No project description provided

Project description

Stockula

Stockula is a comprehensive Python trading platform that provides tools for technical analysis, backtesting, data fetching, and price forecasting. Built with modern Python practices, it integrates popular financial libraries to offer a complete solution for quantitative trading strategy development.

Stockula

✨ Features

📊 Technical Analysis: 40+ indicators (SMA, EMA, RSI, MACD, Bollinger Bands, etc.)
🔄 Backtesting: Test trading strategies with realistic broker costs and commission structures
📈 Data Fetching: Real-time and historical market data via yfinance with intelligent SQLite caching
🔮 Price Forecasting: Automated time series forecasting with multiple backends:
- AutoGluon TimeSeries: Automated ML for accurate predictions (Python < 3.13)
- AutoGluon: Modern AutoML with deep learning models (DeepAR, Temporal Fusion Transformer)
- Chronos (GPU): Zero-shot forecasting with pretrained transformer models
- GluonTS (GPU): Advanced probabilistic models for uncertainty quantification
- Future prediction mode: Forecast N days from today
- Historical evaluation mode: Train/test split with accuracy metrics (RMSE, MAE, MASE)
- GPU Acceleration: Full CUDA support via PyTorch 2.8.0 base images
🎨 Rich CLI Interface: Beautiful progress bars, tables, and colored output
🗄️ Database Caching: Automatic SQLite caching for offline analysis and fast data access
🚀 Modern Python: Built with uv for fast package management and Pydantic for configuration

🚀 Quick Start

Installation

Method 1: Docker (Recommended for GPU Support)

# Standard CPU version
docker pull ghcr.io/mkm29/stockula:latest
docker run ghcr.io/mkm29/stockula:latest -m stockula --help

# GPU-accelerated version (PyTorch 2.8.0 with CUDA 12.9)
docker pull ghcr.io/mkm29/stockula-gpu:latest
docker run --gpus all ghcr.io/mkm29/stockula-gpu:latest -m stockula --help

# Run with mounted config file
docker run -v $(pwd)/.stockula.yaml:/app/.stockula.yaml ghcr.io/mkm29/stockula:latest \
    -m stockula --ticker AAPL --mode forecast

GPU Docker Features:

Based on PyTorch 2.8.0 official images for optimal compatibility
Python 3.11 pre-installed
Includes Chronos (zero-shot forecasting) and GluonTS (probabilistic models)
Full AutoGluon TimeSeries support with GPU acceleration
Non-root user stockula (UID 1000) for security

Method 2: Local Installation with uv

Install uv (if not already installed):

curl -LsSf https://astral.sh/uv/install.sh | sh

Clone and install:

git clone https://github.com/mkm29/stockula.git
cd stockula
uv sync

For GPU support (optional):

# Install GPU extras (requires CUDA 11.8+ and compatible drivers)
uv pip install -r requirements-gpu.txt --extra-index-url https://download.pytorch.org/whl/cu118

Basic Usage

# Analyze a single stock
uv run python -m stockula --ticker AAPL

# Run with configuration file
cp examples/config.simple.yaml .stockula.yaml
uv run python -m stockula

# Run specific analysis modes
uv run python -m stockula --ticker GOOGL --mode ta        # Technical analysis
uv run python -m stockula --ticker MSFT --mode backtest  # Backtesting (results sorted by return, highest first)
uv run python -m stockula --ticker NVDA --mode forecast  # Forecasting with AutoGluon or fallback

# Show help
uv run python -m stockula --help

Configuration Example

data:
  start_date: "2023-01-01"
  end_date: null

portfolio:
  initial_capital: 100000
  allocation_method: equal_weight
  tickers:
    - symbol: AAPL
      quantity: 10
    - symbol: GOOGL
      quantity: 5

backtest:
  initial_cash: 10000.0
  broker_config:
    name: "robinhood"  # Zero commission + TAF
  strategies:
    - name: smacross
      parameters:
        fast_period: 10
        slow_period: 20

Using Chronos (Zero-Shot Forecasting)

Chronos provides zero-shot probabilistic forecasts using pretrained transformer models. Enable it via config:

# examples/config/forecast_chronos.yaml
data:
  start_date: "2023-01-01"

portfolio:
  allocation_method: equal_weight
  tickers:
    - symbol: AAPL
      quantity: 1

forecast:
  forecast_length: 7
  prediction_interval: 0.9
  # Select Chronos explicitly
  models: "zero_shot"           # or ["Chronos"]
  # Optional: choose a specific pretrained Chronos model
  # models: ["Chronos", "amazon/chronos-bolt-small"]

