Hugging Face's logo

Spaces:
felixz
/
us-address-matching-model
Runtime error

App Files Community
Feliks Zaslavskiy commited on
Commit
6005876
•
1 Parent(s): 71667b3

data work

Browse files
Files changed (5) hide show
  1. app.py +1 -1
  2. data_set_training.csv +157 -49
  3. dev_set_training.csv +14 -1
  4. data.py → quick_evaluate.py +23 -1
  5. train.py +1 -1
app.py CHANGED
@@ -14,7 +14,7 @@ from io import BytesIO
14
  #model = AlbertModel.from_pretrained('albert-' + model_size + '-v2')
15
 
16
  # For baseline 'sentence-transformers/paraphrase-albert-base-v2'
17
- model_name = 'output/training_OnlineConstrativeLoss-2023-03-10_11-17-15'
18
 
19
  similarity_threshold = 0.9
20
 
 
14
  #model = AlbertModel.from_pretrained('albert-' + model_size + '-v2')
15
 
16
  # For baseline 'sentence-transformers/paraphrase-albert-base-v2'
17
+ model_name = 'output/training_OnlineConstrativeLoss-2023-03-11_23-47-34'
18
 
19
  similarity_threshold = 0.9
20
 
data_set_training.csv CHANGED
@@ -20,16 +20,16 @@ address1|address2|are_same
20
  65 Mountain Blvd Ext, Warren NJ 07059|65 Mountain Blvd. Extension, Warren NJ 07059|1
21
  65 Mountain Blvd Ext, Warren NJ 07059|65 Mountain Blvd. Extention, Warren NJ 07059|1
22
  65 Mountain Blvd Ext, Warren NJ 07059|65 Mtn Blvd Ext, Warren NJ 07059|1
23
- 65 Mountain Blvd Ext, Warren NJ 07059|65 Mountain Blvd Extension, Suite A|0
24
- 65 Mountain Blvd Ext, Warren NJ 07059|65 Mountain Boulevard Ext, Apt 2B|0
25
- 65 Mountain Blvd Ext, Warren NJ 07059|65 Mountain Blvd Ext, Building C|0
26
- 65 Mountain Blvd Ext, Warren NJ 07059|65 Mountain Blvd Ext., Suite 3|0
27
- 65 Mountain Blvd Ext, Warren NJ 07059|65 Mountain Blvd Ext. W|0
28
- 65 Mountain Blvd Ext, Warren NJ 07059|65 Mountain Blvd Ext, Unit 5|0
29
- 65 Mountain Blvd Ext, Warren NJ 07059|65 Mountain Blvd Extension, Room 12|0
30
- 65 Mountain Blvd Ext, Warren NJ 07059|65 Mountain Blvd Ext, Block D|0
31
- 65 Mountain Blvd Ext, Warren NJ 07059|65 Mountain Blvd Extension, Lot 7|0
32
- 65 Mountain Blvd Ext, Warren NJ 07059|65 Mountain Blvd Ext, Floor 2|0
33
  65 Mountain Blvd Ext, Warren NJ 07059|12 Mountain Blvd Ext, Warren NJ 07059|0
34
  65 Mountain Blvd Ext, Warren NJ 07059|23 Mountain Blvd Ext, Warren NJ 07059|0
35
  65 Mountain Blvd Ext, Warren NJ 07059|54 Mountain Blvd Ext, Warren NJ 07059|0
@@ -40,7 +40,7 @@ address1|address2|are_same
40
  802 New Holland Ave Suite 200, Lancaster, PA 17602|New Holland Avenue Suite 200, 802, Lancaster, PA 17602|1
41
  802 New Holland Ave Suite 200, Lancaster, PA 17602|Suite 200, 802 New Holland Ave, Lancaster, PA 17602|1
42
  802 New Holland Ave Suite 200, Lancaster, PA 17602|802 New Holland Ave #200, Lancaster, PA 17602|1
43
- 802 New Holland Ave Suite 200, Lancaster, PA 17602|802 New Holland Avenue, 2nd Floor, Lancaster, PA 17602|1
44
  802 New Holland Ave Suite 200, Lancaster, PA 17602|200 Suite, 802 New Holland Ave, Lancaster, PA 17602|1
45
  802 New Holland Ave Suite 200, Lancaster, PA 17602|802 New Holland Ave, Suite #200, Lancaster, PA 17602|1
46
  802 New Holland Ave Suite 200, Lancaster, PA 17602|Suite 200, 802 New Holland Avenue, Lancaster, PA 17602|1
@@ -54,7 +54,7 @@ address1|address2|are_same
54
  2205 S Bridge St Ste 300, Brady, TX 76825|Suite 300, 2205 S Bridge Street, Brady, TX 76825|1
55
  2205 S Bridge St Ste 300, Brady, TX 76825|2205 S Bridge Street, Suite #300, Brady, TX 76825|1
56
  2205 S Bridge St Ste 300, Brady, TX 76825|Ste 300, 2205 S Bridge St, Brady, TX 76825|1
57
- 2205 S Bridge St Ste 300, Brady, TX 76825|2205 South Bridge Street, 3rd Floor, Brady, TX 76825|1
58
  7671 W Middle Fork St, Boise, ID 83709|7671 West Middle Fork Street, Boise, ID 83709|1
59
  7671 W Middle Fork St, Boise, ID 83709|7671 W Middle Fork St., Boise, ID 83709|1
60
  7671 W Middle Fork St, Boise, ID 83709|Middle Fork St W, 7671, Boise, ID 83709|1
@@ -64,6 +64,7 @@ address1|address2|are_same
64
  7671 W Middle Fork St, Boise, ID 83709|Middle Fork Street West, 7671, Boise, ID 83709|1
65
  7671 W Middle Fork St, Boise, ID 83709|7671 W Middle Fork Street, Boise, ID 83709|1
66
  7671 W Middle Fork St, Boise, ID 83709|Middle Fork St, 7671 West, Boise, ID 83709|1
 
