Chatbot trained on Microsoft Frames dataset, and deployed on telegram. Pretty bad
- Task 1: Two NLP tasks: Document Classification and Entity Recognition. Using the US Mining Safety Logs data set
- Task 2: Multiclass Document Classification using the
ACTIVITY_CD
labels as classes, and continue to useNARRATIVE
as the documents.
Some R assignments, worksheets aren't included.
Python code for finding synonyms in a corpus of text
- It reads in the corpus file, which is a list of sentences.
- It reads in the common words file, which is a list of stopwords.
- It reads in the test sets file, which is a series of target words to find synonyms for
- Output the target word in test file, and its synonym
This code allows the user to input the name of two files, one containing the units of study and the other containing marks for students. It then takes the data from these files and normalises the marks, and then produces an average mark for each student.
The code above joins all the tables together by matching:
- The customer's phone number with the order's phone number.
- The customer's address ID with the address ID.
- Some other stuff, been too long to remember.