Run with:

uv run python -m stockula --config examples/config/forecast_chronos.yaml --ticker AAPL --mode forecast
# or
uv run python examples/forecast_chronos.py --ticker AAPL

Notes:

When AutoGluon is available (Python 3.11/3.12), Stockula uses Chronos via AutoGluon to enable covariates and ensembling; otherwise it falls back to standalone Chronos.
GPU strongly recommended. The GPU Docker image already includes chronos-forecasting and gluonts[torch]==0.16.2.
If you set forecast.models to "zero_shot" or include "Chronos", Chronos is selected automatically.

Backtest-Optimized Allocation

Stockula includes an advanced allocation strategy that uses historical backtesting to optimize portfolio allocation:

# .stockula.yaml for backtest-optimized allocation
portfolio:
  initial_capital: 100000
  allocation_method: backtest_optimized
  tickers:
    - symbol: AAPL
      category: TECH
      quantity: 0  # Placeholder - will be calculated
    - symbol: SPY
      category: INDEX
      quantity: 0  # Placeholder - will be calculated
    - symbol: GLD
      category: COMMODITY
      quantity: 0  # Placeholder - will be calculated
    - symbol: NVDA
      category: MOMENTUM
      quantity: 0  # Placeholder - will be calculated

# Configure backtest optimization
backtest_optimization:
  train_start_date: "2023-01-01"
  train_end_date: "2023-12-31"
  test_start_date: "2024-01-01"
  test_end_date: "2024-06-30"
  ranking_metric: "Return [%]"    # Default, can also use "Sharpe Ratio", etc.
  min_allocation_pct: 2.0
  max_allocation_pct: 25.0
  initial_allocation_pct: 2.0

The BacktestOptimizedAllocator will:

Test 11 different trading strategies on each asset using training data
Select the best-performing strategy for each asset
Evaluate performance on test data
Allocate capital based on test performance (higher return = larger allocation by default)

Forecast-Aware Optimization (NEW!)

You can now enhance allocation decisions by incorporating price forecasts:

backtest_optimization:
  # ... existing configuration ...

  # Enable forecast integration
  use_forecast: true         # Enable forecast-aware optimization
  forecast_weight: 0.3       # 30% weight to forecast, 70% to historical
  forecast_length: 30        # Predict 30 days ahead
  forecast_backend: null     # Auto-select best backend (chronos/autogluon/simple)

When enabled, the allocator will:

Run historical backtesting as usual
Generate price forecasts for each asset
Combine historical performance with predicted returns using weighted scoring
Allocate capital based on the combined score

This creates a more forward-looking allocation that balances proven historical performance with predicted future potential.

See the Allocation Strategies documentation for more details.

Note: Currently, the backtest_optimized allocation method requires placeholder quantities in the config. Full CLI integration is planned for a future release.

Forecast Evaluation

When running forecasts in evaluation mode (with train/test split), Stockula provides accuracy metrics:

               Portfolio Value
┏━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┳━━━━━━━━━━━━┓
┃ Metric          ┃ Date       ┃ Value      ┃
┡━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━╇━━━━━━━━━━━━┩
│ Observed Value  │ 2025-04-01 │ $20,000.00 │
│ Predicted Value │ 2025-04-30 │ $20,201.99 │
│ Accuracy        │ 2025-04-30 │ 92.4190%   │
└─────────────────┴────────────┴────────────┘

How Accuracy is Calculated:

Portfolio accuracy uses MASE (Mean Absolute Scaled Error), a scale-independent metric that compares model performance to a naive forecast:

MASE < 1.0: Model beats naive forecast (good performance)
MASE = 1.0: Model equals naive forecast
MASE > 1.0: Model worse than naive forecast

For example:

If a stock's MASE is 0.8, the model is 20% better than a naive forecast
The portfolio MASE is the average of all individual stock MASE values

This provides an intuitive measure where:

100% = Perfect prediction
90%+ = Excellent forecast
80-90% = Good forecast
<80% = Consider improving model or data

📚 Documentation

For comprehensive documentation, visit our MkDocs Documentation Site:

🏁 Getting Started

Installation Guide - Detailed setup instructions
Quick Start - Common workflows and examples
Configuration - Complete configuration reference

