bilalaziz786 Goto Github PK

analysis-of-political-sentiments-on-twitter-using-deep-learning

Aim was to develop a machine learning model which can analyze sentiments on twitter and to predict the winner of Lok Sabha Elections 2019. Web scraping was used for comments and then applied feature extraction, TF-IDF, Word2Vec, ANN and LSTM to improve the accuracy of model. Softmax function was used for multiclass classification. Learning curve was used to select the epochs and batch size in ANN and LSTM. Word cloud was made to select the most important features in the dataset. Random forest classification was selected as the best classifier with the help of PR curve by using micro average for average precision and recall.

ant-bot

Aim was to build a bot which can behave like an ant that collects and provides food for not just itself but also its community. White line sensor was used for line following. Color image processing, ant hill detection and service assessment was done by using opencv library. Pick and place mechanism was done by using standard and micro servo motors.

crud-backend-service

CRUD backend service which consists of a worker (consumer) and the following APIs: get: search in cache first and fallback to the db in case of a cache miss, post, put, delete, submit: submit an async job and return a job_id, results: get the results of a previously submitted job. Points to note: each item in the cache has some TTL set, cache is always in sync with the db (insert / update / delete operations), proper logging in all relevant areas. Tech stack: Python3 + Flask, PSQL, Celery (job scheduling), RabbitMQ (message broker) and Redis (cache).

dbmsproject

Front end and backend are connected through PHP. Signup details, Employee details, etc will be stored in the MYSQL database.

probot

Discord bot that would reply hey to your hi. Add functionality to allow a user to search on google through discord. If the user types !google nodejs, reply with top 5 links that you would get when you search nodejs on google.com Implement functionality to search through your search history. If a user uses !google to search for "nodejs" "apple games" "game of thrones", and after these searches, if user types !recent game, your bot should reply with "apple games" and "game of thrones" Make user search history persistent. Use any storage system to store your searches, so even when you kill your nodejs server and start again, your search history is maintained. You can use any language like Python, Nodejs, Golang etc to implement this.

top-google-apps

weather-app

Simple weather app using Python3 + Flask and AJAX seperately. It takes PINCODE as input and return the weather for today. OpenWeatherMap API is used by creating the account and generating the API key.