Machine Learning Notebooks

Collection of reusable notebooks for common machine learning tasks

Each notebook contain minimal code demonstrating usage of a library on a dummy dataset.

Goal	Library	Colab
Commonsense Inference	event2mind
Constituency Parsing	benepar
	benepar in Spacy
	Custom CFG in NLTK
Custom Word Vector	fasttext
	gensim
Emoji Prediction	emojicloud
	huggingface
Evaluation	McNemar’s test
Experiment Management	wandb*
Fuzzy Matching	jellyfish
	rapidfuzz
Hyperparameter optimization	wandb*
Inter-rater Agreement	Metrics
Image Classification	efficientnet
Keyword Extraction	pytextrank
	pyate
	rake
	textacy
Language Modeling	huggingface*
Language Model Scoring	lm_scorer
	DialogRPT
	GPT-2 LM score
Machine Translation	easynmt
Multilabel Classification	scikit-multilearn
Multimodal Search	sentence-transformers(CLIP)
Multitask Learning	Run T5 for 7 tasks
NER	flair
	huggingface*
	spacy
	spacy rule-based
Next Sentence Prediction	huggingface
Open-domain Chatbot	huggingface
Paraphrase Generation	Question Paraphrasing (huggingface)
Pytorch	Serialize model in package format
Question Answering	huggingface*
Question Generation	doc2query
Record Deduplication	mix
Sentence Embeddings	DECLUTR in huggingface
	Quantize sentence-transformers
Sentiment Classification	flair
	vader sentiment(nltk)
	finetune deepmoji
	xlm-t
Semantic Role Labeling	allennlp
Semantic Search	annoy
	faiss
	sentence-transformers
	txtai
Spelling Correction	hunspell, jamspell, textblob
Synonyms	spacy
Topic Modeling	gensim(LDA)
Treemap Chart	squarify
Text Classification	huggingface*
	Huggingface Trainer
	spacy
	fastai(ULMFIT)
	fasttext(automl)
	universal sentence encoder + keras
Text Clustering	hdbscan-umap
Text Generation	markovify
	GPT-2 with simpletransformers
Text Preprocessing	contractions+ftfy+emoji
Verb Conjugation	nodebox-linguistics
Visualization	word sentiment in sentence
	wordcloud
	stem and leaf plot
Weak Supervision	snorkel*
Zero-shot classification	huggingface*

External Notebooks which are not written by me are marked with *.