print_request = raw_input('\nPrint student_locations_world? y or n? ')
if print_request == 'y':
print student_locations_world
print_request = raw_input('\nPrint student_locations_bad_states? y or n? ')
if print_request == 'y':
print student_locations_bad_states
print_request = raw_input('\nPrint student_locations_bad_cities? y or n? ')
if print_request == 'y':
print student_locations_bad_cities
print_request = raw_input(
'\nPrint student_locations_errors_other? y or n? ')
if print_request == 'y':
print student_locations_errors_other
print_request = raw_input(
'\nPrint student_locations_bad_counties? y or n? ')
if print_request == 'y':
print student_locations_bad_counties
run_stats(commencement_line_count, student_locations_us,
student_locations_world, student_locations_bad_states,
student_locations_bad_cities, student_locations_errors_other,
student_locations_bad_counties)
export_tsv_ids_rates(county_ids_ratios, student_locations_us, 'html/files/',
'students_by_county.tsv')
def main(exports_root_path, main_run_index) :
ocr_files = os.listdir(ocr_lists_root_path)
print '\nAvailable OCR text files:'
i = 0
for file in ocr_files :
print '{0}: {1}'.format(i, file)
i = i + 1
ocr_file_index = ''
while ocr_file_index == '' :
ocr_file_index = raw_input('\nWhich file would you like to run the analysis on? ')
ocr_file_index = int(ocr_file_index)
ocr_text_file = ocr_files[ocr_file_index]
year = re.sub('\.txt', '', ocr_text_file)
student_list_text_file_path = ocr_lists_root_path + ocr_text_file
print 'Text file path: \'{0}\''.format(student_list_text_file_path)
exports_root_path = exports_root_path + year + '/'
print 'Export files to: \'{0}\''.format(exports_root_path)
raw_input('\nContinue if the above paths are correct...')
try:
os.makedirs(exports_root_path)
raw_input('Directory created: \'{0}\'\nContinue...'.format(exports_root_path))
except OSError:
if not os.path.isdir(exports_root_path):
raise
# run a new city state analysis with google api call?
run_new = ''
while run_new == '' :
run_new = print_request = raw_input('\nRe-run entire analysis? y or n? ')
# run a new analysis
if run_new == 'y':
def run_new_analysis(main_run_index) :
raw_input('\nFile to be parsed: ' + student_list_text_file_path)
global student_locations_us
global student_locations_world
global student_locations_bad_states
global student_locations_bad_cities
global student_locations_errors_other
global student_locations_bad_counties
global commencement_line_count
global saved_google_city_state_county_responses
student_locations_us, student_locations_world, student_locations_bad_states, student_locations_bad_cities, student_locations_errors_other, student_locations_bad_counties, commencement_line_count = get_student_locations(student_list_text_file_path, us_states, world_countries, state_county_names_ids, main_run_index, saved_google_city_state_county_responses)
print 'Created student_locations_us [dict], student_locations_world [dict], student_locations_bad_states [dict], student_locations_bad_cities [dict], and student_locations_errors_other [list]'
save_request = raw_input('\nSaving commencement_line_count: {0}... (enter \'n\' to escape) '.format(commencement_line_count))
if save_request != 'n' :
commencement_line_count = str(commencement_line_count)
path = exports_root_path + 'commencement_line_count.txt'
with open(path, 'w') as save_file:
save_file.write(commencement_line_count)
# student_locations_us
print_request = raw_input('\nPrinting student_locations_us... (enter \'n\' to escape) ')
if print_request != 'n' :
print json.dumps(student_locations_us, indent=4)
save_request = raw_input('\nSaving student_locations_us... (enter \'n\' to escape) ')
if save_request != 'n' :
path = exports_root_path + 'student_locations_us.json'
json.dump(student_locations_us, open(path,'w'), sort_keys=True)
# student_locations_world
print_request = raw_input('\nPrinting student_locations_world... (enter \'n\' to escape) ')
if print_request != 'n' :
print json.dumps(student_locations_world, indent=4)
save_request = raw_input('\nSaving student_locations_world... (enter \'n\' to escape) ')
