-
Notifications
You must be signed in to change notification settings - Fork 0
/
GSMLS.py
2549 lines (2073 loc) · 115 KB
/
GSMLS.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
import re
import time
import os
from copy import deepcopy
from statistics import mean
import requests
import shelve
import datetime
import traceback
import pandas as pd
import numpy as np
from NJTaxAssessment_v2 import NJTaxAssessment
from bs4 import BeautifulSoup
from sqlalchemy import create_engine
import psycopg2
import logging
from datetime import datetime
import selenium
from selenium import webdriver
from selenium.webdriver.edge.service import Service
from selenium.webdriver.edge.options import Options
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.action_chains import ActionChains as AC
# Allows for Selenium to click a button
from selenium.webdriver.support.select import Select
from selenium.common.exceptions import ElementNotVisibleException
from selenium.common.exceptions import TimeoutException
from selenium.common.exceptions import ElementNotSelectableException
from selenium.common.exceptions import ElementClickInterceptedException
from selenium.common.exceptions import InvalidArgumentException
from selenium.common.exceptions import NoSuchAttributeException
from selenium.common.exceptions import NoSuchDriverException
from selenium.common.exceptions import NoSuchElementException
from selenium.common.exceptions import WebDriverException
class GSMLS:
def __init__(self):
# What information do I need to initialize an instance of this class?
pass
"""
______________________________________________________________________________________________________________
Use this section to house the decorator functions
______________________________________________________________________________________________________________
"""
@staticmethod
def clean_db_decorator(original_function):
def wrapper(*args, **kwargs):
res_db_list = []
mul_db_list = []
lnd_db_list = []
state_data_path = 'F:\\Real Estate Investing\\JQH Holding Company LLC\\Real Estate Data'
path = 'C:\\Users\\Omar\\Desktop\\STF'
os.chdir(state_data_path)
latest_data = os.listdir(state_data_path)[-1]
state_db = pd.read_excel(latest_data, sheet_name='All Months')
os.chdir(path)
dirty_dbs_list = os.listdir(path)
main_driver, gsmls_window, rpr_window = GSMLS.open_browser_windows()
for file in dirty_dbs_list:
if file.endswith('.xlsx'):
db = pd.read_excel(file, engine='openpyxl')
city_name = db.loc[0, 'TOWN'].rstrip('*1234567890().')
city_name2 = deepcopy(city_name)
for ending in ['Town', 'Twp', 'Boro', 'City']:
if ending in city_name:
city_name = city_name.split(ending)[0].strip()
county_name = db.loc[0, 'COUNTY'].rstrip('*')
property_type = file.split(' ')[-3]
mls_type = file.split(' ')[-1].rstrip('.xlsx')
qtr = file.split(' ')[-4][:2]
year = int(file.split(' ')[-4][2:])
tax_db = NJTaxAssessment.city_database(county_name, city_name)
tax_db.set_index('Property Location')
kwargs['driver'] = main_driver
kwargs['gsmls_window'] = gsmls_window
kwargs['rpr_window'] = rpr_window
kwargs['initial_db'] = db
kwargs['tax_db'] = tax_db
kwargs['property_type'] = property_type
kwargs['mls_type'] = mls_type
kwargs['qtr'] = qtr
kwargs['median_sales_price'] = GSMLS.median_sales_price(state_db, city_name2, qtr, year)
result = original_function(*args, **kwargs)
if property_type == 'RES':
res_db_list.append(result)
elif property_type == 'MUL':
mul_db_list.append(result)
elif property_type == 'LND':
lnd_db_list.append(result)
else:
continue
# Separate vars may not be necessary. Just insert the
# Concatenated dbs once the pandas2sql function is created
res_main_db = pd.concat(res_db_list)
mul_main_db = pd.concat(mul_db_list)
lnd_main_db = pd.concat(lnd_db_list)
GSMLS.kill_logger(logger_var=kwargs['logger'], file_handler=kwargs['f_handler'], console_handler=kwargs['c_handler'])
return wrapper
# @staticmethod
# def kpi(original_function):
# def wrapper(*args, **kwargs):
#
# property_type = str(original_function.__name__)[-3:].upper()
# if property_type == 'RES':
# kpi_db = GSMLS.potential_farm_area_res()
# elif property_type == 'MUL':
# pass
# elif property_type == 'LND':
# pass
# elif property_type == 'COM':
# pass
#
# kpi_dict = {}
# quarterly_sales_data = sql2pandas('RES')
# for group, data in kpi:
# kpi_dict.setdefault([group[0], {})
# kpi_dict[group[0]].setdefault(group[1], 0)
# # This currently wont work because the city names from both DB dont match
# sales_price = quarterly_sales_data[quarterly_sales_data['TOWN'] == group[1]]['SALESPRICE'].median()
# std = quarterly_sales_data[quarterly_sales_data['TOWN'] == group[1]].std()
# kpi_dict[group[0]][group[1]] = sales_price - std
@staticmethod
def logger_decorator(original_function):