📖 User Guide

Architecture Overview - System design and data flow
Data Fetching - Market data and caching system
Technical Analysis - 40+ indicators and usage
Backtesting - Strategy testing with realistic costs
Allocation Strategies - Portfolio allocation methods including backtest optimization
Forecasting - Time series prediction with AutoGluon
Forecasting Models - Fast & full financial model details
Rich CLI Features - Enhanced command-line interface

🔧 API Reference

Strategies API - Built-in and custom trading strategies
Broker Configuration - TODO Commission structures and fee models
Data Models - TODO Pydantic models and validation
Database API - TODO SQLite operations and CLI

🛠️ Development

Testing - Comprehensive testing guide, strategy, and coverage
CI/CD - Continuous integration and deployment with GitHub Actions

🔍 Help

Troubleshooting - Common issues and solutions

🏗️ Architecture

graph TB
    subgraph "User Interface"
        CLI["CLI<br/>cli.py"]
        Config["Configuration<br/>.stockula.yaml"]
    end

    subgraph "Managers"
        SM["Stockula Manager"]
        TAM["Technical Analysis<br/>Manager"]
        BTM["Backtesting<br/>Manager"]
        FCM["Forecasting<br/>Manager"]
        ALM["Allocator<br/>Manager"]
    end

    subgraph "Core Domain"
        Factory["Domain Factory"]
        Portfolio["Portfolio"]
        Asset["Asset"]
    end

    subgraph "Allocation Module"
        Allocator["Base Allocator"]
        STD["Standard Allocator"]
        OPT["Backtest Optimized<br/>Allocator"]
    end

    subgraph "Data Layer"
        Fetcher["Data Fetcher<br/>yfinance wrapper"]
        DB[("SQLite Database<br/>stockula.db")]
    end

    subgraph "Analysis Modules"
        TA["Technical Analysis<br/>finta"]
        BT["Backtesting<br/>strategies"]
        FC["Forecasting<br/>AutoGluon/Simple"]
    end

    CLI --> Config
    CLI --> SM
    SM --> TAM
    SM --> BTM
    SM --> FCM
    SM --> ALM
    SM --> Factory
    Config --> Factory
    Factory --> Portfolio
    ALM --> Allocator
    STD --> Allocator
    OPT --> Allocator
    OPT --> BTM
    TAM --> TA
    BTM --> BT
    FCM --> FC
    TA --> Fetcher
    BT --> Fetcher
    FC --> Fetcher
    Fetcher --> DB

    style CLI fill:#2196F3,stroke:#1976D2,color:#fff
    style SM fill:#9C27B0,stroke:#7B1FA2,color:#fff
    style Config fill:#4CAF50,stroke:#388E3C,color:#fff
    style DB fill:#FF9800,stroke:#F57C00,color:#fff

📋 Requirements

Python: 3.11 or higher (3.11 recommended for GPU support)
Operating System: macOS, Linux, or Windows
Memory: 8GB RAM recommended (16GB+ for GPU operations)
Storage: 100MB free space
GPU (optional): NVIDIA GPU with CUDA 11.8+ for acceleration

Key Dependencies

pandas: Data manipulation and analysis
yfinance: Yahoo Finance data fetching
finta: Financial technical analysis indicators
backtesting: Strategy backtesting framework
autogluon-timeseries: Advanced time series forecasting (optional, Python < 3.13)
scikit-learn: Simple fallback forecasting for Python 3.13+
autogluon (optional): Advanced AutoML forecasting with deep learning
chronos-forecasting (GPU): Zero-shot time series forecasting with transformer models
gluonts (GPU): Probabilistic time series modeling (DeepAR, Temporal Fusion Transformer)
rich: Enhanced CLI formatting with progress bars and tables
pydantic: Data validation and settings management

🎨 Rich CLI Examples

Progress Tracking

⠋ Backtesting SMACROSS on AAPL... ━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 85% 0:00:02

