How to create a min-max lineplot by month

Question

I have retail beef ad counts time series data, and I intend to make stacked line chart aim to show On a three-week average basis, quantity of average ads that grocers posted

Answer 1

• Also see How to create a min-max plot by month with fill_between?
• See in-line comments for details

import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import calendar

#################################################################
# setup from question
url = 'https://gist.githubusercontent.com/adamFlyn/96e68902d8f71ad62a4d3cda135507ad/raw/4761264cbd55c81cf003a4219fea6a24740d7ce9/df.csv'
df = pd.read_csv(url, parse_dates=['date'])
df.drop(columns=['Unnamed: 0'], inplace=True)
df_grp = df.groupby(['date', 'retail_item']).agg({'number_of_ads': 'sum'})
df_grp["percentage"] = df_grp.groupby(level=0).apply(lambda x:100 * x / float(x.sum()))
df_grp = df_grp.reset_index(level=[0,1])
#################################################################

# create a month map from long to abbreviated calendar names
month_map = dict(zip(calendar.month_name[1:], calendar.month_abbr[1:]))

# update the month column name
df_grp['month'] = df_grp.date.dt.month_name().map(month_map)

# set month as categorical so they are plotted in the correct order
df_grp.month = pd.Categorical(df_grp.month, categories=month_map.values(), ordered=True)

# use groupby to aggregate min mean and max
dfmm = df_grp.groupby(['retail_item', 'month'])['percentage'].agg([max, min, 'mean']).stack().reset_index(level=[2]).rename(columns={'level_2': 'mm', 0: 'vals'}).reset_index()

# create a palette map for line colors
cmap = {'min': 'k', 'max': 'k', 'mean': 'b'}

# iterate through each retail item and plot the corresponding data
for g, d in dfmm.groupby('retail_item'):
    plt.figure(figsize=(7, 4))
    sns.lineplot(x='month', y='vals', hue='mm', data=d, palette=cmap)

    # select only min or max data for fill_between
    y1 = d[d.mm == 'max']
    y2 = d[d.mm == 'min']
    plt.fill_between(x=y1.month, y1=y1.vals, y2=y2.vals, color='gainsboro')
    
    # add lines for specific years
    for year in [2016, 2018, 2020]:
        data = df_grp[(df_grp.date.dt.year == year) & (df_grp.retail_item == g)]
        sns.lineplot(x='month', y='percentage', ci=None, data=data, label=year)
    
    plt.ylim(0, 100)
    plt.margins(0, 0)
    plt.legend(bbox_to_anchor=(1., 1), loc='upper left')
    
    plt.ylabel('Percentage of Ads')
    plt.title(g)
    plt.show()