ramseshk
b0fab62a87
Phase 1 - Quick Wins: - QuantileEnsemble: P10/P50/P90 predictions for risk-aware bidding - MinutesSurvivalModel: Weibull AFT for minutes distribution modeling Phase 2 - Adaptive Auction: - BanditAuctionSolver: Thompson Sampling for live auction bids - OpponentBidModel: Predict competitor bids via LightGBM - BudgetOptimizer: Bayesian optimization for role-level allocation Phase 3 - Deep Learning: - RLAuctionPolicy: Double DQN agent for auction strategy - SetTransformer: Team composition valuation via set-based ML Phase 4 - Probabilistic: - BayesianPlayerModel: Hierarchical pooling for rookie uncertainty - ConformalPredictor: Calibrated prediction intervals Phase 5 - Chemistry & Form: - PlayerChemistryGAT: Graph attention network for player synergies - PlayerFormModel: Hawkes process for form momentum Phase 6 - Causal: - TransferCausalModel: Causal forest for transfer effects - AuctionEffectAnalyzer: Bid adjustment from causal analysis 81 tests passing
64 lines
932 B
Plaintext
64 lines
932 B
Plaintext
# Fantabeto 2026/27 — Core dependencies
|
|
python-dateutil>=2.8
|
|
requests>=2.31
|
|
beautifulsoup4>=4.12
|
|
lxml>=5.0
|
|
|
|
# Data processing
|
|
pandas>=2.1
|
|
numpy>=1.26
|
|
openpyxl>=3.1
|
|
scipy>=1.11
|
|
pyyaml>=6.0
|
|
|
|
# ML models
|
|
lightgbm>=4.3
|
|
catboost>=1.2
|
|
xgboost>=2.0
|
|
scikit-learn>=1.4
|
|
|
|
# Hyperparameter tuning
|
|
optuna>=3.5
|
|
|
|
# Graph neural network (optional, for T-GNN)
|
|
torch>=2.2
|
|
torch-geometric>=2.5
|
|
|
|
# Optimization
|
|
pulp>=2.8
|
|
scikit-optimize>=0.9
|
|
|
|
# Bayesian modeling (optional)
|
|
pymc>=5.0
|
|
lifelines>=0.28
|
|
|
|
# Causal inference (optional)
|
|
econml>=0.15
|
|
|
|
# Browser automation (Playwright fallback for Cloudflare)
|
|
playwright>=1.42
|
|
|
|
# RAG & LLM (optional, for news pipeline)
|
|
langchain>=0.1
|
|
langchain-community>=0.1
|
|
chromadb>=0.4
|
|
feedparser>=6.0
|
|
|
|
# LLM providers (choose one)
|
|
openai>=1.12
|
|
# anthropic>=0.20
|
|
# ollama>=0.1
|
|
|
|
# Visualization
|
|
matplotlib>=3.8
|
|
seaborn>=0.13
|
|
plotly>=5.18
|
|
|
|
# Development
|
|
pytest>=8.0
|
|
black>=24.0
|
|
ruff>=0.3
|
|
|
|
# Bot
|
|
python-telegram-bot>=21.0
|