Hugging Face's logo

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

App Files Community
felix commited on
Commit
c96e9d6
•
1 Parent(s): db77f64

Start dataset creation.

Browse files
Files changed (4) hide show
  1. data.py +2 -0
  2. data_set_training.csv +119 -0
  3. system_promts.txt +9 -0
  4. train.py +4 -0
data.py CHANGED
@@ -2,6 +2,8 @@ from transformers import AlbertTokenizer, AlbertModel
2
  from sklearn.metrics.pairwise import cosine_similarity
3
  import torch
4
 
 
 
5
  # base
6
  # large
7
  tokenizer = AlbertTokenizer.from_pretrained('albert-base-v2')
 
2
  from sklearn.metrics.pairwise import cosine_similarity
3
  import torch
4
 
5
+ #This is a quick evaluation to see if B
6
+
7
  # base
8
  # large
9
  tokenizer = AlbertTokenizer.from_pretrained('albert-base-v2')
data_set_training.csv ADDED
@@ -0,0 +1,119 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 101 Crawfords Corner Road, Suite 2511-W, Holmdel NJ 07734|101 Crawfords Corner Rd, Ste 2511-W, Holmdel NJ 07734|1
2
+ 101 Crawfords Corner Road, Suite 2511-W, Holmdel NJ 07734|101 Crawfords Corner Road, Ste 2511 W, Holmdel NJ 07734|1
3
+ 101 Crawfords Corner Road, Suite 2511-W, Holmdel NJ 07734|101 Crawfords Corner Rd, Suite 2511-W, Holmdel NJ 07734|1
4
+ 101 Crawfords Corner Road, Suite 2511-W, Holmdel NJ 07734|101 Crawfords Corner Road, Suite #2511-W, Holmdel NJ 07734|1
5
+ 101 Crawfords Corner Road, Suite 2511-W, Holmdel NJ 07734|101 Crawfords Corner Rd, Suite #2511W, Holmdel NJ 07734|1
6
+ 101 Crawfords Corner Road, Suite 2511-W, Holmdel NJ 07734|101 Crawfords Corner Road, Suite 2511W, Holmdel NJ 07734|1
7
+ 101 Crawfords Corner Road, Suite 2511-W, Holmdel NJ 07734|101 Crawfords Corner Rd, Suite #2511-W, Holmdel NJ 07734|1
8
+ 101 Crawfords Corner Road, Suite 2511-W, Holmdel NJ 07734|101 Crawfords Corner Rd, Suite 2511 W, Holmdel NJ 07734|1
9
+ 101 Crawfords Corner Road, Suite 2511-W, Holmdel NJ 07734|101 Crawfords Corner Road, Suite #2511 W, Holmdel NJ 07734|1
10
+ 101 Crawfords Corner Road, Suite 2511-W, Holmdel NJ 07734|101 Crawfords Corner Rd, Suite #2511W, Holmdel NJ 07734|1
11
+ 101 Crawfords Corner Road, Suite 2511-W, Holmdel NJ 07734|200 Crawfords Corner Rd, Holmdel NJ 07734|0
12
+ 65 Mountain Blvd Ext, Warren NJ 07059|65 Mountain Boulevard Ext, Warren NJ 07059|1
13
+ 65 Mountain Blvd Ext, Warren NJ 07059|65 Mountain Blvd Extension, Warren NJ 07059|1
14
+ 65 Mountain Blvd Ext, Warren NJ 07059|65 Mountain Blvd Ext., Warren NJ 07059|1
15
+ 65 Mountain Blvd Ext, Warren NJ 07059|65 Mountain Boulevard Extension, Warren NJ 07059|1
16
+ 65 Mountain Blvd Ext, Warren NJ 07059|65 Mountain Blvd Extention, Warren NJ 07059|1
17
+ 65 Mountain Blvd Ext, Warren NJ 07059|65 Mountain Blvd. Ext, Warren NJ 07059|1
18
+ 65 Mountain Blvd Ext, Warren NJ 07059|65 Mountain Boulevard Ext., Warren NJ 07059|1
19
+ 65 Mountain Blvd Ext, Warren NJ 07059|65 Mountain Blvd. Extension, Warren NJ 07059|1
20
+ 65 Mountain Blvd Ext, Warren NJ 07059|65 Mountain Blvd. Extention, Warren NJ 07059|1
21
