Vincent Soehnchen assignment

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
 
 
@@ -39,9 +40,11 @@ def max_index(X):
     """
     i = 0
     j = 0
-
-    # TODO
-
+    if not isinstance(X, np.ndarray):
+        raise ValueError("This value is not a numpy array")
+    if X.ndim != 2:
+        raise ValueError("This value has the wrong dimensions")
+    i, j = np.unravel_index(np.argmax(X, axis=None), X.shape)
     return i, j
 
 
@@ -62,6 +65,13 @@ def wallis_product(n_terms):
     pi : float
         The approximation of order `n_terms` of pi using the Wallis product.
     """
+    if n_terms < 0:
+        raise ValueError
+    if n_terms == 0:
+        return 1.0
+    current = 1.0
+    for i in range(1, n_terms+1):
+        current *= (4 * i**2) / ((4 * i**2)-1)
     # XXX : The n_terms is an int that corresponds to the number of
     # terms in the product. For example 10000.
-    return 0.
+    return current * 2

sklearn_questions.py

@@ -29,46 +29,94 @@
 
 
 class OneNearestNeighbor(BaseEstimator, ClassifierMixin):
-    "OneNearestNeighbor classifier."
+    """One-Nearest-Neighbor classifier using Euclidean distance.
+
+    The classifier predicts, for each input sample, the label of the single
+    closest training sample in Euclidean distance.
+
+    Attributes
+    ----------
+    classes_ : ndarray of shape (n_classes,)
+        Unique class labels seen during `fit`.
+
+    n_features_in_ : int
+        Number of features seen during `fit`.
+
+    X_ : ndarray of shape (n_samples, n_features)
+        Training data stored after fitting.
+
+    y_ : ndarray of shape (n_samples,)
+        Training labels stored after fitting.
+    """
 
     def __init__(self):  # noqa: D107
         pass
 
     def fit(self, X, y):
-        """Write docstring.
+        """Fit the One-Nearest-Neighbor classifier.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Training data.
 
-        And describe parameters
+        y : array-like of shape (n_samples,)
+            Target labels.
+
+        Returns
+        -------
+        self : OneNearestNeighbor
+            Fitted estimator.
         """
         X, y = check_X_y(X, y)
         check_classification_targets(y)
         self.classes_ = np.unique(y)
         self.n_features_in_ = X.shape[1]
-
-        # XXX fix
+        self.X_ = X
+        self.y_ = y
         return self
 
     def predict(self, X):
-        """Write docstring.
+        """Predict class labels for samples in X.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Input samples.
 
-        And describe parameters
+        Returns
+        -------
+        y_pred : ndarray of shape (n_samples,)
+            Predicted class labels.
         """
         check_is_fitted(self)
         X = check_array(X)
         y_pred = np.full(
             shape=len(X), fill_value=self.classes_[0],
             dtype=self.classes_.dtype
         )
-
-        # XXX fix
+        X_sq = np.sum(X * X, axis=1, keepdims=True)
+        Xtr_sq = np.sum(self.X_ * self.X_, axis=1, keepdims=True)
+        cross = X @ self.X_.T
+        d2 = X_sq - 2.0 * cross + Xtr_sq.T
+        nn_idx = np.argmin(d2, axis=1)
+        y_pred = self.y_[nn_idx]
         return y_pred
 
     def score(self, X, y):
-        """Write docstring.
-
-        And describe parameters
+        """Compute the mean accuracy on the given test data and labels.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Test samples.
+        y : array-like of shape (n_samples,)
+            True labels.
+        Returns
+        -------
+        score : float
+            Mean accuracy of predictions on X compared to y.
         """
         X, y = check_X_y(X, y)
         y_pred = self.predict(X)
-
-        # XXX fix
-        return y_pred.sum()
+        return float(np.mean(y_pred == y))