def wrapper(*args, **kwargs):
logger = logging.getLogger(original_function.__name__)
logger.setLevel(logging.DEBUG)
logger.propagate = False
# Create the FileHandler() and StreamHandler() loggers
f_handler = logging.FileHandler(
original_function.__name__ + ' ' + str(datetime.today().date()) + '.log')
f_handler.setLevel(logging.DEBUG)
c_handler = logging.StreamHandler()
c_handler.setLevel(logging.INFO)
# Create formatting for the loggers
formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s',
datefmt='%d-%b-%y %H:%M:%S')
# Set the formatter for each handler
f_handler.setFormatter(formatter)
c_handler.setFormatter(formatter)
logger.addHandler(f_handler)
logger.addHandler(c_handler)
kwargs['logger'] = logger
kwargs['f_handler'] = f_handler
kwargs['c_handler'] = c_handler
result = original_function(*args, **kwargs)
if result is None:
pass
else:
return result
return wrapper
@staticmethod
def quarterly_sales(original_function):
def wrapper(*args, **kwargs):
logger = kwargs['logger']
f_handler = kwargs['f_handler']
c_handler = kwargs['c_handler']
property_type = str(original_function.__name__)[-3:].upper()
time_periods = {
'Q1': ['01/01/' + str(datetime.today().year), '03/31/' + str(datetime.today().year)],
'Q2': ['04/01/' + str(datetime.today().year), '06/30/' + str(datetime.today().year)],
'Q3': ['07/01/' + str(datetime.today().year), '09/30/' + str(datetime.today().year)],
'Q4': ['10/01/' + str(datetime.today().year), '12/31/' + str(datetime.today().year)]
}
# time_periods = {
# 'Q1': ['01/01/2023', '03/31/2023'],
# 'Q2': ['04/01/2023', '06/30/2023'],
# 'Q3': ['07/01/2023', '09/30/2023'],
# 'Q4': ['10/01/2023', '12/31/2023']
# }
run_log = GSMLS.open_run_log()
for qtr, date_range in time_periods.items():
kwargs['Qtr'] = qtr
kwargs['Dates'] = date_range
kwargs['Run Log'] = run_log
if datetime.today() >= datetime.strptime(date_range[1], '%m/%d/%Y'):
if run_log[property_type][qtr] == 'D.N.A':
# D.N.A means 'Data Not Available'
run_log = original_function(*args, **kwargs)
elif run_log[property_type][qtr] == 'IN PROGRESS':
# run modified_quarterly_download
previous_dir = os.getcwd()
path = 'C:\\Users\\Omar\\Desktop\\Selenium Temp Folder'
os.chdir(path)
latest_file = sorted(os.listdir(path), key=lambda x: os.path.getctime(x))[-1]
db = pd.read_excel(latest_file)
os.chdir(previous_dir)
kwargs['city_name'] = latest_file.split('Q')[0].strip()
kwargs['county_name'] = db.loc[0, 'COUNTY'].rstrip('*')
run_log = original_function(*args, **kwargs)
elif run_log[property_type][qtr] == 'DOWNLOADED':
logger.info(f'The {property_type} data has already been downloaded for {qtr}')
pass
else:
# May need to put a logger msg here
# May need to break the code here. No sense of continuing the loop if all subsequent data isnt
# available
continue
GSMLS.check_run_log(run_log, logger)
logger.removeHandler(f_handler)
logger.removeHandler(c_handler)
logging.shutdown()
return wrapper
@staticmethod
def run_main(original_function):
def wrapper(*args, **kwargs):
pass
# Formulate all the date variables
# todays_date = datetime.datetime.today().date()
# data_avail = Scraper.current_data
# temp_date = str(todays_date).split('-')
# day = int(temp_date[2])
# month = int(temp_date[1])
# year = temp_date[0]
# current_run_date = datetime.datetime.strptime(year + '-' + temp_date[1] + '-' + '24', "%Y-%m-%d").date()
#
# # Logic for calculating the next date to run main()
# if day < 24:
# next_run_date = year + '-' + temp_date[1] + '-' + '24'
# elif day >= 24:
# if data_avail == Scraper.event_log[obj.no_of_runs - 1]['Latest Available Data']:
# next_run_date = year + '-' + temp_date[1] + '-' + '24'
# else:
# if month in [1, 2, 3, 4, 5, 6, 7, 8]:
# nm = str(month + 1)
# next_month = '0' + nm
# next_run_date = year + '-' + next_month + '-' + '24'
# elif month in [9, 10, 11]:
# next_month = str(month + 1)
# next_run_date = year + '-' + next_month + '-' + '24'
# elif month == 12:
# next_month = '01'
# year = str(int(temp_date[0]) + 1)
# next_run_date = year + '-' + next_month + '-' + '24'
#
# next_run_date = datetime.datetime.strptime(next_run_date, "%Y-%m-%d").date()
# if todays_date >= current_run_date:
# if data_avail == Scraper.event_log[Scraper.no_of_runs - 1]['Latest Available Data']:
# sleep_time = timedelta(days=1)
# Scraper.waiting(sleep_time)
#
# return 'RESTART'
#
# else:
# good_to_go = original_function(*args, **kwargs)
#
# return good_to_go
#
# elif current_run_date < todays_date < next_run_date:
# if todays_date < next_run_date:
# sleep_time = next_run_date - todays_date
# Scraper.waiting(sleep_time)
#
# return 'RESTART'
return wrapper
"""
______________________________________________________________________________________________________________
Use this section to house the instance, class and static functions
