无论如何，我可以从 Google 或工具提供的 Job Shop Scheduling 文件主要是 .csv中导入“jobs_data”吗？

如何解决无论如何，我可以从 Google 或工具提供的 Job Shop Scheduling 文件主要是 .csv中导入“jobs_data”吗？

大家好， 我正在尝试从文件（主要是 .csv）导入列表“jobs_data”的数据。我尝试过常见的导入方法，如 open.csv pandas 等，但到目前为止没有任何效果。我大部分时间收到的错误是“类型错误：+ 不支持的操作数类型：‘int’和‘str’”。我也尝试将数据转换为列表，但它失去了预期的格式：

jobs_data = [  # task = (machine_id,processing_time).
    [(0,3),(1,2),(2,2)],# Job0
    [(0,1),4)],# Job1
    [(1,4),3)]  # Job2
]

我不习惯Python编程。所以我希望有人能帮忙。 谢谢。

在@Ashok Arora 给出答案之后，代码的作用就像魅力一样：

import tkinter as tk
import csv
from ortools.sat.python import cp_model



with open("schedule.csv") as csv_file:
    global jd
    csv_reader = csv.reader(csv_file,delimiter=",")
    jd = [[tuple(row[i : i + 2]) for i in range(0,len(row),2)] for row in csv_reader]

def MinimalJobshopSat():

    model = cp_model.CpModel()
    jobs_data = jd
    machines_count = 1 + max(task[0] for job in jobs_data for task in job)
    all_machines = range(machines_count)
    horizon = sum(task[1] for job in jobs_data for task in job)
    task_type = collections.namedtuple('task_type','start end interval')
    assigned_task_type = collections.namedtuple('assigned_task_type','start job index duration')
    all_tasks = {}
    machine_to_intervals = collections.defaultdict(list)
    for job_id,job in enumerate(jobs_data):
        for task_id,task in enumerate(job):
        machine = task[0]
        duration = task[1]
        suffix = '_%i_%i' % (job_id,task_id)
        start_var = model.NewIntvar(0,horizon,'start' + suffix)
        end_var = model.NewIntvar(0,'end' + suffix)
        interval_var = model.NewIntervalVar(start_var,duration,end_var,'interval' + suffix)
            all_tasks[job_id,task_id] = task_type(start=start_var,end=end_var,interval=interval_var)
            machine_to_intervals[machine].append(interval_var)
    for machine in all_machines:
        model.AddNoOverlap(machine_to_intervals[machine])
    for job_id,job in enumerate(jobs_data):
        for task_id in range(len(job) - 1):
            model.Add(all_tasks[job_id,task_id +
                            1].start >= all_tasks[job_id,task_id].end)
    obj_var = model.NewIntvar(0,'makespan')
    model.AddMaxEquality(obj_var,[
    all_tasks[job_id,len(job) - 1].end
    for job_id,job in enumerate(jobs_data)])
    model.Minimize(obj_var)
    solver = cp_model.cpsolver()
    status = solver.solve(model)
    if status == cp_model.OPTIMAL:
        assigned_jobs = collections.defaultdict(list)
        for job_id,job in enumerate(jobs_data):
            for task_id,task in enumerate(job):
                machine = task[0]
                assigned_jobs[machine].append(
                assigned_task_type(start=solver.Value(
                    all_tasks[job_id,task_id].start),job=job_id,index=task_id,duration=task[1]))

    output = ''
    for machine in all_machines:
        assigned_jobs[machine].sort()
        sol_line_tasks = 'Machine ' + str(machine) + ': '
        sol_line = '           '
        
    for assigned_task in assigned_jobs[machine]:
        name = 'job_%i_%i' % (assigned_task.job,assigned_task.index)
        sol_line_tasks += '%-10s' % name
        start = assigned_task.start
        duration = assigned_task.duration
        sol_tmp = '[%i,%i]' % (start,start + duration)
        sol_line += '%-10s' % sol_tmp
    sol_line += '\n
    sol_line_tasks += '\n'
    output += sol_line_tasks
    output += sol_line
    print('Optimal Schedule Length: %i' % solver.ObjectiveValue())
    print(output)
MinimalJobshopSat()

解决方法

假设 jobs.csv 如下：

0,3,1,2,2
0,4
1,4,3

其中每一行代表一个作业，每行都有 len(row)/2 形式的元组 (m,p) 其中 m = 机器 ID 和 p = 处理时间。这遵循 Google OR-Tools 使用的约定。

---

一种将 CSV 读入 a list of list of tuples of string 的方法：

import csv

with open("jobs.csv") as csv_file:
    csv_reader = csv.reader(csv_file,delimiter=",")
    jobs_data = [[tuple(row[i : i + 2]) for i in range(0,len(row),2)] for row in csv_reader]
    print(jobs_data)

将打印：

[[('0','3'),('1','2'),('2','2')],[('0','1'),'4')],[('1','4'),'3')]]

编辑：要生成 int 的元组，请使用 map() 函数。

with open("jobs.csv") as csv_file:
    csv_reader = csv.reader(csv_file,")
    jobs_data = [[tuple(map(int,row[i : i + 2])) for i in range(0,2) ] for row in csv_reader ]
    print(jobs_data)