diff --git a/parse_data.py b/parse_data.py index 4741b9c..dc1b4c7 100644 --- a/parse_data.py +++ b/parse_data.py @@ -1,8 +1,9 @@ import csv import json -node_names = set() -edges = [] +# node_names = set() +movements = [] +items = [] #edges libraries = {} locations = {} @@ -30,25 +31,41 @@ with open("data/locaties.csv") as fp: libraries[library['name']] = library locations[location['code']] = location +def filter_date(date: str): + + date = date.replace('cop.', '©').removeprefix('[').removesuffix(']') + if len(date) and date[-1] == '.': + date = date[:-1] + return date + -with open("data/requests.csv") as fp: - reader = csv.DictReader(fp, delimiter=";") +with open("data/batch2/Rapport_transit_1.csv", encoding='utf-8-sig') as fp: + # items + reader = csv.DictReader(fp, delimiter=",") for item in reader: - node_names.add(item['Owning Library Name']) - node_names.add(item['Pickup Location']) - edges.append(item) + item['Publication Date'] = filter_date(item['Publication Date']) + item['Sort Date'] = item['Publication Date'][-4:] # some dates are ranges, only sort by last year + items.append(item) -nodes = [{'name': n} for n in node_names] +with open("data/batch2/Rapport_transit_2.csv", encoding='utf-8-sig') as fp: + # movements + reader = csv.DictReader(fp, delimiter=",") + for item in reader: + movements.append(item) -print(f"{len(nodes)} nodes, {len(edges)} edges") + +# nodes = [{'name': n} for n in node_names] + +print(f"{len(libraries)} nodes, {len(movements)} movements of {len(items)} items") data = { - 'nodes': list(libraries.values()), #nodes, - 'edges': edges + 'libraries': list(libraries.values()), #nodes, + 'movements': movements, #edges + 'items': items, # item bibliographical data } -fn = 'data/parsed_requests.json' +fn = 'data/parsed_transits.json' with open(fn, 'w') as fp: json.dump(data, fp) diff --git a/src/Viz.svelte b/src/Viz.svelte index 5b553c9..c268ac7 100644 --- a/src/Viz.svelte +++ b/src/Viz.svelte @@ -1,5 +1,5 @@