countvectorizer

For learning Purposes

Graduation Project/Sentiment Analysis in Turkish Film Reviews

Spam message detection using classifier

Created Hate speech detection model using Count Vectorizer & XGBoost Classifier with an Accuracy upto 0.9471, which can be used to predict tweets which are hate or non-hate.

What is the difference between a data scientist and a data analyst? An NLP approach.

This is the Movie Recommendation System project using a Content-Based recommender system trained on more than 5000 movies for generating movie recommendations based on user search.

Grocery Recommendation on Instacart Data

Using content-based approach to construct a suggestion for films. Films based on user feedback are recommended. By the machine learning model, all connected and equivalent films are suggested for the consumer.

This competition is hosted by Kaggle https://www.kaggle.com/c/nlp-getting-started/overview. I participated in the competition in order to try my hands on the field of Artificial Intelligence known as Natural Language Processing.

Predicting Tags for Stack Overflow

Assignment-11-Text-Mining-01-Elon-Musk, Perform sentimental analysis on the Elon-musk tweets (Exlon-musk.csv), Text Preprocessing: remove both the leading and the trailing characters, removes empty strings, because they are considered in Python as False, Joining the list into one string/text, Remove Twitter username handles from a given twitter text. (Removes @usernames), Again Joining the list into one string/text, Remove Punctuation, Remove https or url within text, Converting into Text Tokens, Tokenization, Remove Stopwords, Normalize the data, Stemming (Optional), Lemmatization, Feature Extraction, Using BoW CountVectorizer, CountVectorizer with N-grams (Bigrams & Trigrams), TF-IDF Vectorizer, Generate Word Cloud, Named Entity Recognition (NER), Emotion Mining - Sentiment Analysis.

Practice Rust by making Vectorizer

This project is to compare the F1 scores on performing sentiment analysis on reviews using various methods. We test the efficeintcy of TfidfVectorizer and CountVectrorizers when used with Multinomial Naive Bayes and SVC respectively.

Used NLTK library from text pre-processing, Data Visualisation and Analysis done with matplotlib, used sklearn CountVectorizer and Tfidf transformer for feature extraction from text, then used Linear SVC algorithm to train the ML model. Got 99% accuracy.

A Naive Bayes spam/ham classifier based on Bayes' Theorem. A bunch of email subject is first used to train the classifier and then a previously unseen email subject is fed to predict whether it is Spam or Ham.

Classification of emails received on a mass distribution group

The aim - is to develop a model that will give accurate predictions for the customer's test sample, but the training sample for is not given. It should be collected by parsing

linebot messengerbot @Mango by fastapi

Hire the Perfect candidate. HackerEarth Competitions solution.

SMS SPAM FILTERING

Silicon Valley (TV Show on HBO) language analysis

Spam Detection – Cluster SMS messages to “Spam” and “Ham” (Kaggle Challenge)

This project suggests you the list of movies based on the movie title that you have entered. It uses Count Vectorizer (Text-Feature Extraction tool) to find the relation between similar movies.

Malware classification using Extreme Gradient Boosting - XGBoost, CountVectorizer, TruncatedSVD

Named Entity Recognition , Emotion Mining in Python

Tugas Akhir - Mus Priandi

Develop Machine Learning models to predict sentiments on COVID-19 tweets.

This case study shows how to create a model for text analysis and classification and deploy it as a web service in Azure cloud in order to automatically classify support tickets. This project is a proof of concept made by Microsoft (Commercial Software Engineering team) in collaboration with Endava http://endava.com/en

This is an NLP and Flask-based application which involves predicting the sentiments of the sentences as positive or negative. The classifier is trained on a huge dataset of IMDB movies reviews. The model is then hosted using Flask to be used by end-users.