ProfPedia/data_structure.py at master · felixwqp/ProfPedia · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
from collections import defaultdict
import math
import sys
import numpy as np

class Paper:
  def Paper(self):
      self.title = ""
      self.date = 0
      self.abstract = ""


class Professor:
  def Professor(self):
    self.name = ""
    self.homepage_url = ""
    self.university = ""
    self.field = []


prof_to_info_map = {}
prof_to_paperids_map = {}
profs_to_score_map = {}
paperid_to_vector_map = {}
paperid_to_words_of_title = {}
inverted_index = {}
docLen = {}


def getData():
  #fron test;


def preprocesss(doc_str):
  #output: list of tokens
  pass


def inverted_index(doc):
  pass


def construct_vector_space_model(doc_str):
  #output: word_weight_vector
  pass


def get_score_for_paper(query, paperid):
  #output: score for paperid
  paperVector = paperid_to_vector_map[paperid]
  titleSet = paperid_to_words_of_title[paperid]
  query  = preprocesss(query)
  queryLen = float(0)
  queryDict = defaultdict(lambda: 0)

  # recorded the tf and max tf
  maxTf_ = 1
  lenQuery = len(query)
  for i in range(lenQuery):
    word = query[i]
    if(word in titleSet):
      query.append(word)
  # for normalization::
  newQuery = ' '.join(query)
  vecQuery = construct_vector_space_model(newQuery)

  queryVector = np.array(vecQuery)
  paperVector = np.array(paperVector)


  return np.dot(queryVector, paperVector)


def handle_query(query):
  query = ""
  university = ""
  field = ""
  get_score_for_profs(query)
  rankedProfs = list({k: v for k, v in sorted(profs_to_score_map.items(), key=lambda x: x[1], reverse= True)}.items())
  count = 0
  for prof, score in rankedProfs:
    if prof_in_constraints(prof, university, field):
      count += 1
      printProf(prof)
      if count == 10:
        break


def printProf(profName):
  # f = open(profName, 'r')
  print(profName)
  profInfo = prof_to_info_map[profName]
  print(profInfo.home)
  # f.close()


def main():
  getData()
  # inverted_index()
  # construct_vector_space_model()

  query  = ""

  while(query != ""):
    handle_query(query)

  pass