Metadata-Version: 2.4
Name: seismoai-model-mlops
Version: 0.1.1
Summary: SeismoAI Model module - noise classifier for seismic traces
License: MIT
Requires-Python: >=3.10
Description-Content-Type: text/markdown
Requires-Dist: numpy>=1.21
Requires-Dist: scikit-learn>=1.0

# seismoai-model-mlops

**SeismoAI Model Module** — A noise classifier for seismic traces built on the Utah FORGE dataset.

## Install

```bash
pip install seismoai-model-mlops
```

## What it does

This module is part of the SeismoAI library. It trains a Random Forest classifier to detect good, noisy, and dead seismic traces.

## Functions

- `extract_features(traces)` — Extracts 6 statistical features from each trace
- `train_classifier(traces, labels)` — Trains a Random Forest on QC labels
- `predict_traces(traces, model_dict)` — Predicts labels for new traces

## Usage

```python
from seismoai_model import extract_features, train_classifier, predict_traces
import numpy as np

traces = np.random.randn(30, 4001).astype(np.float32)
labels = ['good'] * 15 + ['noisy'] * 15

model_dict = train_classifier(traces, labels)
preds, probs = predict_traces(traces[:5], model_dict)
print(preds)
```

## Author

Qurat UI Ain and Malaika Saeed — MLOps Course, SeismoAI Group Project
