def score_pods(query, query_dist, query_freqs):
'''Score pods for a query'''
pod_scores = {}
score_sum = 0.0
pods = db.session.query(Pods).filter_by(registered=True).all()
for p in pods:
DS_score = cosine_similarity(convert_to_array(p.DS_vector), query_dist)
term_score, coverage = term_cosine.run(query, query_freqs,
p.word_vector)
score = DS_score + term_score + 2 * coverage
if math.isnan(score):
score = 0
pod_scores[p.name] = score
score_sum += score
print(pod_scores)
'''If all scores are rubbish, search entire pod collection (we're desperate!)'''
if score_sum < 1:
return list(pod_scores.keys())
else:
best_pods = []
for k in sorted(pod_scores, key=pod_scores.get, reverse=True):
if len(best_pods) < 1:
best_pods.append(k)
else:
break
return best_pods
def score(query, query_dist, query_freqs):
""" Get distributional score """
DS_scores = {}
term_scores = {}
coverages = {}
for p in db.session.query(Pods).filter_by(registered=False).all():
DS_scores[p.url] = cosine_similarity(convert_to_array(p.DS_vector), query_dist)
term_scores[p.url], coverages[p.url] = term_cosine.run(query, query_freqs, p.word_vector)
return DS_scores, term_scores
def score(query, query_dist, query_freqs, pod):
""" Get various scores -- This is slow, slow, slow. Add code for vec to matrix calculations """
DS_scores = {}
URL_scores = {}
title_scores = {}
term_scores = {}
coverages = {}
#cosines = cosine_to_matrix(query_dist,DS_M) #Code for vec to matrix cosine calculation -- work in progress
for u in db.session.query(Urls).filter_by(pod=pod).all():
DS_scores[u.url] = cosine_similarity(convert_to_array(u.vector),
query_dist)
#DS_scores[u.url] = cosines[url_to_mat[u.url]]
URL_scores[u.url] = score_url_overlap(query, u.url)
title_scores[u.url] = generic_overlap(query, u.title)
term_scores[u.url], coverages[u.url] = term_cosine.run(
query, query_freqs, u.freqs)
return DS_scores, URL_scores, title_scores, term_scores, coverages