# akhilsinghkoteri/movie-recommender architecture

> Architecture diagram of the GitHub repository akhilsinghkoteri/movie-recommender, 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/akhilsinghkoteri/movie-recommender
- Repository: https://github.com/akhilsinghkoteri/movie-recommender

## Overview

This is a small Streamlit content-based movie recommender. The workflow loads and cleans the movie catalog, builds genre TF-IDF vectors, accepts favorite titles, forms a taste profile, ranks similar movies, and displays the top-N suggestions. The graph separates the interface, recommendation stages, and catalog. The sampled source shows the main execution paths; recommendations are computed on demand rather than through a precomputed similarity matrix.

Main entry points: [`recommender.py`](https://github.com/akhilsinghkoteri/movie-recommender/blob/main/recommender.py) (Similarity ranking), [`app.py`](https://github.com/akhilsinghkoteri/movie-recommender/blob/main/app.py) (Streamlit interface), [`movies.csv`](https://github.com/akhilsinghkoteri/movie-recommender/blob/main/movies.csv) (MovieLens catalog)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_interface["Web interface"]
  node_ui["Streamlit interface<br/>[app.py]"]
  node_engine_setup["Cached engine setup<br/>[app.py]"]
  node_results["Recommendation display<br/>[app.py]"]
end

subgraph group_engine["Recommendation engine"]
  node_vectorizer["Genre TF-IDF vectors<br/>[recommender.py]"]
  node_profile["Taste profile<br/>[recommender.py]"]
  node_ranker["Similarity ranking<br/>[recommender.py]"]
  node_recommendations["Top-N suggestions<br/>[recommender.py]"]
end

subgraph group_catalog["Movie catalog"]
  node_loader["Load and clean data<br/>[recommender.py]"]
  node_movie_data["MovieLens catalog<br/>[movies.csv]"]
end

node_user(("Movie seeker"))

node_user -->|"selects favorites"| node_ui
node_ui -->|"initializes engine"| node_engine_setup
node_engine_setup -->|"loads data"| node_loader
node_loader -->|"reads CSV"| node_movie_data
node_engine_setup -->|"builds vectors"| node_vectorizer
node_loader -->|"provides cleaned genres"| node_vectorizer
node_ui -->|"requests recommendations"| node_ranker
node_ranker -->|"averages favorite vectors"| node_profile
node_profile -->|"provides taste vector"| node_ranker
node_ranker -->|"compares against vectors"| node_vectorizer
node_ranker -->|"selects top matches"| node_recommendations
node_recommendations -->|"returns titles"| node_results
node_results -->|"displays suggestions"| node_user

click node_ui "https://github.com/akhilsinghkoteri/movie-recommender/blob/main/app.py"
click node_engine_setup "https://github.com/akhilsinghkoteri/movie-recommender/blob/main/app.py"
click node_results "https://github.com/akhilsinghkoteri/movie-recommender/blob/main/app.py"
click node_loader "https://github.com/akhilsinghkoteri/movie-recommender/blob/main/recommender.py"
click node_movie_data "https://github.com/akhilsinghkoteri/movie-recommender/blob/main/movies.csv"
click node_vectorizer "https://github.com/akhilsinghkoteri/movie-recommender/blob/main/recommender.py"
click node_profile "https://github.com/akhilsinghkoteri/movie-recommender/blob/main/recommender.py"
click node_ranker "https://github.com/akhilsinghkoteri/movie-recommender/blob/main/recommender.py"
click node_recommendations "https://github.com/akhilsinghkoteri/movie-recommender/blob/main/recommender.py"

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_ui,node_engine_setup,node_results toneBlue
class node_vectorizer,node_profile,node_ranker,node_recommendations toneAmber
class node_loader,node_movie_data toneMint
class node_user toneIndigo
```

## Components

### Web interface

- [Streamlit interface](https://github.com/akhilsinghkoteri/movie-recommender/blob/main/app.py): `app.py`
- [Cached engine setup](https://github.com/akhilsinghkoteri/movie-recommender/blob/main/app.py): `app.py`
- [Recommendation display](https://github.com/akhilsinghkoteri/movie-recommender/blob/main/app.py): `app.py`

### Recommendation engine

- [Genre TF-IDF vectors](https://github.com/akhilsinghkoteri/movie-recommender/blob/main/recommender.py): `recommender.py`
- [Taste profile](https://github.com/akhilsinghkoteri/movie-recommender/blob/main/recommender.py): `recommender.py`
- [Similarity ranking](https://github.com/akhilsinghkoteri/movie-recommender/blob/main/recommender.py): `recommender.py`
- [Top-N suggestions](https://github.com/akhilsinghkoteri/movie-recommender/blob/main/recommender.py): `recommender.py`

### Movie catalog

- [Load and clean data](https://github.com/akhilsinghkoteri/movie-recommender/blob/main/recommender.py): `recommender.py`
- [MovieLens catalog](https://github.com/akhilsinghkoteri/movie-recommender/blob/main/movies.csv): `movies.csv`

### Other components

- **Movie seeker**

## Connections

- Movie seeker → Streamlit interface: selects favorites (evidence: `app.py`)
- Streamlit interface → Cached engine setup: initializes engine (evidence: `app.py`)
- Cached engine setup → Load and clean data: loads data (evidence: `app.py`)
- Load and clean data → MovieLens catalog: reads CSV (evidence: `recommender.py`)
- Cached engine setup → Genre TF-IDF vectors: builds vectors (evidence: `app.py`)
- Load and clean data → Genre TF-IDF vectors: provides cleaned genres (evidence: `recommender.py`)
- Streamlit interface → Similarity ranking: requests recommendations (evidence: `app.py`)
- Similarity ranking → Taste profile: averages favorite vectors (evidence: `recommender.py`)
- Taste profile → Similarity ranking: provides taste vector (evidence: `recommender.py`)
- Similarity ranking → Genre TF-IDF vectors: compares against vectors (evidence: `recommender.py`)
- Similarity ranking → Top-N suggestions: selects top matches (evidence: `recommender.py`)
- Top-N suggestions → Recommendation display: returns titles (evidence: `app.py`)
- Recommendation display → Movie seeker: displays suggestions (evidence: `app.py`)
