make_dataset.py

def make_dataset(carrier_list, range_start = -60, range_end = 120, bin_width = 5):

    # Check to make sure the start is less than the end!
    assert range_start < range_end, "Start must be less than end!"
    
    by_carrier = pd.DataFrame(columns=['proportion', 'left', 'right', 
                                       'f_proportion', 'f_interval',
                                       'name', 'color'])
    range_extent = range_end - range_start
    
    # Iterate through all the carriers
    for i, carrier_name in enumerate(carrier_list):

        # Subset to the carrier
        subset = flights[flights['name'] == carrier_name]

        # Create a histogram with specified bins and range
        arr_hist, edges = np.histogram(subset['arr_delay'], 
                                       bins = int(range_extent / bin_width), 
                                       range = [range_start, range_end])

        # Divide the counts by the total to get a proportion and create df
        arr_df = pd.DataFrame({'proportion': arr_hist / np.sum(arr_hist), 
                               'left': edges[:-1], 'right': edges[1:] })

        # Format the proportion 
        arr_df['f_proportion'] = ['%0.5f' % proportion for proportion in arr_df['proportion']]

        # Format the interval
        arr_df['f_interval'] = ['%d to %d minutes' % (left, right) for left, 
                                right in zip(arr_df['left'], arr_df['right'])]

        # Assign the carrier for labels
        arr_df['name'] = carrier_name

        # Color each carrier differently
        arr_df['color'] = Category20_16[i]

        # Add to the overall dataframe
        by_carrier = by_carrier.append(arr_df)

    # Overall dataframe
    by_carrier = by_carrier.sort_values(['name', 'left'])
    
    # Convert dataframe to column data source
    return ColumnDataSource(by_carrier)