synthera 0.2.3a1

Python client for Synthera AI API

Synthera AI SDK

This provides a Python SDK for accessing the Synthera AI API.

Installation

pip install synthera

API Key

You are required to use an API key to access the Synthera AI API.

For ease of use, set as an environment variable: SYNTHERA_API_KEY.

For example:

export SYNTHERA_API_KEY=<api_key>

Or you can pass to the client.

Getting Started

Import the Synthera client:

from synthera import SyntheraClient

Create a client:

client = SyntheraClient()

Check the connection works:

client.healthy()

`True`

For more advanced connection options, pass parameters to the client:

SyntheraClient(api_key: str, host: str, port: int, timeout_secs: int)

Fixed Income

To run fixed income yield curve simulations.

Parameters

Prepare input parameters.

Parameter	Type	Description	Values
no_of_days	integer	Number of days to simulate forward from the reference date	> 0 (e.g., 3, 30, 60, 120)
no_of_samples	integer	Number of simulation paths to generate	> 0 (e.g., 100, 1024, 10000)
reference_date	string	Reference date for the simulation (in the past)	YYYY-MM-DD format
yield_curve_names	list[string]	List of yield curves to simulate, using their unique identifiers	List of curve names (e.g., ["USD_Z0", "EUR_Z0", "GBP_Z0"])
model_label	string	Version of the model to use	Valid model version (V) and universe (U): "YieldGAN-vV-U"
return_conditional	boolean	Whether to return conditional simulation results	Optional; defaults to false

For example:

params = {
    "no_of_days": 60,
    "no_of_samples": 1024,
    "reference_date": "2010-01-01",
    "yield_curve_names": [
        "USD_Z0",
        "EUR_Z0",
    ],
    "model_label": "YieldGAN-v41-z0",
    "return_conditional": False
}

Simulations

Run directly:

results = client.fixed_income.simulation_past_date(params=params)

To view available yield curves:

print(results.names)

To view yield curve dataframe column names:

print(results.column_names)

To view a specific yield curve dataframes, e.g. for USD_Z0:

print(results.dataframes["USD_Z0"])

To view all yield curves in a single numpy ndarray (order is same as names):

print(results.ndarray)

To view request metadata:

print(results.metadata)

Alternatively, import the fixed income class:

from synthera import FixedIncome

Pass the client:

fixed_income = FixedIncome(client)

Then run a simulations:

results = fixed_income.simulation_past_date(params=params)