add error message when user passes decision trees

boruta/boruta_py.py

@@ -326,7 +326,7 @@ def _fit(self, X, y):
 
         # set n_estimators
         if self.n_estimators != 'auto':
-            self.estimator.set_params(n_estimators=self.n_estimators)
+            self._set_n_estimators(self.n_estimators)
 
         # main feature selection loop
         while np.any(dec_reg == 0) and _iter < self.max_iter:
@@ -335,7 +335,7 @@ def _fit(self, X, y):
                 # number of features that aren't rejected
                 not_rejected = np.where(dec_reg >= 0)[0].shape[0]
                 n_tree = self._get_tree_num(not_rejected)
-                self.estimator.set_params(n_estimators=n_tree)
+                self._set_n_estimators(n_estimators=n_tree)
 
             # make sure we start with a new tree in each iteration
             if self._is_lightgbm:
@@ -452,6 +452,17 @@ def _transform(self, X, weak=False, return_df=False):
             X = X[:, indices]
         return X
 
+    def _set_n_estimators(self, n_estimators):
+        try:
+            self.estimator.set_params(n_estimators=n_estimators)
+        except ValueError:
+            raise ValueError(
+                f"The estimator {self.estimator} does not take the parameter "
+                "n_estimators. Use Random Forests or gradient boosting machines "
+                "instead."
+            )
+        return self
+
     def _get_tree_num(self, n_feat):
         depth = None
         try:

boruta/test/test_boruta.py

@@ -0,0 +1,83 @@
+import numpy as np
+import pandas as pd
+import pytest
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.tree import DecisionTreeClassifier, ExtraTreeClassifier
+
+from boruta import BorutaPy
+
+
+@pytest.mark.parametrize("tree_n,expected", [(10, 44), (100, 141)])
+def test_get_tree_num(tree_n, expected):
+    rfc = RandomForestClassifier(max_depth=10)
+    bt = BorutaPy(rfc)
+    assert bt._get_tree_num(tree_n) == expected
+
+
+@pytest.fixture(scope="module")
+def Xy():
+    np.random.seed(42)
+    y = np.random.binomial(1, 0.5, 1000)
+    X = np.zeros((1000, 10))
+
+    z = (y - np.random.binomial(1, 0.1, 1000) +
+         np.random.binomial(1, 0.1, 1000))
+    z[z == -1] = 0
+    z[z == 2] = 1
+
+    # 5 relevant features
+    X[:, 0] = z
+    X[:, 1] = (y * np.abs(np.random.normal(0, 1, 1000)) +
+               np.random.normal(0, 0.1, 1000))
+    X[:, 2] = y + np.random.normal(0, 1, 1000)
+    X[:, 3] = y**2 + np.random.normal(0, 1, 1000)
+    X[:, 4] = np.sqrt(y) + np.random.binomial(2, 0.1, 1000)
+
+    # 5 irrelevant features
+    X[:, 5] = np.random.normal(0, 1, 1000)
+    X[:, 6] = np.random.poisson(1, 1000)
+    X[:, 7] = np.random.binomial(1, 0.3, 1000)
+    X[:, 8] = np.random.normal(0, 1, 1000)
+    X[:, 9] = np.random.poisson(1, 1000)
+
+    return X, y
+
+
+def test_if_boruta_extracts_relevant_features(Xy):
+    X, y = Xy
+    rfc = RandomForestClassifier()
+    bt = BorutaPy(rfc)
+    bt.fit(X, y)
+    assert list(range(5)) == list(np.where(bt.support_)[0])
+
+
+def test_if_it_works_with_dataframe_input(Xy):
+    X, y = Xy
+    X_df, y_df = pd.DataFrame(X), pd.Series(y)
+    bt = BorutaPy(RandomForestClassifier())
+    bt.fit(X_df, y_df)
+    assert list(range(5)) == list(np.where(bt.support_)[0])
+
+
+def test_dataframe_is_returned(Xy):
+    X, y = Xy
+    X_df, y_df = pd.DataFrame(X), pd.Series(y)
+    rfc = RandomForestClassifier()
+    bt = BorutaPy(rfc)
+    bt.fit(X_df, y_df)
+    assert isinstance(bt.transform(X_df, return_df=True), pd.DataFrame)
+
+
+@pytest.mark.parametrize("tree", [ExtraTreeClassifier(), DecisionTreeClassifier()])
+def test_boruta_with_decision_trees(tree, Xy):
+    msg = (
+        f"The estimator {tree} does not take the parameter "
+        "n_estimators. Use Random Forests or gradient boosting machines "
+        "instead."
+    )
+    X, y = Xy
+    bt = BorutaPy(tree)
+    with pytest.raises(ValueError) as record:
+        bt.fit(X, y)
+
+    assert str(record.value) == msg

test_requirements.txt

@@ -0,0 +1,7 @@
+-r requirements.txt
+pytest>=5.4.1
+
+# repo maintenance tooling
+black>=21.5b1
+flake8>=3.9.2
+isort>=5.8.0