Part B ArthurGaillard

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 +38,20 @@ 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) or (X.ndim != 2):
+        raise ValueError
 
-    # TODO
+    max_i = 0
+    max_j = 0
+    max_val = X[0][0]
 
-    return i, j
+    for i in range(X.shape[0]):
+        for j in range(X.shape[1]):
+            if X[i][j] > max_val:
+                max_val = X[i][j]
+                max_i = i
+                max_j = j
+    return max_i, max_j
 
 
 def wallis_product(n_terms):
@@ -64,4 +73,11 @@ def wallis_product(n_terms):
     """
     # XXX : The n_terms is an int that corresponds to the number of
     # terms in the product. For example 10000.
-    return 0.
+    pi = 1
+
+    if n_terms == 0:
+        return pi
+    else:
+        for i in range(1, n_terms + 1):
+            pi = pi * (4 * i**2) / ((4 * i**2) - 1)
+        return 2 * pi

sklearn_questions.py

@@ -1,74 +1,95 @@
-"""Assignment - making a sklearn estimator.
-
-The goal of this assignment is to implement by yourself a scikit-learn
-estimator for the OneNearestNeighbor and check that it is working properly.
-
-The nearest neighbor classifier predicts for a point X_i the target y_k of
-the training sample X_k which is the closest to X_i. We measure proximity with
-the Euclidean distance. The model will be evaluated with the accuracy (average
-number of samples corectly classified). You need to implement the `fit`,
-`predict` and `score` methods for this class. The code you write should pass
-the test we implemented. You can run the tests by calling at the root of the
-repo `pytest test_sklearn_questions.py`.
-
-We also ask to respect the pep8 convention: https://pep8.org. This will be
-enforced with `flake8`. You can check that there is no flake8 errors by
-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.
-"""
+"""Assignment - making a sklearn estimator."""
+
 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.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):
+    """OneNearestNeighbor classifier."""
 
     def __init__(self):  # noqa: D107
         pass
 
     def fit(self, X, y):
-        """Write docstring.
-
-        And describe parameters
+        """Fit the OneNearestNeighbor classifier.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Training samples.
+        y : array-like of shape (n_samples,)
+            Target labels.
+
+        Returns
+        -------
+        self : object
+            Fitted estimator.
         """
         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-like of shape (n_samples, n_features)
+            Samples to classify. Must have same number of features
+            as training data.
+
+        Returns
+        -------
+        y_pred : ndarray of shape (n_samples,)
+            Predicted labels for each input sample.
         """
         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
-        return y_pred
+        if X.shape[1] != self.n_features_in_:
+            raise ValueError(
+                f"X has {X.shape[1]} features, but "
+                f"{self.__class__.__name__} is expecting "
+                f"{self.n_features_in_} features as input."
+            )
 
-    def score(self, X, y):
-        """Write docstring.
+        distances = np.linalg.norm(self.X_[None, :, :] - X[:, None, :], axis=2)
+        nearest_idx = np.argmin(distances, axis=1)
+
+        return self.y_[nearest_idx]
 
-        And describe parameters
+    def score(self, X, y):
+        """Compute the accuracy of the classifier.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Samples used to evaluate the model.
+        y : array-like of shape (n_samples,)
+            True labels corresponding to X.
+
+        Returns
+        -------
+        score : float
+            Accuracy of predictions, between 0 and 1.
         """
+        check_is_fitted(self)
         X, y = check_X_y(X, y)
-        y_pred = self.predict(X)
 
-        # XXX fix
-        return y_pred.sum()
+        if X.shape[1] != self.n_features_in_:
+            raise ValueError(
+                f"X has {X.shape[1]} features, but "
+                f"{self.__class__.__name__} is expecting "
+                f"{self.n_features_in_} features as input."
+            )
+
+        y_pred = self.predict(X)
+        return np.mean(y_pred == y)