mihaelagrigore Goto Github PK
Name: Mihaela Grigore
Type: User
Company: Intrum
Bio: Data Scientist
Twitter: mishki
Location: Spain
Name: Mihaela Grigore
Type: User
Company: Intrum
Bio: Data Scientist
Twitter: mishki
Location: Spain
In this notebook I go thoroughly through the normal Data Wrangling process performed on any new and potentially messy data. It includes analysis of missing data, uni and bivariate analysis, removal of data that is not useful and some data engineering.
Building a custom architecture Convolutional Neural Network in PyTorch and using the resulting model to classify the Fashion MNIST dataset.
Facial Recognition with Keras, FaceNet and Inception model using Siamese Networks and transfer learning.
Building a 50-layer ResNet model from scratch using Tensorflow and Keras. Training it first on CPU (very slow), then on Kaggle GPU (for a significant improvement in speed).
Introduction to Exploratory Data Analysis (EDA). Made for beginners. Shows how to look at data to uncover patterns.
Huggingface transformers: Finetuning DistilBERT on a toxic comment binary classification task.
Stuck in a weak human body. Help the microbiota recover and wander out these gutsy meanders !
A quick demo of network analysis and network visualisation.
Sentiment analysis performed on tweets. Comparison of performance of a few popular libraries: TextBlob, VADER and Flair. Also includes some pretty plots using Keppler.
Calculate topic coherence for topic models. Discover the semantic structure of texts by examining statistical co-occurrence patterns within a corpus of training documents (tweets) using Latent Dirichlet Allocation.
Real Time object detection using browser deployed Tensorflow.js model
The tool I'm using here for scraping tweets: snscrape. Snscrape is a popular tool with social scientists for Tweets collection, at least in 2021. Apparently, it bypasses several limitations of the Twitter API. The prettiest thing is that you don't need Twitter developer account credentials (like you do with Tweepy, for example)
Social media scraping and NLP for research | Scraping unlimited number of historical tweets using the Academic Track of Twitter Developer API. Exploring the metadata obtained. Text analysis using NLP.
I wanted to see a notebook / tutorial that would take me through the basics of working with time series. Most notebooks I found were not very rigorous. So I wrote my own. This is: 1. a good starting point for understanding time series data and how it differs from problems with other type of tabular data 2. a cookbook to be used for exploration when starting to work with a new dataset
Time series prediction (demand forecast) on a Kaggle competition dataset using smoothing methods, Prophet (+Neural Prophet), ARMA (and several of its versions).
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.