### Setup Virtual Environment

Source: https://systematica.mintlify.app/getting-started/quickstart

Steps to create and activate a Python virtual environment using uv. This isolates project dependencies.

```shell
uv venv

```

```shell
# On Unix or macOS:
source .venv/bin/activate

# On Windows:
.venv\Scripts\activate
```

--------------------------------

### Systematica ArbitrageClipIndex Model Usage

Source: https://systematica.mintlify.app/getting-started/quickstart

Demonstrates importing the Systematica library, loading data, initializing the ArbitrageClipIndex model, and obtaining model outputs and signals.

```python
import systematica as sma

data = sma.load_clean_data('1d')
s1, s2 = data.symbols

model = sma.ArbitrageClipIndex(training_window=365, testing_window=60)
model_output = model(data, s1, s2)
vbt.pprint(model_output)

signals = model.get_signals(model_output, signal_model='twin_spread', long_entries=0.9, long_exits= 0.0, short_entries=-0.9, short_exits=0.0)
vbt.pprint(signals)
```

--------------------------------

### Systematica ArbitrageClipIndex Analyzer and Reporter

Source: https://systematica.mintlify.app/getting-started/quickstart

Illustrates how to run the analyzer and reporter functionalities for the ArbitrageClipIndex model, which process data and generate insights or reports.

```python
# Run analyzer
sma.ArbitrageClipIndex.run_analyzer(data, s1, s2, ...)

# Run report
sma.ArbitrageClipIndex.run_report(data, s1, s2, ...)
```

--------------------------------

### Systematica ArbitrageClipIndex Pipeline Execution

Source: https://systematica.mintlify.app/getting-started/quickstart

Shows how to run the ArbitrageClipIndex model pipeline to generate a Portfolio instance, calculate metrics like Sharpe Ratio, and compute rolling metrics.

```python
# Run pipeline to get Portfolio instance
sma.ArbitrageClipIndex.run_pipeline(data, s1, s2, ...)

# Get specific metrics
sma.ArbitrageClipIndex.run_pipeline(
  data,
  s1,
  s2,
  ...,
  metrics='sharpe_ratio'
)

# Get rolling metrics
sma.ArbitrageClipIndex.run_pipeline(
  data,
  s1,
  s2,
  ...,
  metrics='sharpe_ratio',
  use_rolling=True
)
```

--------------------------------

### Clone the Repository

Source: https://systematica.mintlify.app/getting-started/installation

Clones the project repository using the provided Git URL. This is the first step to get the project files onto your local machine.

```shell
git clone https://github.com/bfcdev/quant-research.git

```

--------------------------------

### Systematica ArbitrageClipIndex Optuna Study

Source: https://systematica.mintlify.app/getting-started/quickstart

Demonstrates using Optuna to run an optimization study for the ArbitrageClipIndex model, specifying metrics, direction, trials, and hyperparameter ranges.

```python
sma.ArbitrageClipIndex.run_optuna_study(
  data,
  s1,
  s2,
  ...,
  metrics='sharpe_ratio',
  direction='maximize',
  n_trials=10,
  training_window=sma.Int('training_window', low=20, high=500, step=10)
)
```

--------------------------------

### Install uv on Windows

Source: https://systematica.mintlify.app/getting-started/installation

Installs the 'uv' package manager on Windows using PowerShell to download and execute the installation script.

```shell
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
```

--------------------------------

### Install vectorbtpro from GitHub

Source: https://systematica.mintlify.app/getting-started/installation

Installs the 'vectorbtpro' package directly from a GitHub repository using 'uv add'. Requires specifying GitHub username, token, and organization. The '[base]' extra installs core functionalities.

```shell
uv add -U "vectorbtpro[base] @ git+https://GH_USER:GH_TOKEN@github.com/ORGANIZATION/vectorbt.pro.git"
```

--------------------------------

### Install dependencies from requirements.txt with uv

Source: https://systematica.mintlify.app/getting-started/installation

Installs project dependencies listed in a requirements.txt file into the activated virtual environment using 'uv pip install'.

```shell
uv pip install -r requirements.txt
```

--------------------------------

### Initialize a new project with uv

Source: https://systematica.mintlify.app/getting-started/installation

Initializes a new Python project using 'uv', creating a pyproject.toml file for project metadata and dependencies.

```shell
uv init
```

