69 of 100: Bar chart in a map in matplotlib

At the beginning of the year I challenged myself to create all 100 visualizations using python and matplotlib from the 1 dataset,100 visualizations project and I am sharing with you the code for all the visualizations.

Note: Data Viz Project is copyright Ferdio and available under a Creative Commons Attribution – Non Commercial – No Derivatives 4.0 International license. I asked Ferdio and they told me they used a Design tool to create all the plots.

Collaborate

There are a ton of improvements that can be made on the code, so let me know in the comments any improvements you make and I will update the post accordingly!

This is the original viz that we are trying to recreate in matplotlib:

Import the packages

We will need the following packages:

import matplotlib.pyplot as plt
import matplotlib as mpl
from matplotlib.lines import Line2D
from svgpathtools import svg2paths
from svgpath2mpl import parse_path
import pandas as pd
import geopandas as gpd

Generate the data

We could actually go from numpy to matplotlib, but most data projects use pandas to transform the data, so I am using a pandas dataframe as the starting point.

color_dict = { 2022: "#A54836", 2004: "#5375D4", }

xy_ticklabel_color, grand_totals_color, grid_color, datalabels_color ='#757C85',"#101628", "#C8C9C9", "#FFFFFF"

data = {
    "year": [2004, 2022, 2004, 2022, 2004, 2022],
    "countries" : [ "Denmark", "Denmark", "Norway", "Norway","Sweden", "Sweden",],
    "sites": [4,10,5,8,13,15]
}
df= pd.DataFrame(data)

We need to create the colors for each year and then sort the data.

sort_order_dict = {"Denmark":2, "Sweden":3, "Norway":1, 2004:5, 2022:4}
df = df.sort_values(by=['year','countries',], key=lambda x: x.map(sort_order_dict))
df['ctry_code'] = df.countries.astype(str).str[:2].astype(str).str.upper()
#map the colors of a dict to a dataframe
df['color']= df.year.map(color_dict)

Add the map

map_df = gpd.read_file("https://raw.githubusercontent.com/eurostat/Nuts2json/master/pub/v2/2021/3035/20M/0.json")
map_df['country'] = map_df['id'].astype(str).str[:2]
map_df = map_df[map_df.country.isin(['NO','SE', 'DK']) ]

Create the marker for the cylinder

icon_path, attributes = svg2paths('flags/cylinder-svgrepo-com2.svg')
#matplotlib path object of the icon
icon_marker  = parse_path(attributes[0]['d'])

icon_marker.vertices -= icon_marker.vertices.mean(axis=0)
icon_marker = icon_marker.transformed(mpl.transforms.Affine2D().rotate_deg(180))
icon_marker = icon_marker.transformed(mpl.transforms.Affine2D().scale(-1,1))

Add the variables

years = df.year.unique() 
countries = df.countries.unique()
colors = df.color.unique()
lat= [0.42,0.48,0.54]
lon =[0.24,0.14,0.28]

Plot the chart

fig = plt.figure(figsize=(15,10))
ax_map = fig.add_axes([0, 0, 1, 1])
map_df.plot(color='#D3D3D3',ax=ax_map)
ax_map.set_axis_off()

for lt,ln,country, in zip(lat,lon,countries, ):
    print(lat, lon)
    ax_bar = fig.add_axes([lt ,ln , 0.03, 0.2])  
    temp_df = df[df.countries == country]
    x = list(range(2))
    y = temp_df.sites
    for value, color, count in zip(x, colors, y):
        ax_bar.plot([value]*count, list(range(count)), marker = icon_marker, ms=20, linestyle='', color=color)
        #add data labels
        ax_bar.text(value, count+1, count, ha= "center", color = "white",
                bbox=dict(facecolor='black', edgecolor='black', boxstyle='round,pad=0.3'))
    ax_bar.set(xlim = (-1,2), ylim=(-2,16))
    ax_bar.set_yticklabels([])
    ax_bar.set_xticklabels([])
    ax_bar.grid(False)
    ax_bar.set_frame_on(False)
    ax_bar.tick_params(axis='both', which='both',length = 0)

#add legend
text_legends = ["Before", "After"]
colors = colors
lines = [Line2D([0], [0], color=c,  marker=icon_marker,linestyle='', markersize=20,) for c in colors]
labels  = [f'{text_legend} 2004' for  text_legend in text_legends]
for year in years:
    plt.figlegend( lines,labels,   
                  labelcolor=xy_ticklabel_color,
            bbox_to_anchor=(0.5, -0.05), loc="lower center",
                ncols = 2,frameon=False, fontsize= 12)

The result: