Answered NumPy and Sklearn questions

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 +38,18 @@ def max_index(X):
         If the input is not a numpy array or
         if the shape is not 2D.
     """
-    i = 0
-    j = 0
+    if type(X) is not np.ndarray:
+        raise ValueError("Input is not a numpy array")
+    if X.ndim != 2:
+        raise ValueError("Input is not 2D")
+
+    maxid = np.argmax(X)
+    ncols = X.shape[1]
 
-    # TODO
+    row = maxid // ncols
+    col = maxid % ncols
 
-    return i, j
+    return (row, col)
 
 
 def wallis_product(n_terms):
@@ -62,6 +69,9 @@ 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
+    else:
+        num = 4 * np.arange(1, n_terms + 1) ** 2
+        pi = 2 * np.prod(num / (num - 1))
+        return pi

sklearn_questions.py

@@ -19,56 +19,86 @@
 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.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(BaseEstimator, ClassifierMixin):
-    "OneNearestNeighbor classifier."
+class OneNearestNeighbor(ClassifierMixin, BaseEstimator):
+    """OneNearestNeighbor classifier."""
 
     def __init__(self):  # noqa: D107
         pass
 
     def fit(self, X, y):
-        """Write docstring.
-
-        And describe parameters
+        """Fit a nearest neighbor model.
+
+        Parameters
+        ----------
+        X : ndarray of shape (n_samples, n_features)
+            The features vector.
+        y : ndarray of shape (n_samples, 1)
+            The target vector.
+
+        Returns
+        -------
+        The fitted model.
         """
         X, y = check_X_y(X, y)
+        X = check_array(X)
         check_classification_targets(y)
         self.classes_ = np.unique(y)
         self.n_features_in_ = X.shape[1]
+        self.X_ = X
+        self.y_ = y
 
-        # XXX fix
         return self
 
     def predict(self, X):
-        """Write docstring.
+        """Predict target from a feature vector with a nearest neighbor model.
+
+        Parameters
+        ----------
+        X : ndarray of shape (n_samples, n_features)
+            The feature vector from which to predict y.
 
-        And describe parameters
+        Returns
+        -------
+        y_pred : ndarray of shape (n_samples, 1)
+            The predicted value for y.
         """
         check_is_fitted(self)
         X = check_array(X)
         y_pred = np.full(
-            shape=len(X), fill_value=self.classes_[0],
-            dtype=self.classes_.dtype
+            shape=len(X), fill_value=self.classes_[0], dtype=self.classes_.dtype
         )
 
-        # XXX fix
+        distances = np.linalg.norm(
+            X[:, np.newaxis, :] - self.X_[np.newaxis, :, :], axis=2
+        )
+        nearest_idx = np.argmin(distances, axis=1)
+        y_pred = self.y_[nearest_idx]
+
         return y_pred
 
     def score(self, X, y):
-        """Write docstring.
-
-        And describe parameters
+        """Return the score of a model evaluating against ground truth.
+
+        Parameters
+        ----------
+        X : ndarray of shape (n_samples, n_features)
+            The features vector.
+        y : ndarray of shape (n_samples, 1)
+            The target vector.
+
+        Returns
+        -------
+        score : float
+            The score of the model.
         """
         X, y = check_X_y(X, y)
         y_pred = self.predict(X)
-
-        # XXX fix
-        return y_pred.sum()
+        score = np.mean(y_pred == y)
+        return score