Display aesthetic

display_aesthetics.py

import pandas as pd

df = pd.read_parquet("aethetic_multi/0000.parquet")

buckets = [(i, i+1) for i in range(10)]

html= "<h1>Aesthetic subsets in Laion2B-multi</h1>"
for [a,b] in buckets:
    total_part = df[(df["prediction"] >= a) & (df["prediction"] <= b)]
    count_part = len(total_part) / len(df) * 100
    estimated =len(total_part) / len(df) * 2.2*10**3
    part = total_part[:200]
    html+=f"<h2>In bucket {a} - {b} there is {count_part:.2f}% ({estimated:.2f}M) samples:</h2> <div>"
    for url in part["url"]:
        html+='<img src="'+url+'" width="100" />'

    html+="</div>"

with open("aesthetic/aesthetic_viz_multi.html", "w") as f:
    f.write(html)

here's the script to print html