67
  7671 W Middle Fork St, Boise, ID 83709|7671 W Middle Fork St, Unit A, Boise, ID 83709|0
68
  3059 W 26th St, Chicago, IL 60623|3059 West 26th Street, Chicago, IL 60623|1
69
  3059 W 26th St, Chicago, IL 60623|3059 W 26th St., Chicago, IL 60623|1
@@ -78,49 +79,156 @@ address1|address2|are_same
78
  3059 W 26th St, Chicago, IL 60623|3059 W 26th St, SAH Community Care Clinic, Chicago, IL 60623|1
79
  125 S Gadsden St #300, Tallahassee, FL 32301|125 S Gadsden St #300A, Tallahassee, FL 32301|0
80
  125 S Gadsden St #300, Tallahassee, FL 32301|125 S Gadsden St, Suite 3A, Tallahassee, FL 32301|0
81
- 5432 Oak Street, Suite 101, Greenfield, 45678|6789 Pine Street, Suite 100, Mountain View, 90123|0
82
- 987 Main Road, Suite B, Roseville, 78901|4567 Birch Court, Suite D, River City, 67890|0
83
- 13579 Maple Boulevard, Suite 3, Springfield, 12345|5678 Park Street, Suite 150, Meadow Glen, 34567|0
84
- 2468 Cedar Lane, Suite 200, Lexington, 56789|9012 Maple Avenue, Suite 3, Springfield, 12345|0
85
- 777 Pine Street, Suite 100, Portland, 90123|2345 Birch Avenue, Suite 50, Manchester, 23456|0
86
- 1234 Birch Court, Suite 50, Manchester, 23456|1234 Cedar Lane, Suite 50, Oceanview, 23456|0
87
- 888 Chestnut Avenue, Suite D, Charleston, 67890|7890 Chestnut Avenue, Suite 300, Lakeside, 89012|0
88
- 999 Willow Drive, Suite 300, Greenville, 89012|2345 Willow Lane, Suite 75, Forest Hills, 23456|0
89
- 111 Park Avenue, Suite 75, Richmond, 23456|9012 Elm Road, Suite 3, Big City, 12345|0
90
- 2222 Grove Street, Suite 150, Savannah, 34567|1234 Elm Street, Suite 101, Greenfield, 45678|0
91
- 2178 Oak Road, Suite 101, Greenfield, 45678|3456 Maple Boulevard, Suite 200, Sunnyville, 56789|0
92
- 43 Main Street, Suite B, Roseville, 78901|5678 Main Avenue, Suite B, Smallville, 78901|0
93
- 900 Maple Avenue, Suite 3, Springfield, 12345|2345 Oak Street, Suite 101, Anytown, 45678|0
94
- 675 Cedar Lane, Suite 200, Lexington, 56789|5678 Oak Road, Suite B, Roseville, 78901|0
95
- 80 Pine Street, Suite 100, Portland, 90123|2345 Park Lane, Suite 75, Richmond, 23456|0
96
- 2345 Birch Avenue, Suite 50, Manchester, 23456|4567 Chestnut Street, Suite D, Charleston, 67890|0
97
- 867 Chestnut Street, Suite D, Charleston, 67890|5678 Grove Boulevard, Suite 150, Savannah, 34567|0
98
- 29 Willow Road, Suite 300, Greenville, 89012|3456 Cedar Lane, Suite 200, Lexington, 56789|0
99
- 345 Park Lane, Suite 75, Richmond, 23456|7890 Willow Road, Suite 300, Greenville, 89012|0
100
- 5678 Grove Boulevard, Suite 150, Savannah, 34567|6789 Pine Street, Suite 100, Portland, 90123|0
101
  900 Army Navy Dr, Arlington, VA 22202|900 Army Navy Dr, Arlington VA 22202|1
102
  900 Army Navy Dr, Arlington, VA 22202|900 Army Navy Drive, Arlington VA 22202|1
103
  2430 Poplar Ave Suite 100, Memphis, TN 38112|2430 Poplar Ave Suite 100, Memphis, TN 38112-4953|1
104
  2058 S Tate St, Corinth, MS 38834|2058 S Tate St, Corinth, MS 38834-1304|1
105
  Valley Healthcare System 1600 Fort Benning Rd, Columbus, GA 31903|1600 Fort Benning Rd, Columbus, GA 31903|1
106
  Valley Healthcare System 1600 Fort Benning Rd, Columbus, GA 31903|1600 Fort Benning Rd, Valley Healthcare System, Columbus, GA 31903|1
107
- Memorial Satilla Health, 1900 Tebeau St, Waycross, GA 31501|1900 Tebeau St, Waycross, GA 31501|1
108
  VA Medical Center 2002 Holcombe Blvd, Houston, TX 77030|VA Medical Center 2002 Holcombe Boulevard, Houston, TX 77030|1
109
  1839 E Capitol Ave, Bismarck, ND 58501|1839 East Capitol Avenue, Bismarck, ND 58501|1
110
  1839 E Capitol Ave, Bismarck, ND 58501|1912 East Capitol Avenue, Bismarck, ND 58501|0
111
-
112
-
113
-
114
-
115
-
116
-
117
-
118
-
119
-
120
-
121
-
122
-
123
-
124
-
125
-
126
-
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
20
  65 Mountain Blvd Ext, Warren NJ 07059|65 Mountain Blvd. Extension, Warren NJ 07059|1
21
  65 Mountain Blvd Ext, Warren NJ 07059|65 Mountain Blvd. Extention, Warren NJ 07059|1
22
  65 Mountain Blvd Ext, Warren NJ 07059|65 Mtn Blvd Ext, Warren NJ 07059|1
23
+ 65 Mountain Blvd Ext, Warren NJ 07059|65 Mountain Blvd Extension, Suite A, Warren NJ 07059|0
24
+ 65 Mountain Blvd Ext, Warren NJ 07059|65 Mountain Boulevard Ext, Apt 2B, Warren NJ 07059|0
25
+ 65 Mountain Blvd Ext, Warren NJ 07059|65 Mountain Blvd Ext, Building C, Warren NJ 07059|0
26
+ 65 Mountain Blvd Ext, Warren NJ 07059|65 Mountain Blvd Ext., Suite 3, Warren NJ 07059|0
27
+ 65 Mountain Blvd Ext, Warren NJ 07059|65 Mountain Blvd Ext. #5, Warren NJ 07059|0
28
+ 65 Mountain Blvd Ext, Warren NJ 07059|65 Mountain Blvd Ext, Unit 5, Warren NJ 07059|0
29
+ 65 Mountain Blvd Ext, Warren NJ 07059|65 Mountain Blvd Extension, Room 12, Warren NJ 07059|0
30
+ 65 Mountain Blvd Ext, Warren NJ 07059|65 Mountain Blvd Ext, Block D, Warren NJ 07059|0
31
+ 65 Mountain Blvd Ext, Warren NJ 07059|65 Mountain Blvd Extension, Lot 7, Warren NJ 07059|0
32
+ 65 Mountain Blvd Ext, Warren NJ 07059|65 Mountain Blvd Ext, Floor 2, Warren NJ 07059|0
33
  65 Mountain Blvd Ext, Warren NJ 07059|12 Mountain Blvd Ext, Warren NJ 07059|0
34
  65 Mountain Blvd Ext, Warren NJ 07059|23 Mountain Blvd Ext, Warren NJ 07059|0
35
  65 Mountain Blvd Ext, Warren NJ 07059|54 Mountain Blvd Ext, Warren NJ 07059|0
 
