compare_lists.py

#!/usr/bin/env python


import csv

def read_csv_file (filename):

    data = {}
    with open(filename) as csvfile:
        rows = csv.reader(csvfile)

        header = next(rows)

        for row in rows:
            if len(row) > 0:
                row_dict = dict(zip(header, row))
                data[row_dict["PartID"]] = row_dict

    return data

def read_header (filename):

    with open(filename) as csvfile:
        rows = csv.reader(csvfile)

        header = next(rows)
        return header


# figure out the parts in file2 that are not in file1
file1 = 'inventory_31313.csv'
file2 = 'inventory_45544.csv'
ofile = 'inventory_combined.csv'

home = read_csv_file(file1)
edu =  read_csv_file(file2)

with open(ofile, 'w') as output:

    parts = set(list(edu.keys()) + list(home.keys()))

    columns = read_header(file1)
    columns.remove('Quantity')
    columns += ['Home', 'Edu', 'Needed']
    output.write(','.join(columns) + '\n')

    home_count = {}
    edu_count = {}
    for part in parts:
        if part in home:
            design_id = home[part]['DesignID']
            count = int(home[part]['Quantity'])
            if design_id in home_count:
                home_count[design_id] += count
            else:
                home_count[design_id] = count

        if part in edu:
            design_id = edu[part]['DesignID']
            count = int(edu[part]['Quantity'])
            if design_id in edu_count:
                edu_count[design_id] += count
            else:
                edu_count[design_id] = count

    for part in parts:
        if part in home:
            design_id = home[part]['DesignID']
            home_quant = home[part]['Quantity']
            part_dict = home[part]
        else:
            home_quant = 0

        if part in edu:
            design_id = edu[part]['DesignID']
            edu_quant = edu[part]['Quantity']
            part_dict = edu[part]
        else:
            edu_quant = 0

        if design_id not in home_count:
            home_count[design_id] = 0
        if design_id not in edu_count:
            edu_count[design_id] = 0

        # just give needed in the first record, otherwise 0
        needed = edu_count[design_id] - home_count[design_id]
        if needed < 0:
            needed = 0
        edu_count[design_id] = 0
        home_count[design_id] = 0

        part_dict['Home'] = str(home_quant)
        part_dict['Edu'] = str(edu_quant)
        part_dict['Needed'] = str(needed)

        output.write(','.join('"' + part_dict[column] + '"' for column in columns) + '\n')

inventory_31313.csv

inventory_45544.csv

inventory_combined.csv

Comparison of items in the Lego Mindstorms Home edition (31313) (inventory here) and the Education core set (45544) (inventory here).

The python script combines the two lists and adds columns with counts of the number of each parts in the two sets, plus a count of the number of parts to get the home edition to match the education core set (ignoring color). A good source for these is BrickLink, but I needed to go purchase through three vendors, and it was still a bit tedious to find all of the parts.