Python SDK

The primary mechanism for submitting data to Distributional is through our Python SDK. This section servers as a reference for the various functionalities available for interacting with DBNL via the SDK.

Example Usage

Below is a basic working example that highlights the SDK workflow. If you have not yet installed the SDK, follow these instructions.

import dbnl
import numpy as np
import pandas as pd


num_results = 500
test_data = pd.DataFrame({
    "idx": np.arange(num_results),
    "age": np.random.randint(5,95, num_results),
    "loc": np.random.choice(["NY", "CA", "FL"], num_results),
    "churn_gtruth": np.random.choice([True, False], num_results)
})

# example user ml app / model
def churn_predictor(input):
    return 1.0 / (1.0 + np.exp(-(input["age"] / 10.0 - 3.5)))

def evaluate_predicton(data):
    return (data["churn_score"] > 0.5 and data["churn_gtruth"]) or \
            (data["churn_score"] < 0.5 and not data["churn_gtruth"])

test_data["churn_score"] = test_data.apply(churn_predictor, axis=1)
test_data["pred_correct"] = test_data.apply(evaluate_predicton, axis=1)
test_data = test_data.astype({"age": "int", "loc": "category"})

# Use DBNL
dbnl.login(api_token="<COPY_PASTE_DBNL_API_TOKEN>")
proj = dbnl.get_or_create_project(name="example_churn_predictor")
run = dbnl.report_run_with_results(
    project=proj,
    column_data=test_data,
    row_id=["idx"],
)