process_gnuplot_usage.py

import argparse
import collections
import csv
import datetime
import functools
import os
import subprocess
import sys

data = []


def aggregate_by_field(f):
    by_date = collections.defaultdict(collections.Counter)
    for row in data:
        cost = row["Price Per Unit ($)"] * row["Quantity"] * row["Multiplier"]
        date = datetime.datetime.strptime(row["Date"], "%Y-%m-%d").date()
        by_date[date][row[f]] += cost
    return by_date


def dump_table(table, field, filename_base):
    keys = functools.reduce(set.union, [set(i.keys()) for i in table.values()])
    columns = sorted(keys)
    start_date = min(table.keys())
    end_date = max(table.keys())
    with open(filename_base + ".csv", "w") as f:
        out = csv.writer(f)
        out.writerow(["date"] + columns)
        while start_date <= end_date:
            this_row = table.get(start_date, {})
            row = [start_date.strftime("%Y-%m-%d")] + [str(this_row.get(c, "")) for c in columns]
            out.writerow(row)
            start_date += datetime.timedelta(days=1)
    gnuplot_file = filename_base + ".gnuplot"
    with open(gnuplot_file, "w") as f:
        f.write('set term png enhanced font "Berkeley Mono" 16 size 1000,800\n')
        f.write(f'set out "{filename_base}.png"\n')
        f.write('set datafile separator ","\n')
        f.write('set timefmt "%Y-%m-%d"\n')
        f.write("set xdata time\n")
        f.write('set ylabel "Cost ($)"\n')
        f.write('set xlabel "Date"\n')
        f.write("set key below\n")
        f.write("set pointsize 1\n")
        f.write(f'set title "Spend By {field}"\n')
        plot = []
        for i, label in enumerate(columns):
            plot.append(f'"{filename_base}.csv" using 1:{i+2} with points title "{label.replace("_", "-")}"')
        plot = ", ".join(plot)
        f.write(f"plot {plot}\n")
    subprocess.check_call(["gnuplot", gnuplot_file])
    os.unlink(gnuplot_file)


def dump_table_by_field(field, filename_base):
    dump_table(aggregate_by_field(field), field, filename_base)


_TRANSFORMS = {"Quantity": float, "Price Per Unit ($)": float, "Multiplier": float}


def transform(row):
    return dict((k, _TRANSFORMS.get(k, str)(v)) for (k, v) in row.items())


def main():
    parser = argparse.ArgumentParser()
    parser.add_argument("-i", "--input", type=argparse.FileType("r"), default=sys.stdin)
    args = parser.parse_args()

    r = csv.DictReader(args.input)
    for row in r:
        data.append(transform(row))

    dump_table_by_field("Owner", "by_owner")
    dump_table_by_field("Repository Slug", "by_repo")
    dump_table_by_field("Username", "by_user")
    dump_table_by_field("SKU", "by_sku")


main()