pranzell Goto Github PK
Name: Pranjal
Type: User
Bio: Nyctophillic, Sacred Geometry. Sustainable Machine Learning
Location: USA
Name: Pranjal
Type: User
Bio: Nyctophillic, Sacred Geometry. Sustainable Machine Learning
Location: USA
This repository contains simple Python programs to get started.
This repository contains use of Classification techniques to make a compatible Netflix Movie Recommender System from scratch. It recommends missing values of "Ratings" by users who have rated atleast some movies.
This repository contains the basics of a Perceptron. Using some example data-sets, it shows how a perceptron works. Each data-set contains two attributes (X1, X2) with a target variable (Y). The model predicts and tells which models are linearly separable and which are not.
This repository dives into the basics of a Deep/Dense Neural Netowrk. It contains an example of building a DNN model from Scratch and also contains an example which uses a KERAS API call. The example contains Energy Efficiency Example which has 8 inputs and 2 output responses.
This repository dives into the basics of a Convolutional Neural Networks. And also shows usage in some examples.
This repository dives into the basics of a Recurrent Neural Netowrk. It contains an example of a RNN network using Keras API to predict: (i). A single character following a series of characters, (ii). A word following a series of words(sentence). Also it contains the usage of LSTM networks.
This repository dives into the basics of a Natrual Language Processing. It contains different kind of tokenization, removal of stop words, lemmatizing, POS tagging, Custom POS Tagging using Brill Tagger, Chunking.
This repository dives into the basics of a Word2Vec Module. It shows the usage of word2vec in converting words into vectors for processing in ML Models.
This repository dives into the basics of a Word Mover's Distance Module. It shows us how to use WMD Model to predict semantic similarity between two sentences.
This repository dives into the basics of a Doc2Vec Module. It shows us how to compute similarity between two documents.
This repository dives into the basics of a TF-IDF Module. It shows us how to compute similarity between two documents.
This repository contains few advanced assignments/examples in Python to get you started towards Data Science field. It also contains two PDF files detailing the mathematical theorems used in the examples.
This repository dives into the basics of a BM-25 Module. It shows us how to compute similarity between two documents.
This repository shows us how to compute similarity between a Sentence and few paragraphs. This also explains how to point to a particular paragraph in a document from where the question was asked.
This repository shows us how to compute similarity between a Sentence and many Documents. Document giving the best score on similarity index as according to different models (BM_25, TFIDF, Doc2Vec, WMD) will be the actual document from where the Sentence has been taken.
This is a Q&A ChatBot based on NLP statistics which responds to statistical based Questions on Indian Premier League Season 1 (2008). This model is based on supervised learning algorithms with limited approach to user questions.
This is a Q&A ChatBot based on NLP statistics which responds to statistical based Questions on Indian Premier League Season 1 (2008). This model is based on supervised learning algorithms with limited approach to user questions.
This is a Q&A Conversation Bot based on NLP tools which responds to user queries by pointing to a paragraph from a bunch of documents. This in turns an unsupervised learning problem into supervised learning using negative sampling.
This repository contains examples in Python to get you started towards Data Science field. It contains examples related to use of Python's 'NUMPY' package.
This repository contains few examples related to use of Python's 'PANDAS' package. Deals with day-to-day usage of Pandas in exploring Datasets.
This repository contains examples related to use of Python's 'PANDAS' package at an expert level. Involves exploring, group-by, drawing plots, generating inferences, etc.
This repository contains use of Python to explore data-sets. It consists of various analysis, plotting, visualization (Heat Maps, Boxplots, etc) to draw inferences from a data given.
This repository contains use of Machine learning models to understand Regression. In this file, it explores the use of sci-kit learn to understand Linear Regression. It further explains Cross Validation technique to use K-Folds. It also explains Ridge and Lasso Regression techniques.
This repository contains use of Linear Regression model to solve some industry problems. Each example gives us a brief about the problem statement and the data-set involved.
This repository contains use of Machine learning models to understand Classification techniques such as Logistic Regression, Comaprison between Linear & Logistic models, Decision Trees, Random Forest algorithms. It also contains the understanding of Label Encoding the data-set.
Applying "ThePhish: an automated phishing email analysis tool" on parsed emails.
Need access to Twitter data? Struggling with managing a developer account? This will help you get started and have access to almost 20 years of historical tweets.
This repo deals with open-sourced exploration for extracting meta-data from PDF files.
This tells about the KNN algorithm coded in Python from Scratch (Mathematical approach) and using sklearn libraries
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.