I'm experiencing some problems with a machine learning project. I use XGBoost for forecast on warehouse items supply and i'm trying to select the best hyperparams with hyperopt and mlflow.
This is the code:
import pandas as pd
import glob
import holidays
import numpy as np
import matplotlib.pyplot as plt
from scipy import stats
from sklearn import metrics,model_selection
from sklearn.model_selection import train_test_split
from typing import Dict,Union,Any,Tuple
import mlflow
import mlflow.xgboost
import xgboost as xgb
import hyperopt
from hyperopt.pyll.base import scope
import findspark
findspark.init()
import pyspark
import logging
import sys
class xgb_tune:
def __init__(self):
logging.basicConfig(format='%(levelname)s %(asctime)s %(message)s')
self.logger = logging.getLogger(__name__)
self.logger.setLevel(logging.DEBUG)
self.nomeFile = 'dati'
self.pathForecast = 'F:\\My-data\\prg\\machine-learning\\forecast\\'
self.pathWS = "F:\\My-data\\prg\\cq_webshaker\\"
self.test = None
self.train = None
print("Python v{}".format(sys.version))
def loadData(self,onlyweek=False,fromFile=True,nomeFile=None):
# method to load the data (hidden here for easy reading)
def reg_metrics(self,actual: pd.Series, pred: pd.Series) -> Dict:
return{
"MAE": metrics.mean_absolute_error(actual, pred),
"RMSE": np.sqrt(metrics.mean_squared_error(actual, pred))
}
def fit_and_log_cv(
self,
x_train: Union[pd.DataFrame, np.array],
y_train: Union[pd.DataFrame, np.array],
x_test: Union[pd.DataFrame, np.array],
y_test: Union[pd.DataFrame, np.array],
params: Dict[str,Any],
nested: bool = False
) -> Tuple[Dict[str,Any],Dict[str,Any]]:
with mlflow.start_run(nested=nested) as run:
print(type(params))
print(params)
model_cv = xgb.XGBRFRegressor(**params)
y_pred_cv = model_selection.cross_val_predict(model_cv, x_train, y_train)
metrics_cv = {
f"val_{metric}":value
for metric, value in self.reg_metrics(y_train, y_pred_cv).items()
}
#fit e log del training
try:
mlflow.xgboost.autolog()
dataset = xgb.DMatrix(x_train,label = y_train)
model = xgb.train(params=params, dtrain=dataset)
y_pred_test = model.predict(xgb.DMatrix(x_test))
metric_test = {
f"test_{metric}": value
for metric,value in self.reg_metrics(y_test, y_pred_test).items()
}
metrics = {**metric_test,**metrics_cv}
mlflow.log_metrics(metrics)
return metrics
except Exception as e:
print('autolog -> {}'.format(e))
def build_train_objective(
self,
x_train: Union[pd.DataFrame,np.array],
y_train: Union[pd.DataFrame,np.array],
x_test: Union[pd.DataFrame,np.array],
y_test: Union[pd.DataFrame,np.array],
metric: str
):
def train_func(params):
""" fa il train del modello e ritorna loss e metriche """
try:
metrics = self.fit_and_log_cv(x_train, y_train, x_test, y_test, params, nested = True)
return {'status': hyperopt.STATUS_OK, 'loss':metrics[metric]}
except Exception as e:
print('train_func -> {}'.format(e))
return train_func
def log_best(self,run: mlflow.entities.Run, metric: str) -> None:
runs = None
try:
client = mlflow.tracking.MlflowClient()
runs = client.search_runs(
[run.info.experiment_id],
"tags.mlflow.parentRunId = '{run_id}' ".format(run_id=run.info.run_id)
)
best_run = min(runs, key=lambda run: run.data.metrics[metric])
mlflow.set_tag("best_run", best_run.info.run_id)
mlflow.log_metric(f"best_{metric}", best_run.data.metrics[metric])
except Exception as e:
self.logger.error('log_best -> {}'.format(e))
if __name__ == '__main__':
mod = xgb_tune()
df = mod.loadData()
print(df)
#splitto i dati i train e test
X = df.loc[:,df.columns != 'qta']
y = df.loc[:,df.columns == 'qta']
X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.2,shuffle=False)
MAX_EVALS = 1
METRIC = "val_RMSE"
# Number of experiments to run at once
PARALLELISM = 8
space = {
'learning_rate': hyperopt.hp.loguniform('learning_rate', 0, 0.3),
'max_depth': scope.int(hyperopt.hp.uniform('max_depth', 1, 100)),
'min_child_weight': hyperopt.hp.loguniform('min_child_weight', -2, 3),