if save_request != 'n' :
path = exports_root_path + 'student_locations_world.json'
json.dump(student_locations_world, open(path,'w'), sort_keys=True)
# student_locations_bad_states
print_request = raw_input('\nPrinting student_locations_bad_states... (enter \'n\' to escape) ')
if print_request != 'n' :
print json.dumps(student_locations_bad_states, indent=4)
save_request = raw_input('\nSaving student_locations_bad_states... (enter \'n\' to escape) ')
if save_request != 'n' :
path = exports_root_path + 'student_locations_bad_states.json'
json.dump(student_locations_bad_states, open(path,'w'), sort_keys=True)
# student_locations_bad_cities
print_request = raw_input('\nPrinting student_locations_bad_cities... (enter \'n\' to escape) ')
if print_request != 'n' :
print json.dumps(student_locations_bad_cities, indent=4)
save_request = raw_input('\nSaving student_locations_bad_cities... (enter \'n\' to escape) ')
if save_request != 'n' :
path = exports_root_path + 'student_locations_bad_cities.json'
json.dump(student_locations_bad_cities, open(path,'w'), sort_keys=True)
# student_locations_errors_other
print_request = raw_input('\nPrinting student_locations_errors_other... (enter \'n\' to escape) ')
if print_request != 'n' :
print json.dumps(student_locations_errors_other, indent=4)
save_request = raw_input('\nSaving student_locations_errors_other... (enter \'n\' to escape) ')
if save_request != 'n' :
path = exports_root_path + 'student_locations_errors_other.json'
json.dump(student_locations_errors_other, open(path,'w'), sort_keys=True)
# student_locations_bad_counties
print_request = raw_input('\nPrinting student_locations_bad_counties... (enter \'n\' to escape) ')
if print_request != 'n' :
print json.dumps(student_locations_bad_counties, indent=4)
save_request = raw_input('\nSaving student_locations_bad_counties... (enter \'n\' to escape) ')
if save_request != 'n' :
path = exports_root_path + 'student_locations_bad_counties.json'
json.dump(student_locations_bad_counties, open(path,'w'), sort_keys=True)
run_new_analysis(main_run_index)
# already ran the analysis, use the files saved from a previous run
else :
raw_input('Loading dictionaries and lists from json files...')
def load_data_from_files() :
path = exports_root_path + 'commencement_line_count.txt'
with open(path) as file :
for line in file :
if line != '' :
global commencement_line_count
commencement_line_count = line
path = exports_root_path + 'student_locations_us.json'
with open(path) as json_file:
global student_locations_us
student_locations_us = json.load(json_file)
path = exports_root_path + 'student_locations_world.json'
with open(path) as json_file:
global student_locations_world
student_locations_world = json.load(json_file)
path = exports_root_path + 'student_locations_bad_states.json'
with open(path) as json_file:
global student_locations_bad_states
student_locations_bad_states = json.load(json_file)
path = exports_root_path + 'student_locations_bad_cities.json'
with open(path) as json_file:
global student_locations_bad_cities
student_locations_bad_cities = json.load(json_file)
path = exports_root_path + 'student_locations_errors_other.json'
with open(path) as json_file:
global student_locations_errors_other
student_locations_errors_other = json.load(json_file)
path = exports_root_path + 'student_locations_bad_counties.json'
with open(path) as json_file:
global student_locations_bad_counties
student_locations_bad_counties = json.load(json_file)
load_data_from_files()
def print_data_from_loaded_files() :
# commencement_line_count
print_request = raw_input('\nPrint commencement_line_count, y or n? ')
if print_request != 'n' :
print json.dumps(commencement_line_count, indent=4)
# student_locations_us
print_request = raw_input('\nPrint student_locations_us, y or n? ')
if print_request != 'n' :
print json.dumps(student_locations_us, indent=4)
# student_locations_world
print_request = raw_input('\nPrint student_locations_world, y or n? ')
if print_request != 'n' :
print json.dumps(student_locations_world, indent=4)