40
  802 New Holland Ave Suite 200, Lancaster, PA 17602|New Holland Avenue Suite 200, 802, Lancaster, PA 17602|1
41
  802 New Holland Ave Suite 200, Lancaster, PA 17602|Suite 200, 802 New Holland Ave, Lancaster, PA 17602|1
42
  802 New Holland Ave Suite 200, Lancaster, PA 17602|802 New Holland Ave #200, Lancaster, PA 17602|1
43
+ 802 New Holland Ave Suite 200, Lancaster, PA 17602|802 New Holland Avenue, 2nd Floor Suite 200 Lancaster, PA 17602|1
44
  802 New Holland Ave Suite 200, Lancaster, PA 17602|200 Suite, 802 New Holland Ave, Lancaster, PA 17602|1
45
  802 New Holland Ave Suite 200, Lancaster, PA 17602|802 New Holland Ave, Suite #200, Lancaster, PA 17602|1
46
  802 New Holland Ave Suite 200, Lancaster, PA 17602|Suite 200, 802 New Holland Avenue, Lancaster, PA 17602|1
 
54
  2205 S Bridge St Ste 300, Brady, TX 76825|Suite 300, 2205 S Bridge Street, Brady, TX 76825|1
55
  2205 S Bridge St Ste 300, Brady, TX 76825|2205 S Bridge Street, Suite #300, Brady, TX 76825|1
56
  2205 S Bridge St Ste 300, Brady, TX 76825|Ste 300, 2205 S Bridge St, Brady, TX 76825|1
57
+ 2205 S Bridge St Ste 300, Brady, TX 76825|2205 South Bridge Street, 3rd Floor Ste 300, Brady, TX 76825|1
58
  7671 W Middle Fork St, Boise, ID 83709|7671 West Middle Fork Street, Boise, ID 83709|1
59
  7671 W Middle Fork St, Boise, ID 83709|7671 W Middle Fork St., Boise, ID 83709|1
60
  7671 W Middle Fork St, Boise, ID 83709|Middle Fork St W, 7671, Boise, ID 83709|1
 
64
  7671 W Middle Fork St, Boise, ID 83709|Middle Fork Street West, 7671, Boise, ID 83709|1
65
  7671 W Middle Fork St, Boise, ID 83709|7671 W Middle Fork Street, Boise, ID 83709|1
66
  7671 W Middle Fork St, Boise, ID 83709|Middle Fork St, 7671 West, Boise, ID 83709|1
67
+ 7671 W Middle Fork St, Boise, ID 83709|Middle Fork St, 7671 West, Boise, ID 83709-3423|1
68
  7671 W Middle Fork St, Boise, ID 83709|7671 W Middle Fork St, Unit A, Boise, ID 83709|0
69
  3059 W 26th St, Chicago, IL 60623|3059 West 26th Street, Chicago, IL 60623|1
70
  3059 W 26th St, Chicago, IL 60623|3059 W 26th St., Chicago, IL 60623|1
 
79
  3059 W 26th St, Chicago, IL 60623|3059 W 26th St, SAH Community Care Clinic, Chicago, IL 60623|1
80
  125 S Gadsden St #300, Tallahassee, FL 32301|125 S Gadsden St #300A, Tallahassee, FL 32301|0
81
  125 S Gadsden St #300, Tallahassee, FL 32301|125 S Gadsden St, Suite 3A, Tallahassee, FL 32301|0
82
+ 5432 Oak Street, Suite 101, Greenfield, AR 45678|6789 Pine Street, Suite 100, Mountain View, CA 90123|0
83
+ 987 Main Road, Suite B, Roseville, RI 78901|4567 Birch Court, Suite D, River City, RI 67890|0
84
+ 13579 Maple Boulevard, Suite 3, Springfield, NY 12345|5678 Park Street, Suite 150, Meadow Glen, CT 34567|0
85
+ 2468 Cedar Lane, Suite 200, Lexington, PA 56789|9012 Maple Avenue, Suite 3, Springfield, NY 12345|0
86
+ 777 Pine Street, Suite 100, Portland, WA 90123|2345 Birch Avenue, Suite 50, Manchester, NY 23456|0
87
+ 1234 Birch Court, Suite 50, Manchester, PA 23456|1234 Cedar Lane, Suite 50, Oceanview, PA 23456|0
88
+ 888 Chestnut Avenue, Suite D, Charleston, CT 67890|7890 Chestnut Avenue, Suite 300, Lakeside, AK 89012|0
89
+ 999 Willow Drive, Suite 300, Greenville, MA 89012|2345 Willow Lane, Suite 75, Forest Hills, IL 23456|0
90
+ 111 Park Avenue, Suite 75, Richmond, NY 23456|9012 Elm Road, Suite 3, Big City, MA 12345|0
91
+ 2222 Grove Street, Suite 150, Savannah, GA 34567|1234 Elm Street, Suite 101, Greenfield, GA 45678|0
92
+ 2178 Oak Road, Suite 101, Greenfield, NC 45678|3456 Maple Boulevard, Suite 200, Sunnyville, PA 56789|0
93
+ 43 Main Street, Suite B, Roseville, LA 78901|5678 Main Avenue, Suite B, Smallville, TX 78901|0
94
+ 900 Maple Avenue, Suite 3, Springfield, FL 12345|2345 Oak Street, Suite 101, Anytown, TX 45678|0
95
+ 675 Cedar Lane, Suite 200, Lexington, TX 56789|5678 Oak Road, Suite B, Roseville, PA 78901|0
96
+ 80 Pine Street, Suite 100, Portland, WA 90123|2345 Park Lane, Suite 75, Richmond, AL 23456|0
97
+ 2345 Birch Avenue, Suite 50, Manchester, PA 23456|4567 Chestnut Street, Suite D, Charleston, MA 67890|0
98
+ 867 Chestnut Street, Suite D, Charleston, CT 67890|5678 Grove Boulevard, Suite 150, Savannah, CT 34567|0
99
+ 29 Willow Road, Suite 300, Greenville, MA 89012|3456 Cedar Lane, Suite 200, Lexington, AL 56789|0
100
+ 345 Park Lane, Suite 75, Richmond, NJ 23456|7890 Willow Road, Suite 300, Greenville, PA 89012|0
101
+ 5678 Grove Boulevard, Suite 150, Savannah, GA 34567|6789 Pine Street, Suite 100, Portland, NJ 90123|0
102
  900 Army Navy Dr, Arlington, VA 22202|900 Army Navy Dr, Arlington VA 22202|1
103
  900 Army Navy Dr, Arlington, VA 22202|900 Army Navy Drive, Arlington VA 22202|1
104
  2430 Poplar Ave Suite 100, Memphis, TN 38112|2430 Poplar Ave Suite 100, Memphis, TN 38112-4953|1
105
  2058 S Tate St, Corinth, MS 38834|2058 S Tate St, Corinth, MS 38834-1304|1
106
  Valley Healthcare System 1600 Fort Benning Rd, Columbus, GA 31903|1600 Fort Benning Rd, Columbus, GA 31903|1
107
  Valley Healthcare System 1600 Fort Benning Rd, Columbus, GA 31903|1600 Fort Benning Rd, Valley Healthcare System, Columbus, GA 31903|1
108
+ Memorial Satilla Health, 1900 Tebeau St, Waycross, GA 31501|1900 Tebeau Street, Waycross, GA 31501|1
109
  VA Medical Center 2002 Holcombe Blvd, Houston, TX 77030|VA Medical Center 2002 Holcombe Boulevard, Houston, TX 77030|1
110
  1839 E Capitol Ave, Bismarck, ND 58501|1839 East Capitol Avenue, Bismarck, ND 58501|1
111
  1839 E Capitol Ave, Bismarck, ND 58501|1912 East Capitol Avenue, Bismarck, ND 58501|0
112
+ 17752 Washington St, Hanover MA 23393|177-52 Washington St, Hanover MA 23393|1
113
+ 17752 Washington St, Hanover MA 23393|177 52 Washington St, Hanover MA 23393|1
114
+ 3949 Route 31, Clay NY 13041|394-9 Route 31, Clay NY 13041|1
115
+ 3949 Route 31, Clay NY 13041|394 9 Route 31, Clay NY 13041|1
116
+ 139 Merchant Place, Cobleskill NY 12043|13-9 Merchant Place, Cobleskill NY 12043|1
117
+ 139 Merchant Place, Cobleskill NY 12043|13 9 Merchant Place, Cobleskill NY 12043|1
118
+ 279 Troy Road, East Greenbush NY 12061|27-8 Troy Road, East Greenbush NY 12061|0
119
+ 279 Troy Road, East Greenbush NY 12061|27 3 Troy Road, East Greenbush NY 12061|0
120
+ 35 33 E Fairmount Ave, Lakewood NY 14750|35-43 E Fairmount Ave, Lakewood NY 14750|0
121
+ 443 45 E Fairmount Ave, Lakewood NY 14750|443-98 E Fairmount Ave, Lakewood NY 14750|0
122
+ 69 Prospect Hill Road, Ste 3B, East Windsor CT 60888|69 Prospect Hill Road, East Windsor CT 60888|0
