# ponjour0602/tokyo-sakura-blossom-prediction architecture

> Architecture diagram of the GitHub repository ponjour0602/tokyo-sakura-blossom-prediction, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2025-05-22). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/ponjour0602/tokyo-sakura-blossom-prediction
- Repository: https://github.com/ponjour0602/tokyo-sakura-blossom-prediction

## Overview

##### Project type and purpose
- This is a data‐science/ML pipeline project for predicting Tokyo cherry‐blossom bloom dates.
- It ingests raw historical bloom‐date and weather data, preprocesses it, then runs three prediction methods: the 600-Degree Rule, a regression model, and an MLP (PyTorch) model.

##### File structure
- Top-level directories:
- Data Collection: Jupyter notebooks to crawl historical bloom dates and weather.
- Dataset: CSV files (raw and split into train/test).
- Prediction: Three sub-folders for each modeling approach (600 Degree Rule, Linear Regression, MLP with various feature sets).
- README.md describes overall flow, model details, data sources, and evaluation metrics (MSE, RMSE, R²).

##### Main components
a. External Data Sources
- Japan Meteorological Agency API / Website (weather, bloom dates)
b. Data‐Collection Module
- Notebook: “Data Crawler for Blossom Date.ipynb”
- Notebook: “Data Crawler for Tokyo Weather.ipynb”
c. Data Preprocessing Module
- Notebook: “Data Preprocessing.ipynb”
- Output: weather_dataset.csv
d. Dataset Storage
- Raw CSVs (weather_dataset.csv)
- Train/Test splits (train.csv, test.csv)
e. Prediction Modules
- 600-Degree Rule (notebook)
- Regression Model (Linear Regression using DTS formula)
- MLP Model (three notebooks for Feature=5,6,11)
f. Evaluation & Reporting
- Metrics computation: MSE, RMSE, R²
- Final comparisons

##### Relationships & data flow
- Data‐Collection Module → Data Preprocessing Module → Dataset Storage
- Dataset Storage → each Prediction Module
- Prediction Modules → Evaluation & Reporting component
- Optionally, loop from Evaluation back to Data Preprocessing for feature engineering

##### Architectural patterns & design principles
- A linear ETL (Extract-Transform-Load) pipeline followed by parallel model execution
- Separation of concerns: crawling, preprocessing, modeling, and evaluation are distinct
- Modularity: each model runs in its own notebook folder, making it simple to add/remove methods

##### Relevant technologies, frameworks & libraries
- Python + Jupyter notebooks (data exploration & orchestration)
- pandas, NumPy (data manipulation)
- scikit-learn (regression)
- PyTorch (MLP)
- CSV storage
- (Optional) cron or workflow manager (Airflow/Prefect) for scheduling

## Diagram (Mermaid)

```mermaid
flowchart TB
    %% External Sources
    External["Japan Meteorological Agency API/Website"]:::external

    %% Data Ingestion
    subgraph "Data Ingestion"
        CrawB["Data Crawler for Blossom Date.ipynb"]:::ingestion
        CrawW["Data Crawler for Tokyo Weather.ipynb"]:::ingestion
    end

    %% Preprocessing & Storage
    subgraph "Preprocessing & Storage"
        Pre["Data Preprocessing.ipynb"]:::pre
        RawCSV["weather_dataset.csv"]:::storage
        TrainCSV["train.csv"]:::storage
        TestCSV["test.csv"]:::storage
    end

    %% Modeling
    subgraph "Modeling"
        M600["600-Degree Rule Module"]:::model
        LR["Regression Model (DTS Formula)"]:::model
        subgraph "MLP Models"
            MLP5["MLP (Feature=5)"]:::model
            MLP6["MLP (Feature=6)"]:::model
            MLP11["MLP (Feature=11)"]:::model
        end
    end

    %% Evaluation
    subgraph "Evaluation"
        Eval["Evaluation & Reporting"]:::eval
    end

    %% Data Flow
    External --> CrawB
    External --> CrawW
    CrawB --> Pre
    CrawW --> Pre
    Pre --> RawCSV
    RawCSV --> TrainCSV
    RawCSV --> TestCSV
    TrainCSV --> M600
    TrainCSV --> LR
    TrainCSV --> MLP5
    TrainCSV --> MLP6
    TrainCSV --> MLP11
    TestCSV --> M600
    TestCSV --> LR
    TestCSV --> MLP5
    TestCSV --> MLP6
    TestCSV --> MLP11
    M600 --> Eval
    LR --> Eval
    MLP5 --> Eval
    MLP6 --> Eval
    MLP11 --> Eval

    %% Click Events
    click CrawB "https://github.com/ponjour0602/tokyo-sakura-blossom-prediction/blob/main/Data Collection/Data Crawler for Blossom Date.ipynb"
    click CrawW "https://github.com/ponjour0602/tokyo-sakura-blossom-prediction/blob/main/Data Collection/Data Crawler for Tokyo Weather.ipynb"
    click Pre "https://github.com/ponjour0602/tokyo-sakura-blossom-prediction/blob/main/Data Collection/Data Preprocessing.ipynb"
    click RawCSV "https://github.com/ponjour0602/tokyo-sakura-blossom-prediction/blob/main/Dataset/weather_dataset.csv"
    click TrainCSV "https://github.com/ponjour0602/tokyo-sakura-blossom-prediction/blob/main/Dataset/train.csv"
    click TestCSV "https://github.com/ponjour0602/tokyo-sakura-blossom-prediction/blob/main/Dataset/test.csv"
    click M600 "https://github.com/ponjour0602/tokyo-sakura-blossom-prediction/blob/main/Prediction/600 Degree Rule.ipynb"
    click LR "https://github.com/ponjour0602/tokyo-sakura-blossom-prediction/blob/main/Prediction/Linear Regression（DTS Formula）.ipynb"
    click MLP5 "https://github.com/ponjour0602/tokyo-sakura-blossom-prediction/blob/main/Prediction/Multilayer Perceptron/MLP（Feature=5） .ipynb"
    click MLP6 "https://github.com/ponjour0602/tokyo-sakura-blossom-prediction/blob/main/Prediction/Multilayer Perceptron/MLP（Feature=6） .ipynb"
    click MLP11 "https://github.com/ponjour0602/tokyo-sakura-blossom-prediction/blob/main/Prediction/Multilayer Perceptron/MLP（Feature=11） .ipynb"
    click Eval "https://github.com/ponjour0602/tokyo-sakura-blossom-prediction/blob/main/README.md"

    %% Styles
    classDef external fill:#87CEFA,stroke:#333,stroke-width:1px
    classDef ingestion fill:#ADD8E6,stroke:#333,stroke-width:1px
    classDef pre fill:#90EE90,stroke:#333,stroke-width:1px
    classDef storage fill:#90EE90,stroke:#333,stroke-width:1px
    classDef model fill:#FFA500,stroke:#333,stroke-width:1px
    classDef eval fill:#DDA0DD,stroke:#333,stroke-width:1px
```
