requirements.txt

# Core Dependencies
groq>=0.13.0  # Updated for httpx compatibility
mistralai>=0.0.7  # Mistral AI - 1B tokens/month (corrected version)
python-dotenv==1.0.0

# Data Processing
polars>=0.20.3
duckdb>=0.10.0
pyarrow>=14.0.1
pandas>=2.2.0  # Updated for Python 3.13 compatibility

# Machine Learning
scikit-learn>=1.4.0
xgboost>=2.0.3
lightgbm>=4.6.0
catboost>=1.2.8
optuna>=3.5.0

# AutoGluon AutoML (modular install - only tabular + timeseries)
autogluon.tabular>=1.2
autogluon.timeseries>=1.2
holidays>=0.40  # Holiday calendar for time series covariates

# Explainability
shap>=0.44.1

# Advanced ML Tools
imbalanced-learn>=0.12.0

# Statistical Analysis
scipy>=1.11.4
statsmodels>=0.14.1

# Visualization
matplotlib>=3.8.2
seaborn>=0.13.1
plotly>=5.18.0  # Interactive visualizations

# EDA Report Generation
ydata-profiling>=4.17.0  # Comprehensive automated EDA reports with Python 3.13 compatibility
sweetviz>=2.3.0  # Interactive EDA with comparison support

# User Interface
# gradio>=5.49.1  # Replaced with React frontend

# REST API (Cloud Run)
fastapi>=0.109.0
uvicorn>=0.25.0
python-multipart>=0.0.6  # For file uploads

# Text Processing
textblob>=0.17.1
vaderSentiment>=3.3.2  # Rule-based sentiment analysis (fast, no GPU needed)

# Time Series Forecasting
prophet>=1.1.5
holidays>=0.38
pmdarima>=2.0  # Auto ARIMA (auto_arima) for optimal order selection

# MLOps & Explainability
lime==0.2.0.1
fairlearn==0.10.0
evidently>=0.4.0  # Production-grade data drift detection & monitoring
dtreeviz>=2.2  # Decision tree visualization

# NLP & Semantic Layer (REQUIRED for column understanding and agent routing)
sentence-transformers>=2.2.2  # For semantic column embeddings and agent routing
tiktoken>=0.5.2  # For accurate token counting in budget management

# Advanced NLP (Optional - Uncomment for advanced NLP tools)
# These are optional but recommended for full NLP capabilities
# spacy==3.7.2  # For named entity recognition (perform_named_entity_recognition)
# transformers==4.35.2  # For transformer-based sentiment & topic modeling
# bertopic==0.16.0  # For advanced topic modeling

# Computer Vision (Optional - Uncomment for CV tools)
# These are optional but recommended for full CV capabilities
# torch==2.1.0  # For CNN-based image feature extraction
# torchvision==0.16.0  # For pre-trained models (ResNet, EfficientNet, VGG)
Pillow==10.1.0  # For basic image processing
#opencv-python==4.8.1  # For advanced image processing & color features

# Business Intelligence (Optional - Uncomment for advanced BI tools)
# These are optional but add specialized capabilities
# lifetimes==0.11.3  # For customer lifetime value modeling
# econml==0.15.0  # For advanced causal inference
dowhy>=0.11  # Formal causal inference with DAG-based reasoning

# Data Quality & Validation
cleanlab>=2.6  # Label error detection using confident learning
pandera>=0.18  # Schema-based DataFrame validation
boruta>=0.3  # All-relevant feature selection (BorutaPy)

# CLI & UI
typer==0.9.0
rich==13.7.0
tqdm==4.66.1

# Utilities
pydantic==2.5.3
joblib==1.3.2

# Google Cloud Integration
google-cloud-bigquery==3.14.1
google-cloud-storage==2.14.0  # For GCS artifact storage
google-auth==2.25.2
google-generativeai==0.3.2  # For Gemini LLM support

# Cloudflare R2 Storage (S3-compatible)
boto3>=1.28.0  # For R2 file storage

# HuggingFace Storage Integration
huggingface_hub>=0.20.0  # For storing user artifacts on HuggingFace

# Supabase Backend
supabase>=2.0.0  # For user file metadata

# Testing
pytest==7.4.3
pytest-mock==3.12.0
pytest-cov==4.1.0

# Development
black==23.12.1
flake8==7.0.0
mypy==1.8.0