Hi 👋🏽, I'm Leondra.

Data Science | Machine Learning | Python | R | SQL | Kusto | Java

Welcome to my Github! I'm so glad that you're here 😊. My name is Leondra Gonzalez (nee James) and I am a 📉 Data Scientist with a passion for sci-fi ⭐, table top games 🎲, video games 🎮, prog rock / metal 🎸, anime, animals 🐱, and B-list horror and action films 🎬.

💼 I’m currently working at Microsoft as a Senior Data & Applied Scientist
🎓 Alumni Affiliations Carnegie Mellon University, Otterbein University, Quantic School of Business and Technology
📚 Currently studying PhD in Information Technology with a Specialization in Artificial Intelligence at University of the Cumberlands, School of Computer and Information Science
📓 Currently learning Deep learning architectures and tuning (RNNs, LSTMs, autoencoders, transformers, etc.) and LLMs
🎵 Currently jamming to Polyphia
📺 Currently obsessed with Cobra Kai, Love Island, Yellowstone
🔋 Passionate / Energized about Inclusion in STEM
🏙 Location Indianapolis, IN
📫 How to reach me [email protected]
📖 Read my book, "Cracking the Data Science Interview"
⚡ Fun fact Former high school United States Chess Federation state and national-level placements 🏆♟️

Connect with me:

Languages and Tools:

Let's Connect!:

Leondra R. Gonzalez's Projects

private_public_colleges

Predicting whether a university is private or public using tree based models (ie: decision tree classifier, random forest classifier and gradient boosted tree classifier) using PySpark and Databricks.

sem-generating-keywords-for-google-ads

Autonomously creating keywords for Google Ads search engine marketing campaign

sme-dle-case-study-datacamp

For consideration: Subject matter expert (SME) for Data Literacy and Essentials (DLE).

sms-spam-prediction

Predicting whether an SMS (text message) is spam using natural language processing (NLP), naive Bayes classifier and cross validation (in Python)

theeconomistdataviz

Re-Imagination of The Economist: Corruption v. Development

thematrixscript_nlp

A project utilizing NLP techniques and analysis including text mining, document term matrices, sentiment analysis, wordclouds and topic modeling with LDA.

titanic_attempt-1

Kaggle Titanic Data Set Using Logit Model

tv-halftime-shows-and-the-big-game

EDA project using SQL in Jupyter Notebooks, focusing on the history of games, broadcasts and performances for the National Football League

tweetclassificationlstm

This project details the creation of a multi-classification Recurent Neural Network (RNN) model using Tensorflow / Keras to predict Tweet emotions. More specifically, this notebook uses a bidirectional LSTM as a means to capture additional semantics often found in sequential (language) data. This project utilizes the Tweet Emotion Recognition with TensorFlow dataset provided by Kaggle.