Workflow Summary
This workflow begins by reading the source CSV data, removing duplicate records, filtering out unwanted rows, and creating cleaned fields to prepare the dataset for analysis. Selected numeric-looking categorical fields are converted to string format, and only the required columns are retained for modeling.
The cleaned dataset is then divided into an 80/20 training and test set. Descriptive statistics are generated using the training data to provide an overview of the dataset. A Decision Tree model is subsequently trained on the training set and used to generate predictions on the test set. Finally, a Scorer evaluates the model's performance by comparing the actual outcomes with the predicted results..
