# petrobras/3w architecture

> Architecture diagram of the GitHub repository petrobras/3w, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2024-12-29). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/petrobras/3w
- Repository: https://github.com/petrobras/3w

## Overview

##### Main Components
The system should be divided into three primary components:

a) Dataset Component:
- Numbered subdirectories (0-9) containing WELL and SIMULATED data files
- Parquet file storage format
- Dataset versioning system
- Dataset structure documentation

b) Toolkit Component:
- Base module
- Dataset handling
- Processing (feature & label mappers)
- Training (multiclass experiments)
- Visualization
- Utils

c) Problems Component:
- Individual problem definitions
- Baseline implementations
- Evaluation metrics

##### Relationships and Data Flow
- Dataset → Toolkit (data ingestion)
- Toolkit → Problems (problem-specific processing)
- Problems → Toolkit (results and metrics)

##### Specific elements
- Data format specifications (Parquet)
- Version control integration
- Environment management (conda)
- Documentation links
- License information

##### Architectural Patterns
Highlight:
- Modular design of toolkit
- Pipeline processing flow
- Experiment management structure
- Version control system

**┌─────────────────────────────────────────────────────┐**
- Documentation Layer                 │
- (README, Structure Docs, License, Contributing)     │
- ┤

- Dataset Layer                     │
- ┌─────────┐    ┌─────────┐    ┌─────────┐      │
- Well   │    │Simulated│    │  Drawn  │      │
- Data   │    │  Data   │    │  Data   │      │
- ┘    └─────────┘    └─────────┘      │

- ┤
- Toolkit Layer                     │
- ┌─────────┐    ┌─────────┐    ┌─────────┐      │
- Dataset  │    │Processing│    │Training │      │
- Handling │───▶│ Module  │───▶│ Module  │      │
- ┘    └─────────┘    └─────────┘      │
- ▲             │              │            │
- ▼              ▼            │
- ┌─────────┐    ┌─────────┐    ┌─────────┐      │
- Utils  │    │Visualiza│    │Problems │      │
- Module  │◀───│  tion   │◀───│ Module  │      │
- ┘    └─────────┘    └─────────┘      │

- ┘

Key Considerations:

##### Integration with external tools (conda, jupyter)

- Double lines: API boundaries

## Diagram (Mermaid)

```mermaid
graph TB
    subgraph Documentation
        Docs[Documentation]
        DatasetDocs[Dataset Structure]
        ToolkitDocs[Toolkit Structure]
    end

    subgraph Dataset
        DatasetMain[Dataset]
        DataConfig[Dataset Config]
        subgraph DataDirs
            Dir0[Directory 0]
            Dir9[Directory 9]
            DirDots[...]
        end
    end

    subgraph Toolkit
        Base[Base Module]
        DatasetHandler[Dataset Handler]
        Processing[Processing]
        Training[Training]
        Visualization[Visualization]
        Utils[Utils]
    end

    subgraph Problems
        ProblemDef[Problem Definitions]
        Baseline[Baseline Implementation]
    end

    subgraph Environment
        CondaEnv[Conda Environment]
        ToolkitEnv[Toolkit Environment]
    end

    subgraph Analysis
        Notebooks[Analysis Notebooks]
        BaselineAnalysis[Baseline Analysis]
    end

    %% Relationships
    DatasetMain --> DatasetHandler
    DatasetHandler --> Processing
    Processing --> Training
    Training --> Visualization
    Utils --> DatasetHandler
    Utils --> Processing
    Utils --> Training
    Training --> ProblemDef
    ProblemDef --> Baseline
    Baseline --> BaselineAnalysis

    %% Click events
    click DatasetMain "https://github.com/petrobras/3W/tree/main/dataset/"
    click DataConfig "https://github.com/petrobras/3W/blob/main/dataset/dataset.ini"
    click Dir0 "https://github.com/petrobras/3W/tree/main/dataset/0/"
    click Dir9 "https://github.com/petrobras/3W/tree/main/dataset/9/"
    click Base "https://github.com/petrobras/3W/blob/main/toolkit/base.py"
    click DatasetHandler "https://github.com/petrobras/3W/blob/main/toolkit/mais/dataset/dataset.py"
    click Processing "https://github.com/petrobras/3W/blob/main/toolkit/mais/processing/feature_mappers.py"
    click Training "https://github.com/petrobras/3W/tree/main/toolkit/mais/training/multiclass/"
    click Visualization "https://github.com/petrobras/3W/tree/main/toolkit/mais/visualization/"
    click Utils "https://github.com/petrobras/3W/blob/main/toolkit/mais/utils/utils.py"
    click ProblemDef "https://github.com/petrobras/3W/tree/main/problems/01_binary_classifier_of_spurious_closure_of_dhsv/"
    click Baseline "https://github.com/petrobras/3W/tree/main/problems/01_binary_classifier_of_spurious_closure_of_dhsv/_baseline/"
    click Docs "https://github.com/petrobras/3W/tree/main/docs/"
    click DatasetDocs "https://github.com/petrobras/3W/blob/main/3W_DATASET_STRUCTURE.md"
    click ToolkitDocs "https://github.com/petrobras/3W/blob/main/3W_TOOLKIT_STRUCTURE.md"
    click Notebooks "https://github.com/petrobras/3W/tree/main/overviews/"
    click BaselineAnalysis "https://github.com/petrobras/3W/tree/main/overviews/_baseline/"
    click CondaEnv "https://github.com/petrobras/3W/blob/main/environment.yml"
    click ToolkitEnv "https://github.com/petrobras/3W/blob/main/toolkit/mais/environment.yml"

    %% Styling
    classDef default fill:#f9f9f9,stroke:#333,stroke-width:1px
    classDef dataset fill:#dff0fa,stroke:#333
    classDef toolkit fill:#e6f3e6,stroke:#333
    classDef problems fill:#fff3e6,stroke:#333
    classDef docs fill:#f5f5f5,stroke:#333
    classDef env fill:#f0f0f0,stroke:#333

    class DatasetMain,DataConfig,Dir0,Dir9,DirDots dataset
    class Base,DatasetHandler,Processing,Training,Visualization,Utils toolkit
    class ProblemDef,Baseline problems
    class Docs,DatasetDocs,ToolkitDocs docs
    class CondaEnv,ToolkitEnv env
```
