Introduction to Data Science Using Python
A textbook that first teaches Python from scratch and then applies machine learning and statistics to data-driven problem solving, including graph theory and scientific computing.
Search titles, authors, subjects and dates from across the DARE African Knowledge Repository.
43 resources found in the repository.
A textbook that first teaches Python from scratch and then applies machine learning and statistics to data-driven problem solving, including graph theory and scientific computing.
An open textbook on machine-learning systems, covering the hardware and software stack for training and serving ML models, distributed training, inference optimisation and systems design.
A practical four-chapter introduction to AI, NLP and machine learning with Python: LSTMs, tokenisation, stopwords, lemmatisation, bag-of-words, supervised learning and text classification.
Open textbook for an introductory machine-learning course in mechanical engineering, with runnable Python examples covering supervised learning, gradient descent, generative adversarial networks, variational autoencoders, normalising flows, diffusion models, reinforcement learning and transformers.
31,102 verse-aligned Bible verses in isiNdebele (Zimbabwe) with full book/chapter/verse metadata; 66 books.
7,957 verse-aligned New Testament verses in chiShona with book/chapter/verse metadata, 27 books, Parquet format.
Translations of a subset of XNLI into 16 African languages with validation and test splits for natural language inference evaluation.
Translations of a subset of MMLU into 15 African languages to benchmark multitask knowledge and reasoning.
A 0.4B-parameter transformer language model trained on African languages by Lelapa AI, released with associated research (arXiv:2408.17024).
~803k aligned four-way parallel sentences across English, Nuer, Dinka and Swahili for multilingual machine translation and cross-lingual transfer.
Evaluation set of GSM8K translations into 16 African languages with 250 test problems per language for multilingual mathematical reasoning.
Largest publicly available topic-classification dataset based on Flores-200, covering 205 languages and dialects with a compact seven-class label set.