-- Apr 27 In-Class Exercise

((resource:Screen Shot 2022-05-02 at 11.22.39 AM.png|Resource Description for Screen Shot 2022-05-02 at 11.22.39 AM.png))

-- Apr 27 In-Class Exercise

    "business": 601,
    "california": 95,
    "return": 607,
    "tax": 354

    score = 0
    for term in query:
        ftd_ = queryNew.count(term) * math.log(1 + avg / len(new_query), 2)
        
        num = math.log((1 + graph[term] / n), 2) + ftd_ * math.log((1 + n / graph[term]), 2)
        den = (ftd_ + 1)
        score += num / den
    return round(score, 3)
 

import math graph = { "business": 601, "california": 95, "return": 607, "tax": 354 } n = 250000 avg = 4 def getScore(queryNew, query, graph, avg, n): score = 0 for term in query: ftd_ = queryNew.count(term) * math.log(1 + avg / len(new_query), 2) num = math.log((1 + graph[term] / n), 2) + ftd_ * math.log((1 + n / graph[term]), 2) den = (ftd_ + 1) score += num / den return round(score, 3) new_query = ["california", "business", "tax"] given_query = ["california", "business"] print(getScore(new_query, given_query, graph, avg, n)) new_query = ["california", "business", "tax", "return"] print(getScore(new_query, given_query, graph, avg, n) ) 11.039 10.035

-- Apr 27 In-Class Exercise

((resource:apr27_dfr.txt|Resource Description for apr27_dfr.txt))

-- Apr 27 In-Class Exercise

1. id = 3 t't,d = 1 * log (1+ 4/3) = 1.223 (log (1+95/250000) + 1.223 * log ( 1 + 250000/95) ) / 1.223 +1 = 6.246 buisness (log (1+ 601/250000) + 1.223 * log ( 1 + 250000/601) ) / 1.223 +1 = 4.778 california + buisness = 11.024 2. id = 4 t't,d = 1 * log (1+ 4/4) = 1 (log (1+95/250000) + 1 * log ( 1 + 250000/95) ) / 1 +1 = 5.68 (log (1+ 601/250000) + 1 * log ( 1 + 250000/601) ) / 1 +1 = 4.353 california + buisness = 10.033