# rosiemin/contraceptive_product_forecast architecture

> Architecture diagram of the GitHub repository rosiemin/contraceptive_product_forecast, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-03). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/rosiemin/contraceptive_product_forecast
- Repository: https://github.com/rosiemin/contraceptive_product_forecast

## Overview

This repository is an analytical forecasting project for monthly contraceptive stock distribution at Côte d’Ivoire health sites. Its main workflow loads and joins inventory and reference data, filters site-product series, then evaluates univariate forecasts and a forecast-distance regression approach for predictions. The README also describes exploratory analysis and verification metrics. The graph includes these documented stages, but source-level relationships are limited to the excerpts and README; the exploratory notebooks and some outputs were not inspected.

Main entry points: [`src/clean_dta.py`](https://github.com/rosiemin/contraceptive_product_forecast/blob/main/src/clean_dta.py) (Load and clean), [`src/forecast_cv.py`](https://github.com/rosiemin/contraceptive_product_forecast/blob/main/src/forecast_cv.py) (Forecast-distance models), [`src/univariate.py`](https://github.com/rosiemin/contraceptive_product_forecast/blob/main/src/univariate.py) (Univariate models), [`src/site_product_univariate.py`](https://github.com/rosiemin/contraceptive_product_forecast/blob/main/src/site_product_univariate.py) (Site-product forecasts)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_data["Data preparation"]
  node_loader["Load and clean<br/>[clean_dta.py]"]
  node_series_filter["Series filtering<br/>[clean_dta.py]"]
end

subgraph group_forecast["Forecasting"]
  node_univariate["Univariate models<br/>[univariate.py]"]
  node_site_product["Site-product forecasts"]
  node_feature_engineering["Lag features<br/>[forecast_cv.py]"]
  node_distance_model["Forecast-distance models<br/>[forecast_cv.py]"]
end

subgraph group_analysis["Analysis and validation"]
  node_eda["Exploratory analysis<br/>[EDA.ipynb]"]
  node_image_eda["Image analysis<br/>[image_code.py]"]
  node_metrics["Verification metrics<br/>[univariate.py]"]
  node_results["Forecast results"]
end

node_analyst(("Analyst"))
node_source_data["Input datasets"]

node_source_data -->|"loads and joins"| node_loader
node_loader -->|"filters series"| node_series_filter
node_analyst -.->|"explores data"| node_eda
node_loader -->|"prepares data"| node_image_eda
node_loader -->|"provides data"| node_site_product
node_site_product -->|"calls models"| node_univariate
node_univariate -->|"computes metrics"| node_metrics
node_loader -->|"provides data"| node_feature_engineering
node_feature_engineering -->|"creates features"| node_distance_model
node_distance_model -->|"uses metrics"| node_univariate
node_distance_model -->|"writes predictions"| node_results
node_metrics -.->|"records scores"| node_results

click node_loader "https://github.com/rosiemin/contraceptive_product_forecast/blob/main/src/clean_dta.py"
click node_series_filter "https://github.com/rosiemin/contraceptive_product_forecast/blob/main/src/clean_dta.py"
click node_eda "https://github.com/rosiemin/contraceptive_product_forecast/blob/main/notebooks/EDA.ipynb"
click node_image_eda "https://github.com/rosiemin/contraceptive_product_forecast/blob/main/src/image_code.py"
click node_univariate "https://github.com/rosiemin/contraceptive_product_forecast/blob/main/src/univariate.py"
click node_site_product "https://github.com/rosiemin/contraceptive_product_forecast/blob/main/src/site_product_univariate.py"
click node_feature_engineering "https://github.com/rosiemin/contraceptive_product_forecast/blob/main/src/forecast_cv.py"
click node_distance_model "https://github.com/rosiemin/contraceptive_product_forecast/blob/main/src/forecast_cv.py"
click node_metrics "https://github.com/rosiemin/contraceptive_product_forecast/blob/main/src/univariate.py"
click node_results "https://github.com/rosiemin/contraceptive_product_forecast/blob/main/results/submission_predictions.csv"

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_loader,node_series_filter toneBlue
class node_univariate,node_site_product,node_feature_engineering,node_distance_model toneAmber
class node_eda,node_image_eda,node_metrics,node_results toneMint
class node_analyst,node_source_data toneIndigo
```

## Components

### Data preparation

- [Load and clean](https://github.com/rosiemin/contraceptive_product_forecast/blob/main/src/clean_dta.py): `src/clean_dta.py`
- [Series filtering](https://github.com/rosiemin/contraceptive_product_forecast/blob/main/src/clean_dta.py): `src/clean_dta.py`

### Forecasting

- [Univariate models](https://github.com/rosiemin/contraceptive_product_forecast/blob/main/src/univariate.py): `src/univariate.py`
- [Site-product forecasts](https://github.com/rosiemin/contraceptive_product_forecast/blob/main/src/site_product_univariate.py): `src/site_product_univariate.py`
- [Lag features](https://github.com/rosiemin/contraceptive_product_forecast/blob/main/src/forecast_cv.py): `src/forecast_cv.py`
- [Forecast-distance models](https://github.com/rosiemin/contraceptive_product_forecast/blob/main/src/forecast_cv.py): `src/forecast_cv.py`

### Analysis and validation

- [Exploratory analysis](https://github.com/rosiemin/contraceptive_product_forecast/blob/main/notebooks/EDA.ipynb): `notebooks/EDA.ipynb`
- [Image analysis](https://github.com/rosiemin/contraceptive_product_forecast/blob/main/src/image_code.py): `src/image_code.py`
- [Verification metrics](https://github.com/rosiemin/contraceptive_product_forecast/blob/main/src/univariate.py): `src/univariate.py`
- [Forecast results](https://github.com/rosiemin/contraceptive_product_forecast/blob/main/results/submission_predictions.csv): `results/submission_predictions.csv`

### Other components

- **Analyst**
- **Input datasets**

## Connections

- Input datasets → Load and clean: loads and joins (evidence: `src/clean_dta.py`)
- Load and clean → Series filtering: filters series (evidence: `src/clean_dta.py`)
- Analyst → Exploratory analysis: explores data (evidence: `README.md`)
- Load and clean → Image analysis: prepares data (evidence: `src/image_code.py`)
- Load and clean → Site-product forecasts: provides data (evidence: `src/site_product_univariate.py`)
- Site-product forecasts → Univariate models: calls models (evidence: `src/site_product_univariate.py`)
- Univariate models → Verification metrics: computes metrics (evidence: `src/univariate.py`)
- Load and clean → Lag features: provides data (evidence: `src/forecast_cv.py`)
- Lag features → Forecast-distance models: creates features (evidence: `src/forecast_cv.py`)
- Forecast-distance models → Univariate models: uses metrics (evidence: `src/forecast_cv.py`)
- Forecast-distance models → Forecast results: writes predictions (evidence: `src/forecast_cv.py`)
- Verification metrics → Forecast results: records scores
