def get_scores(self, terms):
"""Creates a list of scores for each file in corpus.
The score = weighted frequency / the total word count in the file
The score is computed for each term and all scores are summed.
Arguments:
terms (list): A list of str
Returns:
list: a list of tuples, each containing the file_path_name and
its relevancy score
"""
scores = HashTable()
results = []
for term in terms:
if term in self.term_freqs:
for file in self.term_freqs[term].keys():
term_f = self.term_freqs[term][file]
weighted_f = self.get_wf(term_f)
if file not in scores:
scores[file] = weighted_f
else:
scores[file] += weighted_f
for file in scores.keys():
scores[file] /= self.doc_length[file]
results.append((file, scores[file]))
return results
def search(self, query):
"""Search for the query items in files.
Arguments:
query (str): query input: e.g. "Computer Science"
Returns:
list: a list of tuples: (file_path_name, score) sorted
in descending order or relevancy, excluding files whose
relevancy score is 0
"""
query_terms = query.lower().strip().split(' ')
duplicate_check = HashTable()
for term in query_terms:
if term not in duplicate_check:
duplicate_check[term] = 1
else:
duplicate_check[term] += 1
return self.rank(self.get_scores(duplicate_check.keys()))