625/2740
[ stop the slideshow ]

PyData PyLadies Toronto

DI_20200129_Pydata_PyLadies_1661.jpg Heartland neighbourhoodThumbnailsKoffler Centre of the ArtsHeartland neighbourhoodThumbnailsKoffler Centre of the ArtsHeartland neighbourhoodThumbnailsKoffler Centre of the ArtsHeartland neighbourhoodThumbnailsKoffler Centre of the ArtsHeartland neighbourhoodThumbnailsKoffler Centre of the ArtsHeartland neighbourhoodThumbnailsKoffler Centre of the ArtsHeartland neighbourhoodThumbnailsKoffler Centre of the Arts

Joint @PyDataTO @PyLadiesToronto meeting including @sereprz on Improving Law Interpretability with NLP. Unsupervised Machine Learning, using spaCy on Accessibility for Ontarians with Disabilities Act data. Extract burdens (obligations), identify subjects, cluster subject (looking for homogenous groups in vector space. Used GLoVe (global vectors for word representation), with dimensionality reduction for sparse data. K-means clustering and evaluation through TD-IDF. Understood presentation, as a result of taking Big Data classes at Ryerson Chang School. (PyData Toronto, PyLadies Toronto, Intelliware, Adelaide Street West, Toronto, Ontario) 20200129