Lucas lonegro gurfinkel 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
 
 
@@ -36,13 +37,14 @@ def max_index(X):
     ValueError
         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 an ndarray.")
+    if X.ndim != 2:
+        raise ValueError("X must be a matrix")
 
-    return i, j
+    return np.unravel_index(np.argmax(X), X.shape)
 
 
 def wallis_product(n_terms):
@@ -61,7 +63,16 @@ 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 not isinstance(n_terms, int):
+        raise ValueError("n_terms must be an integer")
+
+    if n_terms == 0:
+        return 1.0
+
+    ns = 4.0 * (np.arange(1, n_terms + 1) ** 2.0)
+
+    return (ns / (ns - 1.0)).prod() * 2.0

sklearn_questions.py

@@ -19,57 +19,96 @@
 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_is_fitted,
+    validate_data,
+)
 
 
 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.
+        """Fit the OneNearestNeighbor classifier.
+
+        Parameters
+        ----------
+        X : ndarray of shape (n_samples, n_features)
+            Training data, where `n_samples` is the number of samples
+            and `n_features` is the number of features.
+        y : ndarray of shape (n_samples,)
+            Class labels.
+
+        Returns
+        -------
+        self : OneNearestNeighbor
+            The fitted estimator.
 
-        And describe parameters
         """
-        X, y = check_X_y(X, y)
+        X, y = validate_data(self, X, y, reset=False)
+        check_classification_targets(y)
+        self.classes_ = np.unique(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 : ndarray of shape (n_samples, n_features)
+            The input data to make predictions for.
+
+        Returns
+        -------
+        y_pred : ndarray of shape (n_samples,)
+            Predicted class label for each sample.
 
-        And describe parameters
         """
         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 = validate_data(self, X, reset=False)
+
+        diff = X[:, None, :] - self.X_[None, :, :]
+
+        dist_matrix = np.sum(diff**2, axis=2)
+        closest_indices = np.argmin(dist_matrix, axis=1)
+
+        y_pred = self.y_[closest_indices]
+
         return y_pred
 
     def score(self, X, y):
-        """Write docstring.
+        """Compute accuracy on the test data and labels.
+
+        Parameters
+        ----------
+        X : ndarray of shape (n_samples, n_features)
+            Test samples.
+        y : ndarray of shape (n_samples,)
+            True labels for `X`.
+
+        Returns
+        -------
+        score : float
+            Accuracy of `self.predict(X)` relative to `y`.
 
-        And describe parameters
         """
-        X, y = check_X_y(X, y)
+        X, y = validate_data(self, X, y, reset=False)
         y_pred = self.predict(X)
 
-        # XXX fix
-        return y_pred.sum()
+        return np.mean(y_pred == y)