Skip to content

An open-source Python library that turns multiparty conversational data into social-science backed features.

active 2024-07-312026-07-20 (UTC)

Complete coverage26,406 / 26,406 hourly files (100%) · 2 absent upstream2023-08-152026-08-19 (UTC)
Events
995
Pushes
476
Pull requests
117
Issues
89
Stars
3
Forks
1

Activity over time

Daily event counts in the loaded window

Line chart, 720 days from 2024-07-31 to 2026-07-20. Pushes: 476 total, peak 32 in a day. Pull requests: 117 total, peak 12 in a day. Issues: 89 total, peak 25 in a day. Comments: 125 total, peak 22 in a day. Stars: 3 total, peak 1 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

ContributorContributionsPushesPRsComments
xehu5652748694
sundy1994116651321
amytangzheng979150
agshruti12241761
PriyaDCosta201412
github-actions[bot]8800
JamesPHoughton5003
pradnayapathak5320
rowbotham-evan4310
dependabot[bot]3030
yashveersinghsohi3001
jonkush1001

Recent activity

Latest issues, pull requests and releases

  • Pull request#367sundy19942025-12-17 19:34
  • Issue#366xehu2025-12-12 18:39
    Check for Completely Correlated/Redundant Features and Remove Them
  • Issue#364xehu2025-12-02 22:16
    Create FeatureBuilder Log File
  • Issue#364xehu2025-12-02 22:16
    Create FeatureBuilder Log File
  • Issue comment#323xehu2025-07-18 17:33
    Implementation: Linguistic Alignment (e.g., WHAM)
  • Issue comment#323xehu2025-07-18 17:29
    Implementation: Linguistic Alignment (e.g., WHAM)
  • Issue comment#353xehu2025-06-26 22:59
    Clean up Dependency Checking and Ensure Full Function Modularity
  • Issue comment#353sundy19942025-06-26 22:38
    Clean up Dependency Checking and Ensure Full Function Modularity
  • Issue#362sundy19942025-06-26 22:19
    Make sentiment BERT feature run faster
  • Pull request#361xehu2025-06-26 22:08
  • Issue comment#361xehu2025-06-25 02:53
    Get Tests to 100%, Closes #220
  • Issue comment#361xehu2025-06-25 02:45
    Get Tests to 100%, Closes #220
  • Issue#362xehu2025-06-23 21:20
    Make sentiment BERT feature run faster
  • Issue comment#220sundy19942025-06-17 22:08
    Get Tests to 100%
  • Issue comment#220sundy19942025-06-17 22:07
    Get Tests to 100%
  • Issue comment#220sundy19942025-06-16 22:00
    Get Tests to 100%
  • Issue comment#359sundy19942025-06-09 21:52
    FB Fails if Indices are Missing/Out of Order
  • Issue comment#359sundy19942025-06-09 21:12
    FB Fails if Indices are Missing/Out of Order
  • Issue comment#359xehu2025-06-06 23:55
    FB Fails if Indices are Missing/Out of Order
  • Issue comment#359sundy19942025-06-06 23:12
    FB Fails if Indices are Missing/Out of Order
  • Issue#359xehu2025-06-06 21:14
    FB Fails if Indices are Missing/Out of Order
  • Issue comment#342sundy19942025-06-06 18:05
    Extraneous columns (e.g., metadata not related to the FeatureBuilder inputs) with different types can cause FB to fail
  • Issue comment#342sundy19942025-06-06 17:39
    Extraneous columns (e.g., metadata not related to the FeatureBuilder inputs) with different types can cause FB to fail
  • Issue#358xehu2025-06-05 16:56
    Vector preprocessing happens during initialization rather than after calling .featurize()
  • Issue comment#342yashveersinghsohi2025-06-02 22:50
    Extraneous columns (e.g., metadata not related to the FeatureBuilder inputs) with different types can cause FB to fail

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 3 stars here means stars gained during the window, not the repo's star count.