Commit message (Collapse) | Author | Age | Files | Lines | |
---|---|---|---|---|---|
* | Merge pull request #786 from shivaram/mllib-java | Matei Zaharia | 2013-08-09 | 6 | -30/+285 |
|\ | | | | | Java fixes, tests and examples for ALS, KMeans | ||||
| * | Remove Java-specific constructor for Rating. | Shivaram Venkataraman | 2013-08-08 | 3 | -12/+3 |
| | | | | | | | | | | The scala constructor works for native type java types. Modify examples to match this. | ||||
| * | Add a test case for random initialization. | Shivaram Venkataraman | 2013-08-06 | 2 | -2/+13 |
| | | | | | | | | Also workaround a bug where double[][] class cast fails | ||||
| * | Java examples, tests for KMeans and ALS | Shivaram Venkataraman | 2013-08-06 | 6 | -27/+280 |
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | - Changes ALS to accept RDD[Rating] instead of (Int, Int, Double) making it easier to call from Java - Renames class methods from `train` to `run` to enable static methods to be called from Java. - Add unit tests which check if both static / class methods can be called. - Also add examples which port the main() function in ALS, KMeans to the examples project. Couple of minor changes to existing code: - Add a toJavaRDD method in RDD to convert scala RDD to java RDD easily - Workaround a bug where using double[] from Java leads to class cast exception in KMeans init | ||||
* | | Fixed a typo in mllib inline documentation. | Reynold Xin | 2013-08-08 | 1 | -1/+1 |
|/ | |||||
* | fixing formatting, style, and input | Ginger Smith | 2013-08-05 | 1 | -36/+37 |
| | |||||
* | fixing formatting | Ginger Smith | 2013-08-05 | 1 | -16/+23 |
| | |||||
* | adding matrix factorization data generator | Ginger Smith | 2013-08-02 | 1 | -0/+105 |
| | |||||
* | Increase Kryo buffer size in ALS since some arrays become big | Matei Zaharia | 2013-08-02 | 1 | -0/+1 |
| | |||||
* | Merge pull request #761 from mateiz/kmeans-generator | shivaram | 2013-07-31 | 2 | -4/+85 |
|\ | | | | | Add data generator for K-means | ||||
| * | Turn on caching in KMeans.main | Matei Zaharia | 2013-07-31 | 1 | -1/+1 |
| | | |||||
| * | Added data generator for K-means | Matei Zaharia | 2013-07-31 | 2 | -3/+84 |
| | | | | | | | | Also made it possible to specify the number of runs in KMeans.main(). | ||||
* | | Merge pull request #753 from shivaram/glm-refactor | Matei Zaharia | 2013-07-31 | 1 | -0/+165 |
|\ \ | | | | | | | Build changes for ML lib | ||||
| * | | Add bagel, mllib to SBT assembly. | Shivaram Venkataraman | 2013-07-30 | 1 | -0/+165 |
| | | | | | | | | | | | | Also add jblas dependency to mllib pom.xml | ||||
* | | | Use the Char version of split() instead of the String one for efficiency | Matei Zaharia | 2013-07-31 | 1 | -2/+2 |
| |/ |/| | |||||
* | | Minor style cleanup of mllib. | Reynold Xin | 2013-07-30 | 5 | -35/+39 |
| | | |||||
* | | Use a tigher bound in logistic regression unit test's prediction validation. | Reynold Xin | 2013-07-30 | 1 | -3/+4 |
| | | |||||
* | | Renamed Classification.scala to ClassificationModel.scala and ↵ | Reynold Xin | 2013-07-30 | 2 | -0/+0 |
|/ | | | | Regression.scala to RegressionModel.scala | ||||
* | made SimpleUpdater consistent with other updaters | Ameet Talwalkar | 2013-07-29 | 1 | -1/+2 |
| | |||||
* | Clarify how regVal is computed in Updater docs | Shivaram Venkataraman | 2013-07-29 | 1 | -8/+9 |
| | |||||
* | Remove duplicate loss history and clarify why. | Shivaram Venkataraman | 2013-07-29 | 3 | -13/+9 |
| | | | | Also some minor style fixes. | ||||
* | Style fix | Xinghao | 2013-07-29 | 2 | -2/+4 |
| | | | | Lines shortened to < 100 characters | ||||
* | Fix validatePrediction functions for Classification models | Xinghao | 2013-07-29 | 2 | -4/+2 |
| | | | | | Classifiers return categorical (Int) values that should be compared directly | ||||
