def get_recom_from_input(username, input_name, data):
'''
generate recommendations using input from the request form
- INPUT:
username str
input_name str
data: input from the request form
- OUTPUT: results_dict
dict(username = username,\
input_data = data, input_name = input_name, sorted_topics = sorted_topics_for_inputs, \
idx = range(df_recom.shape[0]), \
df_recom = df_recom, relevant_all=relevant_all)
- pre-requisit:
'''
model_name = 'v2_2'
fname = input_name
relevant_all = None
# hard code process used in v2_2 model
func_tokenizer = TfidfVectorizer(stop_words='english').build_tokenizer()
func_stemmer = PorterStemmer()
# load model
t0 = time.time()
recommender = Recommender(model_name, func_tokenizer, func_stemmer)
# read in input text
cleaned_slack = pre_clean_text(func_tokenizer, data)
W, tokenized_slacks2, test_X2, top_features_list = recommender.process_input(
cleaned_slack)
sorted_topics = recommender.topic_model.sorted_topics_for_articles(W)
print 'input name: %s' % input_name
# recommendations
print '--------------- recommendations --------------'
df_recom = recommender.calculate_recommendations(W, test_X2, fname)
print sorted_topics
t1 = time.time()
print "finished in %4.4f min %s " % ((t1 - t0) / 60, 'finished all processing\n')
df_recom['topics'] = df_recom['topics'].apply(format_related_topics)
results_dict = dict(username=username,
input_data=data, input_name=input_name, sorted_topics=sorted_topics,
idx=range(df_recom.shape[0]),
df_recom=df_recom, relevant_all=relevant_all)
with open(dummy_result_pkl, 'w') as out_fh:
pickle.dump(results_dict, out_fh)
return results_dict