123
+ 69 Prospect Hill Road, Ste 4, East Windsor CT 60888|69 Prospect Hill Road, East Windsor CT 60888|0
124
+ 1100 New Haven Road, STE CF-B, Naugatuck CT 67700|1100 New Haven Road STE CFB, Naugatuck CT 67700|1
125
+ 1100 New Haven Road, STE CF-B, Naugatuck CT 67700|1100 New Haven Road STE CFC, Naugatuck CT 67700|0
126
+ 1300 Gilmer Ave, Suite 3-B, Tallassee AL 36078|1300 Gilmer Ave, STE 3-A, Tallassee AL 36078|0
127
+ 1300 Gilmer Ave, Suite 3, Tallassee AL 36078|1300 Gilmer Ave, STE 3, Tallassee AL 36078|1
128
+ 180 River Rd, Suit 2-1, Lisbon CT 6351|180 River Rd, Suit 21, Lisbon CT 6351|1
129
+ 420 Buckland Hills Dr, Suit 3-A, Manchester CT 60401|420 Buckland Hills Dr, Suit 3-B, Manchester CT 60401|0
130
+ 1365 Boston Post Road, Suit C-F, Milford CT 64603|1365 Boston Post Road, Suit CF, Milford CT 64603|1
131
+ 1100 New Haven Road, Naugatuck CT 67701|1100 New Haven Rd, ST3, Naugatuck CT 67701|0
132
+ 315 Foxon Blvd, New Haven CT 65132|31 5 Foxon Blvd, New Haven CT 65132|1
133
+ 164 Danbury Rd, New Milford CT 67765|16-4 Danbury Rd, New Milford CT 67765|1
134
+ 180 River Rd, St#5A Lisbon CT 63513|180 River Rd, St#6A Lisbon CT 63513|0
135
+ 420 Buckland Hills Dr, Suite 5, Manchester CT 60401|420 Buckland Hills Dr, Ste 5, Manchester CT 60401|1
136
+ 420 Buckland Hills Dr, Suite 5, Manchester CT 60401|420 Buckland Hills Drive, Suite #5, Manchester CT 60401|1
137
+ 420 Buckland Hills Dr, Suite 5, Manchester CT 60401|420 Buckland Hills Dr, Suite 5, Manchester Connecticut 60401|1
138
+ 420 Buckland Hills Dr, Suite 5, Manchester CT 60401|420 Buckland Hills Dr #5, Manchester CT 60401|1
139
+ 420 Buckland Hills Dr, Suite 5, Manchester CT 60401|420 Buckland Hills Dr, Ste #5, Manchester CT 60401|1
140
+ 420 Buckland Hills Dr, Suite 5, Manchester CT 60401|420 Buckland Hills Drive, Unit 5, Manchester CT 60401|1
141
+ 420 Buckland Hills Dr, Suite 5, Manchester CT 60401|420 Buckland Hills Dr, Suite Number 5, Manchester CT 60401|1
142
+ 420 Buckland Hills Dr, Suite 5, Manchester CT 60401|420 Buckland Hills Drive, Apt 5, Manchester CT 60401|1
143
+ 420 Buckland Hills Dr, Suite 5, Manchester CT 60401|420 Buckland Hills Dr, Suite #5, Manchester Connecticut 60401|1
144
+ 420 Buckland Hills Dr, Suite 5, Manchester CT 60401|420 Buckland Hills Dr, 5th Floor Ste 5, Manchester CT 60401|1
145
+ 420 Buckland Hills Dr, Suite 5, Manchester CT 60401|420 Buckland Hills Dr, 5th Floor, Manchester CT 60401|0
146
+ 420 Buckland Hills Dr, Suite 5, Manchester CT 60401|420 Buckland Hills Dr, Suite 6, Manchester CT 60401|0
147
+ 13 65 Boston Post Road, Milford CT 64601|13-65 Boston Post Road, Milford CT 64601|1
148
+ 1365 Boston Post Road, Milford CT 64601|13-65 Boston Post Road, Milford CT 64601|1
149
+ 13 65 Boston Post Road, Milford CT 64601|1365 Boston Post Road, Milford CT 64601|1
150
+ 13 65 Boston Post Road, Milford CT 64601|1367 Boston Post Road, Milford CT 64601|0
151
+ 13 65 Boston Post Road, Milford CT 64601|1323 Boston Post Road, Milford CT 64601|0
152
+ 1100 New Haven Road, Naugatuck CT 67701|1100 New Haven Rd, Naugatuck CT 67701|1
153
+ 315 Foxon Blvd, New Haven CT 65132|31 5 Foxon Blvd, New Haven CT 65132|1
154
+ 164 Danbury Rd, New Milford CT 67762|164-5 Danbury Rd, New Milford CT 67762|0
155
+ 20-1 Dutch Meadows Ln, Glenville NY 12302|20-2 Dutch Meadows Ln, Glenville NY 12302|0
156
+ 20-3 Dutch Meadows Ln, Glenville NY 12302|20 3 Dutch Meadows Ln, Glenville NY 12302|1
157
+ 2233 Dutch Meadows Ln, Glenville NY 12302|22-33 Dutch Meadows Ln, Glenville NY 12302|1
158
+ 100-1 Elm Ridge Center Dr, Greece NY 14626|100 Elm Ridge Center Dr, Greece NY 14626|1
159
+ 100-2 Elm Ridge Center Dr, Greece NY 14626|100-3 Elm Ridge Center Dr, Greece NY 14626|0
160
+ 100-2 Elm Ridge Center Dr, Greece NY 14626|100 2 Elm Ridge Center Dr, Greece NY 14626|1
161
+ 15 49 Rt 9, Halfmoon NY 12065|1549 Rt 9, Halfmoon NY 12065|1
162
+ 154-9 Rt 9, Halfmoon NY 12065|1549 Rt 9, Halfmoon NY 12065|1
163
+ 15 49 Rt 9, Halfmoon NY 12065|15-49 Rt 9, Halfmoon NY 12065|1
164
+ 15 49 Rt 9, Halfmoon NY 12065|15-59 Rt 9, Halfmoon NY 12065|0
165
+ 53 60 Southwestern Blvd, Hamburg NY 14075|53-60 Southwestern Blvd, Hamburg NY 14075|1
166
+ 5360 Southwestern Blvd, Hamburg NY 14075|53-60 Southwestern Blvd, Hamburg NY 14075|1
167
+ 5360 Southwestern Blvd, Hamburg NY 14075|53 60 Southwestern Blvd, Hamburg NY 14075|1
168
