Python 使用pyspark'时出错;s高斯混合模型(NegativeArraySizeException)
我正在探索pyspark,在尝试拟合高斯混合模型时遇到了一个错误。我一直在尝试限制潜在错误的总数,并且我能够用显著减少的向量数(在本例中,只有3个)复制错误 这是我的密码:Python 使用pyspark'时出错;s高斯混合模型(NegativeArraySizeException),python,apache-spark,vector,pyspark,gmm,Python,Apache Spark,Vector,Pyspark,Gmm,我正在探索pyspark,在尝试拟合高斯混合模型时遇到了一个错误。我一直在尝试限制潜在错误的总数,并且我能够用显著减少的向量数(在本例中,只有3个)复制错误 这是我的密码: sc = ps.SparkContext('local[4]') sql_c = SQLContext(sc) test_df = sql_c.createDataFrame([ Row(features_idf=SparseVector(103882, {0: 0.6015, 5: 1.2943, 9: 1.27
sc = ps.SparkContext('local[4]')
sql_c = SQLContext(sc)
test_df = sql_c.createDataFrame([
Row(features_idf=SparseVector(103882, {0: 0.6015, 5: 1.2943, 9: 1.2757, 17: 1.111})),
Row(features_idf=SparseVector(103882, {3: 0.6015, 5: 4.2963, 14: 1.2757, 17: 1.5308})),
Row(features_idf=SparseVector(103882, {5: 0.6015, 13: 1.2343, 15: 1.2757, 17: 3.708}))])
gm = GaussianMixture(featuresCol='features_idf')
gm_model = gm.fit(test_df)
这是回溯:
---------------------------------------------------------------------------
Py4JJavaError Traceback (most recent call last)
<ipython-input-21-34a25cf6f1d8> in <module>()
1 gm = GaussianMixture(featuresCol='features_idf')
----> 2 gm_model = gm.fit(test_df)
/opt/spark/python/pyspark/ml/base.pyc in fit(self, dataset, params)
62 return self.copy(params)._fit(dataset)
63 else:
---> 64 return self._fit(dataset)
65 else:
66 raise ValueError("Params must be either a param map or a list/tuple of param maps, "
/opt/spark/python/pyspark/ml/wrapper.pyc in _fit(self, dataset)
211
212 def _fit(self, dataset):
--> 213 java_model = self._fit_java(dataset)
214 return self._create_model(java_model)
215
/opt/spark/python/pyspark/ml/wrapper.pyc in _fit_java(self, dataset)
208 """
209 self._transfer_params_to_java()
--> 210 return self._java_obj.fit(dataset._jdf)
211
212 def _fit(self, dataset):
/Users/wmees/anaconda/lib/python2.7/site-packages/py4j/java_gateway.pyc in __call__(self, *args)
1131 answer = self.gateway_client.send_command(command)
1132 return_value = get_return_value(
-> 1133 answer, self.gateway_client, self.target_id, self.name)
1134
1135 for temp_arg in temp_args:
/opt/spark/python/pyspark/sql/utils.pyc in deco(*a, **kw)
61 def deco(*a, **kw):
62 try:
---> 63 return f(*a, **kw)
64 except py4j.protocol.Py4JJavaError as e:
65 s = e.java_exception.toString()
/Users/wmees/anaconda/lib/python2.7/site-packages/py4j/protocol.pyc in get_return_value(answer, gateway_client, target_id, name)
317 raise Py4JJavaError(
318 "An error occurred while calling {0}{1}{2}.\n".
--> 319 format(target_id, ".", name), value)
320 else:
321 raise Py4JError(
Py4JJavaError: An error occurred while calling o141.fit.