'subsample': hyperopt.hp.uniform('subsample', 0.5, 1),
'colsample_bytree': hyperopt.hp.uniform('colsample_bytree', 0.5, 1),
'gamma': hyperopt.hp.loguniform('gamma', -10, 10),
'alpha': hyperopt.hp.loguniform('alpha', -10, 10),
'lambda': hyperopt.hp.loguniform('lambda', -10, 10),
'objective': 'reg:squarederror',
'eval_metric': 'rmse',
'seed': 123,
}
trials = hyperopt.SparkTrials(parallelism=PARALLELISM)
train_objective = mod.build_train_objective(
X_train, y_train, X_test, y_test, METRIC)
with mlflow.start_run() as run:
try:
hyperopt.fmin(fn=train_objective,
space=space,
algo=hyperopt.tpe.suggest,
max_evals=MAX_EVALS,
trials=trials)
except Exception as e:
mod.logger.error('main -> {}'.format(e))
mod.log_best(run, METRIC)
search_run_id = run.info.run_id
experiment_id = run.info.experiment_id
But when i run the script i get these errors and i don't know what is the specific error and how to log it.
2022/11/10 11:33:39 WARNING mlflow.utils.autologging_utils: MLflow autologging encountered a warning: "###########\Anaconda3\envs\machine-learning\lib\site-packages\_distutils_hack\__init__.py:33: UserWarning: Setuptools is replacing distutils."
trial task 0 failed, exception is An error occurred while calling z:org.apache.spark.api.python.PythonRDD.collectAndServe.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 0.0 failed 1 times, most recent failure: Lost task 0.0 in stage 0.0 (TID 0) (########### executor driver): org.apache.spark.SparkException: Python worker exited unexpectedly (crashed)
at org.apache.spark.api.python.BasePythonRunner$ReaderIterator$$anonfun$1.applyOrElse(PythonRunner.scala:599)
at org.apache.spark.api.python.BasePythonRunner$ReaderIterator$$anonfun$1.applyOrElse(PythonRunner.scala:581)
at scala.runtime.AbstractPartialFunction.apply(AbstractPartialFunction.scala:38)
at org.apache.spark.api.python.PythonRunner$$anon$3.read(PythonRunner.scala:770)
at org.apache.spark.api.python.PythonRunner$$anon$3.read(PythonRunner.scala:747)
at org.apache.spark.api.python.BasePythonRunner$ReaderIterator.hasNext(PythonRunner.scala:512)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator.foreach(Iterator.scala:943)
at scala.collection.Iterator.foreach$(Iterator.scala:943)
at org.apache.spark.InterruptibleIterator.foreach(InterruptibleIterator.scala:28)
at scala.collection.generic.Growable.$plus$plus$eq(Growable.scala:62)
at scala.collection.generic.Growable.$plus$plus$eq$(Growable.scala:53)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:105)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:49)
at scala.collection.TraversableOnce.to(TraversableOnce.scala:366)
at scala.collection.TraversableOnce.to$(TraversableOnce.scala:364)
at org.apache.spark.InterruptibleIterator.to(InterruptibleIterator.scala:28)
at scala.collection.TraversableOnce.toBuffer(TraversableOnce.scala:358)
at scala.collection.TraversableOnce.toBuffer$(TraversableOnce.scala:358)
at org.apache.spark.InterruptibleIterator.toBuffer(InterruptibleIterator.scala:28)
at scala.collection.TraversableOnce.toArray(TraversableOnce.scala:345)
at scala.collection.TraversableOnce.toArray$(TraversableOnce.scala:339)
at org.apache.spark.InterruptibleIterator.toArray(InterruptibleIterator.scala:28)
at org.apache.spark.rdd.RDD.$anonfun$collect$2(RDD.scala:1021)
at org.apache.spark.SparkContext.$anonfun$runJob$5(SparkContext.scala:2268)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
at org.apache.spark.scheduler.Task.run(Task.scala:136)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:548)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1504)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:551)
at java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.lang.Thread.run(Unknown Source)
Caused by: java.io.EOFException
at java.io.DataInputStream.readInt(Unknown Source)
at org.apache.spark.api.python.PythonRunner$$anon$3.read(PythonRunner.scala:755)