* | Deleting extra LogisticRegressionGenerator and RidgeRegressionGenerator | Xinghao | 2013-07-29 | 2 | -96/+0 |
| | |||||
* | Fix rounding error in LogisticRegression.scala | Xinghao | 2013-07-29 | 1 | -2/+4 |
| | |||||
* | Replace map-reduce with dot operator using DoubleMatrix | Xinghao | 2013-07-28 | 4 | -8/+18 |
| | |||||
* | Fixed SVM and LR train functions to take Int instead of Double for ↵ | Xinghao | 2013-07-28 | 3 | -22/+21 |
| | | | | Classification | ||||
* | Changed Classification to return Int instead of Double | Xinghao | 2013-07-28 | 7 | -30/+28 |
| | | | | Also minor changes to formatting and comments | ||||
* | SVMSuite and LassoSuite rewritten to follow closely with LogisticRegressionSuite | Xinghao | 2013-07-28 | 2 | -35/+161 |
| | |||||
* | Move data generators to util | Xinghao | 2013-07-28 | 2 | -0/+0 |
| | |||||
* | Change *_LocalRandomSGD to *LocalRandomSGD | Xinghao | 2013-07-28 | 6 | -41/+24 |
| | |||||
* | Resolve conflicts with master, removed regParam for LogisticRegression | Xinghao | 2013-07-26 | 6 | -64/+412 |
| | |||||
* | New files from merge with master | Xinghao | 2013-07-26 | 15 | -7/+399 |
|\ | |||||
| * | Use a different validation dataset for Logistic Regression prediction testing. | Reynold Xin | 2013-07-23 | 1 | -12/+17 |
| | | |||||
| * | Made RegressionModel serializable and added unit tests to make sure predict ↵ | Reynold Xin | 2013-07-23 | 6 | -16/+42 |
| | | | | | | | | methods would work. | ||||
| * | Merge pull request #711 from shivaram/ml-generators | Matei Zaharia | 2013-07-19 | 2 | -39/+75 |
| |\ | | | | | | | Move ML lib data generator files to util/ | ||||
| | * | Rename classes to be called DataGenerator | Shivaram Venkataraman | 2013-07-18 | 2 | -3/+2 |
| | | | |||||
| | * | Refactor data generators to have a function that can be used in tests. | Shivaram Venkataraman | 2013-07-18 | 2 | -34/+71 |
| | | | |||||
| | * | Move ML lib data generator files to util/ | Shivaram Venkataraman | 2013-07-17 | 2 | -2/+2 |
| | | | |||||
| * | | Return Array[Double] from SGD instead of DoubleMatrix | Shivaram Venkataraman | 2013-07-17 | 2 | -6/+4 |
| | | | |||||
| * | | Change weights to be Array[Double] in LR model. | Shivaram Venkataraman | 2013-07-17 | 3 | -11/+15 |
| | | | | | | | | | | | | Also ensure weights are initialized to a column vector. | ||||
| * | | Rename loss -> stochasticLoss and add a note to explain why we have | Shivaram Venkataraman | 2013-07-17 | 3 | -8/+13 |
| | | | | | | | | | | | | multiple train methods. | ||||
| * | | Allow initial weight vectors in LogisticRegression. | Shivaram Venkataraman | 2013-07-17 | 5 | -32/+106 |
| |/ | | | | | | | | | Also move LogisticGradient to the LogisticRegression file and fix the unit tests log path. | ||||
| * | Add Apache license headers and LICENSE and NOTICE files | Matei Zaharia | 2013-07-16 | 19 | -1/+324 |
| | | |||||
* | | Making ClassificationModel serializable | Xinghao | 2013-07-26 | 1 | -1/+1 |
| | | |||||
* | | Rename LogisticRegression, SVM and Lasso to *_LocalRandomSGD | Xinghao | 2013-07-26 | 6 | -18/+18 |
| | | |||||
* | | Multiple changes | Xinghao | 2013-07-26 | 4 | -8/+9 |
| | | | | | | | | | | | | | | | | - Changed LogisticRegression regularization parameter to 0 - Removed println from SVM predict function - Fixed "Lasso" -> "SVM" in SVMGenerator - Added comment in Updater.scala to indicate L1 regularization leads to soft thresholding proximal function | ||||
* | | Adding SVM and Lasso, moving LogisticRegression to classification from ↵ | Xinghao | 2013-07-24 | 13 | -18/+642 |
|/ | | | | | | regression Also, add regularization parameter to SGD | ||||
* | Shuffle ratings in a more efficient way at start of ALS | Matei Zaharia | 2013-07-15 | 1 | -4/+14 |
| | |||||
* | Make number of blocks in ALS configurable and lower the default | Matei Zaharia | 2013-07-15 | 1 | -4/+5 |
| |