commit 0a2d98a36105aa8bbd107ba783c492ca3f4b4d4d parent 3821135c51cf97ddac5cbd57f0b188df5411ea8f Author: Andrew Laack <andrew@laack.co> Date: Wed, 6 May 2026 03:55:09 -0500 Basic histogram script Diffstat:
| A | analytics/graph.py | | | 18 | ++++++++++++++++++ |
1 file changed, 18 insertions(+), 0 deletions(-)
diff --git a/analytics/graph.py b/analytics/graph.py @@ -0,0 +1,18 @@ +import plotly.express as px +import os +import subprocess + +def du(path): + """disk usage in human readable format (e.g. '2,1GB')""" + print(path) + return subprocess.check_output(['du','-s', path]).split()[0].decode('utf-8') + +sizes = [] + +# Run this from root of repo +for f in os.listdir('./crawl/outputs/sites/'): + sizes.append(du("./crawl/outputs/sites/" + f)) + +print(sizes) +fig = px.histogram(sizes) +fig.show()