Delete utils/extract_human_annotation.py
Browse files
utils/extract_human_annotation.py
DELETED
|
@@ -1,183 +0,0 @@
|
|
| 1 |
-
import json
|
| 2 |
-
import os
|
| 3 |
-
import re
|
| 4 |
-
import sys
|
| 5 |
-
from tools.flights.apis import Flights
|
| 6 |
-
from tools.accommodations.apis import Accommodations
|
| 7 |
-
from tools.restaurants.apis import Restaurants
|
| 8 |
-
from tools.googleDistanceMatrix.apis import GoogleDistanceMatrix
|
| 9 |
-
from tools.googlePlaces.apis import GooglePlaces
|
| 10 |
-
from tools.attractions.apis import Attractions
|
| 11 |
-
from annotation.src.utils import get_valid_name_city,extract_before_parenthesis
|
| 12 |
-
from tqdm import tqdm
|
| 13 |
-
|
| 14 |
-
sys.path.append(os.path.abspath(os.path.join(os.getcwd(), "..")))
|
| 15 |
-
os.chdir(os.path.dirname(os.path.abspath(__file__)))
|
| 16 |
-
|
| 17 |
-
|
| 18 |
-
flight = Flights()
|
| 19 |
-
accommodations = Accommodations()
|
| 20 |
-
restaurants = Restaurants()
|
| 21 |
-
googleDistanceMatrix = GoogleDistanceMatrix()
|
| 22 |
-
googlePlaces = GooglePlaces()
|
| 23 |
-
attractions = Attractions()
|
| 24 |
-
|
| 25 |
-
|
| 26 |
-
def load_line_json_data(filename):
|
| 27 |
-
data = []
|
| 28 |
-
with open(filename, 'r', encoding='utf-8') as f:
|
| 29 |
-
for line in f.read().strip().split('\n'):
|
| 30 |
-
unit = json.loads(line)
|
| 31 |
-
data.append(unit)
|
| 32 |
-
return data
|
| 33 |
-
|
| 34 |
-
def extract_numbers_from_filenames(directory):
|
| 35 |
-
# Define the pattern to match files
|
| 36 |
-
pattern = r'annotation_(\d+).json'
|
| 37 |
-
|
| 38 |
-
# List all files in the directory
|
| 39 |
-
files = os.listdir(directory)
|
| 40 |
-
|
| 41 |
-
# Extract numbers from filenames that match the pattern
|
| 42 |
-
numbers = [int(re.search(pattern, file).group(1)) for file in files if re.match(pattern, file)]
|
| 43 |
-
|
| 44 |
-
return numbers
|
| 45 |
-
|
| 46 |
-
def extract_from_to(text: str):
|
| 47 |
-
"""
|
| 48 |
-
Extracts 'A' and 'B' from the format "from A to B" in the given text, with B ending at a comma or the end of the string.
|
| 49 |
-
|
| 50 |
-
Args:
|
| 51 |
-
- text (str): The input string.
|
| 52 |
-
|
| 53 |
-
Returns:
|
| 54 |
-
- tuple: A tuple containing 'A' and 'B'. If no match is found, returns (None, None).