______________________________________________________________________________________________________________
"""
@staticmethod
def acres_to_sqft(search_string):
return str(round(float(search_string.group(1).rstrip(' AC.')) * 43560, 2))
@staticmethod
def address_list_scrape(driver_var, logger_var, mls_number, windows_var: list, **kwargs):
property_archive = WebDriverWait(driver_var, 20).until(
EC.presence_of_element_located((By.XPATH, "//span[contains(@class,'fa fa-history fa-lg')]")))
property_archive.click()
time.sleep(2)
windows_list = driver_var.window_handles
new_window2 = [window for window in windows_list if window not in windows_var][0]
driver_var.switch_to.window(new_window2)
time.sleep(2)
address_list = set()
page_results3 = driver_var.page_source
soup = BeautifulSoup(page_results3, 'html.parser')
# print(soup)
mls_tables = soup.find_all('table', {"class": "oneline"})
for table in mls_tables:
main_table2 = table.find('tbody')
mls_history = main_table2.find_all('tr')[1]
address_cell = mls_history.find_all('td')[3]
address_list.add(address_cell.get_text())
logger_var.info(f'{len(address_list)} historical addresses have been found for MLS#:{mls_number}')
driver_var.close()
driver_var.switch_to.window(windows_var[2])
driver_var.close()
driver_var.switch_to.window(windows_var[0])
return address_list
@staticmethod
def address_table_results(page_source_var, mls_number, logger_var):
try:
soup = BeautifulSoup(page_source_var, 'html.parser')
table = soup.find('table', {"class": "df-table nomin mart0", "id": "search-help-table"})
main_table = table.find('tbody')
all_rows = main_table.find_all('tr')
assert len(all_rows) > 0, f'There were no MLS results found. MLS#:{mls_number}'
except AssertionError as AE:
logger_var.info(f'{AE}')
return AE
else:
return all_rows
def area_demographics(self, city):
# Create a method that generates a report on the stores in or near a city,
# school rankings, walk score, public transportation
pass
def available_inventory(self, city=None):
"""
Checks the available inventory in that city and checks the percentage of homes which have
decreased/increased in price and the percentage of the avg increase/decrease with respect to
the original LP
:param city:
:return:
"""
pass
@staticmethod
def check_run_log(run_log_object: dict, logger):
count = 0
for prop_type, run_status in run_log_object.items():
for status in run_status.values():
if status == 'DOWNLOADED':
count += 1
else:
pass
if count == 12:
for prop_type, run_status in run_log_object.items():
for qtr in run_status.keys():
run_log_object[prop_type][qtr] = 'D.N.A'
information = f'The sales data for all quarters have been downloaded. The run log has been reset'
GSMLS.save_run_log(run_log_object, qtr, prop_type, "Doesn't matter", logger, message=information)
def check_status(self):
# Checks the action buttons to filter to the status of the homes we want to look up
pass
@staticmethod
def cities_download_manager(counties, county_id, driver_var, logger):
logger.info(f'Sales data for municipalities located in {counties[county_id]} '
f'County will now be downloaded')
GSMLS.set_county(county_id, driver_var)
time.sleep(1) # Latency period added in order to load and scrape city names
results1 = driver_var.page_source
return GSMLS.find_cities(results1)
@staticmethod
def clean_addresses(search_string):
target_list = str(search_string.group()).split(' ')
new_address_list = [i for i in target_list if i != '']
return ' '.join(new_address_list)
@staticmethod
def clean_and_transform_data_lnd(pandas_db, mls, qtr):
"""
Cleaning that needs to be done
1. Filter for columns that I want displayed
2. Remove the asterics attached to the following columns:
BLOCKID, COUNTY, LOTSIZE, LOTID, STREETNAME
3. Remove the *(NNNN*) from the town name
4. Make LISTDATE, PENDINGDATE, CLOSEDDATE columns date type
5. If no POOL, fillna with 'N' and POOLDESC with 'N'
6. Create ADDRESS column by combining the 'STREETNUMDISPLAY' and 'STREETNAME' columns
7. Create 'LATITUDE' AND 'LONGITUTDE' columns and fill with 'N/A'. Move columns right before ADDRESS column
8. Add a column named "UC-Days" which calculates the total days between going under contract and closing
# Can be vectorized by doing db['UC-Days'] = db['Closing Date'] - db['Under Contract']
9. Convert all the values in the LOTSIZE column to sqft. Use Pandas str methods
:param pandas_db:
:param mls
:param qtr
:return:
"""
pandas_db = pandas_db.astype({'STREETNUMDISPLAY': 'string', 'STREETNAME': 'string',
'ORIGLISTPRICE': 'int64', 'LISTPRICE': 'int64', 'SALESPRICE': 'int64'})
pandas_db.round({'SPLP': 3})
# List item 2
pandas_db['MLS'] = mls
pandas_db['VARIANCE NEEDED'] = 'N*' # This is a temporary value which will be changed to either Y or N when the function is created
