Github user jkbradley commented on a diff in the pull request: https://github.com/apache/spark/pull/11663#discussion_r56406655 --- Diff: python/pyspark/ml/param/__init__.py --- @@ -65,6 +72,106 @@ def __eq__(self, other): return False +class TypeConverters(object): + """ + .. note:: DeveloperApi + + Factory methods for common type conversion functions for `Param.typeConverter`. + + .. versionadded:: 2.0.0 + """ + + @staticmethod + def _is_numeric(value): + vtype = type(value) + return vtype == int or vtype == float or vtype == np.float64 \ + or vtype == np.int64 or vtype.__name__ == 'long' + + @staticmethod + def _can_convert_to_list(value): + vtype = type(value) + return vtype == list or vtype == np.ndarray or isinstance(value, Vector) + + @staticmethod + def identity(value): + """ + Dummy converter that just returns value. + """ + return value + + @staticmethod + def convertToList(value): + """ + Convert a value to a list, if possible. + """ + if type(value) == list: + return value + elif type(value) == np.ndarray: + return list(value) + elif isinstance(value, Vector): + return value.toArray() + else: + raise TypeError("Could not convert %s to list" % value) + + @staticmethod + def convertToListFloat(value): + """ + Convert a value to list of floats, if possible. + """ + if TypeConverters._can_convert_to_list(value) and \ + all(map(lambda v: TypeConverters._is_numeric(v), value)): + value = TypeConverters.convertToList(value) + return list(map(lambda v: float(v), value)) + else: + raise TypeError("Could not convert %s to list of floats" % value) + + @staticmethod + def convertToListInt(value): + """ + Convert a value to list of ints, if possible. + """ + if TypeConverters._can_convert_to_list(value) and \ + all(map(lambda v: TypeConverters._is_numeric(v), value)): + value = TypeConverters.convertToList(value) + return list(map(lambda v: int(v), value)) + else: + raise TypeError("Could not convert %s to list of ints" % value) + + @staticmethod + def convertToVector(value): + """ + Convert a value to a MLlib Vector, if possible. + """ + if isinstance(value, Vector): + return value + elif TypeConverters._can_convert_to_list(value) and \ + all(map(lambda v: TypeConverters._is_numeric(v), value)): + value = DenseVector(value) + else: + raise TypeError("Could not convert %s to vector" % value) + return value + + @staticmethod + def convertToFloat(value): + """ + Convert a value to a float, if possible. + """ + if TypeConverters._is_numeric(value): + return float(value) + else: + raise TypeError("Could not convert %s to float" % value) + + @staticmethod + def convertToInt(value): + """ + Convert a value to an int, if possible. + """ + if TypeConverters._is_numeric(value): --- End diff -- check for integer value
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org