Projects

A list of some of the projects that I have worked on.

Data Science

• Feedback Classification: An LSTM classifier of customer feedback using keras. [Python,Keras]
• FDA_align: An extension of Feature Decay Algorithms used for data selection.[C language]
• MRFDA: A Map-reduce approach of FDA. [Scala]
• ngramCertainty: A tool for computing alignment entropy. [Scala]
• Parallel Data Preprocess: Scripts for preprocessing parallel data. [Shell script]
• CHRF Statistical Significance: Tool for computing the statistical significance improvements of a translation according to CHRF evaluation metric [Python].
• bioc-alzheimer: Preprocessing and data analysis of DNA microarrays using Bioconductor [R language].

Tools

Language Tools

• Tesseract Postprocess: A tool for postprocessing the output of Tesseract. [Python,Bash]
• romanization_wrapper: A tool for romanazing different languages into latin alphabet. [Python]
• generate_anki: Tool for building Anki decks from a file. [Python]
• Thai Writer: Tool for helping to write Thai words. [Flask, AJAX, Python]
• Language Helper Tool: A tool for language learning. [Python, Flask, JQuery, AJAX, SQlite]

Visualization

• graph_display: A tool for displaying graphs. [Python, Flask, D3]
• Barplot: Barplot visualization of CSV files. [Python, Flask, D3]

Other Tools

• articles2acl: Tool for building a proceedings from the individual papers (in pdf format).[LaTeX,Python]

MOOC

• Machine Learning: Scripts for Machine Learning course in Coursera.
• Data science Specialization Scripts: Scripts for Data science Specialization courses in Coursera.
• Data Science Capstone: Final project of Data science Specialization in Coursera.

Technical Documents

• Machine Learning Guidebook
• Data Science Tools Guides
• Data Exploration Notebooks

Others

• Personal Webpage