Fang Zhang – Part B 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
-
-    return i, j
+    flat_idx = np.argmax(X)
+    i, j = np.unravel_index(flat_idx, X.shape)
+    return int(i), int(j)
 
 
 def wallis_product(n_terms):
@@ -62,6 +64,13 @@ 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:
+        raise ValueError("n_terms must be non-negative.")
+
+    if n_terms == 0:
+        return 1.0
+
+    n = np.arange(1, n_terms + 1, dtype=float)
+    terms = (2 * n / (2 * n - 1)) * (2 * n / (2 * n + 1))
+    product = np.prod(terms)
+    return float(2 * product)

sklearn_questions.py

@@ -16,59 +16,112 @@
 calling `flake8` at the root of the repo.
 
 Finally, you need to write docstring similar to the one in `numpy_questions`
-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.
+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 ClassifierMixin, BaseEstimator
+from sklearn.utils.validation import check_X_y, check_array, check_is_fitted
 from sklearn.utils.multiclass import check_classification_targets
 
 
-class OneNearestNeighbor(BaseEstimator, ClassifierMixin):
-    "OneNearestNeighbor classifier."
+class OneNearestNeighbor(ClassifierMixin, BaseEstimator):
+    """One-nearest-neighbor classifier.
+
+    This classifier predicts, for each input sample, the target of the
+    closest training sample in Euclidean distance.
+    """
 
     def __init__(self):  # noqa: D107
+        """Initialize the OneNearestNeighbor classifier."""
+        # This estimator has no hyper-parameters.
         pass
 
     def fit(self, X, y):
-        """Write docstring.
-
-        And describe parameters
+        """Fit the one-nearest-neighbor classifier.
+
+        The training samples and their labels are stored so that predictions
+        can be made by finding the closest training sample to each new point.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Training data.
+        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)
+
+        # Store training data and targets
+        self.X_ = X
+        self.y_ = y
+
+        # Attributes expected by scikit-learn
         self.classes_ = np.unique(y)
         self.n_features_in_ = X.shape[1]
 
-        # XXX fix
         return self
 
     def predict(self, X):
-        """Write docstring.
+        """Predict class labels for samples in X.
+
+        Each sample in X is assigned the label of the closest training sample
+        stored during :meth:`fit`, using the Euclidean distance.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Input samples to classify.
 
-        And describe parameters
+        Returns
+        -------
+        y_pred : ndarray of shape (n_samples,)
+            Predicted class labels for each sample in X.
         """
-        check_is_fitted(self)
+        check_is_fitted(self, attributes=["X_", "y_", "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
+        # Enforce consistency with the number of features seen during fit
+        n_features = X.shape[1]
+        if n_features != self.n_features_in_:
+            msg = (
+                f"X has {n_features} features, but {self.__class__.__name__} "
+                f"is expecting {self.n_features_in_} features as input"
+            )
+            raise ValueError(msg)
+
+        # Compute squared Euclidean distances to all training samples:
+        # diff shape: (n_samples_test, n_samples_train, n_features)
+        diff = X[:, np.newaxis, :] - self.X_[np.newaxis, :, :]
+        distances = np.sum(diff ** 2, axis=2)
+
+        # Index of nearest neighbor in the training set for each test sample
+        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 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 for X.
+
+        Returns
+        -------
+        score : float
+            Mean accuracy of predictions on X with respect 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))