Skip to content
View tophercollins's full-sized avatar
1 follower · 5 following

Block or report tophercollins

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
tophercollins/README.md

I'm a Data Analyst & Data Scientist with experience in Python, R, SQL, TensorFlow, & Scikit-Learn.

  • Red Card / Goal Analysis, Exploratory Data Analysis of the impact of Red Cards on the Number of Goals scored across 5 years of the major European Football Leagues, using Python with Pandas and Matplotlib libraries.
  • EIFO Data Extraction, a Python script to web scrape EIFO Country Risk & Cover Policies and export to Excel.
  • Automated Scorecard Processing Handwritten Character Recognition, Computer Vison model for custom EMNIST character recognition including artificially constructed strikethrough characters.
  • Smoker vs. Non-Smoker Classification, a classification model using Tenserflow, Catboost, XGBoost, & LightGBM for an ensemble stacking classfier.
  • Fine-tuning LLM for RPG Statblocks, fine-tuned Llama3 model for producing Dungeons & Dragons monster statblocks, dataset and model deployed on Hugging Face.
  • Electric Vehicle kWh Consumption Forecasting, explored forecasting daily kWh consumption for a workplace EV charging program.
  • Bitcoin Price Forecasting, implemented time series models (Conv1D, Bidirectional LSTM, GRU) for Bitcoin price forecasting, using metrics (Loss, MAE, MSE) to assess performance.
  • Structured Medical Text Classification with NLP, a multi-class model utilizing Universal Sentence Encoder, Conv1D character embedding, and text position features to classify medical literature sentences.
  • Transfer Learning in Food Image Classification, computer vision model on Food101 dataset utilizing EfficientNetV2 transfer learning.

I'm also a Dungeons & Dragons / Tabletop RPG / Gaming Nerd who uses programming for building gaming related passion projects.

  • DnDwithToph.com, a Dungeons & Dragons platform for online gameplay & adventures built using a Flask framework.
  • D&D Race Classification, a classification problem using Scikit-learn library and models.
  • Zombie Survival, a turn based survival game written in Python focusing on Object Orientated Programming.

For a more detailled view of projects, see my Portfolio.

Pinned Loading

  1. red_card_goal_analysis red_card_goal_analysis Public

    Exploratory Data Analysis of the impact of Red Cards on the Number of Goals scored across 5 years of the major European Football Leagues, using Python with Pandas and Matplotlib libraries.

    Jupyter Notebook

  2. smoker-binary-prediction smoker-binary-prediction Public

    A Binary Prediction of Smoker Status using Bio-Signals for Kaggle's Playground Series. An ensemble stack Neural Network model combining Catboost, XGBoost, LightGBM and Random Forest Classifier models.

    Jupyter Notebook

  3. eifo-data-extraction eifo-data-extraction Public

    A Python script to web scrape EIFO Country Risk & Cover Policies with BeautifulSoup and Selenium and export to Excel.

    Jupyter Notebook

  4. handwritten-character-recognition handwritten-character-recognition Public

    Computer Vison model for custom handwritten character recognition including strikethrough characters.

    Jupyter Notebook

  5. dnd-statblock-generator dnd-statblock-generator Public

    A fine-tuned Llama3-8b model for generating Dungeons & Dragons statblocks.

    Jupyter Notebook

  6. dndwithtoph-eda dndwithtoph-eda Public

    Exploratory data analysis of DnDwithToph using Pandas, Numpy, Matplotlib and Seaborn.

    Jupyter Notebook