akankshadara Goto Github PK

akankshadara.github.io

A lightweight, customizable single-page personal portfolio website template built with JavaScript and Sass

ark-tweet-nlp-python

Simple Python wrapper around runTagger.sh of ark-tweet-nlp

audio-analysis-for-weighting-words-of-a-speech

Assignment under the course Information Retrieval

awesome-deep-learning-papers

The most cited deep learning papers

bits-pilani-thesis-template-latex

LaTeX Template for Reports required of BITS Pilani students (Thesis, Practice School, PhD, Projects - Study, Lab, Design)

competetive-programming

cricket-analytics-using-opencv-and-machine-learning

The project was to retrain the Haar Classifier in the Viola Jones algorithm to identify players on the field and track their positions.

data

Data and code behind the stories and interactives at FiveThirtyEight

data_mining_lab

Python Data Mining

dataquest_practice-codes

Data Science using numpy,pandas, matplotlib, sklearn

davies_bouldin_index_kmeans

This repository contains a naive implementation of Davies Bouldin Index used to find the optimum number of clusters in K-Means clustering.

deception-detection

Detecting Fake hotel reviews from Genuine ones. Used TripAdvisor Hotel reviews.

deeplearning4nlp-tutorial

Hands-on tutorial on deep learning with a special focus on Natural Language Processing (NLP)

diabetes_prediction_deep_learning

This repository contains code used for prediction of diabetes on the Pima Indiana Diabetes dataset using neural networks.

drishti_ocr_tesseract

Drishti is a software that converts printed Hindi text to Braille. Tesseract Open source library is used as an OCR to scan and convert printed Hindi text to unicode characters. These characters are encoded into binary strings which are used to represent alphabets in braille. Arduino is used to display the characters by blinking of corresponsing LED's. For the functioning of this software, You should have installed Tesseract and Leptonica and trained it for Hindi. You can download the dependencies using this Shell script: [Dependencies.sh](https://github.com/rahulchhabra07/Drishti/blob/master/Dependencies.sh). After training, feed a JPEG image file containg printed Hindi text to the Python file. This creates a dialog box showing, the original image and translated text. Now click on next for displaying the text using arduino board.

erplag-compiler

functional_programming_scheme

Contains codes for small functions implemented using Scheme

geotagging_images

A python script to extract the exif data from an image file. The latitude and longitude information from this exif data is used to specify the street address of the image.

hmv-ensemble-for-disease-prediction

ir-implementation

Implementation of basic Information Retrieval systems in Python

microprocessors_fire_alarm_system

This system checks for abnormal smoke content in a room every two seconds. Under abnormal conditions it throws open two doors and two windows and opens a valve that releases the gas to put-out the fire. An Alarm is also sounded; this alarm is sounded until the smoke level in the room drops to an acceptable level. The smoke detection system is made up of two smoke sensors placed on the ceiling of the room. When the smoke level comes back below the danger level, the doors, windows and valves are closed.

mips-verilog

Datapath implementation of MIPS architecture in Verilog Tested on : ModelSIM

mm_task

nlp-progress

Repository to track the progress in Natural Language Processing (NLP), including the datasets and the current state-of-the-art for the most common NLP tasks.

opencv

Open Source Computer Vision Library

practical_nlp_in_pytorch

A repository containing tutorials for practical NLP using PyTorch

recruiting-exercises

Deliverr coding exercises for engineering

sarcasm_detection_twitter

Sarcasm detection is a particularly difficult task even for humans. This repository contains the implementation of a research paper by Ashwin Rajadesingan in python ML libraries.

scikit-learn

scikit-learn: machine learning in Python

spell_checker

The spell checker works by: reading in and tokenizing a vocabulary of correctly spelled words, reading in, cleaning, and tokenizing the piece of text we want spell checked, comparing each word (token) in the piece of text with each word in the vocabulary and returning the ones that weren't found (incorrectly spelled words). The file dictionary.txt contains a sequence of correctly spelled words, which we'll use to seed our vocabulary. The file story.txt is a piece of text containing some misspelled words. In the following code cell, we added the spell checker we wrote so far from the previous mission.