EXCEEDS logo
Exceeds
josezh07

PROFILE

Josezh07

Worked on the d2cml-ai/Data-Science-Python repository to deliver two core features focused on extracting insights from financial documents and optimizing machine learning workflows. Developed a pipeline that combines FinBERT-based sentiment analysis with PDF text extraction and summarization, enabling rapid review of financial texts and contracts. Built an ML experimentation suite to benchmark CPU versus GPU training times for both a Fashion MNIST CNN and a DistilBERT toxicity classifier, supporting data-driven resource planning. Leveraged Python, TensorFlow, and Hugging Face Transformers throughout the project, maintaining reproducible Jupyter Notebook workflows to facilitate scaling and future experimentation in deep learning and NLP tasks.

Overall Statistics

Feature vs Bugs

100%Features

Repository Contributions

2Total
Bugs
0
Commits
2
Features
2
Lines of code
10,801
Activity Months1

Work History

June 2025

2 Commits • 2 Features

Jun 1, 2025

June 2025 performance summary for d2cml-ai/Data-Science-Python: Delivered two core features and established a benchmarking framework to inform resource planning. Key business value: faster extraction of insights from financial texts and contracts; data-driven capacity planning for ML workloads.

Activity

Loading activity data...

Quality Metrics

Correctness80.0%
Maintainability80.0%
Architecture80.0%
Performance80.0%
AI Usage50.0%

Skills & Technologies

Programming Languages

Jupyter NotebookPython

Technical Skills

CNNData PreprocessingDeep LearningDistilBERTHugging Face TransformersKerasMachine LearningNLPNatural Language ProcessingPandasPyMuPDFSentiment AnalysisTensorFlowText Summarization

Repositories Contributed To

1 repo

Overview of all repositories you've contributed to across your timeline

d2cml-ai/Data-Science-Python

Jun 2025 Jun 2025
1 Month active

Languages Used

Jupyter NotebookPython

Technical Skills

CNNData PreprocessingDeep LearningDistilBERTHugging Face TransformersKeras