I'm using Azure Databricks + Hyperopt + MLflow for some hyperparameter tuning on a small dataset. Seem like the job is running, and I get output in MLflow, but the job ends with the following error message:
Hyperopt failed to execute mlflow.end_run() with tracking URI: databricks
Here is my code code with some information redacted:
from pyspark.sql import SparkSession
# spark session initialization
spark = (SparkSession.builder.getOrCreate())
sc = spark.sparkContext
# Data Processing
import pandas as pd
import numpy as np
# Hyperparameter Tuning
from hyperopt import fmin, tpe, hp, anneal, Trials, space_eval, SparkTrials, STATUS_OK
from sklearn.model_selection import RepeatedStratifiedKFold, cross_val_score
# Modeling
from sklearn.ensemble import RandomForestClassifier
# cleaning
import gc
# tracking
import mlflow
# track runtime
from datetime import date, datetime
mlflow.set_experiment('/user/myname/myexp')
# notebook settings \ variable settings
n_splits = #
n_repeats = #
max_evals = #
dfL = pd.read_csv("/my/data/loc/mydata.csv")
x_train = dfL[['f1','f2','f3']]
y_train = dfL['target']
def define_model(params):
model = RandomForestClassifier(n_estimators=int(params['n_estimators']),
criterion=params['criterion'],
max_depth=int(params['max_depth']),
min_samples_split=params['min_samples_split'],
min_samples_leaf=params['min_samples_leaf'],
min_weight_fraction_leaf=params['min_weight_fraction_leaf'],
max_features=params['max_features'],
max_leaf_nodes=None,
min_impurity_decrease=params['min_impurity_decrease'],
min_impurity_split=None,
bootstrap=params['bootstrap'],
oob_score=False,
n_jobs=-1,
random_state=int(params['random_state']),
verbose=0,
warm_start=False,
class_weight={0:params['class_0_weight'], 1:params['class_1_weight']})
return model
space = {'n_estimators': hp.quniform('n_estimators', #, #, #),
'criterion': hp.choice('#', ['#','#']),
'max_depth': hp.quniform('max_depth', #, #, #),
'min_samples_split': hp.quniform('min_samples_split', #, #, #),
'min_samples_leaf': hp.quniform('min_samples_leaf', #, #, #),
'min_weight_fraction_leaf': hp.quniform('min_weight_fraction_leaf', #, #, #),
'max_features': hp.quniform('max_features', #, #, #),
'min_impurity_decrease': hp.quniform('min_impurity_decrease', #, #, #),
'bootstrap': hp.choice('bootstrap', [#,#]),
'random_state': hp.quniform('random_state', #, #, #),
'class_0_weight': hp.choice('class_0_weight', [#,#,#]),
'class_1_weight': hp.choice('class_1_weight', [#,#,#])}
# define hyperopt objective
def objective(params, n_splits=n_splits, n_repeats=n_repeats):
# define model
model = define_model(params)
# get cv splits
kfold = RepeatedStratifiedKFold(n_splits=n_splits, n_repeats=n_repeats, random_state=1331)
# define and run sklearn cv scorer
scores = cross_val_score(model, x_train, y_train, cv=kfold, scoring='roc_auc')
score = scores.mean()
return {'loss': score*(-1), 'status': STATUS_OK}
spark_trials = SparkTrials(parallelism=36, spark_session=spark)
with mlflow.start_run():
best = fmin(objective, space, algo=tpe.suggest, trials=spark_trials, max_evals=max_evals)
and then at the end I get..
100%|██████████| 200/200 [1:35:28<00:00, 100.49s/trial, best loss: -0.9584565527065526]
Hyperopt failed to execute mlflow.end_run() with tracking URI: databricks
Exception: 'MLFLOW_RUN_ID'
Total Trials: 200: 200 succeeded, 0 failed, 0 cancelled.
My Azure Databricks cluster is..
6.6 ML (includes Apache Spark 2.4.5, Scala 2.11)
Standard_DS3_v2
min 9 max 18 nodes
Am I doing something wrong or is this a bug?
