Jul 16, 2024
studio.azureml.net
and sign in.+New
, then select Blank Experiment
.Saved Datasets
under Samples
.Airport Codes
dataset (second in the list)Flight On-time Performance
dataset
onto the workspace.Airport Codes
with the main dataset to map airport IDs to meaningful names and locations.Edit Metadata
on the Airport Codes
dataset to rename columns suitably for merging.origin_airport_id
or dest_airport_id
.origin_airport_id
, dest_airport_id
, cancelled
, and diverted
.Edit Metadata
to segregate categorical vs. numeric features.Clean Missing Data
for categorical and numeric columns separately.Normalize Data
to numeric columns (departure_delay
and arrival_delay
) to ensure consistent scaling.Split Data
component to split data into training (95%) and test (5%) sets.Split Data
to further partition training data into training (81%) and validation (14%) sets.Two-Class Boosted Decision Tree
for classification.Tune Model Hyperparameters
module to find the best configuration for the classification algorithm.best
model from Tune Model Hyperparameters
to Train Model
using the training dataset.Score Model
to test the trained model using the validation and/or test set.Evaluate Model
to obtain metrics like accuracy, F1 score, precision, recall.