def filter_reviews():
businesses = load_data("food_businesses.json")
business_ids = set(food_lib.map_to_arg(food_lib.filter_by_city(businesses, "Las Vegas"), "business_id"))
out_file = open('vegas_reviews.json', 'w+')
with open(env.DATASET_PATH + 'yelp_academic_dataset_review.json', 'r') as f:
for line in f:
line_json = json.loads(line)
if line_json['business_id'] in business_ids:
out_file.write(json.dumps(line_json) + '\n')
def process_categories():
reviews = load_data("vegas_reviews.json")
def pizza(line):
return 'Pizza' in line['categories']
vegas_cats = set(food_lib.map_to_arg(load_data("food_businesses.json", pizza), 'business_id'))
times = []
for r in reviews:
if r['business_id'] in vegas_cats:
times.append(r['date'])
print(sorted(times))
text = r['text']
date = r['date']
converted_date = datetime.datetime.strptime(date, "%Y-%m-%d")
time_constraint_valid = in_time_range(date, (time_start, time_end))
location_constraint_valid = not business_ids or (r['business_id'] in business_ids)
if time_constraint_valid and location_constraint_valid:
for q in query:
if q in text:
key = (converted_date.month, converted_date.year)
if key in date_counts:
date_counts[key] += 1
else:
date_counts[key] = 1
return date_counts
if len(sys.argv) > 1:
businesses = load_data("food_businesses.json")
business_ids = set(food_lib.map_to_arg(food_lib.filter_by_city(businesses, "Las Vegas"), "business_id"))
reviews = load_data("review_test.json")
query = sys.argv[1].strip().split(',')
count_occurrences(query, reviews)
date_counts = count_occurrences(query, reviews, business_ids=business_ids)
print(sorted(date_counts.items(), key=lambda x: x[1], reverse=True)[0:10])