To produce a search engine that works over the https://portal.uea.ac.uk domain( I will grant you access)

There are 2 parts to this assignment however I have done the first one and the second one is build on the first one so I can send part 1 to you. part 2 is to produce a search engine that works over the [login to view URL] domain. Use the crawler and indexer from the first assignment (or Part 1 of the reassessment) as the starting point. The tasks are: 1. Develop a simple vector model retrieval system using tf*idf term weighting. The system should: a) Have a simple interface to run search queries. This should allow for (i) a single query to be entered from the keyboard, or (ii) a set of queries to be read from a text file. b) Return a ranked list of URLs to screen or file. The file output should be a CSV file with the same structure as the template provided on Blackboard. 2. When you have done this, you should: (i) evaluate your system using a set of training queries that you have devised and then (ii) attempt to improve your results by investigating the effects of: 3. Using stemmers. You could use the NLTK lemmatizer and an implementation of the Porter algorithm (e.g. in NLTK or at [login to view URL]) and compare their effects 4. Giving extra weight to terms occurring in titles, headings, etc. 5. Developing a simple system-centred relevance feedback mechanism. 6. …. anything else that you feel is interesting and appropriate