+ 65 Mountain Blvd Ext, Warren NJ 07059|65 Mtn Blvd Ext, Warren NJ 07059|1
22
+ 65 Mountain Blvd Ext, Warren NJ 07059|65 Mountain Blvd Extension, Suite A|0
23
+ 65 Mountain Blvd Ext, Warren NJ 07059|65 Mountain Boulevard Ext, Apt 2B|0
24
+ 65 Mountain Blvd Ext, Warren NJ 07059|65 Mountain Blvd Ext, Building C|0
25
+ 65 Mountain Blvd Ext, Warren NJ 07059|65 Mountain Blvd Ext., Suite 3|0
26
+ 65 Mountain Blvd Ext, Warren NJ 07059|65 Mountain Blvd Ext. W|0
27
+ 65 Mountain Blvd Ext, Warren NJ 07059|65 Mountain Blvd Ext, Unit 5|0
28
+ 65 Mountain Blvd Ext, Warren NJ 07059|65 Mountain Blvd Extension, Room 12|0
29
+ 65 Mountain Blvd Ext, Warren NJ 07059|65 Mountain Blvd Ext, Block D|0
30
+ 65 Mountain Blvd Ext, Warren NJ 07059|65 Mountain Blvd Extension, Lot 7|0
31
+ 65 Mountain Blvd Ext, Warren NJ 07059|65 Mountain Blvd Ext, Floor 2|0
32
+ 65 Mountain Blvd Ext, Warren NJ 07059|12 Mountain Blvd Ext, Warren NJ 07059|0
33
+ 65 Mountain Blvd Ext, Warren NJ 07059|23 Mountain Blvd Ext, Warren NJ 07059|0
34
+ 65 Mountain Blvd Ext, Warren NJ 07059|54 Mountain Blvd Ext, Warren NJ 07059|0
35
+ 65 Mountain Blvd Ext, Warren NJ 07059|102 Mountain Blvd Ext, Warren NJ 07059|0
36
+ 65 Mountain Blvd Ext, Warren NJ 07059|5 Mountain Blvd Ext, Warren NJ 07059|0
37
+ 802 New Holland Ave Suite 200, Lancaster, PA 17602|802 New Holland Avenue Suite 200, Lancaster, PA 17602|1
38
+ 802 New Holland Ave Suite 200, Lancaster, PA 17602|Suite 200, 802 New Holland Avenue, Lancaster, PA 17602|1
39
+ 802 New Holland Ave Suite 200, Lancaster, PA 17602|New Holland Avenue Suite 200, 802, Lancaster, PA 17602|1
40
+ 802 New Holland Ave Suite 200, Lancaster, PA 17602|Suite 200, 802 New Holland Ave, Lancaster, PA 17602|1
41
+ 802 New Holland Ave Suite 200, Lancaster, PA 17602|802 New Holland Ave #200, Lancaster, PA 17602|1
42
+ 802 New Holland Ave Suite 200, Lancaster, PA 17602|802 New Holland Avenue, 2nd Floor, Lancaster, PA 17602|1
43
+ 802 New Holland Ave Suite 200, Lancaster, PA 17602|200 Suite, 802 New Holland Ave, Lancaster, PA 17602|1
44
+ 802 New Holland Ave Suite 200, Lancaster, PA 17602|802 New Holland Ave, Suite #200, Lancaster, PA 17602|1
45
+ 802 New Holland Ave Suite 200, Lancaster, PA 17602|Suite 200, 802 New Holland Avenue, Lancaster, PA 17602|1
46
+ 802 New Holland Ave Suite 200, Lancaster, PA 17602|802 New Holland Ave, Ste 200, Lancaster, PA 17602|1
47
+ 2205 S Bridge St Ste 300, Brady, TX 76825|2205 South Bridge Street Suite 300, Brady, TX 76825|1
48
+ 2205 S Bridge St Ste 300, Brady, TX 76825|Suite 300, 2205 S Bridge St, Brady, TX 76825|1
49
+ 2205 S Bridge St Ste 300, Brady, TX 76825|2205 S Bridge St #300, Brady, TX 76825|1
50
+ 2205 S Bridge St Ste 300, Brady, TX 76825|2205 S Bridge St, Suite 300, Brady, TX 76825|1
51
+ 2205 S Bridge St Ste 300, Brady, TX 76825|Suite 300, 2205 South Bridge St, Brady, TX 76825|1
52
+ 2205 S Bridge St Ste 300, Brady, TX 76825|2205 South Bridge St, Ste 300, Brady, TX 76825|1
53
+ 2205 S Bridge St Ste 300, Brady, TX 76825|Suite 300, 2205 S Bridge Street, Brady, TX 76825|1
54
