我正在探索 pyspark 并且在尝试拟合高斯混合模型时遇到了错误。我一直在尝试限制潜在错误的总数，并且我已经能够通过显着减少的向量数量（在这种情况下，只有 3 个）来复制错误。
这是我的代码：
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: 1.2757, 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)
我一生都无法弄清楚发生了什么——我认为我创建的向量的大小不是负数，所以我不知道是什么引发了这个错误。我看过一些其他问题，但没有什么真正有帮助的，所以任何建议都将不胜感激！