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

added different output locations from single and compound tests #1059

Merged
merged 1 commit into from
Feb 24, 2025
Merged

added different output locations from single and compound tests #1059

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
2 changes: 1 addition & 1 deletion spark/core/src/test/java/zingg/spark/core/executor/TestSparkExecutorsCompound.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@

@ExtendWith(TestSparkBase.class)
public class TestSparkExecutorsCompound extends TestExecutorsCompound<SparkSession,Dataset<Row>,Row,Column,DataType> {
protected static final String CONFIG_FILE = "zingg/spark/core/executor/configSparkIntTest.json";
protected static final String CONFIG_FILE = "zingg/spark/core/executor/compound/configSparkIntTest.json";
protected static final String TEST_DATA_FILE = "zingg/spark/core/executor/test.csv";

public static final Log LOG = LogFactory.getLog(TestSparkExecutorsCompound.class);
Expand Down
4 changes: 2 additions & 2 deletions spark/core/src/test/java/zingg/spark/core/executor/TestSparkExecutorsSingle.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,8 +29,8 @@

@ExtendWith(TestSparkBase.class)
public class TestSparkExecutorsSingle extends TestExecutorsSingle<SparkSession,Dataset<Row>,Row,Column,DataType> {
protected static final String CONFIG_FILE = "zingg/spark/core/executor/configSparkIntTest.json";
protected static final String CONFIGLINK_FILE = "zingg/spark/core/executor/configSparkLinkTest.json";
protected static final String CONFIG_FILE = "zingg/spark/core/executor/single/configSparkIntTest.json";
protected static final String CONFIGLINK_FILE = "zingg/spark/core/executor/single/configSparkLinkTest.json";
protected static final String TEST1_DATA_FILE = "zingg/spark/core/executor/test1.csv";
protected static final String TEST2_DATA_FILE = "zingg/spark/core/executor/test2.csv";
private final SparkSession sparkSession;
Expand Down
106 changes: 106 additions & 0 deletions spark/core/src/test/resources/zingg/spark/core/executor/compound/configSparkIntTest.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,106 @@
{
"trainingSamples" : [{
"name":"trainingPos",
"format":"csv",
"props": {
"location": "./zingg/spark/core/executor/training.csv",
"delimiter": ",",
"header":false,
"badRecordsPath":"/tmp/bad"
},
"schema": "z_cluster string, z_ismatch integer, id string, fname string, lname string, stNo string, add1 string, add2 string, city string, areacode string, state string, dob string, ssn string"
}],
"fieldDefinition":[
{
"fieldName" : "id",
"matchType" : "dont_use",
"fields" : "id",
"dataType": "string"
},
{
"fieldName" : "fname",
"matchType" : "fuzzy",
"fields" : "fname",
"dataType": "string"
},
{
"fieldName" : "lname",
"matchType" : "fuzzy",
"fields" : "lname",
"dataType": "string"
},
{
"fieldName" : "stNo",
"matchType": "fuzzy",
"fields" : "stNo",
"dataType": "string"
},
{
"fieldName" : "add1",
"matchType": "fuzzy",
"fields" : "add1",
"dataType": "string"
},
{
"fieldName" : "add2",
"matchType": "fuzzy",
"fields" : "add2",
"dataType": "string"
},
{
"fieldName" : "city",
"matchType": "fuzzy",
"fields" : "city",
"dataType": "string"
},
{
"fieldName" : "areacode",
"matchType": "fuzzy",
"fields" : "areacode",
"dataType": "string"
},
{
"fieldName" : "state",
"matchType": "fuzzy",
"fields" : "state",
"dataType": "string"
},
{
"fieldName" : "dob",
"matchType": "fuzzy",
"fields" : "dob",
"dataType": "string"
},
{
"fieldName" : "ssn",
"matchType": "fuzzy",
"fields" : "ssn",
"dataType": "string"
}
],
"output" : [{
"name":"output",
"format":"csv",
"props": {
"location": "/tmp/junit_integration_spark/compound/zinggOutput",
"delimiter": ",",
"header":true
}
}],
"data" : [{
"name":"test",
"format":"csv",
"props": {
"location": "./zingg/spark/core/executor/test.csv",
"delimiter": ",",
"header":false
},
"schema": "id string, fname string, lname string, stNo string, add1 string, add2 string, city string, state string, areacode string, dob string, ssn string"
}
],
"labelDataSampleSize" : 0.5,
"numPartitions":4,
"modelId": "junit_integration_spark",
"zinggDir": "/tmp/junit_integration_spark/compound"

}
4 changes: 2 additions & 2 deletions ...ark/core/executor/configSparkIntTest.json → ...e/executor/single/configSparkIntTest.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -82,7 +82,7 @@
"name":"output",
"format":"csv",
"props": {
"location": "/tmp/junit_integration_spark/zinggOutput",
"location": "/tmp/junit_integration_spark/single/zinggOutput",
"delimiter": ",",
"header":true
}
Expand All @@ -101,6 +101,6 @@
"labelDataSampleSize" : 0.5,
"numPartitions":4,
"modelId": "junit_integration_spark",
"zinggDir": "/tmp/junit_integration_spark"
"zinggDir": "/tmp/junit_integration_spark/single"

}
4 changes: 2 additions & 2 deletions ...rk/core/executor/configSparkLinkTest.json → .../executor/single/configSparkLinkTest.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -65,7 +65,7 @@
"name":"output",
"format":"csv",
"props": {
"location": "/tmp/junit_integration_spark/zinggOutput",
"location": "/tmp/junit_integration_spark/single/zinggOutput",
"delimiter": ",",
"header":true
}
Expand Down Expand Up @@ -94,6 +94,6 @@
"labelDataSampleSize" : 0.5,
"numPartitions":4,
"modelId": "junit_integration_spark",
"zinggDir": "/tmp/junit_integration_spark"
"zinggDir": "/tmp/junit_integration_spark/single"

}
Loading