def test_tfidf(self):
record = self.records[0]
create_db_entries(record)
articles = Article.objects.all()
article = articles[0]
implementation = Term.objects.get(term='implementation')
idf = math.log(1.0/2.0)
self.assertEqual(idf, tfidf(implementation, article))
def search(request):
if request.method == 'POST':
form = SearchForm(request.POST)
if form.is_valid():
query_terms = form.cleaned_data['q'].split()
query_terms = [term.lower() for term in query_terms]
intermediate_results = _find_articles(query_terms)
# calculate the TF-IDF of each term per document,
# order results by TF-IDF
terms = Term.objects.filter(term__in=query_terms)
ordered_results = []
for term in terms:
for doc in intermediate_results:
ordered_results.append((tfidf(term, doc), doc))
ordered_results.sort(reverse=True)
# strip out duplicate articles without changing the order
results = _deduplicate_articles(ordered_results)
# calculate total number of articles for "X of Y documents"
total_docs = Article.objects.count()
# Calculate the average TF-IDF for each author in search results.
# Average TF-IDF includes scores of zero for documents that match
# term A, but not term B. That is, a doc that matches A will have a
# TF-IDF of some positive float, but if that same doc does *not*
# match term B, it will have a TF-IDF of 0 for term B.
# ordered_results has a list of (TF-IDF, article) tuples of all
# results, so start with that and create a dictionary with authors
# as keys and lists of (TF-IDF, article) tuples as values.
author_totals = {}
for score, doc in ordered_results:
for author in doc.authors.all():
scores = author_totals.setdefault(author.pk, [])
scores.append(score)
# average the scores per author
author_averages = []
total_results = len(ordered_results)
for author_pk, scores in author_totals.items():
scores_sum = fsum(scores)
average = scores_sum / total_results
author = Author.objects.get(pk=author_pk)
author_averages.append((author, average))
return render(request, 'pubmed_search/search.html', {'articles': results,
'query_terms': query_terms,
'total_documents': total_docs,
'author_averages': author_averages})
else:
return render(request, 'pubmed_search/search.html', {'query_terms': request.POST})
else:
return render(request, 'pubmed_search/search.html')