pandas_db['QTR'] = qtr
pandas_db['Z-SCORE'] = (pandas_db['SALESPRICE'] - pandas_db['SALESPRICE'].mean()) / pandas_db[
'SALESPRICE'].std()
pandas_db.insert(0, 'MLS', pandas_db.pop('MLS'))
pandas_db.insert(1, 'QTR', pandas_db.pop('QTR'))
pandas_db.insert(2, 'LATITUDE', 0)
pandas_db.insert(3, 'LONGITUDE', 0)
pandas_db.insert(4, 'BLOCKID', pandas_db.pop('BLOCKID').str.strip('*'))
pandas_db.insert(5, 'LOTID', pandas_db.pop('LOTID').str.strip('*'))
pandas_db.insert(6, 'STREETNAME', pandas_db.pop('STREETNAME').str.strip('*'))
pandas_db.insert(8, 'COUNTY', pandas_db.pop('COUNTY').str.strip('*'))
pandas_db.insert(9, 'TAXID', pandas_db.pop('TAXID').str.strip('*'))
pandas_db.insert(10, 'MLSNUM', pandas_db.pop('MLSNUM'))
pandas_db.insert(11, 'LOTSIZE', pandas_db.pop('LOTSIZE').str.strip('*'))
pandas_db.insert(12, 'LOTDESC', pandas_db.pop('LOTDESC'))
pandas_db.insert(13, 'VARIANCE NEEDED', pandas_db.pop('VARIANCE NEEDED'))
pandas_db.insert(14, 'Z-SCORE', pandas_db.pop('Z-SCORE'))
pandas_db.insert(15, 'ORIGLISTPRICE', pandas_db.pop('ORIGLISTPRICE'))
pandas_db.insert(16, 'LISTPRICE', pandas_db.pop('LISTPRICE'))
pandas_db.insert(17, 'SALESPRICE', pandas_db.pop('SALESPRICE'))
pandas_db.insert(18, 'SPLP', pandas_db.pop('SPLP'))
# List item 3
pandas_db.insert(7, 'TOWN', pandas_db.pop('TOWN').str.rstrip('*(1234567890)'))
# List item 4 and 8
pandas_db.insert(20, 'LISTDATE', pd.to_datetime(pandas_db.pop('LISTDATE')))
pandas_db.insert(21, 'PENDINGDATE', pd.to_datetime(pandas_db.pop('PENDINGDATE')))
pandas_db.insert(22, 'CLOSEDDATE', pd.to_datetime(pandas_db.pop('CLOSEDDATE')))
pandas_db.insert(23, 'UNDER CONTRACT LENGTH', pandas_db['CLOSEDDATE'] - pandas_db['PENDINGDATE'])
# List item 6
street_num = pandas_db.pop('STREETNUMDISPLAY')
street_add = pandas_db.pop('STREETNAME')
pandas_db.insert(3, 'ADDRESS', street_num.str.cat(street_add, join='left', sep=' ')
.str.replace(r'Rd$', 'Road', regex=True)
.str.replace(r'Ct$', 'Court', regex=True)
.str.replace(r'St$', 'Street', regex=True)
.str.replace(r'Ave$', 'Avenue', regex=True)
.str.replace(r'Dr$', 'Drive', regex=True)
.str.replace(r'Ln$', 'Lane', regex=True)
.str.replace(r'Pl$', 'Place', regex=True)
.str.replace(r'Ter$', 'Terrace', regex=True)
.str.replace(r'Hwy$', 'Highway', regex=True)
.str.replace(r'Pkwy$', 'Parkway', regex=True)
.str.replace(r'Cir$', 'Circle', regex=True))
pandas_db.insert(6, 'ADDRESS', pandas_db.pop('ADDRESS').str.replace(r'.*', GSMLS.clean_addresses, regex=True))
return pandas_db
@staticmethod
def clean_and_transform_data_mul(pandas_db, mls, qtr):
"""
Cleaning that needs to be done
1. Filter for columns that I want displayed
2. Remove the asterics attached to the following columns:
BLOCKID, COUNTY, LOTSIZE, LOTID, STREETNAME
3. Remove the *(NNNN*) from the town name
4. Make LISTDATE, PENDINGDATE, CLOSEDDATE columns date type
5. If no POOL, fillna with 'N' and POOLDESC with 'N'
6. Create ADDRESS column by combining the 'STREETNUMDISPLAY' and 'STREETNAME' columns
7. Create 'LATITUDE' AND 'LONGITUTDE' columns and fill with 'N/A'. Move columns right before ADDRESS column
8. Add a column named "UC-Days" which calculates the total days between going under contract and closing
# Can be vectorized by doing db['UC-Days'] = db['Closing Date'] - db['Under Contract']
9. Convert all the values in the LOTSIZE column to sqft. Use Pandas str methods
:param pandas_db:
:param mls:
:param qtr:
:return:
"""
pandas_db['RENOVATED'] = pandas_db['RENOVATED'].fillna(0)
pandas_db = pandas_db.astype({'STREETNUMDISPLAY': 'string', 'STREETNAME': 'string',
'RENOVATED': 'int64', 'ORIGLISTPRICE': 'int64',
'LISTPRICE': 'int64', 'SALESPRICE': 'int64'})
pandas_db.round({'BATHSTOTAL': 1, 'SPLP': 3})
# List item 2
pandas_db['MLS'] = mls
pandas_db['QTR'] = qtr
pandas_db['Z-SCORE'] = (pandas_db['SALESPRICE'] - pandas_db['SALESPRICE'].mean()) / pandas_db[
'SALESPRICE'].std()
pandas_db.insert(0, 'MLS', pandas_db.pop('MLS'))
pandas_db.insert(1, 'QTR', pandas_db.pop('QTR'))
pandas_db.insert(2, 'LATITUDE', 0)
pandas_db.insert(3, 'LONGITUDE', 0)
pandas_db.insert(4, 'BLOCKID', pandas_db.pop('BLOCKID').str.strip('*'))
pandas_db.insert(5, 'LOTID', pandas_db.pop('LOTID').str.strip('*'))
pandas_db.insert(6, 'STREETNAME', pandas_db.pop('STREETNAME').str.strip('*'))
pandas_db.insert(7, 'COUNTY', pandas_db.pop('COUNTY').str.strip('*'))
pandas_db.insert(11, 'LOTSIZE', pandas_db.pop('LOTSIZE').str.strip('*'))
pandas_db.insert(12, 'LOTDESC', pandas_db.pop('LOTDESC'))
pandas_db.insert(14, 'Z-SCORE', pandas_db.pop('Z-SCORE'))
pandas_db.insert(15, 'ORIGLISTPRICE', pandas_db.pop('ORIGLISTPRICE'))
pandas_db.insert(16, 'LISTPRICE', pandas_db.pop('LISTPRICE'))
pandas_db.insert(17, 'SALESPRICE', pandas_db.pop('SALESPRICE'))