29 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2672)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2608)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2607)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2607)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1182)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1182)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1182)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2860)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2802)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2791)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:952)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2228)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2249)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2268)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2293)
at org.apache.spark.rdd.RDD.$anonfun$collect$1(RDD.scala:1021)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:406)
at org.apache.spark.rdd.RDD.collect(RDD.scala:1020)
at org.apache.spark.api.python.PythonRDD$.collectAndServe(PythonRDD.scala:180)
at org.apache.spark.api.python.PythonRDD.collectAndServe(PythonRDD.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
at java.lang.reflect.Method.invoke(Unknown Source)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:282)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182)
at py4j.ClientServerConnection.run(ClientServerConnection.java:106)
at java.lang.Thread.run(Unknown Source)
Caused by: org.apache.spark.SparkException: Python worker exited unexpectedly (crashed)
at org.apache.spark.api.python.BasePythonRunner$ReaderIterator$$anonfun$1.applyOrElse(PythonRunner.scala:599)
at org.apache.spark.api.python.BasePythonRunner$ReaderIterator$$anonfun$1.applyOrElse(PythonRunner.scala:581)
at scala.runtime.AbstractPartialFunction.apply(AbstractPartialFunction.scala:38)
at org.apache.spark.api.python.PythonRunner$$anon$3.read(PythonRunner.scala:770)
at org.apache.spark.api.python.PythonRunner$$anon$3.read(PythonRunner.scala:747)
at org.apache.spark.api.python.BasePythonRunner$ReaderIterator.hasNext(PythonRunner.scala:512)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator.foreach(Iterator.scala:943)
at scala.collection.Iterator.foreach$(Iterator.scala:943)
at org.apache.spark.InterruptibleIterator.foreach(InterruptibleIterator.scala:28)
at scala.collection.generic.Growable.$plus$plus$eq(Growable.scala:62)
at scala.collection.generic.Growable.$plus$plus$eq$(Growable.scala:53)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:105)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:49)
at scala.collection.TraversableOnce.to(TraversableOnce.scala:366)
at scala.collection.TraversableOnce.to$(TraversableOnce.scala:364)
at org.apache.spark.InterruptibleIterator.to(InterruptibleIterator.scala:28)
at scala.collection.TraversableOnce.toBuffer(TraversableOnce.scala:358)
at scala.collection.TraversableOnce.toBuffer$(TraversableOnce.scala:358)
at org.apache.spark.InterruptibleIterator.toBuffer(InterruptibleIterator.scala:28)
at scala.collection.TraversableOnce.toArray(TraversableOnce.scala:345)
at scala.collection.TraversableOnce.toArray$(TraversableOnce.scala:339)
at org.apache.spark.InterruptibleIterator.toArray(InterruptibleIterator.scala:28)
at org.apache.spark.rdd.RDD.$anonfun$collect$2(RDD.scala:1021)
at org.apache.spark.SparkContext.$anonfun$runJob$5(SparkContext.scala:2268)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
at org.apache.spark.scheduler.Task.run(Task.scala:136)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:548)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1504)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:551)
at java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
1 more
Caused by: java.io.EOFException
at java.io.DataInputStream.readInt(Unknown Source)
at org.apache.spark.api.python.PythonRunner$$anon$3.read(PythonRunner.scala:755)
29 more
.