--------------------------------

### Install uv using pip

Source: https://systematica.mintlify.app/getting-started/installation

Installs the 'uv' package manager using pip, a common Python package installer.

```python
pip install uv
```

--------------------------------

### Create a virtual environment with uv

Source: https://systematica.mintlify.app/getting-started/installation

Creates a virtual environment for the project, typically in a .venv directory, using the 'uv venv' command.

```shell
uv venv
```

--------------------------------

### Setup Virtual Environment

Source: https://systematica.mintlify.app/getting-started/contributing

Instructions for setting up a Python virtual environment using the 'uv' tool and activating it. This ensures project dependencies are isolated.

```shell
uv venv

```

```shell
# On Unix or macOS:
source .venv/bin/activate

# On Windows:
.venv\Scripts\activate

```

--------------------------------

### Install uv using curl

Source: https://systematica.mintlify.app/getting-started/installation

Installs the 'uv' package manager on Linux or macOS using a curl command to download and execute the installation script.

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

--------------------------------

### Run project with uv

Source: https://systematica.mintlify.app/getting-started/installation

Executes a project script (e.g., main.py) within the isolated virtual environment managed by 'uv', ensuring correct dependencies are used.

```shell
uv run main.py
```

--------------------------------

### Workflow Configuration TOML Example

Source: https://systematica.mintlify.app/workspaces/workflow

An example of a workflow configuration file written in TOML format. This file defines a specific strategy, including meta-information, data loading parameters, model settings, signal generation parameters, and portfolio configurations.

```toml
[meta]
study_name = "dale"
tags = ["arbitrage", "copula", "clip-index", "1h"]

[loader]
name = "BFCData"

[loader_params]
symbols = ["CB-BTC-USD", "CB-ETH-USD"]
timeframe = "60m"
table = "candle"
index_col = "close_datetime"
engine_name = "research"
start = "2018-01-01 UTC"

[model]
name = "ArbitrageClipIndex"

[model_params]
training_window = 3244
testing_window = 992
splitter = "from_custom_rolling"
copula = "auto"
method = "aic"
lower = -1.57
upper = 1.11
sequential = false
use_close = true

[signal]
signal_model = "twin_spread"
long_entries = 0.78
long_exits = 0.0
short_entries = -1.33
short_exits = 0.0

[portfolio]
size = 50
size_type = "valuepercent100"
cash_sharing = true
call_seq = "auto"

```

--------------------------------

### Activate virtual environment (Unix/macOS)

Source: https://systematica.mintlify.app/getting-started/installation

Activates the project's virtual environment on Unix-like systems (Linux, macOS) using the 'source' command.

```shell
source .venv/bin/activate
```

--------------------------------

### Activate virtual environment (Windows)

Source: https://systematica.mintlify.app/getting-started/installation

Activates the project's virtual environment on Windows using the 'activate' script within the .venv directory.

```shell
.venv\Scripts\activate
```

--------------------------------

### Install package in development mode

Source: https://systematica.mintlify.app/getting-started/installation

Installs the current project in editable mode using pip, allowing changes to be reflected immediately without reinstallation.

```python
pip install -e .
```

--------------------------------

### Add dependencies with uv

Source: https://systematica.mintlify.app/getting-started/installation

Adds a specified package dependency to your project using the 'uv add' command, updating the pyproject.toml and lockfile.

```shell
uv add PACKAGE_NAME
```

--------------------------------

### Visualize API Reference Locally

Source: https://systematica.mintlify.app/getting-started/development_tips

This command sequence navigates into the `docs` directory and starts a local development server using `mint dev`. This allows you to preview the API reference in your browser.

```bash
cd docs

```

```bash
mint dev

```

--------------------------------

### Run Project Tests with Pytest

Source: https://systematica.mintlify.app/getting-started/tests

Instructions on how to execute the project's tests using the pytest framework. Ensure you are in the project's root directory before running the command.

```bash
uv run pytest tests
```

--------------------------------

### Get Portfolio Statistics

Source: https://systematica.mintlify.app/api-reference/systematica/portfolio/analyzers/base

