From b0c805ca30597af19ae203da39f4e172e873ac07 Mon Sep 17 00:00:00 2001 From: hyukjinkwon Date: Thu, 24 Nov 2016 17:28:30 +0900 Subject: [PATCH] Make wiki links pretty --- mllib/src/main/scala/org/apache/spark/ml/feature/DCT.scala | 2 +- .../org/apache/spark/ml/feature/PolynomialExpansion.scala | 5 +++-- .../org/apache/spark/ml/feature/StopWordsRemover.scala | 2 +- .../apache/spark/ml/regression/AFTSurvivalRegression.scala | 3 ++- .../spark/ml/regression/GeneralizedLinearRegression.scala | 3 ++- .../apache/spark/mllib/evaluation/RegressionMetrics.scala | 6 ++++-- .../spark/mllib/stat/MultivariateOnlineSummarizer.scala | 2 +- .../main/scala/org/apache/spark/mllib/stat/Statistics.scala | 3 ++- .../mllib/stat/distribution/MultivariateGaussian.scala | 2 +- 9 files changed, 17 insertions(+), 11 deletions(-) diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/DCT.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/DCT.scala index c7d6e0f5bcb61..a33a48365fa18 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/feature/DCT.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/feature/DCT.scala @@ -33,7 +33,7 @@ import org.apache.spark.sql.types.DataType * such that the transform matrix is unitary (aka scaled DCT-II). * * More information on - * Wikipedia. + * DCT-II (Wikipedia). */ @Since("1.5.0") class DCT @Since("1.5.0") (@Since("1.5.0") override val uid: String) diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/PolynomialExpansion.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/PolynomialExpansion.scala index eaed2ff298d57..4be17da3e9f76 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/feature/PolynomialExpansion.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/feature/PolynomialExpansion.scala @@ -30,8 +30,9 @@ import org.apache.spark.sql.types.DataType /** * Perform feature expansion in a polynomial space. As said in wikipedia of Polynomial Expansion, - * which is available at here, - * "In mathematics, an expansion of a product of sums expresses it as a sum of products by using + * which is available at + * Polynomial expansion (Wikipedia) + * , "In mathematics, an expansion of a product of sums expresses it as a sum of products by using * the fact that multiplication distributes over addition". Take a 2-variable feature vector * as an example: `(x, y)`, if we want to expand it with degree 2, then we get * `(x, x * x, y, x * y, y * y)`. diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/StopWordsRemover.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/StopWordsRemover.scala index 802cbe95e522e..a55816249c74b 100755 --- a/mllib/src/main/scala/org/apache/spark/ml/feature/StopWordsRemover.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/feature/StopWordsRemover.scala @@ -32,7 +32,7 @@ import org.apache.spark.sql.types.{ArrayType, StringType, StructType} * @note null values from input array are preserved unless adding null to stopWords * explicitly. * - * @see here + * @see Stop words (Wikipedia) */ @Since("1.5.0") class StopWordsRemover @Since("1.5.0") (@Since("1.5.0") override val uid: String) diff --git a/mllib/src/main/scala/org/apache/spark/ml/regression/AFTSurvivalRegression.scala b/mllib/src/main/scala/org/apache/spark/ml/regression/AFTSurvivalRegression.scala index cb58e444838fc..d6ad1ea6d1096 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/regression/AFTSurvivalRegression.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/regression/AFTSurvivalRegression.scala @@ -119,7 +119,8 @@ private[regression] trait AFTSurvivalRegressionParams extends Params /** * :: Experimental :: * Fit a parametric survival regression model named accelerated failure time (AFT) model - * (see here) + * (see + * Accelerated failure time model (Wikipedia)) * based on the Weibull distribution of the survival time. */ @Experimental diff --git a/mllib/src/main/scala/org/apache/spark/ml/regression/GeneralizedLinearRegression.scala b/mllib/src/main/scala/org/apache/spark/ml/regression/GeneralizedLinearRegression.scala index 3e3517562fad0..bb6f1c93dac37 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/regression/GeneralizedLinearRegression.