None
ERROR 2022-11-10 11:33:39,931 trial task 0 failed, exception is An error occurred while calling z:org.apache.spark.api.python.PythonRDD.collectAndServe.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 0.0 failed 1 times, most recent failure: Lost task 0.0 in stage 0.0 (TID 0) (gsuzzi.passepartout.local executor driver): org.apache.spark.SparkException: Python worker exited unexpectedly (crashed)
at org.apache.spark.api.python.BasePythonRunner$ReaderIterator$$anonfun$1.applyOrElse(PythonRunner.scala:599)
at org.apache.spark.api.python.BasePythonRunner$ReaderIterator$$anonfun$1.applyOrElse(PythonRunner.scala:581)
at scala.runtime.AbstractPartialFunction.apply(AbstractPartialFunction.scala:38)
at org.apache.spark.api.python.PythonRunner$$anon$3.read(PythonRunner.scala:770)
at org.apache.spark.api.python.PythonRunner$$anon$3.read(PythonRunner.scala:747)
at org.apache.spark.api.python.BasePythonRunner$ReaderIterator.hasNext(PythonRunner.scala:512)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator.foreach(Iterator.scala:943)
at scala.collection.Iterator.foreach$(Iterator.scala:943)
at org.apache.spark.InterruptibleIterator.foreach(InterruptibleIterator.scala:28)
at scala.collection.generic.Growable.$plus$plus$eq(Growable.scala:62)
at scala.collection.generic.Growable.$plus$plus$eq$(Growable.scala:53)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:105)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:49)
at scala.collection.TraversableOnce.to(TraversableOnce.scala:366)
at scala.collection.TraversableOnce.to$(TraversableOnce.scala:364)
at org.apache.spark.InterruptibleIterator.to(InterruptibleIterator.scala:28)
at scala.collection.TraversableOnce.toBuffer(TraversableOnce.scala:358)
at scala.collection.TraversableOnce.toBuffer$(TraversableOnce.scala:358)
at org.apache.spark.InterruptibleIterator.toBuffer(InterruptibleIterator.scala:28)
at scala.collection.TraversableOnce.toArray(TraversableOnce.scala:345)
at scala.collection.TraversableOnce.toArray$(TraversableOnce.scala:339)
at org.apache.spark.InterruptibleIterator.toArray(InterruptibleIterator.scala:28)
at org.apache.spark.rdd.RDD.$anonfun$collect$2(RDD.scala:1021)
at org.apache.spark.SparkContext.$anonfun$runJob$5(SparkContext.scala:2268)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
at org.apache.spark.scheduler.Task.run(Task.scala:136)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:548)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1504)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:551)
at java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.lang.Thread.run(Unknown Source)
Caused by: java.io.EOFException
at java.io.DataInputStream.readInt(Unknown Source)
at org.apache.spark.api.python.PythonRunner$$anon$3.read(PythonRunner.scala:755)
29 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2672)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2608)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2607)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2607)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1182)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1182)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1182)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2860)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2802)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2791)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:952)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2228)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2249)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2268)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2293)
at org.apache.spark.rdd.RDD.$anonfun$collect$1(RDD.scala:1021)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:406)
at org.apache.spark.rdd.RDD.collect(RDD.scala:1020)
at org.apache.spark.api.python.PythonRDD$.collectAndServe(PythonRDD.scala:180)
at org.apache.spark.api.python.PythonRDD.collectAndServe(PythonRDD.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
at java.lang.reflect.Method.invoke(Unknown Source)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:282)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182)
