Data Labeling and Classification (DataCamp/ML Coursework)
Leveraging DataCamp's 'Data Scientist in Python' and 'Machine Learning Scientist in Python' programs, I worked extensively with labeled text data to train, validate, and tune AI models. The experiences focused on labeling and analyzing data for predictive and classification tasks in civil engineering and urban infrastructure domains. Emphasis was placed on understanding the impact of annotation quality on model outcomes. • Labeled and classified sample datasets for algorithm benchmarking. • Conducted data splitting and labeling for cross-validation experiments. • Integrated SIAM-certified Python tools for annotation and feature extraction. • Produced evaluation metrics to assess model accuracy based on labeled data.