+ 5362 Southwestern Blvd, Hamburg NY 14075|53-60 Southwestern Blvd, Hamburg NY 14075|0
169
+ 103 North Caroline St, Herkimer NY 13350|10 3 North Caroline St, Herkimer NY 13350|1
170
+ 10-3 North Caroline St, Herkimer NY 13350|103 North Caroline St, Herkimer NY 13350|1
171
+ 10 3 North Caroline St, Herkimer NY 13350|10-3 North Caroline St, Herkimer NY 13350|1
172
+ 10-2 North Caroline St, Herkimer NY 13350|10-3 North Caroline St, Herkimer NY 13350|0
173
+ 1022 State Route 36, Hornell NY 14843|10 22 State Route 36, Hornell NY 14843|1
174
+ 10-33 State Route 36, Hornell NY 14843|1033 State Route 36, Hornell NY 14843|1
175
+ 10 44 State Route 36, Hornell NY 14843|10-44 State Route 36, Hornell NY 14843|1
176
+ 10 33 State Route 36, Hornell NY 14843|20 33 State Route 36, Hornell NY 14843|0
177
+ 10 33 State Route 36, Hornell NY 14843|10 43 State Route 36, Hornell NY 14843|0
178
+ 178 31 So Transit Road, Lockport NY 14094|178-31 So Transit Road, Lockport NY 14094|1
179
+ 178 31 So Transit Road, Lockport NY 14094|17856 So Transit Road, Lockport NY 14094|0
180
+ 178 32 So Transit Road, Lockport NY 14094|17886 So Transit Road, Lockport NY 14094|0
181
+ 178 12 So Transit Road, Lockport NY 14094|17889 So Transit Road, Lockport NY 14094|0
182
+ 178 12 So Transit Road, Lockport NY 14094|17812 So Transit Road, Lockport NY 14094|1
183
+ 470 34 Route 211 East, Middletown NY 10940|470-34 Route 211 East, Middletown NY 10940|1
184
+ 470 34 Route 211 East, Middletown NY 10940|470 35 Route 211 East, Middletown NY 10940|0
185
+ 470 34 Route 211 East, Middletown NY 10940|470-35 Route 211 East, Middletown NY 10940|0
186
+ 470 14 Route 211 East, Middletown NY 10940|470-15 Route 211 East, Middletown NY 10940|0
187
+ 470 44 Route 211 East, Middletown NY 10940|470-45 Route 211 East, Middletown NY 10940|0
188
+ 47034 Route 211 East, Middletown NY 10940|470-35 Route 211 East, Middletown NY 10940|0
189
+ 47034 Route 211 East, Middletown NY 10940|47035 Route 211 East, Middletown NY 10940|0
190
+ 152 43 Gold Star Hwy, Groton CT 63403|152-43 Gold Star Hwy, Groton CT 63403|0
191
+ 152 43 Gold Star Hwy, Groton CT 63403|152-44 Gold Star Hwy, Groton CT 63403|0
192
+ 152 13 Gold Star Hwy, Groton CT 63403|152-18 Gold Star Hwy, Groton CT 63403|0
193
+ 235 23 Gold Star Hwy, Groton CT 63403|235-23 Gold Star Hwy, Groton CT 63403|0
194
+ 300 Hollywood Blvd SE, Suit #4, Fort Walton Beach, FL 32548|300 Hollywood Blvd SE, Floor 4, Fort Walton Beach, FL 32548|0
195
+ 300 Hollywood Blvd SE, Ste 2, Fort Walton Beach, FL 32548|300 Hollywood Blvd SE, Fl #2, Fort Walton Beach, FL 32548|0
196
+ 145 34 23TH ST, Jacksonville, FL 32258|145-50 23TH ST, Jacksonville, FL 32258|0
197
+ 145 24 23TH ST, Jacksonville, FL 32258|145 20 23TH ST, Jacksonville, FL 32258|0
198
+ 145-12 23TH ST, Jacksonville, FL 32258|145 29 23TH ST, Jacksonville, FL 32258|0
199
+ 302 S College Ave, Bloomington, IN 47403-3345|302 S College Ave, Bloomington, IN 47403-3343|1
200
+ 310 S College Ave, Bloomington, IN 47403-3234|310 S College Ave, Bloomington, IN 47403-3313|1
201
+ 11230 W Tipton St, Seymour, IN 47274|112-30 W Tipton Street, Seymour, IN 47274|1
202
+ 11230 W Tipton St, Seymour, IN 47274|112-30 West Tipton Str., Seymour, IN 47274|1
203
+ 1118 12TH AVE S, Nashville, TN 37203|1118 12th Avenue S, Nashville, TN 37203|1
204
+ 1970 Bradford Hicks Dr # B, Livingston, TN 38570|1970 BRADFORD HICKS DRIVE # B, Livingston, TN 38570|1
205
+ 1935 MEDICAL DISTRICT DR, Dallas, TX 75235|1935 Medical District Dr, Dallas, TX 75235|1
206
+ 801 7th Ave, Cook Children's Medical Center, Fort Worth, TX 76104|801 7th Ave, Fort Worth, TX 76104|1
207
+ 823- 52 S NEW BRAUNFELS AVENUE Suite 211, San Antonio, TX 78235|823-52 S New Braunfels Ave, San Antonio, TX 78235|0
208
+ 145 34 23TH ST, Jacksonville, FL 32258|145-34 23TH ST, Suit 4, Jacksonville, FL 32258|0
209
+ 1400 E Boulder St, Ste P34, Colorado Springs, CO 80909|1400 East Boulder St, Suite 31 Colorado Springs, CO 80909|0
210
+ 122-37 Meridian Rd, Levittown, NY 11756|122-37 Meridian Road, Levittown, NY 11756|1
211
+ 122-37 Meridian Rd, Levittown, NY 11756|122-57 Meridian Road, Levittown, NY 11756|0
212
+ 122-37 Meridian Rd, Levittown, NY 11756|122-27 Meridian Road, Levittown, NY 11756|0
213
+ 122-37 Meridian Rd, Levittown, NY 11756|122-17 Meridian Road, Levittown, NY 11756|0
214
+ 160-10 N Midland Ave, Nyack, NY 10960|160-10 North Midland Ave, Nyack, NY 10960|1
