Drill 6: Recall — Analysis project

import pandas as pd

raw = pd.read_csv('lessons.csv', parse_dates=['published_at'])
clean = (
    raw.drop_duplicates()
    .dropna(subset=['course', 'minutes'])
    .assign(month=lambda d: d['published_at'].dt.to_period('M'))
)

answer = (
    clean.groupby(['month', 'course'])['minutes']
    .agg(['size', 'mean'])
    .reset_index()
    .sort_values('mean', ascending=False)
)

print(clean.shape, '->', answer.head(10))