# student_locations_bad_states
print_request = raw_input('\nPrint student_locations_bad_states, y or n? ')
if print_request != 'n' :
print json.dumps(student_locations_bad_states, indent=4)
# student_locations_bad_cities
print_request = raw_input('\nPrint student_locations_bad_cities, y or n? ')
if print_request != 'n' :
print json.dumps(student_locations_bad_cities, indent=4)
# student_locations_errors_other
print_request = raw_input('\nPrint student_locations_errors_other, y or n? ')
if print_request != 'n' :
print json.dumps(student_locations_errors_other, indent=4)
# student_locations_bad_counties
print_request = raw_input('\nPrint student_locations_bad_counties, y or n? ')
if print_request != 'n' :
print json.dumps(student_locations_bad_counties, indent=4)
print_data_from_loaded_files()
run_stats(commencement_line_count, student_locations_us, student_locations_world, student_locations_bad_states, student_locations_bad_cities, student_locations_errors_other, student_locations_bad_counties)
# add the new student locations and the county info to a dictionary for reference and fewer google api calls
google_city_state_county_responses = register_google_city_state_county_responses(student_locations_us, saved_google_city_state_county_responses)
print_request = raw_input('Printing google_city_state_county_responses... (enter \'n\' to escape) ')
if print_request != 'n' :
print json.dumps(google_city_state_county_responses, indent=4)
google_saved_count = 0
for state in google_city_state_county_responses :
for city in google_city_state_county_responses :
google_saved_count = google_saved_count + 1
raw_input('\nThe google_city_state_county_responses city count: {0}\n'.format(google_saved_count))
# set the tsv file parameters
tsv_file_name = 'students_by_county_' + year + '.tsv'
tsv_export_path = html_files_path
# get the dictionary to save to tsv and the associated stats
student_county_ids_ratios, tsv_file_stats = prepare_tsv_dictionary(county_ids_ratios, student_locations_us)
# save the tsv file and print out some stats
export_tsv_ids_rates(student_county_ids_ratios, tsv_export_path, tsv_file_name, tsv_file_stats)
print student_locations_us
print_request = raw_input('\nPrint student_locations_world? y or n? ')
if print_request == 'y' :
print student_locations_world
print_request = raw_input('\nPrint student_locations_bad_states? y or n? ')
if print_request == 'y' :
print student_locations_bad_states
print_request = raw_input('\nPrint student_locations_bad_cities? y or n? ')
if print_request == 'y' :
print student_locations_bad_cities
print_request = raw_input('\nPrint student_locations_errors_other? y or n? ')
if print_request == 'y' :
print student_locations_errors_other
print_request = raw_input('\nPrint student_locations_bad_counties? y or n? ')
if print_request == 'y' :
print student_locations_bad_counties
run_stats(commencement_line_count, student_locations_us, student_locations_world, student_locations_bad_states, student_locations_bad_cities, student_locations_errors_other, student_locations_bad_counties)
export_tsv_ids_rates(county_ids_ratios, student_locations_us, 'html/files/', 'students_by_county.tsv')
def main(exports_root_path, main_run_index) :
ocr_files = os.listdir(ocr_lists_root_path)
print '\nAvailable OCR text files:'
i = 0
for file in ocr_files :
print '{0}: {1}'.format(i, file)
i = i + 1
ocr_file_index = ''
while ocr_file_index == '' :
ocr_file_index = raw_input('\nWhich file would you like to run the analysis on? ')
ocr_file_index = int(ocr_file_index)
ocr_text_file = ocr_files[ocr_file_index]
year = re.sub('\.txt', '', ocr_text_file)
student_list_text_file_path = ocr_lists_root_path + ocr_text_file
print 'Text file path: \'{0}\''.format(student_list_text_file_path)
exports_root_path = exports_root_path + year + '/'
print 'Export files to: \'{0}\''.format(exports_root_path)
raw_input('\nContinue if the above paths are correct...')
try:
os.makedirs(exports_root_path)
raw_input('Directory created: \'{0}\'\nContinue...'.format(exports_root_path))
except OSError:
if not os.path.isdir(exports_root_path):
