Skip to content

Caffeine26/NLP-Text-Generator-Project

View on GitHub ↗Related repositories →

The objective of this project is to build and evaluate statistical 4-gram language models using backoff and interpolation techniques, and to analyze their effectiveness in predicting and generating natural language text using perplexity as an evaluation metric.

active 2025-12-152026-01-17 (UTC)

Complete coverage26,432 / 26,432 hourly files (100%) · 2 absent upstream2023-08-152026-08-20 (UTC)
Events
21
Pushes
2
Pull requests
0
Issues
17
Stars
0
Forks
0

Activity over time

Daily event counts in the loaded window

Line chart, 34 days from 2025-12-15 to 2026-01-17. Pushes: 2 total, peak 1 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 17 total, peak 9 in a day. Comments: 0 total, peak 0 in a day. Stars: 0 total, peak 0 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
Caffeine2618100
DeangDane1100

Recent activity

Latest issues, pull requests and releases

  • Issue#12Caffeine262026-01-17 11:10
    Task 1 - Project Setup & File Structure
  • Issue#13Caffeine262026-01-17 11:09
    create folder as : MiniProject2
  • Issue#21Caffeine262026-01-17 11:00
    Task 6 – Report Writing (Max 2 Pages)
  • Issue#17Caffeine262026-01-17 10:26
    Push the project structure back to repo
  • Issue#16Caffeine262026-01-17 10:25
    Split each file
  • Issue#15Caffeine262026-01-17 10:23
    Load positive-reviews.txt and negative-reviews.txt
  • Issue#14Caffeine262026-01-17 10:22
    Task 2 – Load & Preprocess Data
  • Issue#12Caffeine262026-01-17 10:20
    Task 1 - Project Setup & File Structure
  • Issue#12Caffeine262026-01-17 10:20
    Task 1 - Project Setup & File Structure
  • Issue#6Caffeine262025-12-15 05:32
    Step 1: Read data and create n-grams
  • Issue#4Caffeine262025-12-15 05:31
    Phase 4: Vocabulary Limiting + <UNK>
  • Issue#2Caffeine262025-12-15 05:31
    Phase 2: Split Corpus
  • Issue#10Caffeine262025-12-15 05:25
    Phase 6: Evaluate using Test set( Perplexity)
  • Issue#8Caffeine262025-12-15 05:20
    Step 3: Build LM2 (Interpolation + add-k smoothing)
  • Issue#4Caffeine262025-12-15 05:13
    Phase 4: Vocabulary Limiting + <UNK>
  • Issue#3Caffeine262025-12-15 05:11
    Phase 3: Tokenization
  • Issue#2Caffeine262025-12-15 05:10
    Phase 2: Split Corpus

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 0 stars here means stars gained during the window, not the repo's star count.