Skip to content
View cintia-shinoda's full-sized avatar
53 followers · 63 following

Highlights

Block or report cintia-shinoda

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
cintia-shinoda/README.md

Hey! I'm Cintia I. Shinoda

Data Scientist · Database Dev · Machine Learning

Connect with me:

LinkedIn Hugging Face Kaggle Instagram Portfolio

Featured Projects

São Paulo's Transit Network Vulnerability and Resilience Analysis

Map of the top 10 critical nodes according to degree, betweenness and closeness centrality metrics

Analysis of São Paulo's public transit network vulnerability and resilience using Graph Theory and Network Science on SPTrans GTFS data. 22K+ nodes, 29K+ edges. Identifying critical bottlenecks and proposing strategies for improving the system's robustness and efficiency.

Python NetworkX Geopandas SciPy cKDTree pyarrow GTFS Graph Theory Network Science

Dataset Model Space

Astronomia RAG

Demo CLI

Astronomia RAG is a Retrieval-Augmented Generation (RAG)-based question-and-answer (FAQ) system focused on Observational Astronomy.

RAG LLM Astronomy FAISS LangChain Mistral 7B Instruct Python


São Paulo's Legislative Discourses Sentiment Analysis

topic x sentiment Heatmap

NLP pipeline for processing and analyzing Brazilian legislative discourses. The pipeline includes data collection, preprocessing, sentiment analysis, topic modeling, text summarization, and data visualization.

Python NLP Sentiment Analysis Topic Modeling Text Summarization Data Visualization Transformers Streamlit

Professional Background

E-VAL Tecnologia - São Paulo - São Paulo - Brazil

  • Database of a Digital Signature Management System for Hospital Israelita Albert Einstein

SQL SQL Server Database Modeling Data Analysis


  • Diabetes Predictive Model for Central Nacional Unimed - CNU

SQL PL-SQL Predictive Modeling


HandsOn.TV - Mountain View - California - USA

Analytics Analysis

Analytics Data Analysis Excel Data Visualization

Education:

Ongoing:

School / Institution Workload Progress
Data Science Bachelor's Degree UNIVESP 3500h 97.71%
Robotics Specialization UFV 420h 40%
Advanced Python Specialization UTFPR 360h 33%
Statistics IV Prandiano 50h 60%

Tech Stack:

Microsoft SQL Server PL-SQL MongoDB DuckDB

Python Numpy Pandas Polars Matplotlib Plotly Streamlit Scikit Learn OpenCV GeoPandas NetworkX Seaborn NLTK spaCy Transformers

R Tidyverse

Power BI Looker

Languages:

Language Proficiency
🇧🇷 Portuguese Native
🇺🇸 English Advanced
🇯🇵 Japanese Beginner (JLPT N5)
🇫🇷 French Beginner

Areas of Interest:

Data Science · Artificial Intelligence · Operations Research · Robotics


GitHub Stats:

Profile views

Top Languages

Pinned Loading

  1. public-transit-graph-theory public-transit-graph-theory Public

    Vulnerability and Resilience of São Paulo's Public Transit Network: a Topological Analysis based on Graph Theory. Developed as part of the Final Course Project (TCC) in Data Science B.Sc. at UNIVES…

    Jupyter Notebook 1

  2. astronomia-rag astronomia-rag Public

    Astronomia RAG é um sistema de perguntas e respostas (FAQ) sobre Astronomia Observacional baseado em Retrieval-Augmented Generation (RAG).

    Python 1

  3. legislative-nlp-pipeline legislative-nlp-pipeline Public

    Automated pipeline for sentiment and topic analysis in plenary sessions of the São Paulo City Council, using Natural Language Processing (NLP) and Machine Learning techniques.

    Python