Loading repository data…
savanidhene / repository
One of the major projects I have worked on till now outside of curriculum is a Twitter Government Sentiment Analysis. It is not just a regular sentiment analysis from a tweet input but has a lot more functionalities and complexity. To give a brief idea about what it does, the project searches a hashtag and displays real time tweets, the user who tweeted it, total retweet count of that tweet, all the hashtags used in each tweet, and most importantly the sentiment analysis of each tweet (whether it is a positive tweet or negative). The result shows the most recent 200 tweets from the day you want it to be searched from by taking a hashtag and date as input from the user. At the top of the result table, you get the total positive tweets percentage and negative tweets percentage of that hashtag. It is a full-fledged website with attractive frontend and smooth backend developed by me. I have developed the sentiment analysis model using logistic regression algorithm, and sqlite3 for database management. The major libraries I needed in the machine learning part are sklearn for logistic regression, nltk for preprocessing and tweepy for twitter authentication and tweets handling. I used matplotlib and seaborn libraries for result visualization to improve the accuracy of my project. The final accuracy I achieved is 98%. Coming to the website building, I have used Flask as my backend language and HTML, CSS, Javascript for frontend. Using Javascript, I was able to add beautiful scroll-animation effect to my project which gave it a more subtle and pleasing user experience. This project can be very useful for companies wanting to take a quick review on what's being said about their product on social media, especially from a specific period where they have made a significant change in their servicing or any other prospect of their product. They can understand the percentage of people who find their product/service positive or negative within seconds.
One of the major projects I have worked on till now outside of curriculum is a Twitter Government Sentiment Analysis. It is not just a regular sentiment analysis from a tweet input but has a lot more functionalities and complexity. To give a brief idea about what it does, the project searches a hashtag and displays real time tweets, the user who tweeted it, total retweet count of that tweet, all the hashtags used in each tweet, and most importantly the sentiment analysis of each tweet (whether it is a positive tweet or negative). The result shows the most recent 200 tweets from the day you want it to be searched from by taking a hashtag and date as input from the user. At the top of the result table, you get the total positive tweets percentage and negative tweets percentage of that hashtag. It is a full-fledged website with attractive frontend and smooth backend developed by me. I have developed the sentiment analysis model using logistic regression algorithm, and sqlite3 for database management. The major libraries I needed in the machine learning part are sklearn for logistic regression, nltk for preprocessing and tweepy for twitter authentication and tweets handling. I used matplotlib and seaborn libraries for result visualization to improve the accuracy of my project. The final accuracy I achieved is 98%. Coming to the website building, I have used Flask as my backend language and HTML, CSS, Javascript for frontend. Using Javascript, I was able to add beautiful scroll-animation effect to my project which gave it a more subtle and pleasing user experience. This project can be very useful for companies wanting to take a quick review on what's being said about their product on social media, especially from a specific period where they have made a significant change in their servicing or any other prospect of their product. They can understand the percentage of people who find their product/service positive or negative within seconds.
Selected from shared topics, language and repository description—not editorial ratings.
ansible /
AWX provides a web-based user interface, REST API, and task engine built on top of Ansible. It is one of the upstream projects for Red Hat Ansible Automation Platform.
pyenv-win /
pyenv for Windows. pyenv is a simple python version management tool. It lets you easily switch between multiple versions of Python. It's simple, unobtrusive, and follows the UNIX tradition of single-purpose tools that do one thing well.
py-why /
ALICE (Automated Learning and Intelligence for Causation and Economics) is a Microsoft Research project aimed at applying Artificial Intelligence concepts to economic decision making. One of its goals is to build a toolkit that combines state-of-the-art machine learning techniques with econometrics in order to bring automation to complex causal inference problems. To date, the ALICE Python SDK (econml) implements orthogonal machine learning algorithms such as the double machine learning work of Chernozhukov et al. This toolkit is designed to measure the causal effect of some treatment variable(s) t on an outcome variable y, controlling for a set of features x.
graphite-project /
Carbon is one of the components of Graphite, and is responsible for receiving metrics over the network and writing them down to disk using a storage backend.
Prayag2 /
A command line program written in Python to let you backup your dotfiles and switch to other ones in an instant. Works out-of-the box on KDE Plasma!
erning /
gorun is a tool enabling one to put a "bang line" in the source code of a Go program to run it, or to run such a source code file explicitly. It was created in an attempt to make experimenting with Go more appealing to people used to Python and similar languages which operate most visibly with source code.