at py4j.ClientServerConnection.run(ClientServerConnection.java:106)
at java.lang.Thread.run(Unknown Source)
Caused by: org.apache.spark.SparkException: Python worker exited unexpectedly (crashed)
at org.apache.spark.api.python.BasePythonRunner$ReaderIterator$$anonfun$1.applyOrElse(PythonRunner.scala:599)
at org.apache.spark.api.python.BasePythonRunner$ReaderIterator$$anonfun$1.applyOrElse(PythonRunner.scala:581)
at scala.runtime.AbstractPartialFunction.apply(AbstractPartialFunction.scala:38)
at org.apache.spark.api.python.PythonRunner$$anon$3.read(PythonRunner.scala:770)
at org.apache.spark.api.python.PythonRunner$$anon$3.read(PythonRunner.scala:747)
at org.apache.spark.api.python.BasePythonRunner$ReaderIterator.hasNext(PythonRunner.scala:512)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator.foreach(Iterator.scala:943)
at scala.collection.Iterator.foreach$(Iterator.scala:943)
at org.apache.spark.InterruptibleIterator.foreach(InterruptibleIterator.scala:28)
at scala.collection.generic.Growable.$plus$plus$eq(Growable.scala:62)
at scala.collection.generic.Growable.$plus$plus$eq$(Growable.scala:53)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:105)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:49)
at scala.collection.TraversableOnce.to(TraversableOnce.scala:366)
at scala.collection.TraversableOnce.to$(TraversableOnce.scala:364)
at org.apache.spark.InterruptibleIterator.to(InterruptibleIterator.scala:28)
at scala.collection.TraversableOnce.toBuffer(TraversableOnce.scala:358)
at scala.collection.TraversableOnce.toBuffer$(TraversableOnce.scala:358)
at org.apache.spark.InterruptibleIterator.toBuffer(InterruptibleIterator.scala:28)
at scala.collection.TraversableOnce.toArray(TraversableOnce.scala:345)
at scala.collection.TraversableOnce.toArray$(TraversableOnce.scala:339)
at org.apache.spark.InterruptibleIterator.toArray(InterruptibleIterator.scala:28)
at org.apache.spark.rdd.RDD.$anonfun$collect$2(RDD.scala:1021)
at org.apache.spark.SparkContext.$anonfun$runJob$5(SparkContext.scala:2268)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
at org.apache.spark.scheduler.Task.run(Task.scala:136)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:548)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1504)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:551)
at java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
1 more
Caused by: java.io.EOFException
at java.io.DataInputStream.readInt(Unknown Source)
at org.apache.spark.api.python.PythonRunner$$anon$3.read(PythonRunner.scala:755)
29 more
22/11/10 11:33:39 ERROR Executor: Exception in task 0.0 in stage 0.0 (TID 0)
org.apache.spark.SparkException: Python worker exited unexpectedly (crashed)
at org.apache.spark.api.python.BasePythonRunner$ReaderIterator$$anonfun$1.applyOrElse(PythonRunner.scala:599)
at org.apache.spark.api.python.BasePythonRunner$ReaderIterator$$anonfun$1.applyOrElse(PythonRunner.scala:581)
at scala.runtime.AbstractPartialFunction.apply(AbstractPartialFunction.scala:38)
at org.apache.spark.api.python.PythonRunner$$anon$3.read(PythonRunner.scala:770)
at org.apache.spark.api.python.PythonRunner$$anon$3.read(PythonRunner.scala:747)
at org.apache.spark.api.python.BasePythonRunner$ReaderIterator.hasNext(PythonRunner.scala:512)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator.foreach(Iterator.scala:943)
at scala.collection.Iterator.foreach$(Iterator.scala:943)
at org.apache.spark.InterruptibleIterator.foreach(InterruptibleIterator.scala:28)
at scala.collection.generic.Growable.$plus$plus$eq(Growable.scala:62)
at scala.collection.generic.Growable.$plus$plus$eq$(Growable.scala:53)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:105)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:49)
at scala.collection.TraversableOnce.to(TraversableOnce.scala:366)
at scala.collection.TraversableOnce.to$(TraversableOnce.scala:364)
at org.apache.spark.InterruptibleIterator.to(InterruptibleIterator.scala:28)
at scala.collection.TraversableOnce.toBuffer(TraversableOnce.scala:358)
at scala.collection.TraversableOnce.toBuffer$(TraversableOnce.scala:358)
