# steveksh/product-ratings-classifier architecture

> Architecture diagram of the GitHub repository steveksh/product-ratings-classifier, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-02). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/steveksh/product-ratings-classifier
- Repository: https://github.com/steveksh/product-ratings-classifier

## Overview

This repository is an academic project exploring Amazon product-review analysis and recommendation. Its visible runtime utilities parse compressed Amazon JSON records and clean review text; the notebooks indicate exploratory analysis, embeddings, NLP, and baseline/proposed modeling. The README links a project-flow image but does not describe its stages in text, and notebook contents were not sampled, so relationships involving those experiments are shown as unverified rather than asserted. No deployed service or persistent application store is evident.

Main entry points: [`baseline_code/eda_baseline.ipynb`](https://github.com/steveksh/product-ratings-classifier/blob/main/baseline_code/eda_baseline.ipynb) (Exploratory analysis), [`sample_data/sampled_data.csv`](https://github.com/steveksh/product-ratings-classifier/blob/main/sample_data/sampled_data.csv) (Sample reviews), [`modules/json_reader.py`](https://github.com/steveksh/product-ratings-classifier/blob/main/modules/json_reader.py) (JSON data reader), [`baseline_code/model_baseline.ipynb`](https://github.com/steveksh/product-ratings-classifier/blob/main/baseline_code/model_baseline.ipynb) (Baseline model)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_data["Data preparation"]
  node_json_reader["JSON data reader<br/>[json_reader.py]"]
  node_review_cleaner["Review cleaner<br/>[utils.py]"]
  node_tiger_reader["Tiger data reader<br/>[json_reader.py]"]
end

subgraph group_analysis["Analysis and modeling"]
  node_eda["Exploratory analysis<br/>[eda_baseline.ipynb]"]
  node_baseline_model["Baseline model"]
  node_proposed_model["Proposed model"]
  node_nlp["NLP experiments<br/>[nlp.ipynb]"]
  node_embedding["Embedding experiments<br/>[embedding.ipynb]"]
  node_anr["ANR experiment<br/>[ANR.ipynb]"]
  node_tiger_eda["Tiger analysis<br/>[eda.ipynb]"]
end

node_researcher(("Project researcher"))
node_amazon_data["Amazon dataset"]
node_sample_data["Sample reviews<br/>[sampled_data.csv]"]

node_researcher -.->|"selects data"| node_amazon_data
node_amazon_data -.->|"provides records"| node_json_reader
node_researcher -.->|"explores data"| node_eda
node_researcher -.->|"runs baseline"| node_baseline_model
node_researcher -.->|"evaluates model"| node_proposed_model
node_researcher -.->|"explores NLP"| node_nlp
node_researcher -.->|"tests embeddings"| node_embedding
node_researcher -.->|"tests ANR"| node_anr
node_researcher -.->|"explores data"| node_tiger_eda
node_sample_data -.->|"may supply data"| node_eda

click node_json_reader "https://github.com/steveksh/product-ratings-classifier/blob/main/modules/json_reader.py"
click node_review_cleaner "https://github.com/steveksh/product-ratings-classifier/blob/main/modules/utils.py"
click node_eda "https://github.com/steveksh/product-ratings-classifier/blob/main/baseline_code/eda_baseline.ipynb"
click node_baseline_model "https://github.com/steveksh/product-ratings-classifier/blob/main/baseline_code/model_baseline.ipynb"
click node_proposed_model "https://github.com/steveksh/product-ratings-classifier/blob/main/baseline_code/Proposed%20model%20acc_%200.66%20loss_0.546.ipynb"
click node_nlp "https://github.com/steveksh/product-ratings-classifier/blob/main/baseline_code/nlp.ipynb"
click node_embedding "https://github.com/steveksh/product-ratings-classifier/blob/main/baseline_code/embedding.ipynb"
click node_anr "https://github.com/steveksh/product-ratings-classifier/blob/main/baseline_code/ANR.ipynb"
click node_tiger_reader "https://github.com/steveksh/product-ratings-classifier/blob/main/tiger/json_reader.py"
click node_tiger_eda "https://github.com/steveksh/product-ratings-classifier/blob/main/tiger/eda.ipynb"
click node_sample_data "https://github.com/steveksh/product-ratings-classifier/blob/main/sample_data/sampled_data.csv"

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_json_reader,node_review_cleaner,node_tiger_reader,node_sample_data toneBlue
class node_eda,node_baseline_model,node_proposed_model,node_nlp,node_embedding,node_anr,node_tiger_eda toneAmber
class node_researcher,node_amazon_data toneIndigo
```

## Components

### Data preparation

- [JSON data reader](https://github.com/steveksh/product-ratings-classifier/blob/main/modules/json_reader.py): `modules/json_reader.py`
- [Review cleaner](https://github.com/steveksh/product-ratings-classifier/blob/main/modules/utils.py): `modules/utils.py`
- [Tiger data reader](https://github.com/steveksh/product-ratings-classifier/blob/main/tiger/json_reader.py): `tiger/json_reader.py`

### Analysis and modeling

- [Exploratory analysis](https://github.com/steveksh/product-ratings-classifier/blob/main/baseline_code/eda_baseline.ipynb): `baseline_code/eda_baseline.ipynb`
- [Baseline model](https://github.com/steveksh/product-ratings-classifier/blob/main/baseline_code/model_baseline.ipynb): `baseline_code/model_baseline.ipynb`
- [Proposed model](https://github.com/steveksh/product-ratings-classifier/blob/main/baseline_code/Proposed%20model%20acc_%200.66%20loss_0.546.ipynb): `baseline_code/Proposed model acc_ 0.66 loss_0.546.ipynb`
- [NLP experiments](https://github.com/steveksh/product-ratings-classifier/blob/main/baseline_code/nlp.ipynb): `baseline_code/nlp.ipynb`
- [Embedding experiments](https://github.com/steveksh/product-ratings-classifier/blob/main/baseline_code/embedding.ipynb): `baseline_code/embedding.ipynb`
- [ANR experiment](https://github.com/steveksh/product-ratings-classifier/blob/main/baseline_code/ANR.ipynb): `baseline_code/ANR.ipynb`
- [Tiger analysis](https://github.com/steveksh/product-ratings-classifier/blob/main/tiger/eda.ipynb): `tiger/eda.ipynb`

### Other components

- **Project researcher**
- **Amazon dataset**
- [Sample reviews](https://github.com/steveksh/product-ratings-classifier/blob/main/sample_data/sampled_data.csv): `sample_data/sampled_data.csv`

## Connections

- Project researcher → Amazon dataset: selects data
- Amazon dataset → JSON data reader: provides records
- Project researcher → Exploratory analysis: explores data
- Project researcher → Baseline model: runs baseline
- Project researcher → Proposed model: evaluates model
- Project researcher → NLP experiments: explores NLP
- Project researcher → Embedding experiments: tests embeddings
- Project researcher → ANR experiment: tests ANR
- Project researcher → Tiger analysis: explores data
- Sample reviews → Exploratory analysis: may supply data
