Predict Classification
v.1.0.0
Overview
After training your classification models, the predict_classification
function allows you to make predictions on new data. This guide will walk you through the necessary setup and steps to use your trained model for prediction.
Step 0: Get ready
To make predictions you must have trained a classification model first. If you haven't, follow the steps here first: Train Classification.
Step 1: Initialize the Client and set up your workspace
If you haven't, start by importing necessary modules and initializing your client with the appropriate credentials.
Set the same menu path you did when you trained your classification model and disable caching for real-time data processing.
Note: you must have your SHIMOKU_TOKEN
, UNIVERSE_ID
and WORKSPACE_ID
saved as environment variables.
Step 2: Prepare Your Prediction Data
Load the data you wish to predict on and create an input file for the prediction process.
Here's a sample you can use to predict based on the model you created in Train Classification:
Step 3: Execute the Prediction Function
Use your trained model to make predictions on the new data.
Step 4: Monitor and Retrieve Predictions
Wait for the prediction process to complete and the outputs to be available.
Step 5: Access the Prediction Results
Once the execution is complete, retrieve the output files with your predictions.
The dictionary output_dict will have 2 items in which the keys are the names of the outputs and the value are pandas data frames. The following outputs will be available:
Have a look here to better understand the outputs.
Finally, if you want to save these outputs in your local machine, you can execute the following:
Last updated