isg-siegen/auto-surprise

An AutoRecSys library for Surprise. Automate algorithm selection and hyperparameter tuning :rocket:

Auto-Surprise

Auto-Surprise is built as a wrapper around the Python Surprise recommender-system library. It automates algorithm selection and hyper parameter optimization in a highly parallelized manner.

• Documentation is available at Auto-Surprise ReadTheDocs
• AutoSurprise is currently in development.

Setup

Auto-Surprise is easy to install with Pip, and required Python>=3.6 installed on a linux system. Currently not supported in windows, but can be used using WSL.

$ pip install auto-surprise

Usage

Basic usage of AutoSurprise is given below.

from surprise import Dataset
from auto_surprise.engine import Engine

# Load the dataset
data = Dataset.load_builtin('ml-100k')

# Intitialize auto surprise engine
engine = Engine(verbose=True)

# Start the trainer
best_algo, best_params, best_score, tasks = engine.train(
    data=data, 
    target_metric='test_rmse', 
    cpu_time_limit=60 * 60, 
    max_evals=100
)

In the above example, we first initialize the Engine. We then run engine.train() to begin training our model. To train the model we need to pass the following

• data : The data as an instance of surprise.dataset.DatasetAutoFolds. Please read Surprise Dataset docs
• target_metric : The metric we seek to minimize. Available options are test_rmse and test_mae.
• cpu_time_limit : The time limit we want to train. This is in seconds. For datasets like Movielens 100k, 1 hour is sufficient. But you may want to increase this based on the size of your dataset
• max_evals: The maximum number of evaluations each algorithm gets for hyper parameter optimization.
• hpo_algo: Auto-Surprise uses Hyperopt for hyperparameter tuning. By default, it's set to use TPE, but you can change this to any algorithm supported by hyperopt, such as Adaptive TPE or Random search.

Setting the Hyperparameter Optimization Algorithm

Auto-Surprise uses Hyperopt. You can change the HPO algo as shown below.

# Example for setting the HPO algorithm to adaptive TPE
import hyperopt

...

engine = Engine(verbose=True)
engine.train(
    data=data,
    target_metric='test_rmse',
    cpu_time_limit=60 * 60,
    max_evals=100,
    hpo_algo=hyperopt.atpe.suggest
)

Building back the best model

You can build a pickelable model as shown.

model = engine.build_model(best_algo, best_params)

Benchmarks

In my testing, Auto-Surprise performed anywhere from 0.8 to 4% improvement in RMSE compared to the best performing default algorithm configuration. In the table below are the results for the Jester 2 dataset. Benchmark results for Movielens and Book-Crossing dataset are also available here

Algorithm	RMSE	MAE	Time
Normal Predictor	7.277	5.886	00:00:01
SVD	4.905	3.97	00:00:13
SVD++	5.102	4.055	00:00:29
NMF	--	--	--
Slope One	5.189	3.945	00:00:02
KNN Basic	5.078	4.034	00:02:14
KNN with Means	5.124	3.955	00:02:16
KNN with Z-score	5.219	3.955	00:02:20
KNN Baseline	4.898	3.896	00:02:14
Co-clustering	5.153	3.917	00:00:12
Baseline Only	4.849	3.934	00:00:01
GridSearch	4.7409	3.8147	80:52:35
Auto-Surprise (TPE)	4.6489	3.6837	02:00:10
Auto-Surprise (ATPE)	4.6555	3.6906	02:00:01

Papers

Auto-Surprise: An Automated Recommender-System (AutoRecSys) Library with Tree of Parzens Estimator (TPE) Optimization

auto-surprise's Issues

available parameters ?

when it comes to KNN based algos, what similarity options it uses...Also, does it have user_baed parameter as usual surprise library does at sim_options?

Quick Example errors

Hello,
I was trying to run the Quick Example (https://auto-surprise.readthedocs.io/en/stable/usage/quick_start.html#quick-example ) but I got this output:

auto_surprise 0.1.8
Available CPUs: 16
Evaluating RMSE, MAE, MSE of algorithm NormalPredictor on 5 split(s).

