Skip to content
View cybereptilia's full-sized avatar

Block or report cybereptilia

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.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

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

Report abuse
cybereptilia/README.md

Rosaliz Garcia / cybereptilia

Aspiring Machine Learning Engineer, currently building expertise through data analytics and engineering projects.

Python Scikit-Learn TensorFlow Pandas Matplotlib SQL


About Me

Recent CS grad (Data Science concentration) seeking Data Analyst / Junior Data Engineer roles, building toward a long-term goal in machine learning.


Featured Engineering Projects

Healthcare Claims Data Pipeline

End-to-end data pipeline that generates synthetic healthcare claims data, validates records, loads them into PostgreSQL, and produces analytics-ready reports.

Concepts

  • ETL pipeline design
  • SQL analytics views
  • data validation & reject handling
  • indexing and query optimization
  • automated pipeline execution

https://github.com/cybereptilia/healthcare-claims-pipeline


Predictive Maintenance SQL Performance Study

Time-series database experiment (~600k rows) demonstrating PostgreSQL query planner behavior and index selectivity.

Concepts

  • composite index design
  • cost-based query optimization
  • sequential vs index scan behavior
  • EXPLAIN ANALYZE benchmarking

https://github.com/cybereptilia/predictive-maintenance-sql


Current Work

  • MedTracker Frontend — React + Tailwind integration for Front-end
  • ML Study Series — Implementing algorithms from Hands-On Machine Learning with Scikit-Learn, Keras & TensorFlow
  • Data Visualization Projects — Interactive dashboards using Matplotlib, Seaborn, and Plotly

Self-Study & Practice Projects

Iris Project — From-Scratch Classifier

Cross Entropy Loss
Epoch Loss Convergence
Validation Accuracy

Manual Softmax classifier using gradient descent and cross-entropy optimization achieving 96.67% accuracy.


Real Estate Price Prediction — Regression Pipeline

Feature Correlation Heatmap

Complete regression pipeline including EDA, feature engineering, model training, and evaluation.


Evaluation Metrics — MNIST Digit Classifier

Precision vs Recall Curve
Precision Recall vs Threshold

Binary classification evaluation including precision-recall tradeoffs and ROC analysis (AUC ≈ 0.99).


Toolchain

Languages
Python • SQL • JavaScript • C++ • Java

Libraries & ML Frameworks
NumPy • Pandas • Scikit-Learn • TensorFlow • Keras • Matplotlib • Seaborn

Data Tools
PostgreSQL • JupyterLab • Google Colab • Excel

Workflow
Git • GitHub • Virtual Environments

Operating Systems
Rocky Linux • Ubuntu • Windows

Popular repositories Loading

  1. real-estate-ml real-estate-ml Public

    End-to-end regression pipeline: EDA, feature engineering, Random Forest, GridSearchCV - Hands-On ML exercise.

    Jupyter Notebook 1

  2. Chapter-3-Evaluation-Metrics Chapter-3-Evaluation-Metrics Public

    Exercises from Chapter 3 of Hands-On Machine Learning with Scikit-Learn, Keras & TensorFlow - Binary classification, precision/recall, ROC/AUC evaluation.

    Jupyter Notebook 1

  3. Medicine-Tracker-Front Medicine-Tracker-Front Public

    Responsive medication tracking web app - React + Tailwind. CS capstone; frontend and QA role.

    JavaScript

  4. cybereptilia cybereptilia Public

  5. iris_project iris_project Public

    From-scratch Softmax classifier using gradient descent and cross-entropy - Hands-On ML exercise.

    Jupyter Notebook

  6. predictive-maintenance-sql predictive-maintenance-sql Public

    PostgreSQL query planner study on ~600k time-series rows - composite indexing, selectivity, and EXPLAIN ANALYZE.

    Python