quant-glow 0.1.1

Lightweight Cryptocurrency Prediction AI with TinyGraD

quant-glow 🔮

Lightweight Cryptocurrency Prediction with TinyGraD

Lumix adalah package Python untuk prediksi cryptocurrency yang ringan dan efisien, dibangun dengan TinyGraD. Package ini sudah include model LSTM yang telah ditraining dan siap untuk inference.

✨ Features

• 🚀 Pre-trained Model - Model LSTM sudah included, tidak perlu training ulang
• 📈 13 Technical Indicators - Open, High, Low, Close, Volume, RSI, MACD, dll
• 🔮 Trend Prediction - Prediksi bullish/bearish dengan confidence score
• 💻 Minimal Dependencies - Hanya butuh TinyGraD dan NumPy
• 📊 Multi-step Forecasting - Prediksi beberapa steps ke depan
• 🐍 Python & CLI - Bisa digunakan via Python API atau command line

from quant_glow import LuminaPredictor import numpy as np

Initialize predictor

predictor = LuminaPredictor()

Add your cryptocurrency data (13 features)

Format: [open, high, low, close, volume, rsi, macd, macd_signal, bb_high, bb_low, ema_12, ema_26, atr]

sample_data = [ 19500.50, 19800.75, 19450.25, 19700.80, # Price data 3245678901.25, # Volume 65.2, 125.8, 120.3, # RSI, MACD, MACD Signal 19850.25, 19420.75, # Bollinger Bands 19680.40, 19520.60, # EMA 12 & 26 180.45 # ATR ]

Add data points (need at least 30 sequences for prediction)

for i in range(35): # Simulate some price movement features = [x + (i * 10) for x in sample_data] predictor.add_data_point(features)

Get prediction

result = predictor.predict_next() print(f"🎯 Prediction: {result['prediction']:.6f}") print(f"📈 Trend: {result['trend'].upper()}") print(f"🎲 Confidence: {result['confidence']:.4f}") print(f"📊 Features Used: {result['features_used']}")

🚀 Installation

pip install quant-glow