# rehanfarishta03/resume-screening-nlp architecture

> Architecture diagram of the GitHub repository rehanfarishta03/resume-screening-nlp, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-11-16). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/rehanfarishta03/resume-screening-nlp
- Repository: https://github.com/rehanfarishta03/resume-screening-nlp

## Overview

This repository provides a Streamlit resume-screening app: a user supplies a resume and job description, the app extracts file text, then computes a lexical match score, keyword gaps, and a predicted job category. A separate training script builds the TF-IDF classifier artifacts consumed by scoring. The README also describes broader notebook-based model comparisons, evaluation, and BERT features; those capabilities are documented but their implementation was not sampled, so they are shown as a separate, unverified branch.

Main entry points: [`app.py`](https://github.com/rehanfarishta03/resume-screening-nlp/blob/main/app.py) (Streamlit interface), [`train_model.py`](https://github.com/rehanfarishta03/resume-screening-nlp/blob/main/train_model.py) (TF-IDF classifier training), [`Resume Screening with NLP (TF-IDF)/resume Screening using NLP.ipynb`](https://github.com/rehanfarishta03/resume-screening-nlp/blob/main/Resume%20Screening%20with%20NLP%20(TF-IDF)/resume%20Screening%20using%20NLP.ipynb) (Model experiments and evaluation), [`scoring.py`](https://github.com/rehanfarishta03/resume-screening-nlp/blob/main/scoring.py) (ATS scoring and classification)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_application["Screening app"]
  node_streamlit["Streamlit interface<br/>[app.py]"]
end

subgraph group_analysis["Text analysis"]
  node_parser["File text extraction<br/>[parsing.py]"]
  node_scorer["ATS scoring and classification<br/>[scoring.py]"]
  node_artifacts[("Trained model artifacts")]
end

subgraph group_training["Model training"]
  node_dataset["Resume-job dataset"]
  node_trainer["TF-IDF classifier training<br/>[train_model.py]"]
end

subgraph group_research["Notebook capabilities"]
  node_notebook["Model experiments and evaluation"]
  node_bert["BERT embeddings"]
end

node_candidate(("Resume submitter"))

node_candidate -->|"submits inputs"| node_streamlit
node_streamlit -->|"extracts uploaded text"| node_parser
node_streamlit -->|"requests analysis"| node_scorer
node_scorer -->|"loads vectorizer and classifier"| node_artifacts
node_trainer -->|"reads"| node_dataset
node_trainer -->|"saves trained artifacts"| node_artifacts
node_notebook -.->|"uses embeddings"| node_bert
node_notebook -.->|"compares model approaches"| node_trainer

click node_streamlit "https://github.com/rehanfarishta03/resume-screening-nlp/blob/main/app.py"
click node_parser "https://github.com/rehanfarishta03/resume-screening-nlp/blob/main/parsing.py"
click node_scorer "https://github.com/rehanfarishta03/resume-screening-nlp/blob/main/scoring.py"
click node_artifacts "https://github.com/rehanfarishta03/resume-screening-nlp/tree/main/artifacts"
click node_dataset "https://github.com/rehanfarishta03/resume-screening-nlp/blob/main/Resume%20Screening%20with%20NLP%20(TF-IDF)/resume_job_matching_dataset.csv"
click node_trainer "https://github.com/rehanfarishta03/resume-screening-nlp/blob/main/train_model.py"
click node_notebook "https://github.com/rehanfarishta03/resume-screening-nlp/blob/main/Resume%20Screening%20with%20NLP%20(TF-IDF)/resume%20Screening%20using%20NLP.ipynb"
click node_bert "https://github.com/rehanfarishta03/resume-screening-nlp/blob/main/Resume%20Screening%20with%20NLP%20(TF-IDF)/resume%20Screening%20using%20NLP.ipynb"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_streamlit toneBlue
class node_parser,node_scorer,node_artifacts toneAmber
class node_dataset,node_trainer toneMint
class node_notebook,node_bert toneRose
class node_candidate toneIndigo
```

## Components

### Screening app

- [Streamlit interface](https://github.com/rehanfarishta03/resume-screening-nlp/blob/main/app.py): `app.py`

### Text analysis

- [File text extraction](https://github.com/rehanfarishta03/resume-screening-nlp/blob/main/parsing.py): `parsing.py`
- [ATS scoring and classification](https://github.com/rehanfarishta03/resume-screening-nlp/blob/main/scoring.py): `scoring.py`
- [Trained model artifacts](https://github.com/rehanfarishta03/resume-screening-nlp/tree/main/artifacts): `artifacts`

### Model training

- [Resume-job dataset](https://github.com/rehanfarishta03/resume-screening-nlp/blob/main/Resume%20Screening%20with%20NLP%20(TF-IDF)/resume_job_matching_dataset.csv): `Resume Screening with NLP (TF-IDF)/resume_job_matching_dataset.csv`
- [TF-IDF classifier training](https://github.com/rehanfarishta03/resume-screening-nlp/blob/main/train_model.py): `train_model.py`

### Notebook capabilities

- [Model experiments and evaluation](https://github.com/rehanfarishta03/resume-screening-nlp/blob/main/Resume%20Screening%20with%20NLP%20(TF-IDF)/resume%20Screening%20using%20NLP.ipynb): `Resume Screening with NLP (TF-IDF)/resume Screening using NLP.ipynb`
- [BERT embeddings](https://github.com/rehanfarishta03/resume-screening-nlp/blob/main/Resume%20Screening%20with%20NLP%20(TF-IDF)/resume%20Screening%20using%20NLP.ipynb): `Resume Screening with NLP (TF-IDF)/resume Screening using NLP.ipynb`

### Other components

- **Resume submitter**

## Connections

- Resume submitter → Streamlit interface: submits inputs (evidence: `app.py`)
- Streamlit interface → File text extraction: extracts uploaded text (evidence: `app.py`)
- Streamlit interface → ATS scoring and classification: requests analysis (evidence: `app.py`)
- ATS scoring and classification → Trained model artifacts: loads vectorizer and classifier (evidence: `scoring.py`)
- TF-IDF classifier training → Resume-job dataset: reads (evidence: `train_model.py`)
- TF-IDF classifier training → Trained model artifacts: saves trained artifacts (evidence: `train_model.py`)
- Model experiments and evaluation → BERT embeddings: uses embeddings (evidence: `README.md`)
- Model experiments and evaluation → TF-IDF classifier training: compares model approaches (evidence: `README.md`)