215
+ 160-10 N Midland Ave, Nyack, NY 10960|160 10 North Midland Avenue, Nyack, NY 10960|1
216
+ 160-10 N Midland Ave, Nyack, NY 10960|160-10 N Midland Avenue, Nyack, NY 10960|1
217
+ 160-10 N Midland Ave, Nyack, NY 10960|160-10 North Midland AVE, Nyack, NY 10960|1
218
+ 160-10 N Midland Ave, Nyack, NY 10960|160-12 North Midland Ave, Nyack, NY 10960|0
219
+ 160-10 N Midland Ave, Nyack, NY 10960|160-14 North Midland Ave, Nyack, NY 10960|0
220
+ 160-10 N Midland Ave, Nyack, NY 10960|160 20 North Midland Ave, Nyack, NY 10960|0
221
+ 160-10 N Midland Ave, Nyack, NY 10960|160-90 North Midland Ave, Nyack, NY 10960|0
222
+ 91 Mechanic Blvd, Lebanon, NH 03766|91 MECHANIC BLVD, Lebanon, NH 03766-3233|1
223
+ 122 Mechanic Blvd, Lebanon, NH 03766|122 MECHANIC BLVD, Lebanon, NH 03766-3233|1
224
+ 555 Willard Ave, Newington, CT 06111|555 WILLARD AVENUE, Newington, CT 06111-3374|1
225
+ 12 Willard Ave, Newington, CT 06111|12 WILLARD AVENUE, Newington, CT 06111-3374|1
226
+ 12179 Northern Blvd Ste 202, Chesterfield, MO 63017-1123|12179 Northern Boulevard #202, Chesterfield, MO 63017-1123|1
227
+ 12179 Northern Blvd Ste 202, Chesterfield, MO 63017-1123|12179 Northern Blvd, Ste 202, Chesterfield, MO 63017|1
228
+ 12179 Northern Blvd Ste 202, Chesterfield, MO 63017-1123|12179 NORTHERN BOULEVARD, STE 202, Chesterfield, MO 63017-1123|1
229
+ 12179 Northern Blvd Ste 202, Chesterfield, MO 63017-1123|12179 Northern Blvd, Chesterfield, MO 63017-1123, Suite 202|1
230
+ 12179 Northern Blvd Ste 202, Chesterfield, MO 63017-1123|12179 N Blvd, Ste 202, Chesterfield, MO 63017|1
231
+ 12179 Northern Blvd Ste 202, Chesterfield, MO 63017-1123|12179 Northern Blvd, Apt 202, Chesterfield, MO 63017-1123|1
232
+ 12179 Northern Blvd Ste 202, Chesterfield, MO 63017-1123|Suite 202, 12179 Northern Blvd, Chesterfield, MO 63017|1
233
+ 12179 Northern Blvd Ste 202, Chesterfield, MO 63017-1123|#202, 12179 Northern Blvd, Chesterfield, MO 63017|1
234
+ 12179 Northern Blvd Ste 202, Chesterfield, MO 63017-1123|12179 Northern Blvd, Unit 202, Chesterfield, MO, 63017-1123|1
dev_set_training.csv CHANGED
@@ -12,4 +12,17 @@ address1|address2|are_same
12
  440 TECHNOLOGY CENTER DRIVE, Boston, MA 10034|200 Technology Center Drive, Boston, MA 10034|0
13
  65 Mountain Blvd Ext, Warren, NJ 07059|65 Mountain Boulevard Ext, Warren, NJ 07059|1
14
  65 Mountain Blvd Ext, Warren, NJ 07059|5078 S Maryland Pkwy, Las Vegas, NV 89119|0
15
- 65 Mountain Blvd Ext, Warren, NJ 07059|112 Mountain Blvd Ext, Warren, NJ 07059|0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
12
  440 TECHNOLOGY CENTER DRIVE, Boston, MA 10034|200 Technology Center Drive, Boston, MA 10034|0
13
  65 Mountain Blvd Ext, Warren, NJ 07059|65 Mountain Boulevard Ext, Warren, NJ 07059|1
14
  65 Mountain Blvd Ext, Warren, NJ 07059|5078 S Maryland Pkwy, Las Vegas, NV 89119|0
15
+ 65 Mountain Blvd Ext, Warren, NJ 07059|112 Mountain Blvd Ext, Warren, NJ 07059|0
16
+ 872 Route 13, Cortlandville NY 13045|87-2 Route 13, Cortlandville NY 13045|1
17
+ 8724 Route 13, Cortlandville NY 13045|87-24 Route 13, Cortlandville NY 13045|1
18
+ 87 24 Route 13, Cortlandville NY 13045|87-24 Route 13, Cortlandville NY 13045|1
19
+ 87-4 Route 13, Cortlandville NY 13045|87 2 Route 13, Cortlandville NY 13045|0
20
+ 87-43 Route 13, Cortlandville NY 13045|87 24 Route 13, Cortlandville NY 13045|0
21
+ 17752 Main St, Hanover PA 23393|177 52 Main St, Hanover PA 23393|1
22
+ 17752 Main St, Hanover PA 23393|177 52 MAIN ST, Hanover PA 23393-3345|1
23
+ 2575 Us Hwy 43, St 3-A, Winfield AL 35594|2575 Us Hwy 43, St 3A, Winfield AL 35594|1
24
+ 2575 Us Hwy 43, St 3-A, Winfield AL 35594|2575 Us Hwy 43, St 3B, Winfield AL 35594|0
25
+ 115 Dr Jimmy Carr St, Ste 3F, Searcy, AR 72143|115 Dr Jimmy Carr St, Searcy, AR 72143|0
26
+ Heart Health, 90 N Columbus Ave, Louisville, MS 39339|90 N Columbus Ave, Louisville, MS 39339|1
27
+ 545 16th St, Ste 3, Gulfport, MS 39507|545 16th St, Floor 3, Gulfport, MS 39507|0
28
+ 217-12 Loudon Rd, Concord, NH 03301|217-22 Loudon Rd, Concord, NH 03301|0
data.py → quick_evaluate.py RENAMED
@@ -10,6 +10,9 @@ from sentence_transformers import SentenceTransformer
10
  #model = AlbertModel.from_pretrained("albert-base-v2")
11
  #'sentence-transformers/paraphrase-albert-base-v2'
12
  model_name = 'output/training_OnlineConstrativeLoss-2023-03-10_11-17-15'
 