                  Fold 1  Fold 2  Fold 3  Fold 4  Fold 5  Mean    Std     
RMSE (testset)    1.5145  1.5229  1.5190  1.5152  1.5235  1.5190  0.0037  
MAE (testset)     1.2179  1.2228  1.2170  1.2117  1.2180  1.2175  0.0035  
MSE (testset)     2.2937  2.3193  2.3074  2.2960  2.3210  2.3075  0.0114  
Fit time          0.06    0.06    0.07    0.07    0.07    0.07    0.01    
Test time         0.08    0.04    0.07    0.08    0.08    0.07    0.01    
Baseline loss: 1.5190366726386277
Starting process with svd algorithm
Starting process with svdpp algorithm
Starting process with nmf algorithm
Starting process with knn_basic algorithm
Starting process with knn_baseline algorithm
  0%|                                                                                                                                                              | 0/100 [00:00<?, ?trial/s, best loss=?]
Exception for algo svd
Starting process with knn_with_means algorithm
Traceback (most recent call last):
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/auto_surprise/trainer.py", line 85, in start_with_limits
    _, best_trial = self.algo_base.best_hyperparams(max_evals)
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/auto_surprise/algorithms/base.py", line 99, in best_hyperparams
    best = fmin(**fmin_args)
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/hyperopt/fmin.py", line 540, in fmin
    return trials.fmin(
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/hyperopt/base.py", line 671, in fmin
    return fmin(
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/hyperopt/fmin.py", line 586, in fmin
    rval.exhaust()
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/hyperopt/fmin.py", line 364, in exhaust
    self.run(self.max_evals - n_done, block_until_done=self.asynchronous)
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/hyperopt/fmin.py", line 279, in run
    new_ids, self.domain, trials, self.rstate.integers(2 ** 31 - 1)
AttributeError: module 'numpy.random' has no attribute 'integers'

  0%|                                                                                                                                                              | 0/100 [00:00<?, ?trial/s, best loss=?]
  0%|                                                                                                                                                              | 0/100 [00:00<?, ?trial/s, best loss=?]Exception for algo svdpp
  0%|                                                                                                                                                              | 0/100 [00:00<?, ?trial/s, best loss=?]
Starting process with knn_with_z_score algorithm
Exception for algo nmf
Traceback (most recent call last):
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/auto_surprise/trainer.py", line 85, in start_with_limits
    _, best_trial = self.algo_base.best_hyperparams(max_evals)
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/auto_surprise/algorithms/base.py", line 99, in best_hyperparams
    best = fmin(**fmin_args)
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/hyperopt/fmin.py", line 540, in fmin
    return trials.fmin(
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/hyperopt/base.py", line 671, in fmin
    return fmin(
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/hyperopt/fmin.py", line 586, in fmin
    rval.exhaust()
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/hyperopt/fmin.py", line 364, in exhaust
    self.run(self.max_evals - n_done, block_until_done=self.asynchronous)
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/hyperopt/fmin.py", line 279, in run
    new_ids, self.domain, trials, self.rstate.integers(2 ** 31 - 1)
AttributeError: module 'numpy.random' has no attribute 'integers'

Traceback (most recent call last):
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/auto_surprise/trainer.py", line 85, in start_with_limits
    _, best_trial = self.algo_base.best_hyperparams(max_evals)
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/auto_surprise/algorithms/base.py", line 99, in best_hyperparams
    best = fmin(**fmin_args)
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/hyperopt/fmin.py", line 540, in fmin
    return trials.fmin(
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/hyperopt/base.py", line 671, in fmin
    return fmin(
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/hyperopt/fmin.py", line 586, in fmin
    rval.exhaust()
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/hyperopt/fmin.py", line 364, in exhaust
    self.run(self.max_evals - n_done, block_until_done=self.asynchronous)
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/hyperopt/fmin.py", line 279, in run
    new_ids, self.domain, trials, self.rstate.integers(2 ** 31 - 1)
AttributeError: module 'numpy.random' has no attribute 'integers'