pandas_db.insert(18, 'SPLP', pandas_db.pop('SPLP'))
# List item 3
pandas_db.insert(7, 'TOWN', pandas_db.pop('TOWN').str.rstrip('*(1234567890)'))
# List item 4 and 8
pandas_db.insert(26, 'LISTDATE', pd.to_datetime(pandas_db.pop('LISTDATE')))
pandas_db.insert(27, 'PENDINGDATE', pd.to_datetime(pandas_db.pop('PENDINGDATE')))
pandas_db.insert(28, 'CLOSEDDATE', pd.to_datetime(pandas_db.pop('CLOSEDDATE')))
pandas_db.insert(29, 'UNDER CONTRACT LENGTH', pandas_db['CLOSEDDATE'] - pandas_db['PENDINGDATE'])
# List item 6
street_num = pandas_db.pop('STREETNUMDISPLAY')
street_add = pandas_db.pop('STREETNAME')
pandas_db.insert(3, 'ADDRESS', street_num.str.cat(street_add, join='left', sep=' ')
.str.replace(r'Rd$', 'Road', regex=True)
.str.replace(r'Ct$', 'Court', regex=True)
.str.replace(r'St$', 'Street', regex=True)
.str.replace(r'Ave$', 'Avenue', regex=True)
.str.replace(r'Dr$', 'Drive', regex=True)
.str.replace(r'Ln$', 'Lane', regex=True)
.str.replace(r'Pl$', 'Place', regex=True)
.str.replace(r'Ter$', 'Terrace', regex=True)
.str.replace(r'Hwy$', 'Highway', regex=True)
.str.replace(r'Pkwy$', 'Parkway', regex=True)
.str.replace(r'Cir$', 'Circle', regex=True))
pandas_db.insert(6, 'ADDRESS', pandas_db.pop('ADDRESS').str.replace(r'.*', GSMLS.clean_addresses, regex=True))
return pandas_db
@staticmethod
def clean_and_transform_data_res(pandas_db, mls, qtr, median_sales):
"""
Cleaning that needs to be done
1. Filter for columns that I want displayed
2. Remove the asterics attached to the following columns:
BLOCKID, COUNTY, LOTSIZE, LOTID, STREETNAME
3. Remove the *(NNNN*) from the town name
4. Make LISTDATE, PENDINGDATE, CLOSEDDATE columns date type
5. If no POOL, fillna with 'N' and POOLDESC with 'N'
6. Create ADDRESS column by combining the 'STREETNUMDISPLAY' and 'STREETNAME' columns
7. Create 'LATITUDE' AND 'LONGITUTDE' columns and fill with 'N/A'. Move columns right before ADDRESS column
8. Add a column named "UC-Days" which calculates the total days between going under contract and closing
# Can be vectorized by doing db['UC-Days'] = db['Closing Date'] - db['Under Contract']
9. Convert all the values in the LOTSIZE column to sqft. Use Pandas str methods
:param pandas_db:
:param mls:
:param qtr:
:param median_sales:
:return:
"""
pandas_db['SQFTAPPROX'] = pandas_db['SQFTAPPROX'].fillna(0)
pandas_db['RENOVATED'] = pandas_db['RENOVATED'].fillna(0)
pandas_db = pandas_db.astype({'STREETNUMDISPLAY': 'string', 'STREETNAME': 'string',
'SQFTAPPROX': 'int64', 'RENOVATED': 'int64', 'ORIGLISTPRICE': 'int64',
'LISTPRICE': 'int64', 'SALESPRICE': 'int64'})
pandas_db.round({'BATHSTOTAL': 1, 'SPLP': 3})
# List item 2
pandas_db['MLS'] = mls
pandas_db['QTR'] = qtr
pandas_db['Z-SCORE'] = (pandas_db['SALESPRICE'] - median_sales[0]) / median_sales[1]
pandas_db.insert(0, 'MLS', pandas_db.pop('MLS'))
pandas_db.insert(1, 'QTR', pandas_db.pop('QTR'))
pandas_db.insert(2, 'LATITUDE', 0)
pandas_db.insert(3, 'LONGITUDE', 0)
pandas_db.insert(4, 'BLOCKID', pandas_db.pop('BLOCKID').str.strip('*'))
pandas_db.insert(5, 'LOTID', pandas_db.pop('LOTID').str.strip('*'))
pandas_db.insert(6, 'STREETNAME', pandas_db.pop('STREETNAME').str.strip('*'))
pandas_db.insert(7, 'COUNTY', pandas_db.pop('COUNTY').str.strip('*'))
pandas_db.insert(11, 'SQFTAPPROX', pandas_db.pop('SQFTAPPROX'))
pandas_db.insert(13, 'LOTSIZE', pandas_db.pop('LOTSIZE').str.strip('*'))
pandas_db.insert(14, 'LOTDESC', pandas_db.pop('LOTDESC'))
pandas_db.insert(18, 'Z-SCORE', pandas_db.pop('Z-SCORE'))
# List item 3
pandas_db.insert(7, 'TOWN', pandas_db.pop('TOWN').str.rstrip('*(1234567890)'))
# List item 4 and 8
pandas_db.insert(26, 'LISTDATE', pd.to_datetime(pandas_db.pop('LISTDATE')))
pandas_db.insert(27, 'PENDINGDATE', pd.to_datetime(pandas_db.pop('PENDINGDATE')))
pandas_db.insert(28, 'CLOSEDDATE', pd.to_datetime(pandas_db.pop('CLOSEDDATE')))
pandas_db.insert(29, 'UNDER CONTRACT LENGTH', pandas_db['CLOSEDDATE'] - pandas_db['PENDINGDATE'])
# List item 5
pandas_db["POOL"].fillna('N')
pandas_db["POOLDESC"].fillna('N')
# List item 6
street_num = pandas_db.pop('STREETNUMDISPLAY')
street_add = pandas_db.pop('STREETNAME')
pandas_db.insert(3, 'ADDRESS', street_num.str.cat(street_add, join='left', sep=' ')
.str.replace(r'Rd$|Rd\.$', 'Road', regex=True)
.str.replace(r'Ct$|Ct\.$', 'Court', regex=True)
.str.replace(r'St$|St\.$', 'Street', regex=True)
.str.replace(r'Ave$|Ave\.$', 'Avenue', regex=True)
.str.replace(r'Dr$|Dr\.$', 'Drive', regex=True)
.str.replace(r'Ln$|Ln\.$', 'Lane', regex=True)
.str.replace(r'Pl$|Pl\.$', 'Place', regex=True)
.str.replace(r'Ter$|Ter\.$', 'Terrace', regex=True)
.str.replace(r'Hwy$|Hwy\.$', 'Highway', regex=True)
.str.replace(r'Pkwy$|Pkwy\.$', 'Parkway', regex=True)
.str.replace(r'Cir$|Cir\.$', 'Circle', regex=True))
