def init(db): upcomingReleases.getUpcomingReleases() iter = utils.read_movies('newReleases.json') collection = [] print "Pre-processing data" start = time.time() # Pre-process movies to classify file = open('classify.json','w') for movie in iter: if 'imdb_id' in movie: movie['rating'] = 5.0 movie['rating_count'] = 100 collection.append(movie) # Write movie data data = StringIO() json.dump(movie, data) file.write(data.getvalue()) file.write(",\n") file.close() end = time.time() print "Finished in %.3f seconds\n" % (end-start) iter = utils.read_movies('mv.json') for movie in iter: collection.append(movie) for movie in collection: if "poster" not in movie: movie['poster'] = '/static/images/caverlee.png' if "plot_simple" not in movie: movie['plot_simple'] = ' ' if "director" not in movie: movie['directors'] = ['Unknown'] print "Indexing movie titles" start = time.time() indexer = moviesearch.MovieSearch(db) indexer.index_movies(collection) end = time.time() print "Finished in %.3f seconds\n" % (end-start)
for movie in iter: collection.append(movie) for movie in collection: if "poster" not in movie: movie['poster'] = '/static/images/caverlee.png' if "plot_simple" not in movie: movie['plot_simple'] = ' ' if "director" not in movie: movie['directors'] = ['Unknown'] print "Indexing movie titles" start = time.time() indexer = moviesearch.MovieSearch(db) indexer.index_movies(collection) end = time.time() print "Finished in %.3f seconds\n" % (end-start) if __name__=="__main__": print "In Main" _db = utils.connect_db('termather',remove_existing=True) init(_db) _predictor = predictor.Predictor(_db) _predictor.train_classifier(utils.read_movies('mv.json')) _predictor.main(utils.read_movies('classify.json')) _searcher = moviesearch.MovieSearch(_db) bottle.run(host=settings['http_host'], port=settings['http_port'])