Last active
December 21, 2017 22:21
-
-
Save dchud/4abd6748aee4cdd596c5 to your computer and use it in GitHub Desktop.
sample of deduped businesses
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"field_names": ["estab_name", "site_address", "site_city", "site_state", | |
"site_zip", "nr_in_estab", "owner_type"], | |
"field_definitions": [{"field": "estab_name", "type": "String"}, | |
{"field": "site_address", "type": "Address"}, | |
{"field": "site_city", "type": "ShortString", | |
"Has Missing": true}, | |
{"field": "site_state", "type": "ShortString", | |
"Has Missing": true}, | |
{"field": "site_zip", "type": "ShortString", | |
"Has Missing": true}, | |
{"field": "nr_in_estab", "type": "Price", | |
"Has Missing": true}, | |
{"field": "owner_type", "type": "Category", | |
"categories": ["a", "b", "c", "d", "\"\""]} | |
], | |
"output_file": "inspections-deduped.csv", | |
"skip_training": false, | |
"training_file": "training.json", | |
"sample_size": 15000, | |
"recall_weight": 2 | |
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Cluster ID | nr_in_estab | estab_name | site_city | site_state | site_zip | site_address | |
---|---|---|---|---|---|---|---|
0 | 350 | UNION FOUNDRY COMPANY | ANNISTON | AL | 36201 | 1501 WEST 17TH STREET | |
0 | 400 | UNION FOUNDRY COMPANY | ANNISTON | AL | 36201 | 1501 WEST 17TH STREET | |
1 | 329 | VISUAL GRAPHICS CORP | Fort Lauderdale | FL | 33321 | 5701 NW 94TH AVE | |
1 | 450 | VISUAL GRAPHICS CORP | Tamarac | FL | 33321 | 5701 NW 94 AVE | |
2 | 250 | CASCADE WOOD PRODUCTS INC | WHITE CITY | OR | 97503 | 8399 14TH ST | |
2 | 114 | CASCADE WOOD PRODUCTS INC | WHITE CITY | OR | 97503 | 8399 14TH ST | |
2 | 279 | CASCADE WOOD PRODUCTS INC | WHITE CITY | OR | 97503 | 8399 14TH ST | |
3 | 3 | NIKKEL & ASSOCIATES, INC. | AMES | IA | 50010 | 1404 BOSTON AVENUE | |
3 | 4 | NIKKEL & ASSOCIATES, INC. | AMES | IA | 50010 | CARROLL AVENUE & E. 12TH STREET | |
4 | 50 | GEORGE HYMAN CONSTRUCTION CO | Washington | DC | 20008 | 4340 CONNECTICUT AVE NW | |
4 | 800 | GEORGE HYMAN CONSTRUCTION | Washington | DC | 20036 | 1326 CONNECTICUT AVE NW | |
5 | 40 | RICHARD DETLING | UNION CITY | IN | 47390 | 700 NORTH - 700 EAST | |
5 | 60 | RICHARD DETLING | UNION CITY | IN | 47390 | 700 NORTH - 700 EAST | |
6 | BELTRONE CONSTRUCTION CO. | ALBANY | NY | 12207 | 69 STATE ST. | ||
6 | 10 | BELTRONE CONSTRUCTION CO. INC. | ALBANY | NY | 12207 | BRIDGE OVER NYS THRUWAY | |
7 | 33 | ELECTRO-PLATING ENGINEERING CO. | ST. PAUL | MN | 55117 | 45 W. IVY AVE. | |
7 | 28 | ELECTRO-PLATING ENGINEERING CO. | ST. PAUL | MN | 55117 | 45 W. IVY AVE. | |
8 | 157 | TRUE TEMPER HARDWARE COMPANY | HARRISBURG | PA | 17104 | 1500 SOUTH CAMERON STREET | |
8 | 127 | TRUE TEMPER HARDWARE COMPANY | HARRISBURG | PA | 17104 | 1500 SOUTH CAMERON STREET | |
9 | 126 | NASHUA HOMES OF IDAHO INC. | BOISE | ID | 83716 | 5200 S. FEDERAL WAY | |
9 | 150 | NASHUA HOMES OF IDAHO INC. | BOISE | ID | 83716 | 5200 S. FEDERAL WAY | |
9 | 150 | NASHUA HOMES OF IDAHO INC. | BOISE | ID | 83716 | 5200 S. FEDERAL WAY | |
10 | TUALATIN VALLEY BUILDERS SUPPLY INC | LAKE OSWEGO | OR | 97034 | 5930 SW JEAN ROAD | ||
10 | 18 | TUALATIN VALLEY BUILDERS SUPPLY INC | LAKE OSWEGO | OR | 97035 | 15700 SW BOONES FERRY RD | |
10 | 112 | TUALATIN VALLEY BUILDERS SUPPLY INC | LAKE OSWEGO | OR | 97034 | 5930 SW JEAN RD | |
10 | 30 | TUALATIN VALLEY BUILDERS SUPPLY INC | LAKE OSWEGO | OR | 97034 | 5930 SW JEAN RD | |
11 | 118 | KIMBERLY CLARK CORP ATLAS MILL | Appleton | WI | 54911 | 425 W WATER STREET | |
11 | 80 | KIMBERLY CLARK CORP | APPLETON | WI | 54912 | 425 WATER ST | |
12 | 2 | TW ELECTRICAL SERVICE INC | HONOLULU | HI | 96814 | 1450 ALA MOANA BLVD | |
12 | 1 | KOKAMI ELECTRICAL SERVICE INC | HONOLULU | HI | 96814 | 1240 ALA MOANA BLVD | |
13 | 40 | KO-REC TYPE CORP DE PUERTO RIC | Arecibo | PR | 00612 | URB IND ZENO RONDIA | |
13 | 39 | KO-REC TYPE CORP DE PUERTO RIC | Arecibo | PR | 00612 | CALLE B URB IND ZENO CANDIA BO | |
14 | 375 | REFLECTOR HARDWARE CORP | Melrose Park | IL | 60160 | 1400 N 25TH AVE | |
14 | 262 | REFLECTOR HARDWARE SPACEMASTER CORPORATION | MELROSE PARK | IL | 60160 | 1400 N. 25TH AVE. | |
15 | 14 | ACME SCREW & MFG CO INC | Indianapolis | IN | 46202 | 1027 HARRISON ST | |
15 | 10 | ACME SCREW AND MANUFACTURING CO INC | INDIANAPOLIS | IN | 46202 | 1027 HARRISON STREET | |
16 | 95 | TRI ENAMELING, INCORPORATED | CHICAGO | IL | 60608 | 2541 SOUTH WASHTENAW AVENUE | |
16 | 35 | TRIENAMELINY INC | Chicago | IL | 60608 | 2541 WEST WASHTENAW AVENUE |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment