Ezra Kipchirchir Bett

Data Scientist skilled in Python, NumPy, Pandas, with a strong foundation in machine learning frameworks such as Keras, Pytorch, Scikit-Learn and TensorFlow. Expertise in SQL and data visualization tools like Matplotlib, Seaborn, Plotly, and Tableau, complemented by experience in regression, classification, and clustering techniques. Proficient in using Jupyter Notebooks, Git, Docker, and AWS for development and deployment, with a focus on big data processing using Apache Spark and PySpark. Proven ability to manage projects effectively while maintaining attention to detail and fostering collaboration among team members.

Car parking detection using computer vision, https://github.com/dev-ezzy/Car-parking-space-detection-using-computer-vision.git, This project uses computer vision to detect and monitor parking space availability in real time from CCTV footage. By applying object detection and image processing techniques, the system can identify vehicles, map them to predefined parking slots, and determine whether each slot is occupied or vacant.

Traffic-weather analysis, https://github.com/dev-ezzy/TrafficWeather-analysis.git, This repository is a collaborative project where we analyze the impact of weather conditions on traffic patterns using data science techniques. Our goal is to uncover how factors like rain, temperature, wind, and humidity influence traffic flow, congestion, and accident rates.

Recommender system, https://github.com/dev-ezzy/Movie-Recommendation-System-.git, Machine learning project aimed towards making a model to solve the problem of recommending movies to consumers enjoying the film industry products. 

Pump status prediction model, https://github.com/dev-ezzy/Classification-model.git, An intermediate intense machine learning approach to predict binary and ternary classification problems using the most efficient algorithms.

House price prediction model, https://github.com/dev-ezzy/House_price-prediction-model.git, Utilize historical real estate data for training, apply regression techniques to establish correlations, and create a predictive model for accurate price predictions in the housing market. The project aims to assist homebuyers and sellers by providing data-driven insights into property values.