Results Tables

                           Portfolio Composition
┏━━━━━━━━┳━━━━━━━━━━━━━┳━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━┳━━━━━━━━━━━┓
┃ Ticker ┃ Category    ┃ Quantity ┃ Allocation % ┃      Value ┃ Status    ┃
┡━━━━━━━━╇━━━━━━━━━━━━━╇━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━╇━━━━━━━━━━━┩
│ SPY    │ INDEX       │     1.00 │         0.7% │    $637.10 │ Hold Only │
│ VOO    │ INDEX       │     1.00 │         0.6% │    $585.58 │ Hold Only │
│ DFUSX  │ INDEX       │     1.00 │         0.0% │     $42.40 │ Hold Only │
│ FSKAX  │ INDEX       │     1.00 │         0.2% │    $175.65 │ Hold Only │
│ FSMDX  │ INDEX       │   199.00 │         7.8% │  $7,279.42 │ Hold Only │
│ FXAIX  │ INDEX       │     1.00 │         0.2% │    $221.98 │ Hold Only │
│ NVDA   │ MOMENTUM    │     1.00 │         0.2% │    $173.50 │ Tradeable │
│ AMD    │ MOMENTUM    │     1.00 │         0.2% │    $166.47 │ Tradeable │
│ TSM    │ MOMENTUM    │     1.00 │         0.3% │    $245.60 │ Tradeable │
│ AAPL   │ MOMENTUM    │     1.00 │         0.2% │    $213.88 │ Tradeable │
│ MSFT   │ MOMENTUM    │     1.00 │         0.5% │    $513.71 │ Tradeable │
│ GOOGL  │ MOMENTUM    │     1.00 │         0.2% │    $193.18 │ Tradeable │
│ AMZN   │ MOMENTUM    │     1.00 │         0.2% │    $231.44 │ Tradeable │
│ META   │ MOMENTUM    │     1.00 │         0.8% │    $712.68 │ Tradeable │
│ TSLA   │ MOMENTUM    │     1.00 │         0.3% │    $316.06 │ Tradeable │
│ PLTR   │ MOMENTUM    │   469.00 │        79.7% │ $74,477.20 │ Tradeable │
│ LIDR   │ SPECULATIVE │  1631.00 │         7.7% │  $7,233.48 │ Tradeable │
│ OPEN   │ SPECULATIVE │     1.00 │         0.0% │      $2.54 │ Tradeable │
│ SOFI   │ SPECULATIVE │     1.00 │         0.0% │     $21.20 │ Tradeable │
│ IONQ   │ SPECULATIVE │     1.00 │         0.0% │     $43.17 │ Tradeable │
└────────┴─────────────┴──────────┴──────────────┴────────────┴───────────┘

Ticker-Level Backtest Results

                             Ticker-Level Backtest Results
┏━━━━━━━━┳━━━━━━━━━━━━━━━━┳━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━┳━━━━━━━━━━┓
┃ Ticker ┃ Strategy       ┃   Return ┃ Sharpe Ratio ┃ Max Drawdown ┃ Trades ┃ Win Rate ┃
┡━━━━━━━━╇━━━━━━━━━━━━━━━━╇━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━╇━━━━━━━━━━┩
│ NVDA   │ VIDYA          │  +27.67% │         1.50 │       -3.43% │      0 │      N/A │
│ NVDA   │ SMACROSS       │  +44.60% │         0.64 │      -38.09% │      9 │    44.4% │
│ NVDA   │ DOUBLEEMACROSS │  +27.67% │         1.50 │       -3.43% │      0 │      N/A │
│ NVDA   │ VAMA           │  +41.34% │         0.59 │      -42.46% │      9 │    33.3% │
│ NVDA   │ ER             │  +60.37% │         1.20 │      -14.22% │     10 │    40.0% │
| ...    │ ...            │      ... │         ...  │         ...  │    ... │      ... │
└────────┴────────────────┴──────────┴──────────────┴──────────────┴────────┴──────────┘

Strategy Summaries

Strategy summaries are displayed in descending order by "Return During Period" (highest returns first):

╭─────────────────────────────────────────────────── STRATEGY: DOUBLEEMACROSS ────────────────────────────────────────────────────╮
│                                                                                                                                 │
│  Parameters: Default                                                                                                            │
│  Broker: robinhood (zero-commission)                                                                                            │
│                                                                                                                                 │
│  Portfolio Value at Start Date: $19,997.94                                                                                      │
│  Portfolio Value at End (Backtest): $30,261.55                                                                                  │
│                                                                                                                                 │
│  Strategy Performance:                                                                                                          │
│    Average Return: +51.32%                                                                                                      │
│    Winning Stocks: 12                                                                                                           │
│    Losing Stocks: 2                                                                                                             │
│    Total Trades: 22                                                                                                             │
│                                                                                                                                 │
│  Return During Period: $10,263.61 (+51.32%)                                                                                     │
│                                                                                                                                 │
│  Detailed report saved to: results/reports/strategy_report_doubleemacross_20250727_221642.json                                  │
│                                                                                                                                 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯

🚀 CI/CD

Continuous Integration

Stockula uses GitHub Actions for automated testing and deployment:

