def main(likesJson, moviesJson):
global moviesParser
global likesMap
channelIndex = ChannelIndex(Channels.CHANNELS)
likesParser = LikesParser(channelIndex, likeThreshold=3) #out of 5
likesMap = likesParser.getUserDict(likesJson, build = True, count = None)
creatingTrainingData(likesMap)
moviesParser = MoviesParser(channelIndex)
moviesParser.parseMoviesObjects(moviesJson, parse = True)
userCount = len(likesMap)
actorsCount = len(moviesParser.dictActor)
directorsCount = len(moviesParser.dictDirector)
genreCount = len(moviesParser.dictGenre)
print "userCount-", userCount, ";actorsCount-", actorsCount, ";directorsCount-", directorsCount, ";genreCount-", genreCount
# print("%d,%d,%d,%d" % (userCount, actorsCount, directorsCount, genreCount))
graph = Graph(userCount, actorsCount, directorsCount, genreCount)
print "likesMap", likesMap[3]
graph.calculateUserAffinity(moviesParser.dictDirector, moviesParser.dictActor, moviesParser.dictGenre, likesMap)
graph.calculateAffinityBetweenEntities()
graph.calculateSelfAffinity()
reco = Recommender(graph)
movies = reco.recommend(likesParser.model, moviesParser, 3)
print("Recommendations: ")
for m in movies:
movieObj = moviesParser.movies[m]
movieName = movieObj['name']
print "ID:", m, "-", movieName
def main():
'''
INPUT: None
OUTPUT: Recommendations sorted in order of relevance
Uses the TextParser and Recommender classes to generate resource recommendations given a user's Quora data
'''
read = TextParser()
read.assemble_df()
pickle.dump(read.df, open("data/master_df.pkl", "wb"))
quora_user = open('data/quora_data.pkl')
quora = pickle.load(quora_user)
filtered = read.preprocess_quora(quora)
clean_quora = read.clean_up(filtered)
pickle.dump(clean_quora, open("data/clean_quora.pkl", "wb"))
# Make recommendations
rec = Recommender()
test = rec.vectorize()
top_ten_ind = rec.recommend()
recs = read.df.ix[top_ten_ind]
recs = recs.reset_index()
recs['img_link'] = map(get_image, recs['title'])
recs.loc[recs['type']=='course', 'img_link'] = 'http://www.michaellenox.com/wp-content/uploads/2014/07/coursera_square_logo.jpg'
pickle.dump(recs[0:5], open("data/recs.pkl", "wb"))
print "These are your recommendations: \n"
print recs[['title', 'type', 'img_link']]
return recs[['title', 'type', 'img_link']]
def recommend():
resume = request.form.get('resume', None)
requirements = request.form.get('requirements', None)
# Initialize recommender
recommender = Recommender(ngram_range=(1, 1),
use_tagger=True,
use_stem=False)
recommender.fit(resume, requirements)
# Requirement pair: [0] original requirement: [1]Extracted requirement
missing_requirement_pairs = recommender.find_missing_skills()
missing_requirements = [item[1] for item in missing_requirement_pairs]
course_recommedations = recommender.recommend()
if len(missing_requirements) > 0:
return render_template('recommend.html',
data=zip(missing_requirements,
course_recommedations))
return render_template('matchall.html')
def get_recommendations(resume_file,
requirement_file,
ngram_range=(1, 1),
use_tagger=False):
with open(resume_file, 'r') as handle:
resume = handle.read()
with open(requirement_file, 'r') as handle:
requirements = handle.read()
recommender = Recommender(ngram_range=ngram_range, use_tagger=use_tagger)
recommender.initialize_attributes(resume, requirements)
recommender.vectorize_resume()
recommender.vectorize_requirements()
missing_requirements = recommender.find_missing_skills()
print "Requirements:"
print recommender.requirements
print "preprocessed_requirements:"
print recommender.preprocessed_requirements
print "recommender.missing_requirements"
print recommender.missing_requirements
course_recommedations = recommender.recommend()
return missing_requirements, course_recommedations
def recommend():
user_data = str(request.form['user_input'].encode('utf-8'))
# --- Drive to the given URL, scrape and generate recs -- #
scraped = profile_crawl(user_data)
quora = scraped['text']
# Read and clean Quora dump recommendations
read = TextParser()
read.df = master_df
filtered = read.preprocess_quora(quora)
clean_quora = read.clean_up(filtered)
pickle.dump(clean_quora, open("data/clean_quora.pkl", "wb"))
rec = Recommender()
test = rec.vectorize()
top_ten_ind = rec.recommend()
recs = read.df.ix[top_ten_ind]
recs = recs.reset_index()
recs['img_link'] = map(get_image, recs['title'])
recs.loc[recs['type']=='course', 'img_link'] = 'http://www.michaellenox.com/wp-content/uploads/2014/07/coursera_square_logo.jpg'
recs = recs[0:20] # Get the top twenty recommendations
return render_template('testing.html', data = recs[['title', 'img_link']].values)
