import numpy as np
import pandas as pd
from sklearn import set_config
from sklearn.compose import ColumnTransformer
from sklearn.ensemble import HistGradientBoostingRegressor
from sklearn.model_selection import GridSearchCV, RandomizedSearchCV
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import OneHotEncoder, OrdinalEncoder

set_config(transform_output="pandas")

# Setting seed for reproducibility
np.random.seed(42)

# Create a DataFrame with 1000 rows and 5 columns
num_rows = 1000
data = {
    "numeric_1": np.random.randn(num_rows),  # Normally distributed random numbers
    "numeric_3": np.random.randint(
        1, 100, size=num_rows
    ),  # Random integers between 1 and 100
    "object_1": np.random.choice(
        ["A", "B", "C", "D"], size=num_rows
    ),  # Random choice among 'A', 'B', 'C', 'D'
    "object_2": np.random.choice(
        ["X", "Y", "Z"], size=num_rows
    ),  # Random choice among 'X', 'Y', 'Z'
    "target": np.random.rand(num_rows)
    * 100,  # Uniformly distributed random numbers [0, 100)
}

df = pd.DataFrame(data)

X = df.drop("target", axis=1)
y = df["target"]

enc = ColumnTransformer(
    [("enc", OneHotEncoder(sparse_output=False), ["object_1", "object_2"])],
    remainder="passthrough",
    verbose_feature_names_out=False,
)

pipe = Pipeline(
    [
        ("enc", enc),
        ("regressor", HistGradientBoostingRegressor()),
    ]
)

grid_params = {
    "enc__enc": [
        OneHotEncoder(sparse_output=False),
        OrdinalEncoder(),
    ]
}

grid_search = GridSearchCV(pipe, grid_params, cv=5)
grid_search.fit(X, y)
# RandomizedSearchCV produces the same error
# rand_search = RandomizedSearchCV(pipe, grid_params, cv=5)
# rand_search.fit(X, y)

{
	"name": "TypeError",
	"message": "float() argument must be a string or a real number, not 'OneHotEncoder'",
	"stack": "---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
Cell In[108], line 1
----> 1 grid_search.fit(X, y)

File ~/Documents/Coding/ML_exercises/.venv/lib/python3.12/site-packages/sklearn/base.py:1473, in _fit_context.<locals>.decorator.<locals>.wrapper(estimator, *args, **kwargs)
   1466     estimator._validate_params()
   1468 with config_context(
   1469     skip_parameter_validation=(
   1470         prefer_skip_nested_validation or global_skip_validation
   1471     )
   1472 ):
-> 1473     return fit_method(estimator, *args, **kwargs)

File ~/Documents/Coding/ML_exercises/.venv/lib/python3.12/site-packages/sklearn/model_selection/_search.py:968, in BaseSearchCV.fit(self, X, y, **params)
    962     results = self._format_results(
    963         all_candidate_params, n_splits, all_out, all_more_results
    964     )
    966     return results
--> 968 self._run_search(evaluate_candidates)
    970 # multimetric is determined here because in the case of a callable
    971 # self.scoring the return type is only known after calling
    972 first_test_score = all_out[0][\"test_scores\"]

File ~/Documents/Coding/ML_exercises/.venv/lib/python3.12/site-packages/sklearn/model_selection/_search.py:1543, in GridSearchCV._run_search(self, evaluate_candidates)
   1541 def _run_search(self, evaluate_candidates):
   1542     \"\"\"Search all candidates in param_grid\"\"\"
-> 1543     evaluate_candidates(ParameterGrid(self.param_grid))

File ~/Documents/Coding/ML_exercises/.venv/lib/python3.12/site-packages/sklearn/model_selection/_search.py:962, in BaseSearchCV.fit.<locals>.evaluate_candidates(candidate_params, cv, more_results)
    959         all_more_results[key].extend(value)
    961 nonlocal results
--> 962 results = self._format_results(
    963     all_candidate_params, n_splits, all_out, all_more_results
    964 )
    966 return results

File ~/Documents/Coding/ML_exercises/.venv/lib/python3.12/site-packages/sklearn/model_selection/_search.py:1098, in BaseSearchCV._format_results(self, candidate_params, n_splits, out, more_results)
   1094     arr_dtype = object
   1095 if len(param_list) == n_candidates and arr_dtype != object:
   1096     # Exclude `object` else the numpy constructor might infer a list of
   1097     # tuples to be a 2d array.
-> 1098     results[key] = MaskedArray(param_list, mask=False, dtype=arr_dtype)
   1099 else:
   1100     # Use one MaskedArray and mask all the places where the param is not
   1101     # applicable for that candidate (which may not contain all the params).
   1102     ma = MaskedArray(np.empty(n_candidates), mask=True, dtype=arr_dtype)

File ~/Documents/Coding/ML_exercises/.venv/lib/python3.12/site-packages/numpy/ma/core.py:2820, in MaskedArray.__new__(cls, data, mask, dtype, copy, subok, ndmin, fill_value, keep_mask, hard_mask, shrink, order)
   2811 \"\"\"
   2812 Create a new masked array from scratch.
   2813 
   (...)
   2817 
   2818 \"\"\"
   2819 # Process data.
-> 2820 _data = np.array(data, dtype=dtype, copy=copy,
   2821                  order=order, subok=True, ndmin=ndmin)
   2822 _baseclass = getattr(data, '_baseclass', type(_data))
   2823 # Check that we're not erasing the mask.

TypeError: float() argument must be a string or a real number, not 'OneHotEncoder'"
}