Text-Classification-With-LogisticRegression

• Reading the dataset and removing unnecessary characters
• Creating dictionaries representing 2 different topics from the read dataset
• Training the model for these two dictionaries on the training dataset
• C impelemantation of Adam, Stochastic Gradient Descent, Gradient Descent optimization techniques
• Evaluation of the model on the test dataset
• Using T-SNE imaging for comparison of optimization techniques and comparison of loss graphs