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/regression/GeneralizedLinearRegression.scala @@ -124,7 +124,8 @@ private[regression] trait GeneralizedLinearRegressionBase extends PredictorParam * :: Experimental :: * * Fit a Generalized Linear Model - * (see here) + * (see + * Generalized linear model (Wikipedia)) * specified by giving a symbolic description of the linear * predictor (link function) and a description of the error distribution (family). * It supports "gaussian", "binomial", "poisson" and "gamma" as family. diff --git a/mllib/src/main/scala/org/apache/spark/mllib/evaluation/RegressionMetrics.scala b/mllib/src/main/scala/org/apache/spark/mllib/evaluation/RegressionMetrics.scala index 202e4d3f65eba..ad99b00a31fd5 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/evaluation/RegressionMetrics.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/evaluation/RegressionMetrics.scala @@ -74,7 +74,8 @@ class RegressionMetrics @Since("2.0.0") ( /** * Returns the variance explained by regression. * explainedVariance = $\sum_i (\hat{y_i} - \bar{y})^2^ / n$ - * @see here + * @see + * Fraction of variance unexplained (Wikipedia) */ @Since("1.2.0") def explainedVariance: Double = { @@ -110,7 +111,8 @@ class RegressionMetrics @Since("2.0.0") ( /** * Returns R^2^, the unadjusted coefficient of determination. - * @see here + * @see + * Coefficient of determination (Wikipedia) * In case of regression through the origin, the definition of R^2^ is to be modified. * @see * J. G. Eisenhauer, Regression through the Origin. Teaching Statistics 25, 76-80 (2003) diff --git a/mllib/src/main/scala/org/apache/spark/mllib/stat/MultivariateOnlineSummarizer.scala b/mllib/src/main/scala/org/apache/spark/mllib/stat/MultivariateOnlineSummarizer.scala index 114f76659c524..7dc0c459ec032 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/stat/MultivariateOnlineSummarizer.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/stat/MultivariateOnlineSummarizer.scala @@ -38,7 +38,7 @@ import org.apache.spark.mllib.linalg.{Vector, Vectors} * For weighted instances, the unbiased estimation of variance is defined by the reliability * weights: * see - * here. + * Reliability weights (Wikipedia). */ @Since("1.1.0") @DeveloperApi diff --git a/mllib/src/main/scala/org/apache/spark/mllib/stat/Statistics.scala b/mllib/src/main/scala/org/apache/spark/mllib/stat/Statistics.scala index 9130f7b1fde01..7ba9b292969e7 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/stat/Statistics.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/stat/Statistics.scala @@ -186,7 +186,8 @@ object Statistics { * distribution of the sample data and the theoretical distribution we can provide a test for the * the null hypothesis that the sample data comes from that theoretical distribution. * For more information on KS Test: - * @see here + * @see + * Kolmogorov-Smirnov test (Wikipedia) * * @param data an `RDD[Double]` containing the sample of data to test * @param cdf a `Double => Double` function to calculate the theoretical CDF at a given value diff --git a/mllib/src/main/scala/org/apache/spark/mllib/stat/distribution/MultivariateGaussian.scala b/mllib/src/main/scala/org/apache/spark/mllib/stat/distribution/MultivariateGaussian.scala index 09028b2c8775c..835a1e9d70d54 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/stat/distribution/MultivariateGaussian.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/stat/distribution/MultivariateGaussian.scala @@ -29,7 +29,7 @@ import org.apache.spark.mllib.util.MLUtils * the event that the covariance matrix is singular, the density will be computed in a * reduced dimensional subspace under which the distribution is supported. * (see - * here) + * Multivariate normal distribution (Wikipedia)) * * @param mu The mean vector of the distribution * @param sigma The covariance matrix of the distribution