mondobrain 1.0.0a7

MondoBrain API wrapper

MondoBrain Python SDK

MondoBrain Python SDK is a python wrapper for the MondoBrain API that provides additional functionality such as dataframe ingest and one-off processing

Installation

Use the package manager pip to install mondobrain.

pip install mondobrain-sdk

Dependencies

• python3

Install from source

In the mondobrain-python directory (same directory as this README.md file), run this command in your terminal:

pip install -e .

Usage

import mondobrain as mb

# Create a mb client & authenticate using your api-key
client = mb.Client(apiKey="<your-api-token-here>")

# Build a pandas dataframe and store in `df` (not shown)

# Convert your pandas df to a mondobrain df
mdf = mb.MondoDataFrame(df)

# Select a column as your outcome column & specify a target class
outcome = mdf["column_name"]

# for a discrete column
outcome.target_class = "Some_modality"

# for a continuous column the value should be `min` or `max`
outcome.target_class = "max"

# Get a dataframe of all columns you want to explor
explorable = mdf[["column_a", "column_b"]]

# Create a solver instance and pass in your mb client
solver = mb.Solver(client)

# Fit your data
solver.fit(explorable, outcome)

# Check your results
solver.real_values

See documentation and SDK Example.ipynb in the mondobrain-python directory for more in depth examples.

The package includes documentation to provide explanation and examples of usage.

Contributing

Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change. Take a look at CONTRIBUTING.md for more info

Please make sure to update tests as appropriate.

License

MIT