Alvaro Mejia
Alvaro Mejia
Data Scientist | Python, SQL | Machine Learning & Big Data Enthusiast
Hi! I'm Alvaro, and I'm looking for an entry level position in the Data Science field.
Are you looking for a data analyst with a passion for uncovering meaningful insights from complex datasets? You're in the right place. I'm a data enthusiast with a proven track record of transforming raw data into actionable intelligence.
Through a combination of technical proficiency and a keen analytical mindset, I've been working on diverse projects that got interesting insights from diverse datasets. Explore my portfolio to witness the power of data storytelling.
PROJECTS
Some examples of projects I've been working on. I basically use Python and a bit of SQL.
You can also check these projects in detail on my GitHub profile.
Cars Price Prediction Modelling
Develop a Streamlit app that includes an ML model capable of predicting the cars prices attending to different parameters:
-
Cleaned and transformed raw car listings data for ML modeling.
-
Conducted EDA to identify correlations, outliers, and key predictors using Feature Importance.
-
Developed regression models (Linear Regression, KNN, Random Forest, Decision Trees, Gradient Boosting) to estimate car prices.
-
Built a Streamlit app for interactive visual exploration.
-
Currently extending the project to include model deployment via FastAPI and Docker for real-time predictions.
Spanish Electric Network Data Analysis and Energy Demand Prediction
Design a Streamlit app that allows us to navigate and visualize the data of the Spanish Electric Network (REE), using their API:
-
Design the database.
-
Design the ETL process to fetch and transform the data, keeping the DB updated.
-
Perform EDA and outliers analysis to get the data ready for visualization and for later ML models.
-
Develop the application in Streamlit to visualize data: energy demand, balance, generation and interchanges with other countries.
-
Develop different ML models to predict the country energy demand.
SpaceX Data Analysis for ML Predictive Model
This is the final capstone of the IBM Data Science Certificate.
The goal is to develop a Machine Learning model to predict if the first stage of a SpaceX rocket will land successfully, and therefore recovered. This project has several stages:
-
Data collection through SpaceX API and web scraping.
-
Perform data wrangling (data cleaning).
-
Exploratory Data Analysis (EDA) using visualization and SQL.
-
Build interactive visual analytics: a map with Folium and a dashboard with Plotly DASH.
-
Predictive analysis using classification models (Logistic Regression, SVM, Decision Tree and KNN): optimize hyperparameters and evaluate models accuracy.
All Jupyter Notebooks and Python files are available on GitHub.
My foundation in Data Science
Since 2023, I've been developing my skills in Data Science, Machine Learning and AI:
-
The basics of Data Science and its methodology.
-
ETL (Extract-Transform-Load): collect, clean, summarize and prepare data with pandas and numpy in Python.
-
Exploratory Data Analysis (EDA) and feature engineering for preparing the data and getting insights.
-
Understand Relational Database (RDB) concepts and execute SQL queries for data analysis.
-
Inferential and descriptive statistics in Python for Exploratory Data Analysis (EDA).
-
Advanced visualization techniques in Python with matplotlib, seaborn and plotly.
-
Interactive visualization tools with Folium for geospatial data.
-
Streamlit and Plotly Dash for building interactive dashboards and functional applications.
-
Application of different Machine Learning (ML) techniques and algorithms for regression, classification and clustering problems.
-
Deep Learning techniques, applying Neural Networks with TensorFlow and keras.
-
Big Data with pyspark.
-
Prompt Engineering to optimize the time and resources to get the best responses in LLM's like ChatGPT, Gemini, Copilot, etc.
-
Developing apps using Flask in Python.
#Python #SQL #GitHub #ArtificialIntelligence #AI #DataScience #MachineLearning #WebScraping #pandas #NumPy #matplotlib #seaborn #plotly #Folium #Streamlit #TensorFlow #keras #pyspark #JupyterNotebooks #DataVisualization #DASH #Dashboards #DeepLearning #PromptEngineering #ChatGPT #Flask
CERTIFICATIONS
Here, you can find the courses and certifications I've completed regarding Data Science.
Data Science & AI
HACK A BOSS - Bootcamp
This certification is proof of my work during the 6-months intensive bootcamp in HACK A BOSS, learning about Python programming, SQL and databases, statistics, Machine Learning, Big Data and Streamlit among other popular tools and techniques in the Data Science world.