at org.apache.spark.InterruptibleIterator.toBuffer(InterruptibleIterator.scala:28)
at scala.collection.TraversableOnce.toArray(TraversableOnce.scala:345)
at scala.collection.TraversableOnce.toArray$(TraversableOnce.scala:339)
at org.apache.spark.InterruptibleIterator.toArray(InterruptibleIterator.scala:28)
at org.apache.spark.rdd.RDD.$anonfun$collect$2(RDD.scala:1021)
at org.apache.spark.SparkContext.$anonfun$runJob$5(SparkContext.scala:2268)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
at org.apache.spark.scheduler.Task.run(Task.scala:136)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:548)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1504)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:551)
at java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.lang.Thread.run(Unknown Source)
Caused by: java.io.EOFException
at java.io.DataInputStream.readInt(Unknown Source)
at org.apache.spark.api.python.PythonRunner$$anon$3.read(PythonRunner.scala:755)
29 more
22/11/10 11:33:39 WARN TaskSetManager: Lost task 0.0 in stage 0.0 (TID 0) (gsuzzi.passepartout.local executor driver): org.apache.spark.SparkException: Python worker exited unexpectedly (crashed)
at org.apache.spark.api.python.BasePythonRunner$ReaderIterator$$anonfun$1.applyOrElse(PythonRunner.scala:599)
at org.apache.spark.api.python.BasePythonRunner$ReaderIterator$$anonfun$1.applyOrElse(PythonRunner.scala:581)
at scala.runtime.AbstractPartialFunction.apply(AbstractPartialFunction.scala:38)
at org.apache.spark.api.python.PythonRunner$$anon$3.read(PythonRunner.scala:770)
at org.apache.spark.api.python.PythonRunner$$anon$3.read(PythonRunner.scala:747)
at org.apache.spark.api.python.BasePythonRunner$ReaderIterator.hasNext(PythonRunner.scala:512)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator.foreach(Iterator.scala:943)
at scala.collection.Iterator.foreach$(Iterator.scala:943)
at org.apache.spark.InterruptibleIterator.foreach(InterruptibleIterator.scala:28)
at scala.collection.generic.Growable.$plus$plus$eq(Growable.scala:62)
at scala.collection.generic.Growable.$plus$plus$eq$(Growable.scala:53)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:105)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:49)
at scala.collection.TraversableOnce.to(TraversableOnce.scala:366)
at scala.collection.TraversableOnce.to$(TraversableOnce.scala:364)
at org.apache.spark.InterruptibleIterator.to(InterruptibleIterator.scala:28)
at scala.collection.TraversableOnce.toBuffer(TraversableOnce.scala:358)
at scala.collection.TraversableOnce.toBuffer$(TraversableOnce.scala:358)
at org.apache.spark.InterruptibleIterator.toBuffer(InterruptibleIterator.scala:28)
at scala.collection.TraversableOnce.toArray(TraversableOnce.scala:345)
at scala.collection.TraversableOnce.toArray$(TraversableOnce.scala:339)
at org.apache.spark.InterruptibleIterator.toArray(InterruptibleIterator.scala:28)
at org.apache.spark.rdd.RDD.$anonfun$collect$2(RDD.scala:1021)
at org.apache.spark.SparkContext.$anonfun$runJob$5(SparkContext.scala:2268)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
at org.apache.spark.scheduler.Task.run(Task.scala:136)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:548)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1504)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:551)
at java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.lang.Thread.run(Unknown Source)
Caused by: java.io.EOFException
at java.io.DataInputStream.readInt(Unknown Source)
at org.apache.spark.api.python.PythonRunner$$anon$3.read(PythonRunner.scala:755)
29 more
22/11/10 11:33:39 ERROR TaskSetManager: Task 0 in stage 0.0 failed 1 times; aborting job
Total Trials: 1: 0 succeeded, 1 failed, 0 cancelled.
INFO 2022-11-10 11:33:41,318 Total Trials: 1: 0 succeeded, 1 failed, 0 cancelled.
ERROR 2022-11-10 11:33:41,322 main -> There are no evaluation tasks, cannot return argmin of task losses.
ERROR 2022-11-10 11:33:45,578 log_best -> min() arg is an empty sequence
Any suggestions? Thanks
It seems that the problem is related to the number of parallel worker setted. If i change PARALLELISM to some other values (< 8) it works.