def add_similarity_scores_for_nonprofit_tweets():
"""Calculate similarity scores for every pair of nonprofit tweets and store them in the DB."""
logger.debug('Inside add_similarity_scores_for_nonprofit_tweets()')
tweets = DBSession.query(Tweet.twitter_name, func.group_concat(Tweet.text).label('text')).group_by(Tweet.twitter_name).all()
similarity_matrix = similarity.get_similarity_scores_all_pairs([tweet.text for tweet in tweets])
DBSession.query(Nonprofits_Similarity_By_Tweets).delete()
for m in xrange(len(similarity_matrix) - 1):
for n in xrange(m + 1, len(similarity_matrix)):
DBSession.add(Nonprofits_Similarity_By_Tweets(tweets[m].twitter_name, tweets[n].twitter_name, similarity_matrix[m][n]))
DBSession.commit()
def add_similarity_scores_for_nonprofit_descriptions():
"""Calculate similarity scores for every pair of nonprofit descriptions and store them in the DB."""
logger.debug('Inside add_similarity_scores_for_nonprofit_descriptions()')
nonprofits = DBSession.query(Nonprofit).filter(Nonprofit.description != None).all() # nopep8
similarity_matrix = similarity.get_similarity_scores_all_pairs([nonprofit.description for nonprofit in nonprofits])
DBSession.query(Nonprofits_Similarity_By_Description).delete()
for m in xrange(len(similarity_matrix) - 1):
for n in xrange(m + 1, len(similarity_matrix)):
DBSession.add(Nonprofits_Similarity_By_Description(nonprofits[m].nonprofits_id, nonprofits[n].nonprofits_id, similarity_matrix[m][n]))
DBSession.commit()
def add_similarity_scores_for_nonprofit_descriptions():
"""Calculate similarity scores for every pair of nonprofit descriptions and store them in the DB."""
logger.debug('Inside add_similarity_scores_for_nonprofit_descriptions()')
nonprofits = DBSession.query(Nonprofit).filter(
Nonprofit.description != None).all() # nopep8
similarity_matrix = similarity.get_similarity_scores_all_pairs(
[nonprofit.description for nonprofit in nonprofits])
DBSession.query(Nonprofits_Similarity_By_Description).delete()
for m in xrange(len(similarity_matrix) - 1):
for n in xrange(m + 1, len(similarity_matrix)):
DBSession.add(
Nonprofits_Similarity_By_Description(
nonprofits[m].nonprofits_id, nonprofits[n].nonprofits_id,
similarity_matrix[m][n]))
DBSession.commit()
def add_similarity_scores_for_nonprofit_tweets():
"""Calculate similarity scores for every pair of nonprofit tweets and store them in the DB."""
logger.debug('Inside add_similarity_scores_for_nonprofit_tweets()')
tweets = DBSession.query(Tweet.twitter_name,
func.group_concat(
Tweet.text).label('text')).group_by(
Tweet.twitter_name).all()
similarity_matrix = similarity.get_similarity_scores_all_pairs(
[tweet.text for tweet in tweets])
DBSession.query(Nonprofits_Similarity_By_Tweets).delete()
for m in xrange(len(similarity_matrix) - 1):
for n in xrange(m + 1, len(similarity_matrix)):
DBSession.add(
Nonprofits_Similarity_By_Tweets(tweets[m].twitter_name,
tweets[n].twitter_name,
similarity_matrix[m][n]))
DBSession.commit()
