataʼ中行的ʼ后添加...

teams = row.split()[4]
# if the number of occurrences of the first item (which is a team)... is equal to the length of the list of teams, then, all the players are from the same team. 
if teams.count(teams[0]) == len(teams):
    #same lines, but one indentation block due to the `if` condition. 

Answer 2

你的问题不容易回答，但我会试一试。我做了一些假设：

• I假设只有在同一时间段播放时才会发生重叠
• 如果文件中记录的时间不是一位或两位数的格式，它将认为它是零(您可能希望不同地处理这种情况)
• 我假设玩家在一段时间内可能玩多次
• 我假设该时间段是一个数字，并且我可以比较字符串值而不是数值。

<

• >F29

现在有两个文件：

2017020397.csv

LastName,StartTime,EndTime,Duration,Period,TeamAbbrev,Position
Bouwmeester,0:00,0:37,0:37,1,STL,D
Schwartz,0:00,0:40,0:40,1,STL,W
Foligno,0:00,0:40,0:40,1,MIN,W
Pietrangelo,0:00,0:48,0:48,1,STL,D
Suter,0:00,0:40,0:40,1,MIN,D
Staal,0:00,0:40,0:40,1,MIN,C
Niederreiter,0:00,0:40,0:40,1,MIN,W
Allen,0:00,20:00,20:00,1,STL,G
Steen,0:00,0:30,0:30,1,STL,W
Tarasenko,0:30,1:27,0:57,1,STL,W
Parayko,0:37,1:43,1:06,1,STL,D

solution.py

import csv
import re
import itertools

pattern_time = r"(\d{1,2}):(\d{1,2})"
time_tester = re.compile(pattern_time)

def convert_to_seconds(time_string):
    ''' Convert a mm:ss string to seconds '''
    pattern_found = time_tester.match(time_string)
    if pattern_found:
        time_string_separated = pattern_found.group(1, 2)
        minutes, seconds = map(int, time_string_separated)
        return 60 * minutes + seconds
    else:
        # We have a problem
        return 0

file_name = '2017020397.csv'
teams = {}
number_of_players_to_compare = 3

with open(file_name, newline='') as source_file:
    csv_file = csv.DictReader(source_file)
    for row in csv_file:
        if row['TeamAbbrev'] not in teams:
            teams[row['TeamAbbrev']] = {}

        current_team = teams[row['TeamAbbrev']]
        if row['Period'] not in current_team:
            current_team[row['Period']] = {}

        current_team_period = current_team[row['Period']]
        if row['LastName'] not in current_team_period:
            current_team_period[row['LastName']] = []

        current_skater = current_team_period[row['LastName']]
        times_recorded = {'StartTime': convert_to_seconds(row['StartTime']), 
                          'EndTime': convert_to_seconds(row['EndTime'])}
        current_skater.append(times_recorded)

for (current_team_to_show, current_periods) in teams.items():
    current_periods_sorted = sorted(current_periods)
    for current_period_name in current_periods_sorted:
        print("\nFor team", current_team_to_show, "in period", current_period_name, ":")

        current_period = current_periods[current_period_name] 
        current_players = sorted(current_period)
        for current_player_combination in itertools.combinations(current_players, number_of_players_to_compare):
            total = 0
            for times_this_combination in itertools.product(*(current_period[x] for x in current_player_combination)):
                start_times = (x['StartTime'] for x in times_this_combination)
                end_times = (x['EndTime'] for x in times_this_combination)
                total += max(0, min(end_times) - max(start_times))

            print(" ".join(current_player_combination), total)

下面是关于我如何做到这一点的一些评论：

• 我使用了一个DictReader，这样我就不必跳过第一行，并且能够通过它的列名获取行的每一部分。
• 我使用了一个嵌套的字典数据结构来调用数据。它是球员字典中记录时间的字典列表，是球队字典中的周期字典。

如果你有问题，请不要犹豫，尽管问。