# zain-ul-abdin45/sensor_data_processing architecture

> Architecture diagram of the GitHub repository zain-ul-abdin45/sensor_data_processing, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2025-05-26). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/zain-ul-abdin45/sensor_data_processing
- Repository: https://github.com/zain-ul-abdin45/sensor_data_processing

## Overview

##### Project type and purpose
- This is a hybrid data‐analytics & ML demo combining:
- A Streamlit‐based nutrient dashboard (structured data exploration)
- A Jupyter notebook–driven CNN image classification example (unstructured data/ML)
- Purpose: show how food data (CSV vs. images) is ingested, processed, visualized, and modeled.

##### File structure
- Top-level files only:
- sensor_data_exploration.py → Streamlit app + data‐cleaning & Plotly/Seaborn visuals
- image_classification_101_dataset.ipynb → PyTorch CNN training & evaluation
- README.md → project overview, technology stack, future directions
- No nested directories → lightweight, two parallel pipelines.

##### README for additional insights
- Part 1 uses USDA CSV data for nutrient distributions via Streamlit.
- Part 2 uses Food-101 image folders → subset of three classes → basic CNN model.
- Technologies: Python, Streamlit, Plotly, Seaborn, Jupyter Notebook, PyTorch, Torchvision, Matplotlib.

## Diagram (Mermaid)

```mermaid
flowchart TB
    %% Data Sources
    subgraph "Data Sources"
        CSV["USDA CSV Data"]:::datastore
        Images["Food-101 Image Folders"]:::datastore
    end

    %% Structured Data Pipeline
    subgraph "Structured Data Pipeline"
        Cleaner["CSV Loader & Cleaner"]:::processing
        Analytics["Nutrient Analytics & Visualizations"]:::processing
    end

    %% Unstructured Data Pipeline
    subgraph "Unstructured Data Pipeline"
        DataLoader["ImageFolder & DataLoader"]:::processing
        Model["CNN Model Training"]:::processing
        Eval["Evaluation Metrics & Confusion Matrix"]:::processing
    end

    %% Frontends & Visualization
    subgraph "Frontends & Visualization"
        Streamlit["Streamlit Dashboard"]:::frontend
        NotebookUI["Jupyter Notebook UI"]:::frontend
    end

    %% Documentation
    Doc["Project Overview & Documentation (README.md)"]:::external

    %% Connections
    CSV --> Cleaner
    Cleaner --> Analytics
    Analytics --> Streamlit

    Images --> DataLoader
    DataLoader --> Model
    Model --> Eval
    Eval --> NotebookUI

    Doc

    %% Click Events
    click Cleaner "https://github.com/zain-ul-abdin45/sensor_data_processing/blob/main/sensor_data_exploration.py"
    click Analytics "https://github.com/zain-ul-abdin45/sensor_data_processing/blob/main/sensor_data_exploration.py"
    click Streamlit "https://github.com/zain-ul-abdin45/sensor_data_processing/blob/main/sensor_data_exploration.py"
    click DataLoader "https://github.com/zain-ul-abdin45/sensor_data_processing/blob/main/image_classification_101_dataset.ipynb"
    click Model "https://github.com/zain-ul-abdin45/sensor_data_processing/blob/main/image_classification_101_dataset.ipynb"
    click Eval "https://github.com/zain-ul-abdin45/sensor_data_processing/blob/main/image_classification_101_dataset.ipynb"
    click NotebookUI "https://github.com/zain-ul-abdin45/sensor_data_processing/blob/main/image_classification_101_dataset.ipynb"
    click Doc "https://github.com/zain-ul-abdin45/sensor_data_processing/blob/main/README.md"

    %% Styles
    classDef datastore fill:#ADD8E6,stroke:#000,stroke-width:1px
    classDef processing fill:#90EE90,stroke:#000,stroke-width:1px
    classDef frontend fill:#FFA500,stroke:#000,stroke-width:1px
    classDef external fill:#D3D3D3,stroke:#000,stroke-width:1px
```
