Make optional parameter in (#11)

README.md

@@ -40,18 +40,16 @@ X = pd.DataFrame(
     ],
     columns=["trade_price", "bid_ex", "ask_ex"],
 )
-y = pd.Series([1, 1, 1, 1, 1, 1])
 
 clf = ClassicalClassifier(layers=[("quote", "ex")], strategy="random")
-clf.fit(X, y)
+clf.fit(X)
 probs = clf.predict_proba(X)
-print(probs)
 ```
 Run your script with
 ```console
 python main.py
 ```
-In this example, input data is available as a pd.DataFrame/Series with columns conforming to our [naming conventions](https://karelze.github.io/tclf/naming_conventions/).
+In this example, input data is available as a pd.DataFrame with columns conforming to our [naming conventions](https://karelze.github.io/tclf/naming_conventions/).
 
 The parameter `layers=[("quote", "ex")]` sets the quote rule at the exchange level and `strategy="random"` specifies the fallback strategy for unclassified trades. The true label `y` is not used in classification and only for API consistency by convention.
 

docs/index.md

@@ -40,18 +40,16 @@ X = pd.DataFrame(
     ],
     columns=["trade_price", "bid_ex", "ask_ex"],
 )
-y = pd.Series([1, 1, 1, 1, 1, 1])
 
 clf = ClassicalClassifier(layers=[("quote", "ex")], strategy="random")
-clf.fit(X, y)
+clf.fit(X)
 probs = clf.predict_proba(X)
-print(probs)
 ```
 Run your script with
 ```console
 python main.py
 ```
-In this example, input data is available as a pd.DataFrame/Series with columns conforming to our [naming conventions](https://karelze.github.io/tclf/naming_conventions/).
+In this example, input data is available as a pd.DataFrame with columns conforming to our [naming conventions](https://karelze.github.io/tclf/naming_conventions/).
 
 The parameter `layers=[("quote", "ex")]` sets the quote rule at the exchange level and `strategy="random"` specifies the fallback strategy for unclassified trades. The true label `y` is not used in classification and only for API consistency by convention.
 

sonar-project.properties

@@ -1,2 +1,3 @@
-sonar.sources=src\
-sonar.issue.ignore.multicriteria.e1.ruleKey=python:S117
+sonar.issue.ignore.multicriteria=S117
+sonar.issue.ignore.multicriteria.S117.ruleKey=python:S117
+sonar.issue.ignore.multicriteria.S117.resourceKey=*

src/tclf/classical_classifier.py

@@ -12,8 +12,7 @@
 import pandas as pd
 from sklearn.base import BaseEstimator, ClassifierMixin
 from sklearn.utils import check_random_state
-from sklearn.utils.multiclass import check_classification_targets
-from sklearn.utils.validation import _check_sample_weight, check_is_fitted, check_X_y
+from sklearn.utils.validation import _check_sample_weight, check_is_fitted
 
 from tclf.types import ArrayLike, MatrixLike
 
@@ -79,9 +78,8 @@ def __init__(
             ... ],
             ... columns=["trade_price", "bid_ex", "ask_ex"],
             ... )
-            >>> y = pd.Series([-1, 1, 1, -1, -1, 1])
             >>> clf = ClassicalClassifier(layers=[("quote", "ex")], strategy="const")
-            >>> clf.fit(X, y)
+            >>> clf.fit(X)
             ClassicalClassifier(layers=[('quote', 'ex')], strategy='const')
             >>> pred = clf.predict_proba(X)
 
@@ -387,14 +385,14 @@ def _nan(self, subset: str) -> npt.NDArray:
     def fit(
         self,
         X: MatrixLike,
-        y: ArrayLike,
+        y: ArrayLike | None = None,
         sample_weight: npt.NDArray | None = None,
     ) -> ClassicalClassifier:
         """Fit the classifier.
 
         Args:
             X (MatrixLike): features
-            y (ArrayLike): ground truth (ignored)
+            y (ArrayLike | None, optional):  ignored, present here for API consistency by convention.
             sample_weight (npt.NDArray | None, optional):  Sample weights. Defaults to None.
 