pandas_db.insert(6, 'ADDRESS', pandas_db.pop('ADDRESS').str.replace(r'.*', GSMLS.clean_addresses, regex=True))
return pandas_db
@staticmethod
@logger_decorator
@clean_db_decorator
def clean_db(**kwargs):
"""
This function accepts an Excel document or Pandas database to clean and transform all data into uniform
datatypes before being transferred into a SQL database. This also fortifies the data with all the proper
living space sq_ft and converts all lot size values to sq_ft
- Fill the SQFT column using find_sq_ft method
:param dirty_db:
:param tax_db:
:param property_type:
:param qtr:
:return:
"""
dirty_db = kwargs['initial_db']
# tax_db = kwargs['tax_db']
property_type = kwargs['property_type']
mls_type = kwargs['mls_type']
qtr = kwargs['qtr']
median_sales_prices = kwargs['median_sales_price']
target_columns = ['TAXID', 'MLSNUM', 'BLOCKID', 'LOTID', 'STREETNUMDISPLAY', 'STREETNAME', 'TOWN', 'COUNTY',
'ROOMS', 'BEDS', 'BATHSTOTAL', 'LOTSIZE', 'LOTDESC', 'SQFTAPPROX', 'ORIGLISTPRICE', 'LISTPRICE',
'SALESPRICE', 'SPLP', 'LOANTERMS', 'YEARBUILT', 'YEARBUILTDESC', 'STYLEPRIMARY',
'PROPCOLOR', 'RENOVATED', 'TAXAMOUNT', 'TAXRATE', 'LISTDATE', 'PENDINGDATE',
'CLOSEDDATE', 'DAYSONMARKET', 'OFFICENAME', 'OFFICEPHONE', 'FAX',
'AGENTNAME', 'AGENTPHONE', 'COMPBUY', 'SELLOFFICENAME', 'SELLAGENTNAME', 'FIREPLACES',
'GARAGECAP', 'POOL', 'POOLDESC', 'BASEMENT', 'BASEDESC', 'AMENITIES', 'APPLIANCES', 'COOLSYSTEM',
'DRIVEWAYDESC', 'EXTERIOR', 'FLOORS', 'HEATSRC', 'HEATSYSTEM', 'ROOF',
'SIDING', 'SEWER', 'WATER', 'WATERHEATER', 'ROOMLVL1DESC', 'ROOMLVL2DESC', 'ROOMLVL3DESC',
'REMARKSPUBLIC']
if property_type == 'RES':
clean_db = dirty_db[target_columns].fillna(np.nan)
clean_db = clean_db.pipe(GSMLS.clean_and_transform_data_res, mls=mls_type, qtr=qtr, median_sales=median_sales_prices)\
.pipe(GSMLS.find_sq_ft, **kwargs)\
.pipe(GSMLS.convert_lot_size, property_type=property_type)
elif property_type == 'MUL':
temp_target_columns = [column for column in target_columns if column not in ['POOL', 'POOLDESC',
'SQFTAPPROX', 'STYLEPRIMARY', 'FIREPLACES', 'AMENITIES', 'APPLIANCES',
'FLOORS', 'ROOMLVL1DESC', 'ROOMLVL2DESC', 'ROOMLVL3DESC']]
temp_target_columns.extend(['UNIT1BATHS', 'UNIT1BEDS', 'UNIT2BATHS', 'UNIT2BEDS', 'UNIT3BATHS', 'UNIT3BEDS',
'UNIT4BATHS', 'UNIT4BEDS'])
clean_db = dirty_db[temp_target_columns].fillna(np.nan)
clean_db = clean_db.pipe(GSMLS.clean_and_transform_data_mul, mls=mls_type, qtr=qtr)\
.pipe(GSMLS.total_units).pipe(GSMLS.convert_lot_size, property_type=property_type)
elif property_type == 'LND':
remove_columns = ['ROOMS', 'BEDS', 'BATHSTOTAL', 'YEARBUILT', 'POOLDESC', 'SQFTAPPROX',
'YEARBUILTDESC', 'STYLEPRIMARY', 'PROPCOLOR', 'RENOVATED', 'FIREPLACES',
'GARAGECAP', 'POOL', 'BASEMENT', 'BASEDESC', 'AMENITIES', 'APPLIANCES', 'COOLSYSTEM',
'DRIVEWAYDESC', 'EXTERIOR', 'FLOORS', 'HEATSRC', 'HEATSYSTEM', 'ROOF',
'SIDING', 'SEWER', 'WATER', 'WATERHEATER', 'ROOMLVL1DESC', 'ROOMLVL2DESC',
'ROOMLVL3DESC', 'POOL']
temp_target_columns = [column for column in target_columns if column not in remove_columns]
temp_target_columns.extend(['NUMLOTS', 'ZONING', 'BUILDINGSINCLUDED', 'CURRENTUSE', 'DEVSTATUS', 'DOCSAVAIL',
'EASEMENT', 'FLOODINSUR', 'FLOODZONE', 'IMPROVEMENTS', 'LOCATION',
'PERCTEST', 'ROADSURFACEDESC', 'SERVICES', 'SEWERINFO', 'SOILTYPE', 'WATERINFO',
'ZONINGDESC'])
clean_db = dirty_db[temp_target_columns].fillna(np.nan)
clean_db = clean_db.pipe(GSMLS.clean_and_transform_data_lnd, mls=mls_type, qtr=qtr)\
.pipe(GSMLS.convert_lot_size, property_type=property_type)
return clean_db
def comps(self, property_address, br=None, bth=None, sq_ft=None, home_type=None):
"""
Method which accepts a property address as an expected argument. Other expected agruments with a default
value of None but if given, can help better narrow the comps.
I need to be able to animate the GSMLS map tool so I can find all comps within a mile
Follow the NABPOPs Guidelines for Comparables to ensure the model gives the best comps.
The following ideas need to be included:
- Guidelines for comps
- Lack of comps
- Market Considerations
- Rating Property/Amenities
- Adjustment features
- Land Value
TRANSFORM THE DATABASE TO HAVE COLUMN NAMES AS THE INDEX AND THE PROPERTY NAMES AS THE COLUMN NAMES!!!
:param property_address:
:param br:
:param bth:
:param sq_ft:
:param home_type:
:return:
"""
pass
@staticmethod
def connect2postgresql():
# Do I create a function which retrieve my info from UniversalFunction.get_us_pw?
'''
database: the name of the database that you want to connect.
user: the username used to authenticate.
password: password used to authenticate.
host: database server address e.g., localhost or an IP address.
port: the port number that defaults to 5432 if it is not provided.
