kelseymour Goto Github PK

api-data-wrangling-project

This exercise entails using the python requests package to pull stock data from Quandl, then explores the data from its nested dictionary format.

audio-moderator

Machine translation project with goal of translating Chinese audio to English text for content moderation.

bayesian-inference

This exercise uses Bayesian Inference and the PyMC3 library to model financial conditions from the hospital billing dataset.

chinese-nlp_buddhist-texts

This notebook explores using the SpaCy Chinese model to tokenize and analyze parts of speech for a short Buddhist text. Mistakes in the tags were corrected by hand to train an improved model for Pre-Modern Literary Chinese Texts. It was built with Pandas, SpaCy, and Xiaoquan Kong's Chinese SpaCy model. It implements a Part of Speech tagger and visualizations using diSplaCy.

clustering

This exercise uses unsupervised learning methods (K-Means, Spectral clustering, DBSCAN) to analyze wine buyer data.

fastai_bears

Repo for FastAI Deep Learning practice

fastai_cats

Cat breed classifier on small dataset

hello-world

inferential-statistics-1

Exercise to review key concepts in frequentist statistics.

inferential-statistics-2

This exercise uses frequentist statistics to explore insured and uninsured populations from a dataset of hospital charges.

inferential-statistics-3

This exercise uses bootstrap sampling to make inferences about insured and uninsured populations from a dataset of hospital billing information.

json_project

This exercise deals with flattening json files using World Bank economic projects data.

judith-botler

Judith Botler is a Twitter bot that parodies opaque academic writing.

kickstarter-project

Machine learning project to predict the success of Kickstarter projects.

linear-regression

This exercise uses Linear Regression to predict housing prices based on features from the Boston housing dataset.

logistic-regression

This exercise uses Logistic Regression to model and predict gender based on a dataset of physical attributes.

musician-matcher

This project uses unstructured text data to create a recommendation system based on artist descriptions.

nea-grant-topic-modeling

Project to optimize grant writing and increase chances of a successful NEA grant application for an orchestra

practice_repo

This is a practice repository made using the command line.

relax-challenge

Practice take home challenge about predicting user retention.

springboard

sql-project

SQL query exercises using database of country club bookings.

text-classification-naive-bayes

Sentiment analysis on movie reviews.

titanic_datascience

This projects aims at analyzing Kaggle's Titanic dataset and build a predictive model for the Titanic data science challenge.

ultimate-challenge

Practice take-home challenge about increasing customer usage for a rideshare app.