import logging
import numpy as np
import openml
import sklearn.compose
import sklearn.ensemble
import sklearn.feature_selection
import sklearn.impute
import sklearn.preprocessing

task = openml.tasks.get_task(6)  # use task 2 on live, or task 6 on test


def get_model():
    numeric_transformer = sklearn.pipeline.make_pipeline(
        sklearn.preprocessing.Imputer(),
        sklearn.preprocessing.StandardScaler())

    categorical_transformer = sklearn.pipeline.make_pipeline(
        sklearn.impute.SimpleImputer(strategy='constant', fill_value=-1),
        sklearn.preprocessing.OneHotEncoder(handle_unknown='ignore'))

    nominal_indices = task.get_dataset().get_features_by_type('nominal', [task.target_name])
    numeric_indices = task.get_dataset().get_features_by_type('numeric', [task.target_name])

    transformer = sklearn.compose.ColumnTransformer(
        transformers=[
            ('numeric', numeric_transformer, numeric_indices),
            ('nominal', categorical_transformer, nominal_indices)],
        remainder='passthrough')

    clf = sklearn.pipeline.make_pipeline(transformer,
                                         sklearn.feature_selection.VarianceThreshold(),
                                         sklearn.ensemble.RandomForestClassifier())
    return clf


model_original = get_model()

run = openml.runs.run_model_on_task(
    model_original,
    task,
    avoid_duplicate_runs=False)
run_original = run.publish()  # this implicitly uploads the flow

run_downloaded = openml.runs.get_run(run_original.run_id)
setup_id = run_downloaded.setup_id

model_duplicate = openml.setups.initialize_model(setup_id)

run_duplicate = openml.runs.run_model_on_task(
    model_duplicate, task, avoid_duplicate_runs=False)

Traceback (most recent call last):
  File "/home/janvanrijn/projects/openml-python/examples/run_setup_tutorial.py", line 102, in <module>
    model_duplicate, task, avoid_duplicate_runs=False)
  File "/home/janvanrijn/projects/openml-python/openml/runs/functions.py", line 48, in run_model_on_task
    add_local_measures=add_local_measures)
  File "/home/janvanrijn/projects/openml-python/openml/runs/functions.py", line 119, in run_flow_on_task
    res = _run_task_get_arffcontent(flow.model, task, add_local_measures=add_local_measures)
  File "/home/janvanrijn/projects/openml-python/openml/runs/functions.py", line 458, in _run_task_get_arffcontent
    add_local_measures=add_local_measures)
  File "/home/janvanrijn/projects/openml-python/openml/runs/functions.py", line 572, in _run_model_on_fold
    model.fit(trainX, trainY)
  File "/home/janvanrijn/anaconda3/envs/openml-python/lib/python3.6/site-packages/sklearn/pipeline.py", line 265, in fit
    Xt, fit_params = self._fit(X, y, **fit_params)
  File "/home/janvanrijn/anaconda3/envs/openml-python/lib/python3.6/site-packages/sklearn/pipeline.py", line 230, in _fit
    **fit_params_steps[name])
  File "/home/janvanrijn/anaconda3/envs/openml-python/lib/python3.6/site-packages/sklearn/externals/joblib/memory.py", line 329, in __call__
    return self.func(*args, **kwargs)
  File "/home/janvanrijn/anaconda3/envs/openml-python/lib/python3.6/site-packages/sklearn/pipeline.py", line 614, in _fit_transform_one
    res = transformer.fit_transform(X, y, **fit_params)
  File "/home/janvanrijn/anaconda3/envs/openml-python/lib/python3.6/site-packages/sklearn/base.py", line 465, in fit_transform
    return self.fit(X, y, **fit_params).transform(X)
  File "/home/janvanrijn/anaconda3/envs/openml-python/lib/python3.6/site-packages/sklearn/feature_selection/variance_threshold.py", line 64, in fit
    X = check_array(X, ('csr', 'csc'), dtype=np.float64)
  File "/home/janvanrijn/anaconda3/envs/openml-python/lib/python3.6/site-packages/sklearn/utils/validation.py", line 568, in check_array
    allow_nan=force_all_finite == 'allow-nan')
  File "/home/janvanrijn/anaconda3/envs/openml-python/lib/python3.6/site-packages/sklearn/utils/validation.py", line 56, in _assert_all_finite
    raise ValueError(msg_err.format(type_err, X.dtype))
ValueError: Input contains NaN, infinity or a value too large for dtype('float64').