# psubhajit042-tech/ipl-winodds-engine architecture

> Architecture diagram of the GitHub repository psubhajit042-tech/ipl-winodds-engine, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-06). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/psubhajit042-tech/ipl-winodds-engine
- Repository: https://github.com/psubhajit042-tech/ipl-winodds-engine

## Overview

This repository is an IPL chasing-team win-probability pipeline. Its main workflow loads match and delivery data, builds second-innings features, trains and evaluates match-grouped classifiers, then uses a trained model for live predictions and historical over-by-over analysis; visualization renders the resulting metrics and progressions. The README also documents an interactive predictor. Source excerpts establish the main orchestration and key data transfers; some training internals and README-level capabilities are represented at module level.

Main entry points: [`main.py`](https://github.com/psubhajit042-tech/ipl-winodds-engine/blob/main/main.py) (Pipeline runner), [`model_training.py`](https://github.com/psubhajit042-tech/ipl-winodds-engine/blob/main/model_training.py) (Grouped training), [`data_preprocessing.py`](https://github.com/psubhajit042-tech/ipl-winodds-engine/blob/main/data_preprocessing.py) (Feature engineering), [`predictor.py`](https://github.com/psubhajit042-tech/ipl-winodds-engine/blob/main/predictor.py) (Live prediction)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_workflow["Pipeline orchestration"]
  node_orchestrator["Pipeline runner<br/>[main.py]"]
end

subgraph group_data["Match data"]
  node_raw_matches["Match records"]
  node_raw_deliveries["Ball deliveries"]
  node_preprocessing["Feature engineering"]
  node_clean_data["Training dataset"]
end

subgraph group_models["Model training"]
  node_training["Grouped training<br/>[model_training.py]"]
  node_model_pipelines["Classifier pipelines<br/>[model_training.py]"]
  node_model_files["Saved models"]
end

subgraph group_prediction["Prediction and charts"]
  node_live_prediction["Live prediction<br/>[predictor.py]"]
  node_progression["Match progression<br/>[predictor.py]"]
  node_comparison_plot["Metrics chart<br/>[visualization.py]"]
  node_progression_plot["Progression chart<br/>[visualization.py]"]
end

node_operator(("Operator"))
node_results["Prediction results"]

node_operator -->|"runs"| node_orchestrator
node_orchestrator -->|"calls"| node_preprocessing
node_raw_matches -->|"loads"| node_preprocessing
node_raw_deliveries -->|"loads"| node_preprocessing
node_preprocessing -->|"returns features"| node_orchestrator
node_orchestrator -->|"writes"| node_clean_data
node_clean_data -->|"reads"| node_training
node_orchestrator -->|"calls"| node_training
node_training -->|"fits and evaluates"| node_model_pipelines
node_training -->|"returns metrics and models"| node_orchestrator
node_orchestrator -->|"saves"| node_model_files
node_model_files -->|"loads model"| node_live_prediction
node_orchestrator -->|"requests prediction"| node_live_prediction
node_orchestrator -->|"requests analysis"| node_progression
node_preprocessing -->|"returns delivery details"| node_progression
node_live_prediction -->|"returns probabilities"| node_results
node_progression -->|"provides progression data"| node_progression_plot
node_orchestrator -->|"plots metrics"| node_comparison_plot
node_orchestrator -->|"plots progression"| node_progression_plot
node_training -->|"returns plot metrics"| node_comparison_plot

click node_orchestrator "https://github.com/psubhajit042-tech/ipl-winodds-engine/blob/main/main.py"
click node_preprocessing "https://github.com/psubhajit042-tech/ipl-winodds-engine/blob/main/data_preprocessing.py"
click node_training "https://github.com/psubhajit042-tech/ipl-winodds-engine/blob/main/model_training.py"
click node_model_pipelines "https://github.com/psubhajit042-tech/ipl-winodds-engine/blob/main/model_training.py"
click node_live_prediction "https://github.com/psubhajit042-tech/ipl-winodds-engine/blob/main/predictor.py"
click node_progression "https://github.com/psubhajit042-tech/ipl-winodds-engine/blob/main/predictor.py"
click node_comparison_plot "https://github.com/psubhajit042-tech/ipl-winodds-engine/blob/main/visualization.py"
click node_progression_plot "https://github.com/psubhajit042-tech/ipl-winodds-engine/blob/main/visualization.py"

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_orchestrator toneBlue
class node_raw_matches,node_raw_deliveries,node_preprocessing,node_clean_data toneAmber
class node_training,node_model_pipelines,node_model_files toneMint
class node_live_prediction,node_progression,node_comparison_plot,node_progression_plot toneRose
class node_operator,node_results toneIndigo
```

## Components

### Pipeline orchestration

- [Pipeline runner](https://github.com/psubhajit042-tech/ipl-winodds-engine/blob/main/main.py): `main.py`

### Match data

- **Match records**
- **Ball deliveries**
- [Feature engineering](https://github.com/psubhajit042-tech/ipl-winodds-engine/blob/main/data_preprocessing.py): `data_preprocessing.py`
- **Training dataset**

### Model training

- [Grouped training](https://github.com/psubhajit042-tech/ipl-winodds-engine/blob/main/model_training.py): `model_training.py`
- [Classifier pipelines](https://github.com/psubhajit042-tech/ipl-winodds-engine/blob/main/model_training.py): `model_training.py`
- **Saved models**

### Prediction and charts

- [Live prediction](https://github.com/psubhajit042-tech/ipl-winodds-engine/blob/main/predictor.py): `predictor.py`
- [Match progression](https://github.com/psubhajit042-tech/ipl-winodds-engine/blob/main/predictor.py): `predictor.py`
- [Metrics chart](https://github.com/psubhajit042-tech/ipl-winodds-engine/blob/main/visualization.py): `visualization.py`
- [Progression chart](https://github.com/psubhajit042-tech/ipl-winodds-engine/blob/main/visualization.py): `visualization.py`

### Other components

- **Operator**
- **Prediction results**

## Connections

- Operator → Pipeline runner: runs (evidence: `main.py`)
- Pipeline runner → Feature engineering: calls (evidence: `main.py`)
- Match records → Feature engineering: loads (evidence: `data_preprocessing.py`)
- Ball deliveries → Feature engineering: loads (evidence: `data_preprocessing.py`)
- Feature engineering → Pipeline runner: returns features (evidence: `main.py`)
- Pipeline runner → Training dataset: writes (evidence: `main.py`)
- Training dataset → Grouped training: reads (evidence: `model_training.py`)
- Pipeline runner → Grouped training: calls (evidence: `main.py`)
- Grouped training → Classifier pipelines: fits and evaluates (evidence: `model_training.py`)
- Grouped training → Pipeline runner: returns metrics and models (evidence: `main.py`)
- Pipeline runner → Saved models: saves (evidence: `main.py`)
- Saved models → Live prediction: loads model (evidence: `predictor.py`)
- Pipeline runner → Live prediction: requests prediction (evidence: `main.py`)
- Pipeline runner → Match progression: requests analysis (evidence: `main.py`)
- Feature engineering → Match progression: returns delivery details (evidence: `main.py`)
- Live prediction → Prediction results: returns probabilities (evidence: `predictor.py`)
- Match progression → Progression chart: provides progression data (evidence: `main.py`)
- Pipeline runner → Metrics chart: plots metrics (evidence: `main.py`)
- Pipeline runner → Progression chart: plots progression (evidence: `main.py`)
- Grouped training → Metrics chart: returns plot metrics (evidence: `main.py`)
