Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

data and scripts for amazon-google dataset #131

Merged
merged 3 commits into from
Jan 17, 2022
Merged

data and scripts for amazon-google dataset #131

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
54a41be
added amazon-google dataset used in DeepMatcher
navinrathore Jan 12, 2022
933fb69
pyspark scripts to preprocess amazon-google data #110
navinrathore Jan 14, 2022
17facc4
single pyspark script to do all the needful to preprocess data #110
navinrathore Jan 15, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
72 changes: 72 additions & 0 deletions examples/amazon-google/config.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,72 @@
{
"fieldDefinition":[
{
"fieldName" : "title",
"matchType" : "text",
"fields" : "title",
"dataType": "\"string\""
},
{
"fieldName" : "manufacturer",
"matchType": "fuzzy",
"fields" : "manufacturer",
"dataType": "\"string\""
},
{
"fieldName" : "price",
"matchType": "fuzzy",
"fields" : "price",
"dataType": "\"double\""
}],
"output" : [{
"name":"output",
"format":"csv",
"props": {
"location": "/tmp/zinggOutput",
"delimiter": ",",
"header":false
}
}],
"data" : [{
"name":"test1",
"format":"csv",
"props": {
"location": "examples/Amazon-Google/dataset_orig/tableA.csv",
"delimiter": ",",
"header":false
},
"schema":
"{\"type\" : \"struct\",
\"fields\" : [
{\"name\":\"id\", \"type\":\"string\", \"nullable\":false},
{\"name\":\"title\", \"type\":\"string\", \"nullable\":true},
{\"name\":\"manufacturer\",\"type\":\"string\",\"nullable\":true} ,
{\"name\":\"price\", \"type\":\"double\", \"nullable\":true}
]
}"
},
{
"name":"test2",
"format":"csv",
"props": {
"location": "examples/Amazon-Google/dataset_orig/tableB.csv",
"delimiter": ",",
"header":false
},
"schema":
"{\"type\" : \"struct\",
\"fields\" : [
{\"name\":\"id\", \"type\":\"string\", \"nullable\":false},
{\"name\":\"title\", \"type\":\"string\", \"nullable\":true},
{\"name\":\"manufacturer\",\"type\":\"string\",\"nullable\":true} ,
{\"name\":\"price\", \"type\":\"double\", \"nullable\":true}
]
}"
}
],
"labelDataSampleSize" : 0.4,
"numPartitions":4,
"modelId": 1100,
"zinggDir": "models",
"collectMetrics": false
}
77 changes: 77 additions & 0 deletions examples/amazon-google/configLink.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,77 @@
{
"fieldDefinition":[
{
"fieldName" : "id",
"matchType" : "DONT_USE",
"fields" : "id",
"dataType": "\"string\""
},
{
"fieldName" : "title",
"matchType" : "text",
"fields" : "title",
"dataType": "\"string\""
},
{
"fieldName" : "manufacturer",
"matchType": "fuzzy",
"fields" : "manufacturer",
"dataType": "\"string\""
},
{
"fieldName" : "price",
"matchType": "fuzzy",
"fields" : "price",
"dataType": "\"double\""
}],
"output" : [{
"name":"output",
"format":"csv",
"props": {
"location": "/tmp/zinggOutput",
"delimiter": ",",
"header":false
}
}],
"data" : [{
"name":"testA",
"format":"csv",
"props": {
"location": "examples/amazon-google/testA.csv",
"delimiter": ",",
"header":true
},
"schema":
"{\"type\" : \"struct\",
\"fields\" : [
{\"name\":\"id\", \"type\":\"string\", \"nullable\":false},
{\"name\":\"title\", \"type\":\"string\", \"nullable\":true},
{\"name\":\"manufacturer\",\"type\":\"string\",\"nullable\":true} ,
{\"name\":\"price\", \"type\":\"double\", \"nullable\":true}
]
}"
},
{
"name":"testB",
"format":"csv",
"props": {
"location": "examples/amazon-google/testB.csv",
"delimiter": ",",
"header":true
},
"schema":
"{\"type\" : \"struct\",
\"fields\" : [
{\"name\":\"id\", \"type\":\"string\", \"nullable\":false},
{\"name\":\"title\", \"type\":\"string\", \"nullable\":true},
{\"name\":\"manufacturer\",\"type\":\"string\",\"nullable\":true} ,
{\"name\":\"price\", \"type\":\"double\", \"nullable\":true}
]
}"
}
],
"labelDataSampleSize" : 0.4,
"numPartitions":4,
"modelId": 103,
"zinggDir": "models"
}
101 changes: 101 additions & 0 deletions examples/amazon-google/configWithTrainingSamples.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,101 @@
{
"trainingSamples" : [{
"name":"trainingPos",
"format":"csv",
"props": {
"location": "examples/amazon-google/training.csv",
"delimiter": ",",
"header":true,
"badRecordsPath":"/tmp/bad"
},
"schema":
"{\"type\" : \"struct\",
\"fields\" : [

{\"name\" : \"z_cluster\",\"type\" : \"string\",\"nullable\" : false, \"metadata\" : {}},
{\"name\":\"z_ismatch\",\"type\":\"integer\",\"nullable\":true,\"metadata\" : {}},
{\"name\":\"id\", \"type\":\"string\", \"nullable\":true},
{\"name\":\"title\", \"type\":\"string\", \"nullable\":true},
{\"name\":\"manufacturer\",\"type\":\"string\",\"nullable\":true} ,
{\"name\":\"price\", \"type\":\"double\", \"nullable\":true}

]
}"

}],
"fieldDefinition":[
{
"fieldName" : "id",
"matchType" : "DONT_USE",
"fields" : "id",
"dataType": "\"string\""
},
{
"fieldName" : "title",
"matchType" : "text",
"fields" : "title",
"dataType": "\"string\""
},
{
"fieldName" : "manufacturer",
"matchType": "fuzzy",
"fields" : "manufacturer",
"dataType": "\"string\""
},
{
"fieldName" : "price",
"matchType": "exact",
"fields" : "price",
"dataType": "\"double\""
}],
"output" : [{
"name":"output",
"format":"csv",
"props": {
"location": "/tmp/zinggOutput",
"delimiter": ",",
"header":false
}
}],
"data" : [{
"name":"test1",
"format":"csv",
"props": {
"location": "examples/amazon-google/original/tableA.csv",
"delimiter": ",",
"header":true
},
"schema":
"{\"type\" : \"struct\",
\"fields\" : [
{\"name\":\"id\", \"type\":\"string\", \"nullable\":false},
{\"name\":\"title\", \"type\":\"string\", \"nullable\":true},
{\"name\":\"manufacturer\",\"type\":\"string\",\"nullable\":true} ,
{\"name\":\"price\", \"type\":\"double\", \"nullable\":true}
]
}"
},
{
"name":"test2",
"format":"csv",
"props": {
"location": "examples/amazon-google/original/tableB.csv",
"delimiter": ",",
"header":true
},
"schema":
"{\"type\" : \"struct\",
\"fields\" : [
{\"name\":\"id\", \"type\":\"string\", \"nullable\":false},
{\"name\":\"title\", \"type\":\"string\", \"nullable\":true},
{\"name\":\"manufacturer\",\"type\":\"string\",\"nullable\":true} ,
{\"name\":\"price\", \"type\":\"double\", \"nullable\":true}
]
}"
}
],
"labelDataSampleSize" : 0.4,
"numPartitions":4,
"modelId": 103,
"zinggDir": "models"
}
Loading