'''
username, pw = GSMLS.get_us_pw('PostgreSQL')
conn = psycopg2.connect(
host="localhost",
database="nj_realestate_data",
user=username,
password=pw)
cur = conn.cursor()
return tuple([cur, conn, username, pw])
@staticmethod
def convert_lot_size(db, property_type):
"""
:param db:
:param property_type:
:return:
"""
acres_pattern = r'(\.\d{1,6}(\sAC)?|\.\d{1,6}(\sAC.)?|\d{1,4}\.\d{1,6}(\sAC)?|\d{1,4}\.\d{1,6}(\sAC.)?)'
by_pattern = r'(\d{1,5})X\s(\d{1,5})|(\d{1,5})X(\d{1,5})|(\d{1,5})\sX\s(\d{1,5})|(\d{1,5})\sX(\d{1,5})'
db = db.astype({'LOTSIZE': 'string'})
lotsize_sqft = db['LOTSIZE']
if property_type == 'RES':
db.insert(12, 'LOTSIZE (SQFT)', lotsize_sqft.str.replace(acres_pattern, GSMLS.acres_to_sqft, regex=True)
.str.replace(by_pattern, GSMLS.length_and_width_to_sqft, regex=True).str.rstrip('.')
.str.replace(',', ''))
elif property_type == 'MUL':
db.insert(12, 'LOTSIZE (SQFT)', lotsize_sqft.str.replace(acres_pattern, GSMLS.acres_to_sqft, regex=True)
.str.replace(by_pattern, GSMLS.length_and_width_to_sqft, regex=True).str.rstrip('.')
.str.replace(',', ''))
elif property_type == 'LND':
db.insert(16, 'LOTSIZE (SQFT)', lotsize_sqft.str.replace(acres_pattern, GSMLS.acres_to_sqft, regex=True)
.str.replace(by_pattern, GSMLS.length_and_width_to_sqft, regex=True).str.rstrip('.')
.str.replace(',', ''))
db = db.astype({'LOTSIZE (SQFT)': 'float64'})
db = db.round({'LOTSIZE (SQFT)': 2})
return db
@staticmethod
def cooling_system_statistics(db, **kwargs):
# Can only be used with RES and MUL property types
property_type = str(db.__name__)[-3:].upper()
if property_type == 'RES' or 'MUL':
interior_columns = ['COUNTY', 'TOWN', 'COOLSYSTEM']
interior_df = db[interior_columns].groupby(['COUNTY', 'TOWN'])
cooling_system_stats = interior_df['COOLSYSTEM'].value_counts()
return cooling_system_stats
else:
raise ValueError
@staticmethod
def create_lnd_sales_table(cursor_var, conn_var):
statement = "CREATE TABLE mul_sales_data (id serial, mls varchar(20), quarter char(2), latitude numeric," \
"longitude numeric, blockid smallint, lotid smallint, address varchar(100), town varchar(100)," \
"county varchar(100), tax_id varchar(100), mlsnum real, lotsize varchar(50), lotsize_sqft real," \
"lot_desc varchar(50), variance_needed varchar(3), z_score real, origlistprice integer," \
"listprice integer, salesprice integer, splp real, listdate date, pendingdate date," \
"closeddate date, under_contract_length interval, loan_terms varchar(50), tax_amount integer," \
"tax_rate real, dom smallint, lotsize varchar(50), office_name varchar(250), office_phone varchar(15)," \
"fax varchar(15), listing_agent varchar(100), agent_phone varchar(15), comp_buy varchar(20)," \
"buying_office varchar(250), buying_agent varchar(100), public_remarks text, num_lots smallint," \
"zoning varchar(50), buildings_included varchar(50), current_use varchar(100)," \
"development_status varchar(100), docs_avaialable varchar(100), easement varchar(5)," \
"flood_insurance varchar(10), flood_zone varchar(10), improvements varchar(100)," \
"location varchar(100), perc_test varchar(100), road_surface_desc varchar(100)," \
"services varchar(100), sewer varchar(100) soil_type varchar(100), water_info varchar(100)," \
"zoning varchar(100));"
cursor_var.execute(statement)
conn_var.commit()
@staticmethod
def create_mul_sales_table(cursor_var, conn_var):
statement = "CREATE TABLE mul_sales_data (id serial, mls varchar(20), quarter char(2), latitude numeric," \
"longitude numeric, blockid smallint, lotid smallint, total_units smallint, address varchar(100), town varchar(100)," \
"county varchar(100), tax_id varchar(100), mlsnum real, sqft_approx smallint," \
"lotsize varchar(50), lotsize_sqft real, rooms smallint, beds smallint, bathstotal real," \
"lot_desc varchar(50), z_score real, origlistprice integer, listprice integer, salesprice integer," \
"splp real, loan_terms varchar(50), yearbuilt smallint, yearbuilt_desc varchar(20)," \
"listdate date, pending_date date, closeddate date, under_contract_length interval, dom smallint," \
"primary_style varchar(100), property_color varchar(20), renovated smallint, tax_amount integer," \
"tax_rate real, office_name varchar(250), office_phone varchar(15), fax varchar(15)," \
"listing_agent varchar(100), agent_phone varchar(15), comp_buy varchar(20)," \
"buying_office varchar(250), buying_agent varchar(100), basement char(1), basement_desc varchar(100)," \
"coolsystem varchar(100), driveway_desc varchar(100), exterior varchar(100)," \
"heatsource varchar(50), heatsystem varchar(100), roof varchar(100)," \
"siding varchar(50), sewer varchar(10), water varchar(10), waterheater varchar(10)," \
"unit1_baths real, unit1_beds smallint, unit2_baths real, unit2_beds smallint," \
"unit3_baths real, unit3_beds smallint, unit4_baths real, unit4_beds smallint," \
"public_remarks text);"
cursor_var.execute(statement)
conn_var.commit()
@staticmethod
def create_res_sales_table(cursor_var, conn_var):
statement = "CREATE TABLE res_sales_data (id serial, mls varchar(20), quarter char(2), latitude numeric," \
"longitude numeric, blockid smallint, lotid smallint, address varchar(100), town varchar(100)," \
"county varchar(100), tax_id varchar(100), mlsnum real, sqft_approx smallint," \
"lotsize varchar(50), lotsize_sqft real, rooms smallint, beds smallint, bathstotal real," \
"lot_desc varchar(50), z_score real, origlistprice integer, listprice integer, salesprice integer," \
"splp real, loan_terms varchar(50), yearbuilt smallint, yearbuilt_desc varchar(20)," \
"listdate date, pending_date date, closeddate date, under_contract_length interval, dom smallint," \
"primary_style varchar(100), property_color varchar(20), renovated smallint, tax_amount integer," \
"tax_rate real, office_name varchar(250), office_phone varchar(15), fax varchar(15)," \
"listing_agent varchar(100), agent_phone varchar(15), comp_buy varchar(20)," \
"buying_office varchar(250), buying_agent varchar(100), fireplaces smallint, garagecap smallint, " \
"pool char(1), pooldesc varchar(50), basement char(1), basement_desc varchar(100), ammenities varchar(50)," \
"appliances varchar(250), coolsystem varchar(100), driveway_desc varchar(100), exterior varchar(100)," \
"floors varchar(100), heatsource varchar(50), heatsystem varchar(100), roof varchar(100), " \
"siding varchar(50), sewer varchar(10), water varchar(10), waterheater varchar(10), interior varchar(250)," \
"roomlvl1desc text, roomlvl2desc text, roomlvl3desc text, public_remarks text);" \
cursor_var.execute(statement)
conn_var.commit()
@staticmethod
def create_sql_table(table_name, cursor_var, conn_var, **kwargs):
logger = kwargs['logger']
if table_name == 'res_sales_data':
GSMLS.create_res_sales_table(cursor_var, conn_var)
logger.info(f'PostgreSQL table named {table_name} has been created')
elif table_name == 'mul_sales_data':
GSMLS.create_mul_sales_table(cursor_var, conn_var)
logger.info(f'PostgreSQL table named {table_name} has been created')
elif table_name == 'lnd_sales_data':
GSMLS.create_res_sales_table(cursor_var, conn_var)
logger.info(f'PostgreSQL table named {table_name} has been created')
else:
# placeholder for a block that a user can create a table on spot?
pass
def descriptive_stats_state(self):
# Run descriptive analysis on all the homes for the state for the quarter
pass
@staticmethod
def descriptive_statistics_county(db, **kwargs):
# Can be used with any property type RES, MUL, LND
main_columns = ['COUNTY', 'TOWN', 'LISTPRICE', 'SALESPRICE', 'DAYSONMARKET', 'UC-DAYS', 'SPLP']
target_df = db[main_columns].groupby(['COUNTY', 'TOWN'])
descriptive_stats = target_df.describe()
return descriptive_stats
@staticmethod
def download_manager(cities, city_id, property_type, qtr, driver_var, logger):
GSMLS.set_city(city_id, driver_var)
GSMLS.show_results(driver_var)
time.sleep(2)
page_results1 = driver_var.page_source
if "close_generated_popup('alert_popup')" in str(page_results1):
# No results found
GSMLS.no_results(city_id, driver_var)
logger.info(f'There is no GSMLS {property_type} sales data available for {cities[city_id]}')
else:
# Results were found
GSMLS.results_found(driver_var, cities[city_id], qtr, property_type)
GSMLS.set_city(city_id, driver_var)
logger.info(f'Sales data for {cities[city_id]} has been downloaded')
@staticmethod
@logger_decorator
# @kpi
def email_campaign(**kwargs):
pass
@staticmethod
def find_cities(page_source):
"""
:param page_source:
:return:
"""
# Find the counties on the NJ Tax Assessment page
value_pattern = re.compile(r'title="(\d{4,5}?)\s-\s(.*)"')
soup = BeautifulSoup(page_source, 'html.parser')
target = soup.find('div', {"id": "town1"})
target_contents = target.find_all('div', {'class': 'selection-item'})
cities = {}
for i in target_contents:
main_contents = str(i) # Strips the contents of the target counties (ie: 10 Atlantic ---> [10, Atlantic])
target_search = value_pattern.search(main_contents)
cities[target_search[1]] = target_search[2]
return cities
@staticmethod
def find_counties(page_source):
"""
:param page_source:
:return:
"""
# Find the counties on the NJ Tax Assessment page
value_pattern = re.compile(r'(\d{2})\s-\s(\w+)')
target_pattern = re.compile(r'title="(\d{2,3}?)\s-\s(.*)"')
soup = BeautifulSoup(page_source, 'html.parser')
target_contents = soup.find_all('label', {'title': value_pattern})
counties = {}
for i in target_contents:
main_contents = str(i) # Strips the contents of the target counties (ie: 10 Atlantic ---> [10, Atlantic])
target_search = target_pattern.search(main_contents)
counties[target_search[1]] = target_search[2]
return counties
@staticmethod
def find_sq_ft(db, tax_db, **kwargs):
"""
:param db:
:param tax_db:
:return:
"""
numbers_dict = {'1ST': 'FIRST', 'FIRST': '1ST', '2ND': 'SECOND', 'SECOND': '2ND',
'3RD': 'THIRD', 'THIRD': '3RD', '4TH': 'FOURTH', 'FOURTH': '4TH',
'5TH': 'FIFTH', 'FIFTH': '5TH', '6TH': 'SIXTH', 'SIXTH': '6TH',
'7TH': 'SEVENTH', 'SEVENTH': '7TH', '8TH': 'EIGHTH', 'EIGHTH': '8TH',
'9TH': 'NINTH', 'NINTH': '9TH', '10TH': 'TENTH', 'TENTH': '10TH'}
address_list = db['ADDRESS'].to_list()
tax_address_list = tax_db['Property Location'].to_list()
db.set_index('ADDRESS', inplace=True, drop=True)
tax_db.set_index('Property Location', inplace=True, drop=False) # Column would still need to be indexed in the event of a ValueError so leave duplicate
numbered_blocks = re.compile(
r'\d{1,2}?st|\d{1,2}?nd|\d{1,2}?rd|\d{1,2}?th|First|Second|Third|Fourth|Fifth|Sixth|Seventh|Eighth|Nineth|Tenth')