 
 
13
  model_sbert = SentenceTransformer(model_name)
14
 
15
  def get_sbert_embedding(input_text):
@@ -27,7 +30,11 @@ a8 = "200 Technology Center Drive, Boston, MA 10034"
27
  a8x= "87 Technology Center Drive, Boston, MA 10034"
28
  a9 = "440 Technology Center Dr., Boston, MA 10034-0345"
29
  a10 = "440 Technology Center Dr., Boston, MA 10034"
30
-
 
 
 
 
31
  #def get_embedding(input_text):
32
  # encoded_input = tokenizer(input_text, return_tensors='pt')
33
  # input_ids = encoded_input.input_ids
@@ -58,6 +65,12 @@ e8 = get_sbert_embedding(a8)
58
  e8x = get_sbert_embedding(a8x)
59
  e9 = get_sbert_embedding(a9)
60
  e10 = get_sbert_embedding(a10)
 
 
 
 
 
 
61
  print(f"a1 \"{a1}\" to \"{a2}\" a2 - expected Different")
62
  print(cosine_similarity([e1], [e2]))
63
  print(f"a1 \"{a1}\" to \"{a4}\" a4 - expected Different")
@@ -75,6 +88,15 @@ print(cosine_similarity([e7], [e9]))
75
 
76
  print(f"a7 \"{a7}\" to \"{a10}\" a10 - expected Same")
77
  print(cosine_similarity([e7], [e10]))
 
 
 
 
 
 
 
 
 
78
  # with base
79
  #a1 to a2
80
  #[[0.99512167]]
 
10
  #model = AlbertModel.from_pretrained("albert-base-v2")
11
  #'sentence-transformers/paraphrase-albert-base-v2'
12
  model_name = 'output/training_OnlineConstrativeLoss-2023-03-10_11-17-15'
13
+ model_name = 'output/training_OnlineConstrativeLoss-2023-03-11_00-24-35'
14
+ model_name = 'output/training_OnlineConstrativeLoss-2023-03-11_01-00-19'
15
+ model_name='output/training_OnlineConstrativeLoss-2023-03-12_00-42-41'
16
  model_sbert = SentenceTransformer(model_name)
17
 
18
  def get_sbert_embedding(input_text):
 
30
  a8x= "87 Technology Center Drive, Boston, MA 10034"
31
  a9 = "440 Technology Center Dr., Boston, MA 10034-0345"
32
  a10 = "440 Technology Center Dr., Boston, MA 10034"
33
+ a11="872 Route 13, Cortlandville NY 13045"
34
+ a12="87-2 Route 13, Cortlandville NY 13045"
35
+ a13="87-5 Route 13, Cortlandville NY 13045"
36
+ a14="257 37 US Rt 11, Evans Mills NY 13637"
37
+ a15="257-37 US Route 11, Evans Mills NY 13637"
38
  #def get_embedding(input_text):
39
  # encoded_input = tokenizer(input_text, return_tensors='pt')
40
  # input_ids = encoded_input.input_ids
 
65
  e8x = get_sbert_embedding(a8x)
66
  e9 = get_sbert_embedding(a9)
67
  e10 = get_sbert_embedding(a10)
68
+ e11 = get_sbert_embedding(a11)
69
+ e12 = get_sbert_embedding(a12)
70
+ e13 = get_sbert_embedding(a13)
71
+ e14 = get_sbert_embedding(a14)
72
+ e15 = get_sbert_embedding(a15)
73
+
74
  print(f"a1 \"{a1}\" to \"{a2}\" a2 - expected Different")
75
  print(cosine_similarity([e1], [e2]))
76
  print(f"a1 \"{a1}\" to \"{a4}\" a4 - expected Different")
 
88
 
89
  print(f"a7 \"{a7}\" to \"{a10}\" a10 - expected Same")
90
  print(cosine_similarity([e7], [e10]))
91
+
92
+ print(f"a11 \"{a11}\" to \"{a12}\" a12 - expected Same")
93
+ print(cosine_similarity([e11], [e12]))
94
+
95
+ print(f"a11 \"{a11}\" to \"{a13}\" a13 - expected Different")
96
+ print(cosine_similarity([e11], [e13]))
97
+
98
+ print(f"a14 \"{a14}\" to \"{a15}\" a15 - expected Same")
99
+ print(cosine_similarity([e14], [e15]))
100
  # with base
101
  #a1 to a2
102
  #[[0.99512167]]
train.py CHANGED
@@ -26,7 +26,7 @@ logger = logging.getLogger(__name__)
26
  #As base model, we use DistilBERT-base that was pre-trained on NLI and STSb data
27
  model = SentenceTransformer('sentence-transformers/paraphrase-albert-base-v2')
28
  num_epochs = 10
29
- train_batch_size = 8
30
 
31
  #As distance metric, we use cosine distance (cosine_distance = 1-cosine_similarity)
32
  distance_metric = losses.SiameseDistanceMetric.COSINE_DISTANCE
 
26
  #As base model, we use DistilBERT-base that was pre-trained on NLI and STSb data
27
  model = SentenceTransformer('sentence-transformers/paraphrase-albert-base-v2')
28
  num_epochs = 10
29
+ train_batch_size = 10
30
 
31
  #As distance metric, we use cosine distance (cosine_distance = 1-cosine_similarity)
32
  distance_metric = losses.SiameseDistanceMetric.COSINE_DISTANCE