From 99ce4304f3f826901ad33d682832b95ccd5c94d1 Mon Sep 17 00:00:00 2001
From: Xiangrui Meng <meng@databricks.com>
Date: Thu, 13 Aug 2015 09:24:03 -0700
Subject: [PATCH] fix mllib pydoc warnings

---
 python/pyspark/mllib/regression.py | 14 ++++++++++----
 python/pyspark/mllib/util.py       |  1 +
 2 files changed, 11 insertions(+), 4 deletions(-)

diff --git a/python/pyspark/mllib/regression.py b/python/pyspark/mllib/regression.py
index 5b7afc15ddfba..41946e3674fbe 100644
--- a/python/pyspark/mllib/regression.py
+++ b/python/pyspark/mllib/regression.py
@@ -207,8 +207,10 @@ def train(cls, data, iterations=100, step=1.0, miniBatchFraction=1.0,
         Train a linear regression model using Stochastic Gradient
         Descent (SGD).
         This solves the least squares regression formulation
-                f(weights) = 1/n ||A weights-y||^2^
-        (which is the mean squared error).
+
+            f(weights) = 1/(2n) ||A weights - y||^2,
+
+        which is the mean squared error.
         Here the data matrix has n rows, and the input RDD holds the
         set of rows of A, each with its corresponding right hand side
         label y. See also the documentation for the precise formulation.
@@ -334,7 +336,9 @@ def train(cls, data, iterations=100, step=1.0, regParam=0.01,
         Stochastic Gradient Descent.
         This solves the l1-regularized least squares regression
         formulation
-            f(weights) = 1/2n ||A weights-y||^2^  + regParam ||weights||_1
+
+            f(weights) = 1/(2n) ||A weights - y||^2  + regParam ||weights||_1.
+
         Here the data matrix has n rows, and the input RDD holds the
         set of rows of A, each with its corresponding right hand side
         label y. See also the documentation for the precise formulation.
@@ -451,7 +455,9 @@ def train(cls, data, iterations=100, step=1.0, regParam=0.01,
         Stochastic Gradient Descent.
         This solves the l2-regularized least squares regression
         formulation
-            f(weights) = 1/2n ||A weights-y||^2^  + regParam/2 ||weights||^2^
+
+            f(weights) = 1/(2n) ||A weights - y||^2 + regParam/2 ||weights||^2.
+
         Here the data matrix has n rows, and the input RDD holds the
         set of rows of A, each with its corresponding right hand side
         label y. See also the documentation for the precise formulation.
diff --git a/python/pyspark/mllib/util.py b/python/pyspark/mllib/util.py
index 916de2d6fcdbd..10a1e4b3eb0fc 100644
--- a/python/pyspark/mllib/util.py
+++ b/python/pyspark/mllib/util.py
@@ -300,6 +300,7 @@ def generateLinearInput(intercept, weights, xMean, xVariance,
         :param: seed      Random Seed
         :param: eps       Used to scale the noise. If eps is set high,
                           the amount of gaussian noise added is more.
+
         Returns a list of LabeledPoints of length nPoints
         """
         weights = [float(weight) for weight in weights]