# yukti20/ecomm-sentiment-analysis architecture

> Architecture diagram of the GitHub repository yukti20/ecomm-sentiment-analysis, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-09-28). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/yukti20/ecomm-sentiment-analysis
- Repository: https://github.com/yukti20/ecomm-sentiment-analysis

## Overview

This is a notebook-based demo for fine-tuning a Hugging Face sentiment model on Amazon product reviews and using it for binary sentiment classification. The README documents the dataset fields, pretrained model, and optional saving of fine-tuned outputs. The notebook source was not sampled, so the graph reflects documented capabilities rather than verified internal calls; preprocessing and evaluation details are omitted.

Main entry points: [`ecomm_sentiment_analysis.ipynb`](https://github.com/yukti20/ecomm-sentiment-analysis/blob/main/ecomm_sentiment_analysis.ipynb) (Analysis notebook)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_data["Review data"]
  node_dataset["Amazon Polarity"]
end

subgraph group_model["Sentiment model"]
  node_notebook["Analysis notebook"]
  node_pretrained["DistilBERT base"]
  node_finetune["Fine-tune model"]
end

subgraph group_outputs["Results"]
  node_classify["Classify reviews"]
  node_saved["Saved artifacts"]
end

node_user(("Notebook user"))

node_user -->|"runs"| node_notebook
node_notebook -->|"loads splits"| node_dataset
node_notebook -->|"loads model"| node_pretrained
node_dataset -->|"provides reviews"| node_finetune
node_pretrained -->|"provides weights"| node_finetune
node_finetune -->|"uses tuned model"| node_classify
node_notebook -.->|"optionally saves"| node_saved

click node_notebook "https://github.com/yukti20/ecomm-sentiment-analysis/blob/main/ecomm_sentiment_analysis.ipynb"
click node_dataset "https://github.com/yukti20/ecomm-sentiment-analysis/blob/main/ecomm_sentiment_analysis.ipynb"
click node_pretrained "https://github.com/yukti20/ecomm-sentiment-analysis/blob/main/ecomm_sentiment_analysis.ipynb"
click node_finetune "https://github.com/yukti20/ecomm-sentiment-analysis/blob/main/ecomm_sentiment_analysis.ipynb"
click node_classify "https://github.com/yukti20/ecomm-sentiment-analysis/blob/main/ecomm_sentiment_analysis.ipynb"
click node_saved "https://github.com/yukti20/ecomm-sentiment-analysis/blob/main/ecomm_sentiment_analysis.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_dataset,node_user toneBlue
class node_notebook,node_pretrained,node_finetune toneAmber
class node_classify,node_saved toneMint
```

## Components

### Review data

- [Amazon Polarity](https://github.com/yukti20/ecomm-sentiment-analysis/blob/main/ecomm_sentiment_analysis.ipynb): `ecomm_sentiment_analysis.ipynb`

### Sentiment model

- [Analysis notebook](https://github.com/yukti20/ecomm-sentiment-analysis/blob/main/ecomm_sentiment_analysis.ipynb): `ecomm_sentiment_analysis.ipynb`
- [DistilBERT base](https://github.com/yukti20/ecomm-sentiment-analysis/blob/main/ecomm_sentiment_analysis.ipynb): `ecomm_sentiment_analysis.ipynb`
- [Fine-tune model](https://github.com/yukti20/ecomm-sentiment-analysis/blob/main/ecomm_sentiment_analysis.ipynb): `ecomm_sentiment_analysis.ipynb`

### Results

- [Classify reviews](https://github.com/yukti20/ecomm-sentiment-analysis/blob/main/ecomm_sentiment_analysis.ipynb): `ecomm_sentiment_analysis.ipynb`
- [Saved artifacts](https://github.com/yukti20/ecomm-sentiment-analysis/blob/main/ecomm_sentiment_analysis.ipynb): `ecomm_sentiment_analysis.ipynb`

### Other components

- **Notebook user**

## Connections

- Notebook user → Analysis notebook: runs
- Analysis notebook → Amazon Polarity: loads splits
- Analysis notebook → DistilBERT base: loads model
- Amazon Polarity → Fine-tune model: provides reviews
- DistilBERT base → Fine-tune model: provides weights
- Fine-tune model → Classify reviews: uses tuned model
- Analysis notebook → Saved artifacts: optionally saves