raise
# run a new city state analysis with google api call?
run_new = ''
while run_new == '' :
run_new = print_request = raw_input('\nRe-run entire analysis? y or n? ')
# run a new analysis
if run_new == 'y':
def run_new_analysis(main_run_index) :
raw_input('\nFile to be parsed: ' + student_list_text_file_path)
global student_locations_us
global student_locations_world
global student_locations_bad_states
global student_locations_bad_cities
global student_locations_errors_other
global student_locations_bad_counties
global commencement_line_count
global saved_google_city_state_county_responses
student_locations_us, student_locations_world, student_locations_bad_states, student_locations_bad_cities, student_locations_errors_other, student_locations_bad_counties, commencement_line_count = get_student_locations(student_list_text_file_path, us_states, world_countries, state_county_names_ids, main_run_index, saved_google_city_state_county_responses)
print 'Created student_locations_us [dict], student_locations_world [dict], student_locations_bad_states [dict], student_locations_bad_cities [dict], and student_locations_errors_other [list]'
save_request = raw_input('\nSaving commencement_line_count: {0}... (enter \'n\' to escape) '.format(commencement_line_count))
if save_request != 'n' :
commencement_line_count = str(commencement_line_count)
path = exports_root_path + 'commencement_line_count.txt'
with open(path, 'w') as save_file:
save_file.write(commencement_line_count)
# student_locations_us
print_request = raw_input('\nPrinting student_locations_us... (enter \'n\' to escape) ')
if print_request != 'n' :
print json.dumps(student_locations_us, indent=4)
save_request = raw_input('\nSaving student_locations_us... (enter \'n\' to escape) ')
if save_request != 'n' :
path = exports_root_path + 'student_locations_us.json'
json.dump(student_locations_us, open(path,'w'), sort_keys=True)
# student_locations_world
print_request = raw_input('\nPrinting student_locations_world... (enter \'n\' to escape) ')
if print_request != 'n' :
print json.dumps(student_locations_world, indent=4)
save_request = raw_input('\nSaving student_locations_world... (enter \'n\' to escape) ')
if save_request != 'n' :
path = exports_root_path + 'student_locations_world.json'
json.dump(student_locations_world, open(path,'w'), sort_keys=True)
# student_locations_bad_states
print_request = raw_input('\nPrinting student_locations_bad_states... (enter \'n\' to escape) ')
if print_request != 'n' :
print json.dumps(student_locations_bad_states, indent=4)
save_request = raw_input('\nSaving student_locations_bad_states... (enter \'n\' to escape) ')
if save_request != 'n' :
path = exports_root_path + 'student_locations_bad_states.json'
json.dump(student_locations_bad_states, open(path,'w'), sort_keys=True)
# student_locations_bad_cities
print_request = raw_input('\nPrinting student_locations_bad_cities... (enter \'n\' to escape) ')
if print_request != 'n' :
print json.dumps(student_locations_bad_cities, indent=4)
save_request = raw_input('\nSaving student_locations_bad_cities... (enter \'n\' to escape) ')
if save_request != 'n' :
path = exports_root_path + 'student_locations_bad_cities.json'
json.dump(student_locations_bad_cities, open(path,'w'), sort_keys=True)
# student_locations_errors_other
print_request = raw_input('\nPrinting student_locations_errors_other... (enter \'n\' to escape) ')
if print_request != 'n' :
print json.dumps(student_locations_errors_other, indent=4)
save_request = raw_input('\nSaving student_locations_errors_other... (enter \'n\' to escape) ')
if save_request != 'n' :
path = exports_root_path + 'student_locations_errors_other.json'
json.dump(student_locations_errors_other, open(path,'w'), sort_keys=True)
# student_locations_bad_counties
print_request = raw_input('\nPrinting student_locations_bad_counties... (enter \'n\' to escape) ')
if print_request != 'n' :
print json.dumps(student_locations_bad_counties, indent=4)
save_request = raw_input('\nSaving student_locations_bad_counties... (enter \'n\' to escape) ')
if save_request != 'n' :
path = exports_root_path + 'student_locations_bad_counties.json'
json.dump(student_locations_bad_counties, open(path,'w'), sort_keys=True)
run_new_analysis(main_run_index)
# already ran the analysis, use the files saved from a previous run
else :
raw_input('Loading dictionaries and lists from json files...')
def load_data_from_files() :
path = exports_root_path + 'commencement_line_count.txt'
with open(path) as file :
for line in file :
if line != '' :
global commencement_line_count
commencement_line_count = line
path = exports_root_path + 'student_locations_us.json'
with open(path) as json_file:
global student_locations_us
student_locations_us = json.load(json_file)
path = exports_root_path + 'student_locations_world.json'
with open(path) as json_file:
global student_locations_world
student_locations_world = json.load(json_file)
path = exports_root_path + 'student_locations_bad_states.json'
with open(path) as json_file:
global student_locations_bad_states
