petermartens98 Goto Github PK

amazon-product-reviews-nlp-sentiment-analysis

Python Jupyter Notebook that reads in 10,000 Amazon Product Reviews and then performs an NLP Sentiment Analysis on the data with both the VADER Model and Roberta pretrained model, and then comparing the two models .

autism-diagnosis-predictive-model-web-app

This project analyzes and visualizes Autism diagnosis based off the AQ-10 Questionnaire. Then predictively modelling (Keras/TensorFlow) unseen instances of ASD with up to 98% accuracy. Lastly the Project is implemented into a autism prediction web application.

big-mac-global-prices-eda-2000-to-2022

Jupyter notebook that takes, analyzes and visualized McDonalds Big Mac price data from all countries from 2000 to 2022.

bowling-game-three.js-cannon.js

Originally designed JavaScript (Vanilla framework) bowling game, using three.js for 3D modeling and cannon.js for physics/collisions.

brain-tumor-detection-model

Jupyter notebook that reads in images of brains with and without tumors and then using a sequential Tensorflow/Keras model to predicts and detect tumors given an image.

breadth-first-search-word-chain-coding-solutions

cleveland_guardians_ticket_request_webapp

Cleveland Guardians coding assessment web UI for fictional employee ticket requesrts.

compuer-vision-security-camera-app

Python program utilizing OpenCV and webcam input, and also multiple haarcascade model to detect and display any movement, faces or bodies perceived by the model and then save it to an output folder.

computer-vision-deadlift-counter-app

Python app that uses OpenCV, mediapipe, pandas and tkinter to make an interactive python application that counts the user deadlifts from video input.

computer-vision-image-to-text-and-speech

Python programs that takes in an image path and then using OpenCV and Tesseract returns the image's text/speech

dangpt

Python streamlit web app utilizing the openAI API to run on top of the GPT-3.5-Turbo language model. The app implements a user interface to interact with a chat bot set to Do Anything Now (DAN) mode.

doom-reinforcement-learning-models

Reinforcement Learning / CNN model trained to play Doom video game within the VizDoom gym environment, for a variety of scenarios and difficulties.

double-flip-flop-model-of-sleep-and-dreams-relating-to-eeg-activity

Quant Neuro final project modelling the double flip flop neuronal firing model modulating wake/sleep and then REM/nREM. Models are created in MATLAB and XPP

eeg-schizophrenia-classification-cnn-model

Python TensorFlow / Keras convolutional neural net (CNN) model trained on EEG data to classify schizophrenia vs control subjects with up to 98% accuracy.

email-spam-classification-naive-bayes-ai-prediction-model

Utilizing pandas, numpy, scikitlearn and NLTK, this repository contains a Jupyter notebook for classifying spam and non-spam messages using the Naive Bayes algorithm with up to 98% accuracy on unseen examples.

english-spanish-speech-translation-app

Python programs that takes in microphone audio and then returns audio and text for English and Spanish.

face-detection-opencv-streamlit-web-app

This code uses Streamlit and OpenCV to create a real-time facial recognition web app. It captures video, detects faces using Haar cascade classifier, and highlights them. The app runs until video ends or "Stop" button is pressed. Powered by OpenCV, Streamlit.

fc-cincinnati-attendance-analysis-and-forcasting

This study used Python, NumPy, Pandas, matplotlib, seaborn, statsmodels, scikitlearn, and scipy to analyze the effects of promotional nights, day of the week, and team performance on attendance at FC Cincinnati matches in the 2021 and 2022 seasons. The analysis included data visualization, descriptive analytics, hypothesis testing, and regression.

flappy-bird-featuring-larry-bird

Unity / C# Game built for PC, inspired by Flappy Bird, but replaces bird with Larry Bird

flask-application-login-page

This is a Flask web application that enables users to create accounts using a form, with SQLite as the database. It includes functions for handling errors and queries, and provides users with success/error messages.

flask-sqlite-banking-web-application

This is a Flask banking app with login and dashboard pages, using POST requests to submit data to the server. It displays user balance and transaction history in a table, with deposit and withdraw buttons, and uses flash messages, CSS, and jQuery DataTables. The SQLite database has 'users' and 'transactions' tables.

golang-projects

Collection of Golang projects including: movie ticketing SQL app, file compression program, link webscraper, To-Do list web app

gold-prices-eda-and-visualizations-2000-to-2022

Python Jupyter notebook that take in gold price (open, close, high, low) and volume data from 2000 to 2022. Then using Pandas, NumPy, Matplotlib, Seaborn and Statsmodels.api to clean, analyze and visualize the data.

gpt4-langchain-agents-research-web-app

Python Streamlit web app utilizing OpenAI (GPT4) and LangChain LLM tools with access to Wikipedia, DuckDuckgo Search, and a ChromaDB with previous research embeddings. Ultimately delivering a research report for a user-specified input, including an introduction, quantitative facts, as well as relevant publications, books, and youtube links.

gpt4-programming-assistant

Streamlit web app utilizing OpenAI (GPT-4) and LangChain LLM tools. Application includes an SQLite DB for login/authentication and message storage for later retrieval. Users can upload/embed their own PDF documents for chatbot reference. The user can then interact with a GPT-4 chatbot intended for the user's specified input, context, and scenario.

handwritten-digit-classification

Python program that defines a TensorFlow/Keras model, which is trained on the mnist handwritten digit dataset.

heart-attack-analysis-and-predictive-models

Python EDA looking at the physiological factors contributing to heart attacks for over 300 patients. After looking at multiple ML predictive models, able to predict the likelihood of a heart attack with up to 92%

heart-rate-analysis-and-prediction-models

A Keras NN is trained on ECG data to predict heart rate. It has 3 dense layers, ReLU activation, dropout, Adam optimizer, MSE loss, MAE metric. Test set evaluation, hyperparameter optimization with GridSearchCV, visualizations (correlation matrix, distribution, actual vs predicted).

hello-world-react-google-chrome-extension

huggingface-api-ai-stable-diffusion-image-generator-react-app

Stable Diffusion Image Generation: A captivating React app utilizing the Huggingface API to create unique AI-generated images based on user prompts. Explore endless creativity with the OpenJourney model, enjoy an intuitive interface, and unleash your artistic potential. Utilizing React + Styled Components for a seamless experience.