Answer Questions - Maurice Van den Boogaerde

numpy_questions.py

@@ -15,6 +15,7 @@
 This will be enforced with `flake8`. You can check that there is no flake8
 errors by calling `flake8` at the root of the repo.
 """
+
 import numpy as np
 
 
@@ -37,12 +38,12 @@ def max_index(X):
         If the input is not a numpy array or
         if the shape is not 2D.
     """
-    i = 0
-    j = 0
-
-    # TODO
+    if not isinstance(X, np.ndarray):
+        raise ValueError("X must be a numpy array.")
+    if X.ndim != 2:
+        raise ValueError("X must be 2D.")
 
-    return i, j
+    return np.unravel_index(np.argmax(X), X.shape)
 
 
 def wallis_product(n_terms):
@@ -64,4 +65,16 @@ def wallis_product(n_terms):
     """
     # XXX : The n_terms is an int that corresponds to the number of
     # terms in the product. For example 10000.
-    return 0.
+
+    if n_terms < 0:
+        raise ValueError("n_terms must be non-negative.")
+
+    if n_terms == 0:
+        return 1.0
+
+    product = 1.0
+
+    for i in range(1, n_terms + 1):
+        product *= (4 * i**2) / (4 * i**2 - 1)
+
+    return 2 * product

sklearn_questions.py

@@ -19,57 +19,92 @@
 for the methods you code and for the class. The docstring will be checked using
 `pydocstyle` that you can also call at the root of the repo.
 """
+
 import numpy as np
-from sklearn.base import BaseEstimator
-from sklearn.base import ClassifierMixin
-from sklearn.utils.validation import check_X_y
-from sklearn.utils.validation import check_array
-from sklearn.utils.validation import check_is_fitted
-from sklearn.utils.validation import validate_data
+from sklearn.base import BaseEstimator, ClassifierMixin
 from sklearn.utils.multiclass import check_classification_targets
+from sklearn.utils.validation import check_array, check_is_fitted, check_X_y
 
 
 class OneNearestNeighbor(ClassifierMixin, BaseEstimator):
-    "OneNearestNeighbor classifier."
+    """OneNearestNeighbor classifier."""
 
-    def __init__(self):  # noqa: D107
+    def __init__(self):
+        """Initialize the OneNearestNeighbor classifier."""
         pass
 
     def fit(self, X, y):
-        """Write docstring.
-
-        And describe parameters
+        """Store the training samples and their labels.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Training samples.
+        y : array-like of shape (n_samples,)
+            Class labels.
+
+        Returns
+        -------
+        self : OneNearestNeighbor
+            The fitted classifier.
         """
         X, y = check_X_y(X, y)
         check_classification_targets(y)
+
+        self.X_train_ = X.copy()
+        self.y_train_ = y.copy()
         self.classes_ = np.unique(y)
         self.n_features_in_ = X.shape[1]
 
-        # XXX fix
         return self
 
     def predict(self, X):
-        """Write docstring.
+        """Predict labels using the nearest training sample.
 
-        And describe parameters
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Samples to classify.
+
+        Returns
+        -------
+        y_pred : ndarray of shape (n_samples,)
+            Predicted class labels.
         """
-        check_is_fitted(self)
+        check_is_fitted(self, ["X_train_", "y_train_", "n_features_in_"])
         X = check_array(X)
-        y_pred = np.full(
-            shape=len(X), fill_value=self.classes_[0],
-            dtype=self.classes_.dtype
-        )
 
-        # XXX fix
+        if X.shape[1] != self.n_features_in_:
+            raise ValueError(
+                f"X has {X.shape[1]} features, but "
+                f"{self.__class__.__name__} is expecting "
+                f"{self.n_features_in_} features as input."
+            )
+
+        y_pred = np.empty(X.shape[0], dtype=self.y_train_.dtype)
+
+        for i, x in enumerate(X):
+            distances = np.sum((self.X_train_ - x) ** 2, axis=1)
+            nearest_index = np.argmin(distances)
+            y_pred[i] = self.y_train_[nearest_index]
+
         return y_pred
 
     def score(self, X, y):
-        """Write docstring.
-
-        And describe parameters
+        """Return the mean accuracy on the given data.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Samples to score.
+        y : array-like of shape (n_samples,)
+            True class labels.
+
+        Returns
+        -------
+        score : float
+            The mean accuracy.
         """
         X, y = check_X_y(X, y)
         y_pred = self.predict(X)
-
-        # XXX fix
-        return y_pred.sum()
+        return np.mean(y_pred == y)