|
| 55 |
-
"""
|
| 56 |
-
pattern = r"from\s+(.+?)\s+to\s+([^,]+)(?=[,\s]|$)"
|
| 57 |
-
matches = re.search(pattern, text)
|
| 58 |
-
return matches.groups() if matches else (None, None)
|
| 59 |
-
|
| 60 |
-
def extract_city_list(query_data, annotated_data):
|
| 61 |
-
city_list = []
|
| 62 |
-
for unit in annotated_data[:query_data['days']]:
|
| 63 |
-
if 'from' in unit['current_city']:
|
| 64 |
-
from_city, to_city = extract_from_to(unit['current_city'])
|
| 65 |
-
from_city = extract_before_parenthesis(from_city)
|
| 66 |
-
to_city = extract_before_parenthesis(to_city)
|
| 67 |
-
if from_city not in city_list:
|
| 68 |
-
city_list.append(from_city)
|
| 69 |
-
if to_city not in city_list:
|
| 70 |
-
city_list.append(to_city)
|
| 71 |
-
else:
|
| 72 |
-
city = extract_before_parenthesis(unit['current_city'])
|
| 73 |
-
if city not in city_list:
|
| 74 |
-
city_list.append(city)
|
| 75 |
-
|
| 76 |
-
return city_list
|
| 77 |
-
|
| 78 |
-
|
| 79 |
-
# if __name__ == '__main__':
|
| 80 |
-
# user_name = 'all'
|
| 81 |
-
# directory = '../data/annotation/{}'.format(user_name)
|
| 82 |
-
# query_data_list = load_line_json_data('../data/query/{}.jsonl'.format(user_name))
|
| 83 |
-
# numbers = extract_numbers_from_filenames(directory)
|
| 84 |
-
# print(numbers)
|
| 85 |
-
# for number in tqdm(numbers):
|
| 86 |
-
# json_data = json.load(open(os.path.join(directory, 'annotation_{}.json'.format(number))))
|
| 87 |
-
# query_data = query_data_list[number-1]
|
| 88 |
-
# city_list = extract_city_list(query_data,json_data)
|
| 89 |
-
# human_collected_info = []
|
| 90 |
-
|
| 91 |
-
# for city in city_list[1:]:
|
| 92 |
-
# attractions_data = attractions.run(city)
|
| 93 |
-
# if type(attractions_data) != str:
|
| 94 |
-
# attractions_data.drop(['Latitude','Longitude','Address','Phone','Website','City'],axis=1,inplace=True)
|
| 95 |
-
# if type(attractions_data) != str:
|
| 96 |
-
# attractions_data = attractions_data.to_string(index=False)
|
| 97 |
-
# restaurants_data = restaurants.run(city)
|
| 98 |
-
# restaurants_data.drop(['City'],axis=1,inplace=True)
|
| 99 |
-
# if type(restaurants_data) != str:
|
| 100 |
-
# restaurants_data = restaurants_data.to_string(index=False)
|
| 101 |
-
# accommodations_data = accommodations.run(city)
|
| 102 |
-
# accommodations_data.drop(['city'],axis=1,inplace=True)
|
| 103 |
-
# if type(accommodations_data) != str:
|
| 104 |
-
# accommodations_data = accommodations_data.to_string(index=False)
|
| 105 |
-
# human_collected_info.append({"Description":"Attractions in {}".format(city),"Content":attractions_data})
|
| 106 |
-
# human_collected_info.append({"Description":"Restaurants in {}".format(city),"Content":restaurants_data})
|
| 107 |
-
# human_collected_info.append({"Description":"Accommodations in {}".format(city),"Content":accommodations_data})
|
| 108 |
-
|
| 109 |
-
|
| 110 |
-
# for idx, unit in enumerate(json_data):
|
| 111 |
-
# if unit != {}:
|
| 112 |
-
# if 'from' in unit['current_city']:
|
| 113 |
-
# from_city, to_city = extract_from_to(unit['current_city'])
|
| 114 |
-
# from_city = extract_before_parenthesis(from_city)
|
| 115 |
-
# to_city = extract_before_parenthesis(to_city)
|
| 116 |
-
# date = query_data_list[number-1]['date'][idx]
|
| 117 |
-
# flight_data = flight.run(from_city, to_city, date)
|
| 118 |
-
# if type(flight_data) != str:
|
| 119 |
-
# flight_data.drop(['OriginCityName','DestCityName','Distance','FlightDate'],axis=1,inplace=True)
|
| 120 |
-
# flight_data = flight_data.to_string(index=False)
|
| 121 |
-
# human_collected_info.append({"Description":"Flight from {} to {} on {}".format(from_city, to_city, date), "Content":flight_data})
|
| 122 |
-
# self_driving_data = googleDistanceMatrix.run(from_city, to_city,mode="self-driving")
|
| 123 |
-
# human_collected_info.append({"Description":"Self-driving from {} to {}".format(from_city, to_city), "Content":self_driving_data})
|
| 124 |
-
# taxi_data = googleDistanceMatrix.run(from_city, to_city, mode='taxi')
|