student_locations_bad_states = json.load(json_file)
path = exports_root_path + 'student_locations_bad_cities.json'
with open(path) as json_file:
global student_locations_bad_cities
student_locations_bad_cities = json.load(json_file)
path = exports_root_path + 'student_locations_errors_other.json'
with open(path) as json_file:
global student_locations_errors_other
student_locations_errors_other = json.load(json_file)
path = exports_root_path + 'student_locations_bad_counties.json'
with open(path) as json_file:
global student_locations_bad_counties
student_locations_bad_counties = json.load(json_file)
load_data_from_files()
def print_data_from_loaded_files() :
# commencement_line_count
print_request = raw_input('\nPrint commencement_line_count, y or n? ')
if print_request != 'n' :
print json.dumps(commencement_line_count, indent=4)
# student_locations_us
print_request = raw_input('\nPrint student_locations_us, y or n? ')
if print_request != 'n' :
print json.dumps(student_locations_us, indent=4)
# student_locations_world
print_request = raw_input('\nPrint student_locations_world, y or n? ')
if print_request != 'n' :
print json.dumps(student_locations_world, indent=4)
# student_locations_bad_states
print_request = raw_input('\nPrint student_locations_bad_states, y or n? ')
if print_request != 'n' :
print json.dumps(student_locations_bad_states, indent=4)
# student_locations_bad_cities
print_request = raw_input('\nPrint student_locations_bad_cities, y or n? ')
if print_request != 'n' :
print json.dumps(student_locations_bad_cities, indent=4)
# student_locations_errors_other
print_request = raw_input('\nPrint student_locations_errors_other, y or n? ')
if print_request != 'n' :
print json.dumps(student_locations_errors_other, indent=4)
# student_locations_bad_counties
print_request = raw_input('\nPrint student_locations_bad_counties, y or n? ')
if print_request != 'n' :
print json.dumps(student_locations_bad_counties, indent=4)
print_data_from_loaded_files()
run_stats(commencement_line_count, student_locations_us, student_locations_world, student_locations_bad_states, student_locations_bad_cities, student_locations_errors_other, student_locations_bad_counties)
# add the new student locations and the county info to a dictionary for reference and fewer google api calls
google_city_state_county_responses = register_google_city_state_county_responses(student_locations_us, saved_google_city_state_county_responses)
print_request = raw_input('Printing google_city_state_county_responses... (enter \'n\' to escape) ')
if print_request != 'n' :
print json.dumps(google_city_state_county_responses, indent=4)
google_saved_count = 0
for state in google_city_state_county_responses :
for city in google_city_state_county_responses :
google_saved_count = google_saved_count + 1
raw_input('\nThe google_city_state_county_responses city count: {0}\n'.format(google_saved_count))
# set the tsv file parameters
tsv_file_name = 'students_by_county_' + year + '.tsv'
tsv_export_path = html_files_path
# get the dictionary to save to tsv and the associated stats
student_county_ids_ratios, tsv_file_stats = prepare_tsv_dictionary(county_ids_ratios, student_locations_us)
# save the tsv file and print out some stats
export_tsv_ids_rates(student_county_ids_ratios, tsv_export_path, tsv_file_name, tsv_file_stats)
def stats():
run_stats()
return jsonify(OK("Sync stats complete"))
def test_look_elevator(limit=None):
"""method that tests the look elevator"""
result_dir = "look"
# create directory if not existing
dirs = os.path.join(BASE_DIR, result_dir)
if not os.path.exists(dirs):
os.makedirs(dirs)
# create loggers
person_logger_path = os.path.join(dirs, settings.LOG_DIR,
settings.PERSON_LOG_FNAME)
person_logger = logger.PersonLogger(person_logger_path, remove_old=True)
# create building
building = Building([
'SB',
'B',
'G',
'1',
'2',
'3',
'4',
'5',
'6',
'7',
'8',
'9',
'10',
'11',
'12',
])
# generate arrivals
arr_gen = ArrivalGenerator(building=building, person_logger=person_logger)
days = ["M", "Tu", "W", "Th", "F"]
for day in days:
# load saved arrivals or generate new arrivals
arr_gen.arrival_times = []
save_path = os.path.join(settings.ARRIVALS_DIR,
"{}_arrivals.csv".format(day))
if not os.path.exists(save_path):
arr_gen.gen_from_classes(file_path=settings.ARRIVALS_DATA_SET_CSV,
days=[day])
arr_gen.save(save_path)
else:
arr_gen.load(save_path)
# add first 100 floor arrivals to FEQ
cnt = 0
for time, person in arr_gen.arrival_times:
cnt += 1
if limit is not None and cnt > limit:
break
settings.FEQ.put_nowait((time, person, person.States.QUEUED))
# create 6 elevators
settings.ELEVATORS = []
for _ in range(6):
settings.ELEVATORS.append(elevators.LookElevator(None, building))
while not settings.FEQ.empty():
curr_time, obj, state = settings.FEQ.get_nowait()
settings.CURR_TIME = curr_time
obj.update_state(state)
# commit changes to person_logger
person_logger.conn.commit()
print("Done with", day)
sim_stats.run_stats(person_log_path=person_logger_path,
stats_dir=os.path.join(dirs, "stats"))
print("done simulating", result_dir)