Retrieves all statistics for a given portfolio, allowing specification of start and end dates, and additional arguments for stats and drawdowns. Returns a pandas Series containing comprehensive portfolio metrics.

```python
all_stats(
    self,
    start: str | pandas._libs.tslibs.timestamps.Timestamp = None,
    end: str | pandas._libs.tslibs.timestamps.Timestamp = None,
    portfolio: Dict[str, Any] = None,
    drawdowns: Dict[str, Any] = None,
) -> pandas.core.series.Series

Get all statistics of the portfolio.
Parameters:
start: The start date. Defaults to None.
end: The end date. Defaults to None.
portfolio: Addtional arguments for vbt.stats. Defaults to None.
drawdowns: Addtional arguments for vbt.drawdowns.stats. Defaults to None.
Returns:
pd.Series: All portfolio, returns, orders, trades and drawdowns statistics.
```

--------------------------------

### Systematica Mintlify App API Reference

Source: https://systematica.mintlify.app/api-reference/systematica/portfolio/analyzers/base

Comprehensive API documentation for the Systematica Mintlify App, including class variables, instance variables, and method signatures with parameter and return value details.

```APIDOC
Class Variables:
  data: vectorbtpro.data.base.Data
    Data object.
  s1: str
    First symbol.
  s2: str
    Second symbol.
  vbt: vectorbtpro.portfolio.base.Portfolio
    VectorBT PRO Portfolio object.
  model_output: pandas.core.frame.DataFrame | numpy.ndarray
    Model output used in the strategy. Defaults to None.
  window: int
    Rolling window used in the model. Defaults to None.
  minp: int
    Minimum number of observations required in the model. Defaults to None.

Instance Variables:
  freq: pandas._libs.tslibs.timedeltas.Timedelta
    Get the frequency of the data.
  column_wrapper: List[str]
    Get the column wrapper for the portfolio. If MultiIndex (where group_by is False), Get the first level only.
  categories: pandas.core.frame.DataFrame | None
    Retrieve asset categories.
  drawdowns_readable
    Get the drawdowns of the portfolio.
  pfo: vectorbtpro.portfolio.pfopt.base.PortfolioOptimizer
    Pick allocations from an already filled array.
  pfo_allocations: pandas.core.frame.DataFrame
    Get the portfolio allocations.
  latest_allocation: pandas.core.frame.DataFrame
    Get the latest allocation of the portfolio.
  current_holdings
    Get the current holdings of the portfolio.
  pfo_describe: pandas.core.frame.DataFrame
    Get descriptive statistics of portfolio allocations.
  average_allocation
    Get the average allocation of the portfolio.
  allocation_records_readable
    Get readable allocation records.
  latest_allocation_records
    Get the latest allocation records.

Methods:
  get_signals(sim_start: ArrayLike = None, sim_end: ArrayLike = None, group_by: bool = False) -> systematica.signals.base.Signals
    Return signals for long and short entries and exits.
    Compute boolean signals indicating the occurrence of long entry orders, long exit orders, short entry orders, and short exit orders. Signals are computed per group if grouping is enabled. Pass group_by=False to disable grouping.
    Parameters:
      sim_start: Start index of the simulation range.
      sim_end: End index of the simulation range.
      group_by: Grouping specification.
    Returns:
      Signals: systematica Signals namedtuple class.

  get_market_returns() -> pandas.core.frame.DataFrame
    Calculate market returns without NaNs.
    Returns:
      pd.DataFrame: DataFrame of market returns.

  get_rolling_metrics(metrics: str | List[str], window: int = None, minp: int = None, to_numpy: bool = False, validate_metrics: bool = True, **kwargs) -> pandas.core.frame.DataFrame | numpy.ndarray
    Get rolling metrics.
    Parameters:
      metrics: Metric to compute
      window: Rolling window length. The default is None.
      minp: Minimum periods. The default is None.
      to_numpy: Output numpy array if True. The default is False.
      validate_metrics: Validate metrics if True. The default is True.
      kwargs: Additional key-word arguments passed to MetricRegistry.run_rolling_metric.
    Raises:
      ValueError: if parameter window is to be specified.
    Returns:
      pd.DataFrame | tp.Array: Rolling metrics.
```

--------------------------------

### Pie Class Example - systematica

Source: https://systematica.mintlify.app/api-reference/systematica/utils/custom_plots

Example demonstrating how to create and display a pie chart using the systematica.Pie class with sample data.

```python
import numpy as np
import systematica as sma

pie = sma.Pie(
    data=np.array([0.06, 0.02, 0.05, 0.09]),
    trace_names=['SPY', 'TLT', 'XLF', 'XLE'],
)
pie.fig.show()
```

--------------------------------

### Activate conda environment

Source: https://systematica.mintlify.app/getting-started/installation

Activates an existing conda environment, making its packages and Python interpreter available.

```shell
conda activate your_environment_name
```