         Raises:
@@ -429,14 +427,13 @@ def fit(
         if isinstance(X, pd.DataFrame):
             self.columns_ = X.columns.tolist()
 
-        check_classification_targets(y)
-
-        X, y = check_X_y(
-            X, y, multi_output=False, accept_sparse=False, force_all_finite=False
+        X = self._validate_data(
+            X,
+            dtype=[np.float64, np.float32],
+            accept_sparse=False,
+            force_all_finite=False,
         )
 
-        # FIXME: make flexible if open-sourced
-        # self.classes_ = np.unique(y)
         self.classes_ = np.array([-1, 1])
 
         # if no features are provided or inferred, use default
@@ -467,6 +464,12 @@ def predict(self, X: MatrixLike) -> npt.NDArray:
             npt.NDArray: Predicted traget values for X.
         """
         check_is_fitted(self)
+        X = self._validate_data(
+            X,
+            dtype=[np.float64, np.float32],
+            accept_sparse=False,
+            force_all_finite=False,
+        )
 
         rs = check_random_state(self.random_state)
 
@@ -514,7 +517,7 @@ def predict_proba(self, X: MatrixLike) -> npt.NDArray:
         mask = np.flatnonzero(preds)
 
         # get index of predicted class and one-hot encode it
-        indices = np.where(preds[mask, None] == self.classes_[None, :])[1]
+        indices = np.nonzero(preds[mask, None] == self.classes_[None, :])[1]
         n_classes = np.max(self.classes_) + 1
 
         # overwrite defaults with one-hot encoded classes.

tests/test_classical_classifier.py

@@ -24,15 +24,14 @@ def setup(self) -> None:
         self.x_train = pd.DataFrame(
             [[1, 1], [1, 1], [1, 1], [1, 1]], columns=["ask_best", "bid_best"]
         )
-        self.y_train = pd.Series([1, 1, -1, -1])
         self.x_test = pd.DataFrame(
             [[1, 2], [3, 4], [1, 2], [3, 4]], columns=["ask_best", "bid_best"]
         )
         self.y_test = pd.Series([1, -1, 1, -1])
         self.clf = ClassicalClassifier(
             layers=[("nan", "ex")],
             random_state=7,
-        ).fit(self.x_train, self.y_train)
+        ).fit(self.x_train)
 
     def test_random_state(self) -> None:
         """Test, if random state is correctly set.
@@ -42,13 +41,13 @@ def test_random_state(self) -> None:
         first_classifier = ClassicalClassifier(
             layers=[("nan", "ex")],
             random_state=50,
-        ).fit(self.x_train, self.y_train)
+        ).fit(self.x_train)
         first_y_pred = first_classifier.predict(self.x_test)
 
         second_classifier = ClassicalClassifier(
             layers=[("nan", "ex")],
             random_state=50,
-        ).fit(self.x_train, self.y_train)
+        ).fit(self.x_train)
         second_y_pred = second_classifier.predict(self.x_test)
 
         assert (first_y_pred == second_y_pred).all()
@@ -61,7 +60,7 @@ def test_fit(self) -> None:
         fitted_classifier = ClassicalClassifier(
             layers=[("nan", "ex")],
             random_state=42,
-        ).fit(self.x_train, self.y_train)
+        ).fit(self.x_train)
         assert check_is_fitted(fitted_classifier) is None
 
     def test_strategy_const(self) -> None:
@@ -72,7 +71,7 @@ def test_strategy_const(self) -> None:
         """
         fitted_classifier = ClassicalClassifier(
             layers=[("nan", "ex")], strategy="const"
-        ).fit(self.x_train, self.y_train)
+        ).fit(self.x_train)
         assert (fitted_classifier.predict_proba(self.x_test) == 0.5).all()
 
     def test_invalid_func(self) -> None:
@@ -86,7 +85,7 @@ def test_invalid_func(self) -> None:
             random_state=42,
         )
         with pytest.raises(ValueError, match=r"Unknown function string"):
-            classifier.fit(self.x_train, self.y_train)
+            classifier.fit(self.x_train)
 
     def test_invalid_col_length(self) -> None:
         """Test, if only valid column length can be passed.
@@ -100,7 +99,7 @@ def test_invalid_col_length(self) -> None:
             layers=[("tick", "all")], random_state=42, features=["one"]
         )
         with pytest.raises(ValueError, match=r"Expected"):
-            classifier.fit(self.x_train.values, self.y_train.values)
+            classifier.fit(self.x_train.values)
 
     def test_override(self) -> None:
         """Test, if classifier does not override valid results from layer one.