: java.lang.NegativeArraySizeException
at scala.reflect.ManifestFactory$$anon$12.newArray(Manifest.scala:141)
at scala.reflect.ManifestFactory$$anon$12.newArray(Manifest.scala:139)
at breeze.linalg.DenseMatrix$.zeros(DenseMatrix.scala:340)
at breeze.linalg.diag$$anon$1.apply(diag.scala:19)
at breeze.linalg.diag$$anon$1.apply(diag.scala:17)
at breeze.generic.UFunc$class.apply(UFunc.scala:48)
at breeze.linalg.diag$.apply(diag.scala:15)
at org.apache.spark.mllib.clustering.GaussianMixture.org$apache$spark$mllib$clustering$GaussianMixture$$initCovariance(GaussianMixture.scala:269)
at org.apache.spark.mllib.clustering.GaussianMixture$$anonfun$3.apply(GaussianMixture.scala:188)
at org.apache.spark.mllib.clustering.GaussianMixture$$anonfun$3.apply(GaussianMixture.scala:186)
at scala.Array$.tabulate(Array.scala:331)
at org.apache.spark.mllib.clustering.GaussianMixture.run(GaussianMixture.scala:186)
at org.apache.spark.ml.clustering.GaussianMixture.fit(GaussianMixture.scala:331)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:237)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:280)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:214)
at java.lang.Thread.run(Thread.java:745)
---------------------------------------------------------------------------
Py4JJavaError回溯(最近一次调用)
在()
1 gm=高斯混合(featuresCol='features\u idf')
---->2 gm_模型=gm.fit(测试_df)
/opt/spark/python/pyspark/ml/base.pyc in-fit(self、dataset、params)
62返回自复制(参数)。_fit(数据集)
63.其他:
--->64返回自拟合(数据集)
65.其他:
66 raise VALUERROR(“参数必须是参数映射或参数映射的列表/元组,”
/opt/spark/python/pyspark/ml/wrapper.pyc in_-fit(self,dataset)
211
212 def_拟合(自身,数据集):
-->213 java_model=self._fit_java(数据集)
214返回自创建模型(java模型)
215
/java中的opt/spark/python/pyspark/ml/wrapper.pyc(self,数据集)
208 """
209 self.\u将参数转移到\u java()
-->210返回self.\u java.\u obj.fit(数据集.\u jdf)
211
212 def_拟合(自身,数据集):
/Users/wmees/anaconda/lib/python2.7/site-packages/py4j/java_gateway.pyc in____调用(self,*args)
1131 answer=self.gateway\u client.send\u命令(command)
1132返回值=获取返回值(
->1133应答,self.gateway\u客户端,self.target\u id,self.name)
1134
1135对于临时参数中的临时参数:
/装饰中的opt/spark/python/pyspark/sql/utils.pyc(*a,**kw)
61 def装饰(*a,**千瓦):
62尝试:
--->63返回f(*a,**kw)
64除py4j.protocol.Py4JJavaError外的其他错误为e:
65 s=e.java_exception.toString()
/获取返回值(应答、网关客户端、目标id、名称)中的Users/wmees/anaconda/lib/python2.7/site-packages/py4j/protocol.pyc
317 raise Py4JJavaError(
318“调用{0}{1}{2}时出错。\n”。
-->319格式(目标id,“.”,名称),值)
320其他:
321升起Py4JError(
Py4JJavaError:调用o141.fit时出错。
:java.lang.NegativeArraySizeException
位于scala.reflect.ManifestFactory$$anon$12.newArray(Manifest.scala:141)
位于scala.reflect.ManifestFactory$$anon$12.newArray(Manifest.scala:139)
在breeze.linalg.DenseMatrix$.zeros(DenseMatrix.scala:340)
在breeze.linalg.diag$$anon$1.apply(diag.scala:19)
在breeze.linalg.diag$$anon$1.apply(diag.scala:17)
位于breeze.generic.UFunc$class.apply(UFunc.scala:48)
在breeze.linalg.diag$.apply(diag.scala:15)
位于org.apache.spark.mllib.clustering.GaussianMixture.org$apache$spark$mllib$clustering$GaussianMixture$$initconvariance(GaussianMixture.scala:269)
位于org.apache.spark.mllib.clustering.GaussianMixture$$anonfun$3.apply(GaussianMixture.scala:188)
位于org.apache.spark.mllib.clustering.GaussianMixture$$anonfun$3.apply(GaussianMixture.scala:186)
位于scala.Array$.tablate(Array.scala:331)
位于org.apache.spark.mllib.clustering.GaussianMixture.run(GaussianMixture.scala:186)
位于org.apache.spark.ml.clustering.GaussianMixture.fit(GaussianMixture.scala:331)
在sun.reflect.NativeMethodAccessorImpl.invoke0(本机方法)处
位于sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
在sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)中
位于java.lang.reflect.Method.invoke(Method.java:498)
位于py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:237)
位于py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
在py4j.Gateway.invoke处(Gateway.java:280)
位于py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
在py4j.commands.CallCommand.execute(CallCommand.java:79)
在py4j.GatewayConnection.run处(GatewayConnection.java:214)
运行(Thread.java:745)
我一辈子都搞不清楚到底发生了什么——我不认为我创建的向量的大小是负数,所以我不知道是什么触发了这个错误。我已经研究了一些其他问题,没有什么真正的帮助,所以任何建议都将不胜感激!
Spark MLlib中的GaussianMixture
创建用于期望最大化算法的协方差矩阵。在您的情况下,该矩阵由大小为103882 x 103882
的数组支持。正如有人指出的那样,这会导致整数溢出,试图分配大小为103882*103882=-2093431964
的数组。但这似乎是一个错误,Spark MLlib使用的Guassian混合算法在高维数据上无法正常工作。请参阅警告:
@注:对于高维数据(具有许多特征),该算法的性能可能较差。这是因为高维数据(a)使聚类变得困难(基于统计/理论参数)和(b)高斯分布的数值问题。
否定raysizeexception
通常是整数溢出的症状