Muhammad Usman's repositories
Classification-IBM-Project
The dataset is about past loans. The loan_train.csv data set includes details of 346 customers whose loans are already paid off or defaulted.
coursera-test
Coursera test repository
R-Programming
Various R solutions
SVM-Boosting-DTree-Twitter-Sentiment-Analysis-on-Twitter-Dataset
What is the relationship between airline sentiments and airlines? What is the reason for the negativity mentioned in the dataset? What is the relation of time with sentiments? Which model is best for sentiment analysis when we do ensemble learning?
Text-mining-and-NLP-using-1.6-million-dataset
1. Explored and prepared the data (Tokenization, Stemming, Stopwords, visualization, etc.) 2. Build a BOW and trained a KNN, Decision Tree, and SVM model 3. Evaluated the above models (confusion matrix, accuracy, classification report, etc.) 4. Used word2vec and build a CNN model 5. Compared the results with all above.