anetakovacheva Goto Github PK

adult-income-explained-with-shap

airports

correlation-between-population-growth-and-food-prices.

coursera-deep-learning

My notes / works on deep learning from Coursera

esrgan

heart-disease

mixing-imagination-and-reality

modelling-bank-churn-data

models_from_scratch

mslearn-demo

ner

In this Notebook, I explain what Named Entity Recognition is, and how it works. The example is demonstrated with a sentence taken from a public source, and an article from an online media. I use both NLTK and SpaCy libraries to preprocess data, to explain language elements, and to make the computer to name recognized entities.

occupancy_detection

patient-survival

predicting-clothes-size

predicting-diamonds-price

probabilistic-data-structures

shelter-animal-outcomes

speech-to-text

This Notebook is inspired by a Tutorial on Speech-to-Text conversion of Analytics Vidhya.

splink

tensorflow

An Open Source Machine Learning Framework for Everyone

text-to-speech

In this Notebook, I explore gTTS - the Google's Text-to-Speech engine. It writes text data to a mp3 file. I show a very simple example, inspired by an article in Towards Data Science.

text_classification_pyspark

In this Notebook, I explore and classify the legal text data, available on Kaggle. The dataset contains legal cases from the Federal Court of Australia. All cases are from 2006, 2007, 2008 and 2009. Catchphrases, citations sentences, citation catchphrases, and citation classes are captured for each document. Citation classes indicate the type of treatment given to the cases cited by the present case. There are more than 20000 cases in the dataset. I use PySpark to explore, clean, preprocess, and model the data.

text_summarization

This Notebook explains what text summarization is, and how the extractive approach works. Several examples are provided, both with short and long texts in English and Bulgarian.

the-art-of-buying-a-new-old-car

wonders-of-world