[
https://issues.apache.org/jira/browse/SPARK-18476?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15713515#comment-15713515
]
Miao Wang commented on SPARK-18476:
-----------------------------------
spark.logit predict should output original label instead of a numerical value
as the prediction column. Example:
> training <- suppressWarnings(createDataFrame(iris))
> binomial_training <- training[training$Species %in% c("versicolor",
> "virginica"), ]
> binomial_model <- spark.logit(binomial_training, Species ~ Sepal_Length +
> Sepal_Width)
> prediction <- predict(binomial_model, binomial_training)
> showDF(prediction)
Output:
+------------+-----------+------------+-----------+----------+--------------------+--------------------+----------+
|Sepal_Length|Sepal_Width|Petal_Length|Petal_Width| Species|
rawPrediction| probability|prediction|
+------------+-----------+------------+-----------+----------+--------------------+--------------------+----------+
| 7.0| 3.2| 4.7|
1.4|versicolor|[-1.5655042626435...|[0.17285823940230...| virginica|
| 6.4| 3.2| 4.5|
1.5|versicolor|[-0.4240802660720...|[0.39554079174312...| virginica|
| 6.9| 3.1| 4.9|
1.5|versicolor|[-1.3348014339322...|[0.20836626079909...| virginica|
| 5.5| 2.3| 4.0|
1.3|versicolor|[1.65224519232947...|[0.83919426374389...|versicolor|
| 6.5| 2.8| 4.6|
1.5|versicolor|[-0.4524556150364...|[0.38877708044707...| virginica|
| 5.7| 2.8| 4.5|
1.3|versicolor|[1.06944304705877...|[0.74449098435029...|versicolor|
| 6.3| 3.3| 4.7|
1.6|versicolor|[-0.2743084292595...|[0.43184968922729...| virginica|
| 4.9| 2.4| 3.3|
1.0|versicolor|[2.75320369295153...|[0.94009402758065...|versicolor|
| 6.6| 2.9| 4.6|
1.3|versicolor|[-0.6831584437477...|[0.33555673563505...| virginica|
| 5.2| 2.7| 3.9|
1.4|versicolor|[2.06109520681768...|[0.88706393592062...|versicolor|
| 5.0| 2.0| 3.5|
1.0|versicolor|[2.72482834398713...|[0.93847590782569...|versicolor|
| 5.9| 3.0| 4.2|
1.5|versicolor|[0.60803738963620...|[0.64749297424084...|versicolor|
| 6.0| 2.2| 4.0|
1.0|versicolor|[0.74152402446931...|[0.67732902849243...|versicolor|
| 6.1| 2.9| 4.7|
1.4|versicolor|[0.26802822006176...|[0.56660877197498...|versicolor|
| 5.6| 2.9| 3.6|
1.3|versicolor|[1.21921488387130...|[0.77192535405997...|versicolor|
| 6.7| 3.1| 4.4|
1.4|versicolor|[-0.9543267684084...|[0.27801550694056...| virginica|
| 5.6| 3.0| 4.5|
1.5|versicolor|[1.17874938792192...|[0.76472286588073...|versicolor|
| 5.8| 2.7| 4.1|
1.0|versicolor|[0.91967121024624...|[0.71497510778599...|versicolor|
| 6.2| 2.2| 4.5|
1.5|versicolor|[0.36104935894550...|[0.58929443051304...|versicolor|
| 5.6| 2.5| 3.9|
1.1|versicolor|[1.38107686766881...|[0.79916389423163...|versicolor|
+------------+-----------+------------+-----------+----------+--------------------+--------------------+----------+
The `prediction` column should be the original label as shown above.
> SparkR Logistic Regression should should support output original label.
> -----------------------------------------------------------------------
>
> Key: SPARK-18476
> URL: https://issues.apache.org/jira/browse/SPARK-18476
> Project: Spark
> Issue Type: Bug
> Components: SparkR
> Reporter: Miao Wang
> Assignee: Miao Wang
> Fix For: 2.1.0
>
>
> Similar to [SPARK-18401], as a classification algorithm, logistic regression
> should support output original label instead of supporting index label.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