Starting process with co_clustering algorithm
  0%|                                                                                                                                                              | 0/100 [00:00<?, ?trial/s, best loss=?]
Exception for algo knn_basic
Starting process with slope_one algorithm
Traceback (most recent call last):
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/auto_surprise/trainer.py", line 85, in start_with_limits
    _, best_trial = self.algo_base.best_hyperparams(max_evals)
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/auto_surprise/algorithms/base.py", line 99, in best_hyperparams
    best = fmin(**fmin_args)
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/hyperopt/fmin.py", line 540, in fmin
    return trials.fmin(
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/hyperopt/base.py", line 671, in fmin
    return fmin(
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/hyperopt/fmin.py", line 586, in fmin
    rval.exhaust()
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/hyperopt/fmin.py", line 364, in exhaust
    self.run(self.max_evals - n_done, block_until_done=self.asynchronous)
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/hyperopt/fmin.py", line 279, in run
    new_ids, self.domain, trials, self.rstate.integers(2 ** 31 - 1)
AttributeError: module 'numpy.random' has no attribute 'integers'

Starting process with baseline_only algorithm
  0%|                                                                                                                                                              | 0/100 [00:00<?, ?trial/s, best loss=?]
  0%|                                                                                                                                                              | 0/100 [00:00<?, ?trial/s, best loss=?]Exception for algo knn_baseline
  0%|                                                                                                                                                              | 0/100 [00:00<?, ?trial/s, best loss=?]
Exception for algo knn_with_means
Traceback (most recent call last):
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/auto_surprise/trainer.py", line 85, in start_with_limits
    _, best_trial = self.algo_base.best_hyperparams(max_evals)
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/auto_surprise/algorithms/base.py", line 99, in best_hyperparams
    best = fmin(**fmin_args)
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/hyperopt/fmin.py", line 540, in fmin
    return trials.fmin(
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/hyperopt/base.py", line 671, in fmin
    return fmin(
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/hyperopt/fmin.py", line 586, in fmin
    rval.exhaust()
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/hyperopt/fmin.py", line 364, in exhaust
    self.run(self.max_evals - n_done, block_until_done=self.asynchronous)
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/hyperopt/fmin.py", line 279, in run
    new_ids, self.domain, trials, self.rstate.integers(2 ** 31 - 1)
AttributeError: module 'numpy.random' has no attribute 'integers'

  0%|                                                                                                                                                              | 0/100 [00:00<?, ?trial/s, best loss=?]
Exception for algo knn_with_z_score
Traceback (most recent call last):
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/auto_surprise/trainer.py", line 85, in start_with_limits
    _, best_trial = self.algo_base.best_hyperparams(max_evals)
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/auto_surprise/algorithms/base.py", line 99, in best_hyperparams
    best = fmin(**fmin_args)
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/hyperopt/fmin.py", line 540, in fmin
    return trials.fmin(
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/hyperopt/base.py", line 671, in fmin
    return fmin(
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/hyperopt/fmin.py", line 586, in fmin
    rval.exhaust()
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/hyperopt/fmin.py", line 364, in exhaust
    self.run(self.max_evals - n_done, block_until_done=self.asynchronous)
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/hyperopt/fmin.py", line 279, in run
    new_ids, self.domain, trials, self.rstate.integers(2 ** 31 - 1)
AttributeError: module 'numpy.random' has no attribute 'integers'

Traceback (most recent call last):
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/auto_surprise/trainer.py", line 85, in start_with_limits
    _, best_trial = self.algo_base.best_hyperparams(max_evals)
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/auto_surprise/algorithms/base.py", line 99, in best_hyperparams
    best = fmin(**fmin_args)
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/hyperopt/fmin.py", line 540, in fmin
    return trials.fmin(
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/hyperopt/base.py", line 671, in fmin
    return fmin(
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/hyperopt/fmin.py", line 586, in fmin
    rval.exhaust()
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/hyperopt/fmin.py", line 364, in exhaust
    self.run(self.max_evals - n_done, block_until_done=self.asynchronous)
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/hyperopt/fmin.py", line 279, in run
    new_ids, self.domain, trials, self.rstate.integers(2 ** 31 - 1)
AttributeError: module 'numpy.random' has no attribute 'integers'

