diff options
Diffstat (limited to 'python/pyspark/mllib/util.py')
-rw-r--r-- | python/pyspark/mllib/util.py | 14 |
1 files changed, 6 insertions, 8 deletions
diff --git a/python/pyspark/mllib/util.py b/python/pyspark/mllib/util.py index d94900cefd..639cda6350 100644 --- a/python/pyspark/mllib/util.py +++ b/python/pyspark/mllib/util.py @@ -16,6 +16,7 @@ # import numpy as np +import warnings from pyspark.mllib.linalg import Vectors, SparseVector from pyspark.mllib.regression import LabeledPoint @@ -29,9 +30,9 @@ class MLUtils: Helper methods to load, save and pre-process data used in MLlib. """ - @deprecated @staticmethod def _parse_libsvm_line(line, multiclass): + warnings.warn("deprecated", DeprecationWarning) return _parse_libsvm_line(line) @staticmethod @@ -67,9 +68,9 @@ class MLUtils: " but got " % type(v)) return " ".join(items) - @deprecated @staticmethod def loadLibSVMFile(sc, path, multiclass=False, numFeatures=-1, minPartitions=None): + warnings.warn("deprecated", DeprecationWarning) return loadLibSVMFile(sc, path, numFeatures, minPartitions) @staticmethod @@ -106,7 +107,6 @@ class MLUtils: >>> tempFile.write("+1 1:1.0 3:2.0 5:3.0\\n-1\\n-1 2:4.0 4:5.0 6:6.0") >>> tempFile.flush() >>> examples = MLUtils.loadLibSVMFile(sc, tempFile.name).collect() - >>> multiclass_examples = MLUtils.loadLibSVMFile(sc, tempFile.name).collect() >>> tempFile.close() >>> type(examples[0]) == LabeledPoint True @@ -115,20 +115,18 @@ class MLUtils: >>> type(examples[1]) == LabeledPoint True >>> print examples[1] - (0.0,(6,[],[])) + (-1.0,(6,[],[])) >>> type(examples[2]) == LabeledPoint True >>> print examples[2] - (0.0,(6,[1,3,5],[4.0,5.0,6.0])) - >>> multiclass_examples[1].label - -1.0 + (-1.0,(6,[1,3,5],[4.0,5.0,6.0])) """ lines = sc.textFile(path, minPartitions) parsed = lines.map(lambda l: MLUtils._parse_libsvm_line(l)) if numFeatures <= 0: parsed.cache() - numFeatures = parsed.map(lambda x: 0 if x[1].size == 0 else x[1][-1]).reduce(max) + 1 + numFeatures = parsed.map(lambda x: -1 if x[1].size == 0 else x[1][-1]).reduce(max) + 1 return parsed.map(lambda x: LabeledPoint(x[0], Vectors.sparse(numFeatures, x[1], x[2]))) @staticmethod |