race_plot_scatter.py

import sys
import matplotlib.pyplot as plt
import pandas as pd
from matplotlib import cm
from datetime import datetime, timezone, timedelta
plt.style.use('ggplot')
ticks_format = {
    'day': '%b, %-d',
    'week': '%b, %-d',
    'month': '%b',
    'year': '%Y'
}

def group_date(gr):
    def str_to_datetime(s):
        date_format = "%Y-%m-%d %H:%M:%S"
        return datetime.strptime(s, date_format)

    def utc_to_local(utc_dt):
        return utc_dt.replace(tzinfo=timezone.utc).astimezone(tz=None)

    group_method = {
        'day': datetime.date,
        'week': lambda dt: dt.date() + timedelta(days=6-(dt.weekday() % 7)),
        'month': lambda dt: datetime(dt.year, dt.month, 1),
        'year': lambda dt: datetime(dt.year, 1, 1)
    }

    return lambda s: group_method[gr](utc_to_local(str_to_datetime(s)))

if __name__ == "__main__":
    data = pd.read_csv(sys.argv[1], sep=',')
    gr = sys.argv[2] if (
        len(sys.argv) > 2 and sys.argv[2] in ticks_format) else 'day'
    data['date'] = data['Date/Time (UTC)'].map(group_date(gr))

    avg = []
    for date in set(data['date']):
        d = data.loc[data['date'] == date]
        avg.append((len(d), d['Accuracy'].mean(), d['WPM'].mean()))

    _, acc, wpm = zip(*avg)

    plt.scatter(acc, wpm)
    for n, *coord in avg:
        plt.annotate(n, coord)

    plt.show()