  0%|                                                                                                                                                              | 0/100 [00:00<?, ?trial/s, best loss=?]
Exception for algo co_clustering
Traceback (most recent call last):
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/auto_surprise/trainer.py", line 85, in start_with_limits
    _, best_trial = self.algo_base.best_hyperparams(max_evals)
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/auto_surprise/algorithms/base.py", line 99, in best_hyperparams
    best = fmin(**fmin_args)
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/hyperopt/fmin.py", line 540, in fmin
    return trials.fmin(
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/hyperopt/base.py", line 671, in fmin
    return fmin(
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/hyperopt/fmin.py", line 586, in fmin
    rval.exhaust()
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/hyperopt/fmin.py", line 364, in exhaust
    self.run(self.max_evals - n_done, block_until_done=self.asynchronous)
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/hyperopt/fmin.py", line 279, in run
    new_ids, self.domain, trials, self.rstate.integers(2 ** 31 - 1)
AttributeError: module 'numpy.random' has no attribute 'integers'

  0%|                                                                                                                                                              | 0/100 [00:00<?, ?trial/s, best loss=?]
Exception for algo baseline_only
Traceback (most recent call last):
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/auto_surprise/trainer.py", line 85, in start_with_limits
    _, best_trial = self.algo_base.best_hyperparams(max_evals)
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/auto_surprise/algorithms/base.py", line 99, in best_hyperparams
    best = fmin(**fmin_args)
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/hyperopt/fmin.py", line 540, in fmin
    return trials.fmin(
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/hyperopt/base.py", line 671, in fmin
    return fmin(
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/hyperopt/fmin.py", line 586, in fmin
    rval.exhaust()
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/hyperopt/fmin.py", line 364, in exhaust
    self.run(self.max_evals - n_done, block_until_done=self.asynchronous)
  File "/home/mbaleato/AutoSurpriseExample/venv/lib/python3.8/site-packages/hyperopt/fmin.py", line 279, in run
    new_ids, self.domain, trials, self.rstate.integers(2 ** 31 - 1)
AttributeError: module 'numpy.random' has no attribute 'integers'

Evaluating RMSE, MAE, MSE of algorithm SlopeOne on 5 split(s).

                  Fold 1  Fold 2  Fold 3  Fold 4  Fold 5  Mean    Std     
RMSE (testset)    0.9453  0.9533  0.9335  0.9422  0.9494  0.9447  0.0068  
MAE (testset)     0.7435  0.7469  0.7337  0.7397  0.7495  0.7426  0.0056  
MSE (testset)     0.8936  0.9089  0.8713  0.8878  0.9014  0.8926  0.0128  
Fit time          0.39    0.36    0.34    0.40    0.38    0.38    0.02    
Test time         1.59    1.20    1.30    1.50    1.20    1.36    0.16    
----Done!----
Best algorithm: slope_one
Best hyperparameters: None
┏━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━┓
┃ Algorithm        ┃ Hyperparameters ┃               Loss ┃
┡━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━┩
│ svd              │ None            │               None │
│ svdpp            │ None            │               None │
│ nmf              │ None            │               None │
│ knn_basic        │ None            │               None │
│ knn_baseline     │ None            │               None │
│ knn_with_z_score │ None            │               None │
│ knn_with_means   │ None            │               None │
│ co_clustering    │ None            │               None │
│ baseline_only    │ None            │               None │
│ slope_one        │ None            │ 0.9447460038754011 │
└──────────────────┴─────────────────┴────────────────────┘

I have tried with other dataset, and always the same AttributeError:
AttributeError: module 'numpy.random' has no attribute 'integers'

Is there another version that works fine? Or another version of numpy?

custom dataset / simple product recsys

Hi @thededlier , all,

Hope you are all well !

