我在本地机器上复制数据营课程代码时遇到了困难。课程名为“pyspark中的推荐引擎”。如果有人知道如何在本地机器或googlecolab上使用pyspark训练als模型,请帮助。每次遇到这个错误,我都会在本地机器和googlecolab上尝试同样的过程。可能我错过了一些非常基本的东西
ratings = ratings.select(ratings.user_id.cast("integer"), ratings.movie_id.cast("integer"), ratings.rating.cast("double"))
ratings.printSchema()
(train, test) = ratings.randomSplit([0.8, 0.2], seed = 1234)
from pyspark.ml.recommendation import ALS
als = ALS(userCol="user_id", itemCol="movie_id", ratingCol="rating",rank =25, maxIter = 100, regParam = 0.5, nonnegative = True,coldStartStrategy= "drop", implicitPrefs = False)
model=als.fit(train)
输出:
Py4JJavaError Traceback (most recent call last)
<ipython-input-5-c31a339ff67a> in <module>
11 als = ALS(userCol="user_id", itemCol="movie_id", ratingCol="rating",rank =25, maxIter = 100, regParam = 0.5, nonnegative = True,coldStartStrategy= "drop", implicitPrefs = False)
12
---> 13 model=als.fit(train)
~/venv/lib/python3.6/site-packages/pyspark/ml/base.py in fit(self, dataset, params)
127 return self.copy(params)._fit(dataset)
128 else:
--> 129 return self._fit(dataset)
130 else:
131 raise ValueError("Params must be either a param map or a list/tuple of param maps, "
~/venv/lib/python3.6/site-packages/pyspark/ml/wrapper.py in _fit(self, dataset)
319
320 def _fit(self, dataset):
--> 321 java_model = self._fit_java(dataset)
322 model = self._create_model(java_model)
323 return self._copyValues(model)
~/venv/lib/python3.6/site-packages/pyspark/ml/wrapper.py in _fit_java(self, dataset)
316 """
317 self._transfer_params_to_java()
--> 318 return self._java_obj.fit(dataset._jdf)
319
320 def _fit(self, dataset):
~/venv/lib/python3.6/site-packages/py4j/java_gateway.py in __call__(self, *args)
1303 answer = self.gateway_client.send_command(command)
1304 return_value = get_return_value(
-> 1305 answer, self.gateway_client, self.target_id, self.name)
1306
1307 for temp_arg in temp_args:
~/venv/lib/python3.6/site-packages/pyspark/sql/utils.py in deco(*a,**kw)
129 def deco(*a,**kw):
130 try:
--> 131 return f(*a,**kw)
132 except py4j.protocol.Py4JJavaError as e:
133 converted = convert_exception(e.java_exception)
~/venv/lib/python3.6/site-packages/py4j/protocol.py in get_return_value(answer, gateway_client, target_id, name)
326 raise Py4JJavaError(
327 "An error occurred while calling {0}{1}{2}.\n".
--> 328 format(target_id, ".", name), value)
329 else:
330 raise Py4JError(
Py4JJavaError: An error occurred while calling o59.fit.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 62.0 failed 1 times, most recent failure: Lost task 0.0 in stage 62.0 (TID 544, 192.168.101.225, executor driver): java.lang.StackOverflowError
------------------------------------------------
----------------------------------------
Exception happened during processing of request from ('127.0.0.1', 54328)
Traceback (most recent call last):
File "/usr/lib/python3.6/socketserver.py", line 320, in _handle_request_noblock
self.process_request(request, client_address)
File "/usr/lib/python3.6/socketserver.py", line 351, in process_request
self.finish_request(request, client_address)
File "/usr/lib/python3.6/socketserver.py", line 364, in finish_request
self.RequestHandlerClass(request, client_address, self)
File "/usr/lib/python3.6/socketserver.py", line 724, in __init__
self.handle()
File "/home/abhilash/venv/lib/python3.6/site-packages/pyspark/accumulators.py", line 268, in handle
poll(accum_updates)
File "/home/abhilash/venv/lib/python3.6/site-packages/pyspark/accumulators.py", line 241, in poll
if func():
File "/home/abhilash/venv/lib/python3.6/site-packages/pyspark/accumulators.py", line 245, in accum_updates
num_updates = read_int(self.rfile)
File "/home/abhilash/venv/lib/python3.6/site-packages/pyspark/serializers.py", line 595, in read_int
raise EOFError
EOFError
---------------------------------------
暂无答案!
目前还没有任何答案,快来回答吧!