--------------------------------

### Get Annualized Return Method

Source: https://systematica.mintlify.app/api-reference/systematica/api/base

Computes and returns the annualized returns specifically for the test set of the dataset.

```apidoc
get_annualized_return() -> pandas.core.series.Series
  Description: Computes the annualized returns for the test set.
  Returns:
    - pd.Series: Series containing the annualized returns for the test set.
```

--------------------------------

### Systematica API Models

Source: https://systematica.mintlify.app/api-reference/systematica/api/models/volume_profile

References to various models available within the Systematica API, including their specific documentation paths.

```APIDOC
API Reference - Models:

- Arbitrage Index: /api-reference/systematica/api/models/arbitrage_index
- Meta Model: /api-reference/systematica/api/models/meta_model
- Momentum: /api-reference/systematica/api/models/momentum
- Ou Process: /api-reference/systematica/api/models/ou_process
- Range Breakout: /api-reference/systematica/api/models/range_breakout
- Volatility: /api-reference/systematica/api/models/volatility
- Volume Profile: /api-reference/systematica/api/models/volume_profile
```

--------------------------------

### Systematica API Signals

Source: https://systematica.mintlify.app/api-reference/systematica/api/models/volume_profile

References to various signals available within the Systematica API, including their specific documentation paths.

```APIDOC
API Reference - Signals:

- Cross Spread: /api-reference/systematica/api/signals/cross_spread
- Crossover: /api-reference/systematica/api/signals/crossover
- Spread: /api-reference/systematica/api/signals/spread
- Twin Spread: /api-reference/systematica/api/signals/twin_spread
```

--------------------------------

### Systematica API Reports

Source: https://systematica.mintlify.app/api-reference/systematica/api/models/volume_profile

References to various reports available within the Systematica API, including their specific documentation paths.

```APIDOC
API Reference - Reports:

- Arbitrage Index: /api-reference/systematica/api/reports/arbitrage_index
- Meta Model: /api-reference/systematica/api/reports/meta_model
- Momentum: /api-reference/systematica/api/reports/momentum
- Ou Process: /api-reference/systematica/api/reports/ou_process
- Range Breakout: /api-reference/systematica/api/reports/range_breakout
- Volatility: /api-reference/systematica/api/reports/volatility
- Volume Profile: /api-reference/systematica/api/reports/volume_profile
```

--------------------------------

### Data Loading and Pipeline Initialization

Source: https://systematica.mintlify.app/workspaces/sandbox

Describes the initial data fetching and preparation steps using vectorbtpro's Data objects and the load_clean_data function. This sets up the foundation for strategy execution and optimization.

```python
from vectorbtpro import Data

# Load and clean historical market data
data = Data.load_clean_data(symbols=["BTC-USD", "ETH-USD"], timeframe="1D")
```

--------------------------------

### run method for data pipeline execution

Source: https://systematica.mintlify.app/api-reference/systematica/portfolio/composers/models

Executes a data pipeline with specified input data and symbols. It is designed to process financial data for portfolio analysis.

```APIDOC
run(self, data: vectorbtpro.data.base.Data, s1: str, s2: str, use_close: bool = True) -> systematica.portfolio.analyzers.base.PortfolioAnalyzer
  Executes the pipeline with the given data and symbols.
  Parameters:
    data (vbt.Data): Input data for the pipeline.
    s1 (str): First symbol.
    s2 (str): Second symbol.
    use_close (bool, optional): Whether to use ‘Close’ prices. Defaults to True.
  Returns:
    PortfolioAnalyzer: Portfolio analyzer object with the pipeline results.
```

--------------------------------

### Sandbox Configuration and Execution

Source: https://systematica.mintlify.app/workspaces/sandbox

Covers configuration options for the Sandbox, which manages the OptunaTuner. Key parameters include n_trials, n_jobs, gc_after_trial, and cross_validate. It also mentions the use of Samplers and Pruners.

```python
from vectorbtpro.sandbox import Sandbox
from optuna.samplers import TPESampler
from optuna.pruners import SuccessiveHalvingPruner

# Sandbox configuration
sandbox_config = {
    "n_trials": 50,
    "n_jobs": -1,  # Use all available cores
    "gc_after_trial": True,
    "cross_validate": True,
    "sampler": TPESampler(),
    "pruner": SuccessiveHalvingPruner()
}

# The Sandbox passes these options to OptunaTuner
```

