Accumulated enrollment and daily growth of FutureLearn data

gistfile1.py

# Extension of https://github.com/psychemedia/futurelearnStatsSketches/blob/master/notebooks/FutureLearn%20Stats%20Recipes.ipynb

def plot_cumulativeCount(df, group, groupset, index, title, start, end):
    plt.rc("figure", figsize=(15, 10))
    df=df[df[group].isin(groupset)]
    df=df.reset_index().set_index(index)
    df.sort_index(inplace=True)
    df=date_limiter(df, start, end)
    df['Total enrollments']=range(len(df))
     
    ax=df['Total enrollments'].plot(title=title, color='fuchsia')
    
    ax2 = ax.twinx()
    ax2=df.groupby(df.index.date).size().plot()
    
    ax.axvspan(pd.to_datetime(COURSE_START_DATE), pd.to_datetime(COURSE_END_DATE), color='grey', alpha=0.4, lw=0)
    
    grey_patch = mpatches.Patch(color='grey', alpha=0.4, label='Course running')
    acum_line = mlines.Line2D([], [], color='fuchsia', label='Total enrollments')
    day_line = mlines.Line2D([], [], label='Enrollments by day')
    
    ax2.legend(loc=2, prop={'size':13}, handles=[grey_patch, acum_line, day_line])
    
    ax.set_xlabel('Date')
    ax.set_ylabel('Accumulated Enrollments')
    ax2.set_ylabel('Daily Enrollments')
    
    ax.get_yaxis().set_major_formatter(
    tkr.FuncFormatter(lambda x, p: format(int(x), ',')))
    ax2.get_yaxis().set_major_formatter(
    tkr.FuncFormatter(lambda x, p: format(int(x), ',')))
    
    for item in ([ax.title, ax.xaxis.label, ax.yaxis.label, ax2.yaxis.label] +
             ax.get_xticklabels() + ax.get_yticklabels() + ax2.get_yticklabels()):
        item.set_fontsize(13)
        
    ax2.grid(None)
    align_axis(ax, ax2)

    
# http://stackoverflow.com/a/28527815/1027723        
def align_axis(ax1, ax2, step=1):
    """ Sets both axes to have the same number of gridlines
        ax1: left axis
        ax2: right axis
        step: defaults to 1 and is used in generating a range of values to check new boundary 
              as in np.arange([start,] stop[, step])
    """
    ax1.set_aspect('auto')
    ax2.set_aspect('auto')

    grid_l = len(ax1.get_ygridlines())  # N of gridlines for left axis
    grid_r = len(ax2.get_ygridlines())  # N of gridlines for right axis
    grid_m = max(grid_l, grid_r)  # Target N of gridlines

    #  Choose the axis with smaller N of gridlines 
    if grid_l < grid_r:
        y_min, y_max = ax1.get_ybound()  # Get current boundaries 
        parts = (y_max - y_min) / (grid_l - 1)  # Get current number of partitions
        left = True 
    elif grid_l > grid_r:
        y_min, y_max = ax2.get_ybound()
        parts = (y_max - y_min) / (grid_r - 1)
        left = False
    else:
        return None

    # Calculate the new boundary for axis:
    yrange = np.arange(y_max + 1, y_max * 2 + 1, step)  # Make a range of potential y boundaries
    parts_new = (yrange - y_min) / parts  # Calculate how many partitions new boundary has
    y_new = yrange[np.isclose(parts_new, grid_m - 1)]  # Find the boundary matching target

    # Set new boundary
    if left:
        return ax1.set_ylim(top=y_new, emit=True, auto=True)
    else:
        return ax2.set_ylim(top=y_new, emit=True, auto=True)

    
plot_cumulativeCount(enrolments,
                     'learner_id',
                     enrolled_learners,
                     'enrolled_at',
                     '{} enrolment accumulation'.format(COURSE_SHORTNAME),
                     COURSE_OPEN_REGISTRATION,
                     offsetDays(COURSE_END_DATE,7)
                    )