Ben Poppe: numpy and sklearn assignment

numpy_questions.py

@@ -37,12 +37,14 @@ def max_index(X):
         If the input is not a numpy array or
         if the shape is not 2D.
     """
-    i = 0
-    j = 0
+    if not isinstance(X, np.ndarray):
+        raise ValueError("X must be a numpy array.")
+    if X.ndim != 2:
+        raise ValueError("X must be a 2D array.")
 
-    # TODO
+    i, j = np.unravel_index(np.argmax(X), X.shape)
 
-    return i, j
+    return int(i), int(j)
 
 
 def wallis_product(n_terms):
@@ -62,6 +64,11 @@ def wallis_product(n_terms):
     pi : float
         The approximation of order `n_terms` of pi using the Wallis product.
     """
-    # 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:
+        return 1.
+
+    n = np.arange(1, n_terms + 1)
+    four_n_sq = 4 * n ** 2
+    pi_approx = 2 * np.prod(four_n_sq / (four_n_sq - 1))
+
+    return float(pi_approx)

sklearn_questions.py

@@ -25,51 +25,90 @@
 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.utils.multiclass import check_classification_targets
 
 
 class OneNearestNeighbor(ClassifierMixin, BaseEstimator):
-    "OneNearestNeighbor classifier."
+    """OneNearestNeighbor classifier.
+
+    Predict the label of each sample as the label of its closest
+    training sample, measured with the Euclidean distance.
+    """
 
     def __init__(self):  # noqa: D107
         pass
 
     def fit(self, X, y):
-        """Write docstring.
-
-        And describe parameters
+        """Fit the one nearest neighbor classifier.
+
+        Parameters
+        ----------
+        X : ndarray of shape (n_samples, n_features)
+            The training samples.
+        y : ndarray of shape (n_samples,)
+            The labels of the training samples.
+
+        Returns
+        -------
+        self : OneNearestNeighbor
+            The fitted classifier.
         """
         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_train_ = X
+        self.y_train_ = y
         return self
 
     def predict(self, X):
-        """Write docstring.
-
-        And describe parameters
+        """Predict the labels of the samples in X.
+
+        Parameters
+        ----------
+        X : ndarray of shape (n_samples, n_features)
+            The samples to classify.
+
+        Returns
+        -------
+        y_pred : ndarray of shape (n_samples,)
+            The predicted label of each sample, i.e. the label of its
+            nearest training sample.
         """
         check_is_fitted(self)
         X = check_array(X)
+        if X.shape[1] != self.n_features_in_:
+            raise ValueError(
+                f"X has {X.shape[1]} features, but OneNearestNeighbor "
+                f"is expecting {self.n_features_in_} features as input."
+            )
         y_pred = np.full(
             shape=len(X), fill_value=self.classes_[0],
             dtype=self.classes_.dtype
         )
 
-        # XXX fix
+        for i, x in enumerate(X):
+            distances = np.sqrt(np.sum((self.X_train_ - x) ** 2, axis=1))
+            y_pred[i] = self.y_train_[np.argmin(distances)]
         return y_pred
 
     def score(self, X, y):
-        """Write docstring.
-
-        And describe parameters
+        """Return the accuracy of the classifier on X and y.
+
+        Parameters
+        ----------
+        X : ndarray of shape (n_samples, n_features)
+            The test samples.
+        y : ndarray of shape (n_samples,)
+            The true labels of the test samples.
+
+        Returns
+        -------
+        score : float
+            The fraction of correctly classified samples.
         """
         X, y = check_X_y(X, y)
         y_pred = self.predict(X)
 
-        # XXX fix
-        return y_pred.sum()
+        return np.mean(y_pred == y)