Testing (test.yml): Runs on all pull requests and pushes to main
- Linting: Code style checks with ruff
- Unit Tests: Fast, isolated tests with coverage reporting
- Integration Tests: Currently disabled, will test with SQLite database
Release Management (release-please.yml): Automated versioning and releases
- Monitors commits using Conventional Commits
- Creates release PRs automatically
- Publishes to PyPI on release
Docker Builds (docker-build.yml): Multi-platform container images
- Triggers on version tags (v*)
- Builds for linux/amd64 and linux/arm64/v8
- Publishes to GitHub Container Registry

Commit Guidelines

This project uses Conventional Commits:

feat: New features
fix: Bug fixes
chore: Maintenance tasks
docs: Documentation updates
test: Test additions or changes

🔗 Links

📖 Full Documentation: docs/
🐛 Issue Tracker: GitHub Issues
💡 Feature Requests: GitHub Discussions

📝 License

MIT License - see LICENSE file for details.

🔄 Git Flow & Release Process

We follow a Git Flow branching strategy with automated releases via Release Please.

Branching Strategy

graph LR
    A[feature/*] -->|Push| K[Docker Build<br/>0.12.1-feat.branch.sha]
    K -->|GHCR| L[ghcr.io/mkm29/stockula:feat]
    A -->|PR| B[develop]
    C[bugfix/*] -->|PR| B
    B -->|Release Please| D[RC Release<br/>0.12.1-rc.1]
    D -->|Docker Build| E[ghcr.io/mkm29/stockula:0.12.1-rc.1]
    B -->|Promote PR| F[main]
    F -->|Release Please| G[Stable Release<br/>v0.12.1]
    G -->|Docker Build| H[ghcr.io/mkm29/stockula:v0.12.1]
    G -->|Publish| I[PyPI]
    J[hotfix/*] -->|PR| F
    J -->|Auto-backport| B

develop - Integration branch for active development
main - Production-ready releases only
Feature branches (feature/*) - New features
Bugfix branches (bugfix/*) - Bug fixes
Hotfix branches (hotfix/*) - Critical production fixes

Release Types

Type	Branch	Git Tag	Docker Tag	Example
Feature Branch	feature/*	None	`X.Y.Z-feat.<branch>.<sha>`	`ghcr.io/mkm29/stockula:0.12.1-feat.new-api.a1b2c3d`
Release Candidate	develop	`0.Y.Z-rc.N`	`0.Y.Z-rc.N`	`ghcr.io/mkm29/stockula:0.12.1-rc.1`
Stable Release	main	`vX.Y.Z`	`vX.Y.Z`	`ghcr.io/mkm29/stockula:v0.12.1`

Docker Images

Automated builds are triggered on releases and feature branch pushes:

Image	Description	Latest Feature	Latest RC	Latest Stable
`ghcr.io/mkm29/stockula`	CLI with development tools	`:feat`	`:rc`	`:latest`
`ghcr.io/mkm29/stockula-gpu`	GPU-accelerated CLI (CUDA)	N/A	`:rc`	`:latest`

# Pull latest stable
docker pull ghcr.io/mkm29/stockula:latest

# Pull latest RC for testing
docker pull ghcr.io/mkm29/stockula:rc

# Pull latest feature branch build
docker pull ghcr.io/mkm29/stockula:feat

# Pull specific versions (tags match Git tags for releases)
docker pull ghcr.io/mkm29/stockula:v0.12.1      # Stable release
docker pull ghcr.io/mkm29/stockula:0.12.1-rc.1  # Release candidate

# Pull specific feature branch build
docker pull ghcr.io/mkm29/stockula:0.12.1-feat.new-api.a1b2c3d

# Run GPU-accelerated version (requires NVIDIA Docker runtime)
docker run --gpus all ghcr.io/mkm29/stockula-gpu:latest

# Check GPU availability
docker run --gpus all ghcr.io/mkm29/stockula-gpu:latest bash -c "/home/stockula/gpu_info.sh"

🤝 Contributing

Contributions are welcome! Please see our Contributing Guide for development setup and guidelines.

Development Setup

Install pre-commit hooks:
```
uv run pre-commit install
```

Run tests and linting:

# Run tests
uv run pytest

# Run linting (checks src, tests, and utils directories)
uv run lint

# Or run individual commands
uv run ruff check src tests utils
uv run ruff format --check src tests utils

# Fix linting issues automatically
uv run lint --fix

Utility commands:

# Check Python compatibility
uv run check-python

# Verify GPU packages
uv run verify-gpu

# Validate Docker configuration
uv run validate-docker
uv run verify-build

# Format YAML files
uv run format-yaml

See Utility Commands Documentation for all available commands.

