Skip to content
View nykolai-d's full-sized avatar
9 followers · 11 following

Block or report nykolai-d

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.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

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

Report abuse
nykolai-d/README.md

Hi, I’m Nicolas Diaz-Durana. I am a mathematician with a Master's degree in linguistics. I’m fluent in Python, and deeply interested in Natural Language Processing and Machine Learning, as well as Statistics and data-driven analysis.

Some Python libraries that I feel confortable with are NLTK, TensorFlow, Pandas, Numpy, Scipy, Matplotlib, Sympy and Scikit-Learn TextBlob. I know my way around R, Java and SQL.

Here, you will find works that I have developed in Python, R and LaTeX, the latter focusing on some advanced math and physics topics. I'm into projects that can potentially integrate diverse domains of knowledge. I speak, read and write in English, Spanish and French.

I’m looking to collaborate on anything that tackles with real-life data-driven problems, especially (but not limited to) Natural Language Processing. Feel free to contact me anytime through my email: nicolasdiazdurana@gmail.com

Pinned Loading

  1. fake_news_detection fake_news_detection Public

    This project trains a Long Short Term Memory (LSTM) network to detect and classify fake news.

    Jupyter Notebook 11 4

  2. FFT FFT Public

    The Fast Fourier Transform With One Application In Audio Correction

    Jupyter Notebook 1

  3. web-scraping-legal-entities-usa web-scraping-legal-entities-usa Public

    Web scraping of wikipedia page regarding the legal entity types per state, territory or commonwealth in the US. We use Beautiful Soup. Text is then preprocessed using NLTK, and most common words ar…

    Jupyter Notebook

  4. time-series-decomposition time-series-decomposition Public

    Time series decomposition using pandas-datareader and dtw

    Jupyter Notebook

  5. random-forests-breast-cancer-prediction random-forests-breast-cancer-prediction Public

    We use the Breast Cancer Wisconsin Diagnostic Data Set to train and test the model that classifies whether a tumor with certain characteristics is a malignant or a benign tumor.

    Jupyter Notebook

  6. most_common_words_in_news most_common_words_in_news Public

    We create a function that takes the data from the csv file and prints the five classifications with a list of the x most repeated words for each classification.

    Jupyter Notebook