Letter based language classification: Data preprocessing is done using npm nlp libraries because some languages were like Polish were not present in the python libraries and also because I am good at it.
Folder Structure: Algorithm Code: Naive Bayes and kNN implementation Algorithm Wise Output: prediction results algorithm wise Centroid: Approach 1 data set Code: Code related to tfidf values DataCleaningType2: data cleaning code type 2 as mentioned in report
Letter based language classification: Data preprocessing is done using npm nlp libraries because some languages were like Polish were not present in the python libraries and also because I am good at it.