+ 2205 S Bridge St Ste 300, Brady, TX 76825|2205 S Bridge Street, Suite #300, Brady, TX 76825|1
55
+ 2205 S Bridge St Ste 300, Brady, TX 76825|Ste 300, 2205 S Bridge St, Brady, TX 76825|1
56
+ 2205 S Bridge St Ste 300, Brady, TX 76825|2205 South Bridge Street, 3rd Floor, Brady, TX 76825|1
57
+ 7671 W Middle Fork St, Boise, ID 83709|7671 West Middle Fork Street, Boise, ID 83709|1
58
+ 7671 W Middle Fork St, Boise, ID 83709|7671 W Middle Fork St., Boise, ID 83709|1
59
+ 7671 W Middle Fork St, Boise, ID 83709|Middle Fork St W, 7671, Boise, ID 83709|1
60
+ 7671 W Middle Fork St, Boise, ID 83709|7671 Middle Fork St West, Boise, ID 83709|1
61
+ 7671 W Middle Fork St, Boise, ID 83709|W Middle Fork St, 7671, Boise, ID 83709|1
62
+ 7671 W Middle Fork St, Boise, ID 83709|7671 Middle Fork Street, Boise, ID 83709|1
63
+ 7671 W Middle Fork St, Boise, ID 83709|Middle Fork Street West, 7671, Boise, ID 83709|1
64
+ 7671 W Middle Fork St, Boise, ID 83709|7671 W Middle Fork Street, Boise, ID 83709|1
65
+ 7671 W Middle Fork St, Boise, ID 83709|Middle Fork St, 7671 West, Boise, ID 83709|1
66
+ 7671 W Middle Fork St, Boise, ID 83709|7671 W Middle Fork St, Unit A, Boise, ID 83709|0
67
+ 3059 W 26th St, Chicago, IL 60623|3059 West 26th Street, Chicago, IL 60623|1
68
+ 3059 W 26th St, Chicago, IL 60623|3059 W 26th St., Chicago, IL 60623|1
69
+ 3059 W 26th St, Chicago, IL 60623|West 26th St, 3059, Chicago, IL 60623|1
70
+ 3059 W 26th St, Chicago, IL 60623|3059 26th St West, Chicago, IL 60623|1
71
+ 3059 W 26th St, Chicago, IL 60623|W 26th St, 3059, Chicago, IL 60623|1
72
+ 3059 W 26th St, Chicago, IL 60623|3059 26th Street, Chicago, IL 60623|1
73
+ 3059 W 26th St, Chicago, IL 60623|West 26th Street, 3059, Chicago, IL 60623|1
74
+ 3059 W 26th St, Chicago, IL 60623|3059 W 26th Street, Chicago, IL 60623|1
75
+ 3059 W 26th St, Chicago, IL 60623|26th St, 3059 West, Chicago, IL 60623|1
76
+ 3059 W 26th St, Chicago, IL 60623|3059 W 26th St, Apt B, Chicago, IL 60623|0
77
+ 3059 W 26th St, Chicago, IL 60623|3059 W 26th St, SAH Community Care Clinic, Chicago, IL 60623|1
78
+ 125 S Gadsden St #300, Tallahassee, FL 32301|125 S Gadsden St #300A, Tallahassee, FL 32301|0
79
+ 125 S Gadsden St #300, Tallahassee, FL 32301|125 S Gadsden St, Suite 3A, Tallahassee, FL 32301|0
80
+ 5432 Oak Street, Suite 101, Greenfield, 45678|6789 Pine Street, Suite 100, Mountain View, 90123|0
81
+ 987 Main Road, Suite B, Roseville, 78901|4567 Birch Court, Suite D, River City, 67890|0
82
+ 13579 Maple Boulevard, Suite 3, Springfield, 12345|5678 Park Street, Suite 150, Meadow Glen, 34567|0
83
+ 2468 Cedar Lane, Suite 200, Lexington, 56789|9012 Maple Avenue, Suite 3, Springfield, 12345|0
84
+ 777 Pine Street, Suite 100, Portland, 90123|2345 Birch Avenue, Suite 50, Manchester, 23456|0
85
+ 1234 Birch Court, Suite 50, Manchester, 23456|1234 Cedar Lane, Suite 50, Oceanview, 23456|0
86
+ 888 Chestnut Avenue, Suite D, Charleston, 67890|7890 Chestnut Avenue, Suite 300, Lakeside, 89012|0
87
+ 999 Willow Drive, Suite 300, Greenville, 89012|2345 Willow Lane, Suite 75, Forest Hills, 23456|0