Manual pre-commit run:
```
uv run pre-commit run --all-files
```

This project uses:

Conventional Commits for commit messages
Release Please for automated releases
pre-commit for code quality checks

📚 For detailed documentation, examples, and API references, visit our comprehensive documentation site.

Project details

Release history Release notifications | RSS feed

This version

0.16.0

Aug 11, 2025

0.15.7

Aug 11, 2025

0.11.0

Aug 9, 2025

0.10.0

Aug 5, 2025

0.9.1

Aug 4, 2025

0.9.0

Aug 4, 2025

0.8.0

Aug 4, 2025

0.7.0

Aug 3, 2025

0.6.1

Aug 2, 2025

0.6.0

Aug 2, 2025

0.5.2

Aug 2, 2025

0.5.1

Aug 2, 2025

0.5.0

Aug 2, 2025

0.4.3

Aug 1, 2025

0.4.2

Aug 1, 2025

0.4.1

Aug 1, 2025

0.4.0

Aug 1, 2025

0.3.2

Aug 1, 2025

0.3.1

Aug 1, 2025

0.3.0

Aug 1, 2025

0.2.0

Jul 31, 2025

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

stockula-0.16.0.tar.gz (652.0 kB view details)

Uploaded Aug 11, 2025 Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

The dropdown lists show the available interpreters, ABIs, and platforms. Enable javascript to be able to filter the list of wheel files.

stockula-0.16.0-py3-none-any.whl (164.7 kB view details)

Uploaded Aug 11, 2025 Python 3

File details

Details for the file stockula-0.16.0.tar.gz.

File metadata

Download URL: stockula-0.16.0.tar.gz
Upload date: Aug 11, 2025
Size: 652.0 kB
Tags: Source
Uploaded using Trusted Publishing? No
Uploaded via: uv/0.8.8

File hashes

Hashes for stockula-0.16.0.tar.gz
Algorithm	Hash digest
SHA256	`5ed8fb13cc4b557a8fe08ebc4d018e9845689c93ea5704d62e83eedcc516382c`
MD5	`ec1c415f2fda1c0cda7ed44dc43ce795`
BLAKE2b-256	`1fd658f0c2eb843d5181fcbba8236a640c2432652c785275a61a80aab57f5278`

See more details on using hashes here.

File details

Details for the file stockula-0.16.0-py3-none-any.whl.

File metadata

Download URL: stockula-0.16.0-py3-none-any.whl
Upload date: Aug 11, 2025
Size: 164.7 kB
Tags: Python 3
Uploaded using Trusted Publishing? No
Uploaded via: uv/0.8.8

File hashes

Hashes for stockula-0.16.0-py3-none-any.whl
Algorithm	Hash digest
SHA256	`33d97e93581f77eaa9731634d61e4c3dedc34d95a8c7e696ecbb1a3cb328ac9a`
MD5	`78b6f068595bc0186f74972184b9ab00`
BLAKE2b-256	`37afa29c4d02a96cc4f3e5785caae5522d7cde46ac751960f82de7bdb7a4b9f1`

See more details on using hashes here.

stockula 0.16.0

Navigation

Verified details

Maintainers

Unverified details

Meta

Project description

Stockula

✨ Features

🚀 Quick Start

Installation

Method 1: Docker (Recommended for GPU Support)

Method 2: Local Installation with uv

Basic Usage

Configuration Example

Using Chronos (Zero-Shot Forecasting)

Backtest-Optimized Allocation

Forecast-Aware Optimization (NEW!)

Forecast Evaluation

📚 Documentation

🏁 Getting Started

📖 User Guide

🔧 API Reference

🛠️ Development

🔍 Help

🏗️ Architecture

📋 Requirements

Key Dependencies

🎨 Rich CLI Examples

Progress Tracking

Results Tables

Ticker-Level Backtest Results

Strategy Summaries

🚀 CI/CD

Continuous Integration

Commit Guidelines

🔗 Links

📝 License

🔄 Git Flow & Release Process

Branching Strategy

Release Types

Docker Images

🤝 Contributing

Development Setup

Project details

Verified details

Maintainers

Unverified details

Meta

Release history Release notifications | RSS feed

Download files

Source Distribution

Built Distribution

File details

File metadata

File hashes

File details

File metadata

File hashes