Learn Azure Machine Learning from scratch

Learn azure machine learning from scratch: preprocess flight data by combining flight delays and weather datasets, clean missing values, normalize data with descriptive statistics, and prepare for model training.

Learn to clean data and convert columns to categorical in Azure Machine Learning, preparing origin and destination airport IDs, year, month, and day of week for delay prediction.

Map weather and flight data through data cleaning and applied math, extracting hours from times by dividing by 100, rounding, and visualizing results in Azure machine learning.

Preprocess the weather data for Azure machine learning by visualizing, cleaning missing values, removing incomplete rows, converting airport id to categorical, and adjusting time fields with math.

Join weather and planes data in Azure Machine Learning by selecting join keys (year, month, day, airport id, departure time) and split the merged data to prepare flight delay predictions.

Explore available machine learning algorithms, including regression, classification, clustering, and early detection, by dragging them into your experiment and training, splitting data, and evaluating models.

Explore a free machine learning cheat sheet to help you select Azure Machine Learning algorithms for regression, classification, clustering, and anomaly detection based on your data and prediction goals.

Drag and drop multiclass algorithms in Azure Machine Learning to train and score models using an 80/20 data split, comparing multiclass logistic regression and multiclass decision jungle.

Explore how to work with two datasets, split data, train models, and visualize decision trees in Azure machine learning for analysis across experiments.

Publish your Azure ML experiment to the Azure AI Gallery by providing a name, summary, and description. Browse published models, download them, and adapt examples for your project.