Calendar Heatmap of FutureLearn steps

gistfile1.py

#generate a calendar heatmap of step visits
# http://stackoverflow.com/a/32492179
# Extension of https://github.com/psychemedia/futurelearnStatsSketches/blob/master/notebooks/FutureLearn%20Stats%20Recipes.ipynb

import datetime as dt

def generate_data():
    num = 100
    data = np.random.randint(0, 20, num)
    start = pd.to_datetime(COURSE_START_DATE)
    dates = [start + dt.timedelta(days=i) for i in range(num)]
    return dates, data

def calendar_array(dates, data):
    i, j = zip(*[d.isocalendar()[1:] for d in dates])
    i = np.array(i) - min(i)
    j = np.array(j) - 1
    ni = max(i) + 1

    calendar = np.nan * np.zeros((ni, 7))
    calendar[i, j] = data
    return i, j, calendar

def calendar_heatmap(ax, dates, data):
    i, j, calendar = calendar_array(dates, data)
    im = ax.imshow(calendar, interpolation='none', cmap=sns.light_palette("purple", reverse=False,as_cmap=True))
    label_days(ax, dates, i, j, calendar)
    label_months(ax, dates, i, j, calendar)
    ax.figure.colorbar(im)

def label_days(ax, dates, i, j, calendar):
    ni, nj = calendar.shape
    day_of_month = np.nan * np.zeros((ni, 7))
    day_of_month[i, j] = [d.day for d in dates]

    for (i, j), day in np.ndenumerate(day_of_month):
        if np.isfinite(day):
            ax.text(j, i, int(day), ha='center', va='center')

    ax.set(xticks=np.arange(7), 
           xticklabels=['M', 'T', 'W', 'T', 'F', 'S', 'S'])
    ax.xaxis.tick_top()

def label_months(ax, dates, i, j, calendar):
    month_labels = np.array(['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul',
                             'Aug', 'Sep', 'Oct', 'Nov', 'Dec'])
    months = np.array([d.month for d in dates])
    uniq_months = sorted(set(months))
    yticks = [i[months == m].mean() for m in uniq_months]
    labels = [month_labels[m - 1] for m in uniq_months]
    ax.set(yticks=yticks)
    ax.set_yticklabels(labels, rotation=90)
    

#plt.show()
tmp = date_limiter(steps[steps['first_visited_at'].notnull()], start=COURSE_START_DATE+' 01:10:50', end=COURSE_END_DATE+' 02', index='first_visited_at')
tmp=tmp.reset_index().set_index('first_visited_at')
tmp=tmp.groupby(pd.TimeGrouper(freq='D')).size().reset_index()
tmp.rename(columns={0:'count'},inplace=True)


#tmp = tmp.groupby([pd.Grouper(freq='D',key='first_visited_at')]).count()
fig, ax = plt.subplots(figsize=(10, 10))
calendar_heatmap(ax, tmp['first_visited_at'], tmp['count'])