I was wondering if you could explain quickly how to use a simple csv file with columns like productId, customerId and ratings with auto surprise ?

Also, would it be complicated to create a Fastapi server ?

Thanks for any insights or inputs on these questions.

Cheers,
Luc Michalski

Windows/Mac OS functionality?

Hello! I'm very interested in using this package for surprise algorithm selection but not sure if it's working properly for me. I see in Setup it's mentioned that the package requires installation on linux. Is the package not functional on Windows or Mac in that case?

I tried running the ml-100k usage example on my Windows 10 machine but I don't think the output I got was correct (best_model: svd, best_params: NoneType object of builtins module, best_score: 100). Or if this is the intended output could you advise on how to interpret it?

Thank you

Can't run the basic usage

Hello, I was trying to use auto-surprise and run the Basic Usage, it does run properly the baseline loss part, but as soon as it start with the svd algorithm, I get the following error:

Starting process with svd algorithm
Traceback (most recent call last):
  File "<string>", line 1, in <module>
  File "C:\Users\jmetchebarne\anaconda3\envs\Proyecto Recomendaciones\lib\multiprocessing\spawn.py", line 105, in spawn_main
    exitcode = _main(fd)
  File "C:\Users\jmetchebarne\anaconda3\envs\Proyecto Recomendaciones\lib\multiprocessing\spawn.py", line 115, in _main
    self = reduction.pickle.load(from_parent)
EOFError: Ran out of input
Traceback (most recent call last):
  File "C:\Users\jmetchebarne\anaconda3\envs\Proyecto Recomendaciones\lib\site-packages\IPython\core\interactiveshell.py", line 3418, in run_code
    exec(code_obj, self.user_global_ns, self.user_ns)
  File "<ipython-input-2-56575903e07a>", line 19, in <module>
    max_evals=10
  File "C:\Users\jmetchebarne\anaconda3\envs\Proyecto Recomendaciones\lib\site-packages\auto_surprise\engine.py", line 96, in train
    best_algo, best_params, best_score, tasks = strategy.evaluate()
  File "C:\Users\jmetchebarne\anaconda3\envs\Proyecto Recomendaciones\lib\site-packages\auto_surprise\strategies\continuous_parallel.py", line 50, in evaluate
    p.start()
  File "C:\Users\jmetchebarne\anaconda3\envs\Proyecto Recomendaciones\lib\multiprocessing\process.py", line 115, in start
    self._popen = self._Popen(self)
  File "C:\Users\jmetchebarne\anaconda3\envs\Proyecto Recomendaciones\lib\multiprocessing\context.py", line 223, in _Popen
    return _default_context.get_context().Process._Popen(process_obj)
  File "C:\Users\jmetchebarne\anaconda3\envs\Proyecto Recomendaciones\lib\multiprocessing\context.py", line 322, in _Popen
    return Popen(process_obj)
  File "C:\Users\jmetchebarne\anaconda3\envs\Proyecto Recomendaciones\lib\multiprocessing\popen_spawn_win32.py", line 89, in __init__
    reduction.dump(process_obj, to_child)
  File "C:\Users\jmetchebarne\anaconda3\envs\Proyecto Recomendaciones\lib\multiprocessing\reduction.py", line 60, in dump
    ForkingPickler(file, protocol).dump(obj)
TypeError: can't pickle module objects

Not sure if I'm doing something wrong here, to be honest, I just executed the code posted:

from surprise import Dataset
from auto_surprise.engine import Engine

# Load the dataset
data = Dataset.load_builtin('ml-100k')

# Intitialize auto surprise engine
engine = Engine(verbose=True)

# Start the trainer
best_algo, best_params, best_score, tasks = engine.train(
    data=data, 
    target_metric='test_rmse', 
    cpu_time_limit=60 * 60, 
    max_evals=100
)

Any help is really appreciated.