diff options
| author | Sean Owen <sowen@cloudera.com> | 2016-01-12 12:13:32 +0000 |
|---|---|---|
| committer | Sean Owen <sowen@cloudera.com> | 2016-01-12 12:13:32 +0000 |
| commit | 9c7f34af37ef328149c1d66b4689d80a1589e1cc (patch) | |
| tree | ef899b4df0e2bd15a8e95339407910069fcf0797 /docs/mllib-linear-methods.md | |
| parent | c48f2a3a5fd714ad2ff19b29337e55583988431e (diff) | |
| download | spark-9c7f34af37ef328149c1d66b4689d80a1589e1cc.tar.gz spark-9c7f34af37ef328149c1d66b4689d80a1589e1cc.tar.bz2 spark-9c7f34af37ef328149c1d66b4689d80a1589e1cc.zip | |
[SPARK-5273][MLLIB][DOCS] Improve documentation examples for LinearRegression
Use a much smaller step size in LinearRegressionWithSGD MLlib examples to achieve a reasonable RMSE.
Our training folks hit this exact same issue when concocting an example and had the same solution.
Author: Sean Owen <sowen@cloudera.com>
Closes #10675 from srowen/SPARK-5273.
Diffstat (limited to 'docs/mllib-linear-methods.md')
| -rw-r--r-- | docs/mllib-linear-methods.md | 8 |
1 files changed, 5 insertions, 3 deletions
diff --git a/docs/mllib-linear-methods.md b/docs/mllib-linear-methods.md index 20b35612ca..aac8f7560a 100644 --- a/docs/mllib-linear-methods.md +++ b/docs/mllib-linear-methods.md @@ -590,7 +590,8 @@ val parsedData = data.map { line => // Building the model val numIterations = 100 -val model = LinearRegressionWithSGD.train(parsedData, numIterations) +val stepSize = 0.00000001 +val model = LinearRegressionWithSGD.train(parsedData, numIterations, stepSize) // Evaluate model on training examples and compute training error val valuesAndPreds = parsedData.map { point => @@ -655,8 +656,9 @@ public class LinearRegression { // Building the model int numIterations = 100; + double stepSize = 0.00000001; final LinearRegressionModel model = - LinearRegressionWithSGD.train(JavaRDD.toRDD(parsedData), numIterations); + LinearRegressionWithSGD.train(JavaRDD.toRDD(parsedData), numIterations, stepSize); // Evaluate model on training examples and compute training error JavaRDD<Tuple2<Double, Double>> valuesAndPreds = parsedData.map( @@ -706,7 +708,7 @@ data = sc.textFile("data/mllib/ridge-data/lpsa.data") parsedData = data.map(parsePoint) # Build the model -model = LinearRegressionWithSGD.train(parsedData) +model = LinearRegressionWithSGD.train(parsedData, iterations=100, step=0.00000001) # Evaluate the model on training data valuesAndPreds = parsedData.map(lambda p: (p.label, model.predict(p.features))) |