| 125 |
-
# human_collected_info.append({"Description":"Taxi from {} to {}".format(from_city, to_city), "Content":taxi_data})
|
| 126 |
-
|
| 127 |
-
# # write to json file
|
| 128 |
-
# with open(os.path.join(directory, 'human_collected_info_{}.json'.format(number)), 'w', encoding='utf-8') as f:
|
| 129 |
-
# json.dump(human_collected_info, f, indent=4, ensure_ascii=False)
|
| 130 |
-
# # break
|
| 131 |
-
|
| 132 |
-
|
| 133 |
-
if __name__ == '__main__':
|
| 134 |
-
set_type = ['train','dev','test'][2]
|
| 135 |
-
directory = '/home/xj/toolAugEnv/code/toolConstraint/data/final_data/{}'.format(set_type)
|
| 136 |
-
query_data_list = load_line_json_data('/home/xj/toolAugEnv/code/toolConstraint/data/final_data/{}/query/query.jsonl'.format(set_type))
|
| 137 |
-
numbers = [i for i in range(1,len(query_data_list)+1)]
|
| 138 |
-
for number in tqdm(numbers):
|
| 139 |
-
json_data = json.load(open(os.path.join(directory, 'plan/plan_{}.json'.format(number))))[1]
|
| 140 |
-
query_data = query_data_list[number-1]
|
| 141 |
-
city_list = extract_city_list(query_data,json_data)
|
| 142 |
-
human_collected_info = []
|
| 143 |
-
|
| 144 |
-
for city in city_list[1:]:
|
| 145 |
-
attractions_data = attractions.run(city)
|
| 146 |
-
# if type(attractions_data) != str:
|
| 147 |
-
# attractions_data.drop(['Latitude','Longitude','Address','Phone','Website','City'],axis=1,inplace=True)
|
| 148 |
-
if type(attractions_data) != str:
|
| 149 |
-
attractions_data = attractions_data.to_string(index=False)
|
| 150 |
-
restaurants_data = restaurants.run(city)
|
| 151 |
-
# restaurants_data.drop(['City'],axis=1,inplace=True)
|
| 152 |
-
if type(restaurants_data) != str:
|
| 153 |
-
restaurants_data = restaurants_data.to_string(index=False)
|
| 154 |
-
accommodations_data = accommodations.run(city)
|
| 155 |
-
# accommodations_data.drop(['city'],axis=1,inplace=True)
|
| 156 |
-
if type(accommodations_data) != str:
|
| 157 |
-
accommodations_data = accommodations_data.to_string(index=False)
|
| 158 |
-
human_collected_info.append({"Description":"Attractions in {}".format(city),"Content":attractions_data})
|
| 159 |
-
human_collected_info.append({"Description":"Restaurants in {}".format(city),"Content":restaurants_data})
|
| 160 |
-
human_collected_info.append({"Description":"Accommodations in {}".format(city),"Content":accommodations_data})
|
| 161 |
-
|
| 162 |
-
|
| 163 |
-
for idx, unit in enumerate(json_data):
|
| 164 |
-
if unit != {}:
|
| 165 |
-
if 'from' in unit['current_city']:
|
| 166 |
-
from_city, to_city = extract_from_to(unit['current_city'])
|
| 167 |
-
from_city = extract_before_parenthesis(from_city)
|
| 168 |
-
to_city = extract_before_parenthesis(to_city)
|
| 169 |
-
date = query_data_list[number-1]['date'][idx]
|
| 170 |
-
flight_data = flight.run(from_city, to_city, date)
|
| 171 |
-
if type(flight_data) != str:
|
| 172 |
-
# flight_data.drop(['OriginCityName','DestCityName','Distance','FlightDate'],axis=1,inplace=True)
|
| 173 |
-
flight_data = flight_data.to_string(index=False)
|
| 174 |
-
human_collected_info.append({"Description":"Flight from {} to {} on {}".format(from_city, to_city, date), "Content":flight_data})
|
| 175 |
-
self_driving_data = googleDistanceMatrix.run(from_city, to_city,mode="self-driving")
|
| 176 |
-
human_collected_info.append({"Description":"Self-driving from {} to {}".format(from_city, to_city), "Content":self_driving_data})
|
| 177 |
-
taxi_data = googleDistanceMatrix.run(from_city, to_city, mode='taxi')
|
| 178 |
-
human_collected_info.append({"Description":"Taxi from {} to {}".format(from_city, to_city), "Content":taxi_data})
|
| 179 |
-
|
| 180 |
-
# write to json file
|
| 181 |
-
with open(os.path.join(directory, 'plan/human_collected_info_{}.json'.format(number)), 'w', encoding='utf-8') as f:
|
| 182 |
-
json.dump(human_collected_info, f, indent=4, ensure_ascii=False)
|
| 183 |
-
# break
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|