---
title: HP Printer Cost & Ink Optimization
emoji: 🖨️
colorFrom: blue
colorTo: indigo
sdk: streamlit
sdk_version: 1.31.0
app_file: app.py
pinned: false
---

# HP Printer Cost Prediction & Ink Usage Optimization

This application provides tools for predicting printing costs and optimizing ink usage for HP printers using machine learning.

## Features

- **Data Exploration**: Visualize and analyze printing data, including costs, substrate usage, and ink consumption.
- **Model Training**: Train various machine learning models to predict printing costs with high accuracy.
- **Cost Prediction**: Estimate the cost of print jobs based on parameters such as substrate type, ink usage, and print settings.
- **Ink Optimization**: Optimize ink usage to reduce costs while maintaining print quality.

## Dataset

The application uses the "Hp printer accounting.csv" dataset, which contains detailed information about print jobs including:

- Document information
- Cost values (total and per-component)
- Substrate type and usage
- Ink consumption (total and by color)
- Print settings (DPI, passes, print speed, etc.)

## Machine Learning Models

The application supports multiple regression models for cost prediction:

- Random Forest
- XGBoost
- LightGBM
- Gradient Boosting
- Linear Regression
- Ridge
- Lasso

## Installation and Usage

1. **Install the required packages**:

```
pip install -r requirements.txt
```

2. **Run the application**:

```
streamlit run app.py
```

3. **Using the application**:
   - Start by exploring the data in the "Data Explorer" tab
   - Train a model in the "Model Training" tab
   - Make predictions in the "Cost Prediction" tab
   - Optimize ink usage in the "Ink Optimization" tab

## Requirements

- Python 3.8+
- Streamlit
- pandas
- numpy
- matplotlib
- scikit-learn
- XGBoost
- LightGBM
- plotly

## Technical Implementation

- Data preprocessing includes handling missing values, feature extraction, and normalization
- Machine learning pipeline with preprocessing and model training
- Cross-validation for model evaluation
- Feature importance analysis
- Cost breakdown and optimization recommendations

## Future Enhancements

- Time series analysis for cost trends over time
- Integration with printer APIs for real-time data
- More advanced optimization algorithms
- Print quality prediction based on settings