--------------------------------

### BaseTransformer Instantiation

Source: https://systematica.mintlify.app/api-reference/systematica/portfolio/transformers/base

Example of how to instantiate the BaseTransformer class. This is typically used as a base for creating specific transformer implementations.

```Python
from systematica.portfolio.transformers.base import BaseTransformer

# Instantiate the base transformer (or a subclass)
transformer = BaseTransformer()
```

--------------------------------

### Get Plants API Endpoint

Source: https://systematica.mintlify.app/api-reference/post-plants

Retrieves a list of plants from the store. This endpoint is part of the plant management API.

```APIDOC
GET /plants

Retrieves a list of plants from the store.

This is a placeholder for the GET /plants endpoint documentation. Specific parameters, request/response formats, and authorization details would be detailed here.
```

--------------------------------

### OptunaTuner Constructor

Source: https://systematica.mintlify.app/api-reference/systematica/portfolio/tuners/optuna_tuner

Initializes the OptunaTuner with various parameters for hyperparameter optimization. It allows configuration of samplers, pruners, optimization direction, trial counts, parallel jobs, and tracking mechanisms.

```python
OptunaTuner(
    pruner: optuna.pruners._base.BasePruner = <optuna.pruners._successive_halving.SuccessiveHalvingPruner object>,
    sampler: optuna.samplers._base.BaseSampler = <optuna.samplers._tpe.sampler.TPESampler object>,
    direction: str | List[str] = 'maximize',
    create_study_kwargs: Dict[str, Any] = _Nothing.NOTHING,
    n_trials: int = 100,
    n_completed_trials: int = None,
    n_jobs: int = -1,
    gc_after_trial: bool = False,
    optimize_kwargs: Dict[str, Any] = _Nothing.NOTHING,
    verbose: bool = True,
    tracker: systematica.portfolio.trackers.base.BaseTracker = None,
    metrics: str | List[str] = 'sharpe_ratio',
    metric_registry_kwargs: Dict[str, Any] = _Nothing.NOTHING,
    cross_validate: bool = False,
    reduce_func: Callable = CPUDispatcher(<function nanmedian_nb>),
    use_rolling: bool = False,
)
```

--------------------------------

### Cross-Validation Loop Example

Source: https://systematica.mintlify.app/api-reference/systematica/models/meta_model/clf_model

Demonstrates a cross-validation loop, fitting a pipeline on training data and predicting on test data for each split.

```python
X_slices, y_slices = splitter.take(X), splitter.take(y)
y_tests = []
y_preds = []
for split in X_slices.index.unique(level="split"):
    X_train_slice = X_slices[(split, "train")]
    y_train_slice = y_slices[(split, "train")]
    X_test_slice = X_slices[(split, "test")]
    y_test_slice = y_slices[(split, "test")]
    try:
        fitted_pipe = pipeline.fit(X_train_slice, y_train_slice)
        test_pred = fitted_pipe.predict(X_test_slice)
        test_pred_ser = pd.Series(test_pred, index=y_test_slice.index)
```

--------------------------------

### Get Kurtosis Python

Source: https://systematica.mintlify.app/api-reference/systematica/preprocessing/stats

Estimates the kurtosis of time series data. Takes a 2D NumPy array of time series. Returns the kurtosis.

```python
get_kurtosis(
    rets: numpy.ndarray,
) ‑> numpy.ndarray

Estimate kurtosis.
**Parameters**:

| Name | Type | Default | Description |
| --- | --- | --- | --- |
| `rets` | `tp.Array2d` | `--` | A 2D NumPy array where each column represents a time series. |

**Returns**:

| Type | Description |
| --- | --- |
| `tp.Array2d` | The kurtosis. |

```

--------------------------------

### Get Skewness Python

Source: https://systematica.mintlify.app/api-reference/systematica/preprocessing/stats

Estimates the skewness of time series data. Takes a 2D NumPy array of time series. Returns the skewness.

```python
get_skewness(
    rets: numpy.ndarray,
) ‑> numpy.ndarray

Estimate skewness.
**Parameters**:

| Name | Type | Default | Description |
| --- | --- | --- | --- |
| `rets` | `tp.Array2d` | `--` | A 2D NumPy array where each column represents a time series. |

**Returns**:

| Type | Description |
| --- | --- |
| `tp.Array2d` | The skewness. |

```