FAS Account Cohort Analysis¶
This notebook tracks community re‑engagement over time by analyzing Fedora account creation and return activity using weekly cohorts and visualizing user retention rates.
We define a Cohort of FAS accounts based on the week they enrolled into FAS and group their activity going forward.
In [1]:
import os
import glob
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from datetime import datetime, timedelta
In [2]:
# @replace DATA_SOURCES
DATA_SOURCES = {'badges': '/data/badges', 'datagrepper-raw': '/data/datagrepper-raw', 'datagrepper-parse-accounts': '/data/datagrepper-parse-accounts'}
parquet_dir = DATA_SOURCES["datagrepper-parse-accounts"]
parquet_files = sorted(glob.glob(f"{parquet_dir}/*.parquet"))
chunks = []
for batch_start in range(0, len(parquet_files), 50):
batch = parquet_files[batch_start:batch_start + 50]
chunk_df = pd.concat(
[pd.read_parquet(f) for f in batch],
ignore_index=True
)
chunk_df['sent_at'] = pd.to_datetime(chunk_df['sent_at'], errors='coerce').dt.floor('s')
chunks.append(chunk_df)
combined_df = pd.concat(chunks, ignore_index=True)
combined_df.dropna(subset=['sent_at', 'username'], inplace=True)
max_date = combined_df['sent_at'].max().date()
min_date = combined_df['sent_at'].min().date()
print(f"Maximum date in data: {max_date}")
print(f"Minimum date in data: {min_date}")
Maximum date in data: 2025-06-28 Minimum date in data: 2024-01-01
In [3]:
new_users_df = combined_df[
combined_df['topic'] == 'org.fedoraproject.prod.fas.user.create'
].copy()
new_users_df['cohort_week'] = new_users_df['sent_at'].dt.to_period('W').dt.start_time
new_users_df['cohort_label'] = new_users_df['cohort_week'].dt.strftime('Week of %Y-%m-%d')
cohort_sizes = new_users_df.groupby('cohort_week')['username'].nunique()
user_cohorts = new_users_df[['username', 'cohort_week', 'cohort_label']].drop_duplicates()
In [4]:
activity_df = combined_df.merge(user_cohorts, on='username', how='inner')
activity_df['week_since_cohort'] = ((activity_df['sent_at'] - activity_df['cohort_week']).dt.days // 7).astype(int)
activity_df = activity_df[activity_df['week_since_cohort'] >= 0]
In [5]:
weekly_activity = (
activity_df
.groupby(['cohort_week', 'week_since_cohort'])['username']
.nunique()
.reset_index()
)
retention_counts = weekly_activity.pivot(
index='cohort_week',
columns='week_since_cohort',
values='username'
).fillna(0)
retention_counts = retention_counts.reindex(cohort_sizes.index.sort_values())
retention_rate = retention_counts.div(cohort_sizes, axis=0) * 100
In [6]:
annotated = retention_counts.astype(object).copy()
for i, cohort in enumerate(annotated.index):
cohort_start = pd.to_datetime(cohort_sizes.index[i], format='Week of %m/%d').date()
for week in annotated.columns:
week_date = cohort_start + timedelta(weeks=int(week))
if week_date > max_date:
annotated.loc[cohort, week] = "N/A"
else:
returned = retention_counts.loc[cohort, week]
total = cohort_sizes[cohort]
annotated.loc[cohort, week] = f"{int(returned)}/{int(total)}"
retention_rate = retention_rate.iloc[:, :12]
annotated = annotated.iloc[:, :12]
label_map = new_users_df.drop_duplicates('cohort_week').set_index('cohort_week')['cohort_label']
The table below shows a weekly count of FAS accounts created each week. The table shows a number in "Number of Returned Users" / "Total Accounts Created in that Week" and then a weekly X axis to show weeks looking forward. If the account that was created in that week returns in what is that user's Week 2, the count will increase.
In [7]:
plt.figure(figsize=(16, 20))
sns.heatmap(
retention_rate,
annot=annotated,
fmt="",
cmap="Blues",
cbar_kws={'label': 'Retention Rate (%)'},
linewidths=0.5,
linecolor='gray'
)
plt.title('FAS Weekly Cohort Retention')
plt.xlabel('Weeks Since Account Creation')
plt.ylabel('Cohort Week')
plt.xticks(ticks=range(12), labels=[f"Week {i}" for i in range(12)])
plt.yticks(
ticks=np.arange(len(retention_rate.index)),
labels=[label_map.get(cohort, cohort.strftime('%Y-%m-%d')) for cohort in retention_rate.index]
)
plt.tight_layout()
plt.show()
In [8]:
user_event_counts = activity_df.groupby('username').size()
valid_users = user_event_counts[user_event_counts >= 5].index
filtered_activity = activity_df[activity_df['username'].isin(valid_users)].copy()
In [9]:
filtered_weekly = (
filtered_activity
.groupby(['cohort_week', 'week_since_cohort'])['username']
.nunique()
.reset_index()
)
filtered_counts = filtered_weekly.pivot(
index='cohort_week',
columns='week_since_cohort',
values='username'
).fillna(0).reindex(cohort_sizes.index.sort_values())
filtered_rate = filtered_counts.div(cohort_sizes, axis=0) * 100
In [10]:
filtered_annotated = filtered_counts.astype(object).copy()
for cohort in filtered_annotated.index:
cohort_start = cohort.date()
for week in filtered_annotated.columns:
current_week_date = cohort_start + timedelta(weeks=int(week))
if current_week_date > max_date:
filtered_annotated.loc[cohort, week] = "N/A"
else:
returned = filtered_counts.loc[cohort, week]
total = cohort_sizes.get(cohort, 0)
filtered_annotated.loc[cohort, week] = f"{int(returned)}/{int(total)}" if total else "0/0"
filtered_rate = filtered_rate.iloc[:, :12]
filtered_annotated = filtered_annotated.iloc[:, :12]
label_map = new_users_df.drop_duplicates('cohort_week').set_index('cohort_week')['cohort_label']
This view shows if the user performed 5 or more activities across the message bus in that week to be counted as a returned contributor.
In [11]:
plt.figure(figsize=(16, 20))
sns.heatmap(
filtered_rate,
annot=filtered_annotated,
fmt="",
cmap="Blues",
cbar_kws={'label': 'Retention Rate (%)'},
linewidths=0.5,
linecolor='gray'
)
plt.title('Filtered Retention: Users with ≥5 Events')
plt.xlabel('Weeks Since Account Creation')
plt.ylabel('Cohort Week')
plt.xticks(ticks=range(12), labels=[f"Week {i}" for i in range(12)])
plt.yticks(
ticks=np.arange(len(retention_rate.index)),
labels=[label_map.get(cohort, cohort.strftime('%Y-%m-%d')) for cohort in retention_rate.index]
)
plt.tight_layout()
plt.show()
