def test_X_y_from_arff():
# https://www.openml.org/d/23380
x, y = X_y_from_arff("tests/data/openml_d_23380.arff", split_column="TR")
assert isinstance(x, pd.DataFrame)
assert (2796, 34) == x.shape
assert 68100 == x.isnull().sum().sum()
assert 32 == sum([dtype in NUMERIC_TYPES for dtype in x.dtypes])
assert 2 == sum([dtype.name == "category" for dtype in x.dtypes])
assert isinstance(y, pd.Series)
assert (2796, ) == y.shape
assert 0 == y.isnull().sum()
assert 6 == len(y.dtype.categories)
def predict_proba_arff(
self,
arff_file_path: str,
target_column: Optional[str] = None,
encoding: Optional[str] = None,
):
""" Predict the class probabilities for input in the arff_file.
Parameters
----------
arff_file_path: str
An ARFF file with the same columns as the one that used in fit.
Target column must be present in file, but its values are ignored.
target_column: str, optional (default=None)
Specifies which column the model should predict.
If left None, the last column is taken to be the target.
encoding: str, optional
Encoding of the ARFF file.
Returns
-------
numpy.ndarray
Numpy array with class probabilities.
The array is of shape (N, K) where N is len(X),
and K is the number of class labels found in `y` of `fit`.
"""
x, _ = X_y_from_arff(arff_file_path, target_column, encoding)
x = self._prepare_for_prediction(x)
return self._predict_proba(x)
def score_arff(
self,
arff_file_path: str,
target_column: Optional[str] = None,
encoding: Optional[str] = None,
) -> float:
""" Calculate `self.scoring` metric of the model on data in the file.
Parameters
----------
arff_file_path: str
An ARFF file with which to calculate the score.
target_column: str, optional (default=None)
Specifies which column the model should predict.
If left None, the last column is taken to be the target.
encoding: str, optional
Encoding of the ARFF file.
Returns
-------
float
The score obtained on the given test data according to the `scoring` metric.
"""
x, y = X_y_from_arff(arff_file_path,
split_column=target_column,
encoding=encoding)
return self.score(x, y)
def fit_arff(
self,
arff_file_path: str,
target_column: Optional[str] = None,
encoding: Optional[str] = None,
*args,
**kwargs,
) -> None:
""" Find and fit a model to predict the target column (last) from other columns.
Parameters
----------
arff_file_path: str
Path to an ARFF file containing the training data.
target_column: str, optional (default=None)
Specifies which column the model should predict.
If left None, the last column is taken to be the target.
encoding: str, optional
Encoding of the ARFF file.
"""
x, y = X_y_from_arff(arff_file_path,
split_column=target_column,
encoding=encoding)
self.fit(x, y, *args, **kwargs)
def predict_arff(
self,
arff_file_path: str,
target_column: Optional[str] = None,
encoding: Optional[str] = None,
) -> np.ndarray:
""" Predict the target for input found in the ARFF file.
Parameters
----------
arff_file_path: str
An ARFF file with the same columns as the one that used in fit.
Target column must be present in file, but its values are ignored.
target_column: str, optional (default=None)
Specifies which column the model should predict.
If left None, the last column is taken to be the target.
encoding: str, optional
Encoding of the ARFF file.
Returns
-------
numpy.ndarray
array with predictions for each row in the ARFF file.
"""
x, _ = X_y_from_arff(arff_file_path,
split_column=target_column,
encoding=encoding)
x = self._prepare_for_prediction(x)
return self._predict(x)