88
+ 111 Park Avenue, Suite 75, Richmond, 23456|9012 Elm Road, Suite 3, Big City, 12345|0
89
+ 2222 Grove Street, Suite 150, Savannah, 34567|1234 Elm Street, Suite 101, Greenfield, 45678|0
90
+ 2178 Oak Road, Suite 101, Greenfield, 45678|3456 Maple Boulevard, Suite 200, Sunnyville, 56789|0
91
+ 43 Main Street, Suite B, Roseville, 78901|5678 Main Avenue, Suite B, Smallville, 78901|0
92
+ 900 Maple Avenue, Suite 3, Springfield, 12345|2345 Oak Street, Suite 101, Anytown, 45678|0
93
+ 675 Cedar Lane, Suite 200, Lexington, 56789|5678 Oak Road, Suite B, Roseville, 78901|0
94
+ 80 Pine Street, Suite 100, Portland, 90123|2345 Park Lane, Suite 75, Richmond, 23456|0
95
+ 2345 Birch Avenue, Suite 50, Manchester, 23456|4567 Chestnut Street, Suite D, Charleston, 67890|0
96
+ 867 Chestnut Street, Suite D, Charleston, 67890|5678 Grove Boulevard, Suite 150, Savannah, 34567|0
97
+ 29 Willow Road, Suite 300, Greenville, 89012|3456 Cedar Lane, Suite 200, Lexington, 56789|0
98
+ 345 Park Lane, Suite 75, Richmond, 23456|7890 Willow Road, Suite 300, Greenville, 89012|0
99
+ 5678 Grove Boulevard, Suite 150, Savannah, 34567|6789 Pine Street, Suite 100, Portland, 90123|0
100
+
101
+
102
+
103
+
104
+
105
+
106
+
107
+
108
+
109
+
110
+
111
+
112
+
113
+
114
+
115
+
116
+
117
+
118
+
119
+
system_promts.txt ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ Create similar addresses:
2
+ ----------------------------
3
+ You are tasked with helping to generate test data for machine learning dataset. Do no prefix numbers before each line of output. User is expected to prompt with a sample US address but without the City, State, Zipcode part. As a model your task is to generate 10 variations of the provided address as a regular person may enter it into some system. All outputs should be a list of 10 sample.
4
+
5
+ Create similar but different addresses:
6
+ You are tasked with helping to generate test data for machine learning dataset. Do no prefix numbers before each line of output. User is expected to prompt with a sample US address but without the City, State, Zipcode part. As a model your task is to generate 10 variations of the provided address that are actually different addresses. Address formats should be as if a regular person may enter it into some system.
7
+
8
+ Generate completely different addresses.
9
+ You are tasked with helping to generate test data for machine learning dataset. Do no prefix numbers before each line of output. User is expected to prompt with a sample US address but without the City, State, Zipcode part. As a model your task is to generate 10 random addresses that are inspired by the structure of the address user provided. Address formats should be as if a regular person may enter it into some system.
train.py ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ # Will be based on
2
+ # ConstructiveLoss function.
3
+ #
4
+ # https://github.com/UKPLab/sentence-transformers/blob/master/examples/training/quora_duplicate_questions/training_OnlineContrastiveLoss.py