pangeo_cmip6_heatmap.py

import pandas as pd
from matplotlib import pyplot as plt
import numpy as np
%matplotlib inline

url = 'https://storage.googleapis.com/pangeo-cmip6/pangeo-cmip6-zarr-consolidated-stores.csv'
df = pd.read_csv(url)
run_count = df[df.activity_id == 'CMIP'].groupby(['experiment_id', 'source_id']).zstore.count()
rcu = run_count.unstack(level=-1)

data = rcu.values
models = list(rcu.columns)
scenarios = list(rcu.index)

# adopted from https://matplotlib.org/3.1.1/gallery/images_contours_and_fields/image_annotated_heatmap.html
fig, ax = plt.subplots(figsize=(20, 7))
im = ax.imshow(data, cmap='Reds')

# We want to show all ticks...
ax.set_xticks(np.arange(len(models)))
ax.set_yticks(np.arange(len(scenarios)))
# ... and label them with the respective list entries
ax.set_xticklabels(models)
ax.set_yticklabels(scenarios)
ax.set_ylim([-0.5, len(scenarios)-0.5])

# Rotate the tick labels and set their alignment.
plt.setp(ax.get_xticklabels(), rotation=45, ha="right",
         rotation_mode="anchor")

# Loop over data dimensions and create text annotations.
for i in range(len(scenarios)):
    for j in range(len(models)):
        if data[i, j] > 0:
            text = ax.text(j, i, int(data[i, j]),
                       ha="center", va="center", color='c')

plt.title('Pangeo CMIP6 Data Holdings')

As of today: