Cristhian Castro

Data Scientist with experience in Python, SQL, Data Analysis, Machine Learning, Power BI, among other technologies. I have a background in chemical engineering and quality control that has helped me in the analysis and optimization of processes that occur in the data industry.

I am a highly adaptable individual who feels comfortable in different roles, willing to learn and unlearn. I enjoy working in teams, sharing knowledge, asking for help, and offering support when necessary. I am passionate about constantly learning and always seeking new opportunities to expand my knowledge and skills.

Email: cristhiancastro001@gmail.com / LinkedIn / GitHub

Projects

Sentiment Analysis and Text Classification of Hotels Reviews
September 2023
Skills and Tools:
Natural Language Processing (NLP) · Google Cloud Platform (GCP) · Apache Airflow · Text Classification · Python · Data Science · System Deployment · Data Warehousing · Extract, Transform, Load (ETL) · Data Analytics · Data Engineering · Data Analysis · Microsoft Power BI
Activities:
- Data extraction from Google Maps and Yelp API.
- Data cleansing and warehousing using Google Cloud Platform.
- Use of Power BI and Python visualization libraries to look for insights.
- Development, deployment and demonstration of Machine Learning models and data visualization via Streamlit Apps.
Repository Deployment



Analysis and Visualization of Internet usage in Argentina
August 2023
Skills and Tools:
Data Extraction · Plotly · Matplotlib · Seaborn · Data Visualization · Data Analytics · SQL · Dashboards · Data Analysis · Microsoft Power BI · MySQL
Activities:
- Data extraction, cleansing and transformation from a governmental API using Python libraries like Pandas and requests.
- Exploration, visualization and analysis of the variables of the different tables using Matplotlib, Seaborn and Plotly.
- Building ER model, dashboards, defining metrics and KPI's with Power BI and DAX.
Repository



Content-Based Movie Recommendation System
July 2023
Skills and Tools:
Matplotlib · Seaborn · Python · Data Cleaning · Scikit-Learn · FastAPI · Data Wrangling · Recommender Systems · System Deployment · GitHub · Machine Learning · Pandas (Software) · NumPy
Activities:
- Management and data cleaning of a dataset related to the film industry using Python libraries such as Pandas, NumPy and ast.
- Development of a recommendation model through vectorization, dimension reduction and cosine similarity.
- Deployment of the application with Render and an API built with FastApi.
Repository Deployment

Experience

Internet Ads Assessor
Feb 2024 - Present
Responsabilities:
- Reviewing online advertisements in order to improve their content, quality and layout.
- Providing feedback and analysis on advertisements found in search engine results.
- Providing ratings on ads relevance to the search terms used.
- Measuring how appropiate the ads are for the target audience.