Brisset 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
 
 
@@ -37,12 +38,15 @@ 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("Input must be a numpy array.")
+    if X.ndim != 2:
+        raise ValueError("Input array must be 2D.")
 
-    # TODO
+    max_val = X.max()
+    i, j = np.where(X == max_val)
 
-    return i, j
+    return i[0], j[0]
 
 
 def wallis_product(n_terms):
@@ -62,6 +66,12 @@ 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.
+    pi_approx = 1
+
+    if n_terms == 0:
+        return pi_approx
+
+    for k in range(1, n_terms + 1):
+        pi_approx *= (4 * k**2) / (4 * k**2 - 1)
+
+    return 2 * pi_approx

sklearn_questions.py

@@ -19,6 +19,7 @@
 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
@@ -29,7 +30,7 @@
 
 
 class OneNearestNeighbor(BaseEstimator, ClassifierMixin):
-    "OneNearestNeighbor classifier."
+    """OneNearestNeighbor classifier."""
 
     def __init__(self):  # noqa: D107
         pass
@@ -39,36 +40,83 @@ def fit(self, X, y):
 
         And describe parameters
         """
+        """Fit the model on the training data.
+
+        Parameters
+        ----------
+        X : array of shape (n_samples, n_features)
+            These are the training samples. These are the points the model will
+            use later to find the nearest neighbor.
+
+        y : array of shape (n_samples,)
+            These are the labels for each training sample in X. This is what we
+            want to predict when we see new data.
+
+        Returns
+        -------
+        self
+            The model itself, following the sklearn convention.
+        """
         X, y = check_X_y(X, y)
         check_classification_targets(y)
+        self.X_ = X
+        self.y_ = y
         self.classes_ = np.unique(y)
         self.n_features_in_ = X.shape[1]
 
-        # XXX fix
         return self
 
     def predict(self, X):
         """Write docstring.
 
         And describe parameters
         """
+        """Predict labels for the input samples.
+
+        Parameters
+        ----------
+        X : array of shape (n_samples, n_features)
+            These are the data points we want to classify. They must have the
+            same number of features as the training data.
+
+
+        Returns
+        -------
+        y_pred : array of shape (n_samples,)
+            These are the predicted labels. For each sample, we look at the
+            closest point in the training set and use its label.
+
+        """
+
         check_is_fitted(self)
         X = check_array(X)
-        y_pred = np.full(
-            shape=len(X), fill_value=self.classes_[0],
-            dtype=self.classes_.dtype
-        )
+        distances = np.linalg.norm(self.X_[None, :, :] - X[:, None, :], axis=2)
+        nearest_idx = np.argmin(distances, axis=1)
+        y_pred = self.y_[nearest_idx]
 
-        # XXX fix
         return y_pred
 
     def score(self, X, y):
         """Write docstring.
 
         And describe parameters
         """
+        """Compute the accuracy of the model.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            The samples used to test the model.
+
+        y : array-like of shape (n_samples,)
+            The true labels, so we can compare them with what we predicted.
+
+        Returns
+        -------
+        score : float
+            The accuracy of the predictions, between 0 and 1.
+        """
         X, y = check_X_y(X, y)
         y_pred = self.predict(X)
 
-        # XXX fix
-        return y_pred.sum()
+        return np.mean(y_pred == y)