Print

40 of 100: Stepped chart 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!

To be improved: I want to improve how to place the flags and arrows.

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
from matplotlib.offsetbox import OffsetImage, AnnotationBbox
import numpy as np
import pandas as pd

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 = {"Norway": "#2B314D", "Denmark": "#A54836", "Sweden": "#5375D4", }

xy_ticklabel_color,  grid_color, datalabels_color ='#101628', "#C8C9C9", "#FFFFFF"

data = {
    "year": [2004, 2022, 2004, 2022, 2004, 2022],
    "countries" : ["Sweden", "Sweden", "Denmark", "Denmark", "Norway", "Norway"],
    "sites": [13,15,4,10,5,8]
}
df= pd.DataFrame(data)
indexyearcountriessites
02004Sweden13
12022Sweden15
22004Denmark4
32022Denmark10
42004Norway5
52022Norway8

We need to sort the data, add the sub totals, diff and color columns:

df['sub_total'] = df.groupby('year')['sites'].transform('sum')
df['diff'] = df.groupby(['countries'])['sites'].diff()
#custom sort
df = df.sort_values(by=['year', 'countries'])
#map the colors of a dict to a dataframe
df['color']= df.countries.map(color_dict)
indexyearcountriessitessub_totaldiffcolor
22004Denmark422NaN#A54836
42004Norway522NaN#2B314D
02004Sweden1322NaN#5375D4
32022Denmark10336.0#A54836
52022Norway8333.0#2B314D
12022Sweden15332.0#5375D4

Generate the colors for the tick labels

color_ticks = df[df.year==df.year.max()].sort_values("sites", ascending= False)['color'].values
color_ticks = np.insert(color_ticks, range(1,4), [["#0E0E0E"]*4,["#0E0E0E"],["#0E0E0E"]*7] )
color_ticks = np.hstack(color_ticks) #flatten the array
color_ticks

array([‘#5375D4’, ‘#0E0E0E’, ‘#0E0E0E’, ‘#0E0E0E’, ‘#0E0E0E’, ‘#A54836’, ‘#0E0E0E’, ‘#2B314D’, ‘#0E0E0E’, ‘#0E0E0E’, ‘#0E0E0E’, ‘#0E0E0E’, ‘#0E0E0E’, ‘#0E0E0E’, ‘#0E0E0E’], dtype='<U7′)

Define the variables

sites = df.sites
img = [plt.imread("flags/de-sq-transparent.png"),plt.imread("flags/no-sq-transparent.png"),plt.imread("flags/sw-sq-transparent.png"),plt.imread("flags/de-sq.png"),plt.imread("flags/no-sq.png"), plt.imread("flags/sw-sq.png")]
colors_= df.color
start_pos_arrows = df[df.year==df.year.min()]['sites'].values
end_pos_arrows = df[df.year==df.year.max()]['sites'].values
diff = df['diff'].dropna().astype(int)
text = ["bold"]+["light"]*4+["bold"]+["light"]*1+["bold"]+ ["light"]*7

Plot the chart

#create the axis
mosaic = np.zeros((15, 15), dtype=int)
for j in range(15):
    mosaic[j, j] = j + 1
ax = plt.figure().subplot_mosaic(
    np.fliplr(mosaic),
    empty_sentinel=0,
    gridspec_kw={
        "wspace": 0,
        "hspace": 0,
    }
)


for lbl, color, text, (label,ax) in zip(reversed(range(15)), color_ticks,  text, ax.items()):

    ax.text(0.5, 0.5, lbl+1, ha="center", va="center", fontsize=10, color=color, weight=text)
    ax.set_xticklabels([])
    ax.set_yticklabels([])
    ax.tick_params(length = 0)
    ax.spines[['bottom','right']].set_visible(False)
    ax.spines[['top','left']].set_color(spines_color)


for site,im in zip(sites, img):
    ib = OffsetImage(im, zoom=.03)
    ab = AnnotationBbox(ib,
                    (0,0),
                    xybox=(site-0.6,site+0.7),
                    alpha=0.5,
                    frameon=False,
                    )
    ax.add_artist(ab)

offset_x=0.5
offset_y=1.5
for end_pos, start_pos, color in zip(end_pos_arrows, start_pos_arrows,colors_):
    ax.annotate("", xy= (start_pos-offset_x, start_pos+offset_y),
                xytext=(end_pos-offset_x, end_pos+offset_y), annotation_clip= False,
                arrowprops=dict(arrowstyle='-', connectionstyle='arc3,rad=0.5',
                            color=color, linewidth=2, linestyle='-', antialiased=True))

pos_numbers= [(7,12),(6,10), (13,17)]
for p, d, c in zip(pos_numbers, diff, colors_):
    ax.annotate(f"+{str(d)}", xy= p, color= c, weight= "bold", annotation_clip=False)

The result:

40 of 100: Stepped chart in matplotlib
Was this helpful?

Reader Interactions

Leave a Reply

Your email address will not be published. Required fields are marked *

Table of Contents