Abel Dornbusch Answers to the 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
 
 
@@ -36,11 +37,15 @@ def max_index(X):
     ValueError
         If the input is not a numpy array or
         if the shape is not 2D.
+    Method : checking for the errors, then converting the indices of the max
+            into a tuple ready to be returned
     """
-    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 2-dimensional array")
 
-    # TODO
+    i, j = np.unravel_index(np.argmax(X), X.shape)
 
     return i, j
 
@@ -62,6 +67,14 @@ 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:
+        pi = 1
+        for n in range(1, n_terms + 1):
+            pi = pi * (2 * n) ** 2 / ((2 * n - 1) * (2 * n + 1))
+
+    return pi * 2
+
+
+"""Method : 'for' loop in order to compute the desired product"""

sklearn_questions.py

@@ -1,3 +1,13 @@
+"""One-nearest-neighbor classifier."""
+
+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.multiclass import check_classification_targets
+
 """Assignment - making a sklearn estimator.
 
 The goal of this assignment is to implement by yourself a scikit-learn
@@ -19,57 +29,59 @@
 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.utils.multiclass import check_classification_targets
 
 
-class OneNearestNeighbor(ClassifierMixin, BaseEstimator):
+class OneNearestNeighbor(ClassifierMixin, BaseEstimator):  # noqa: D300
     "OneNearestNeighbor classifier."
 
     def __init__(self):  # noqa: D107
         pass
 
-    def fit(self, X, y):
-        """Write docstring.
-
-        And describe parameters
+    def fit(self, X, y):  # noqa: D205, D400, D401
+        """Here self corresponds to the particular
+        instance of the OneNearestNeighbor.
+        X is the observations with their features
+        y is the class of the observations
         """
         X, y = check_X_y(X, 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.
+    def predict(self, X):  # noqa: D205, D400, D401
+        """We first raise an error
+        if X doesn't have the right dimensions.
 
-        And describe parameters
+        Then we compute the euclidean distance of
+        every observation to a given observation,
+        take the indice of the minimal one and
+        assign the class therefore predict to the indice of y_pred.
         """
         check_is_fitted(self)
         X = check_array(X)
+        if X.shape[1] != self.n_features_in_:
+            raise ValueError(
+                f"X has {X.shape[1]} features, but OneNearestNeighbor "
+                f"is expecting {self.n_features_in_} features as input."
+            )
         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
+        for i in range(len(y_pred)):
+            distances = np.linalg.norm(self.X_ - X[i], axis=1)
+            y_pred[i] = self.y_[np.argmin(distances)]
         return y_pred
 
-    def score(self, X, y):
-        """Write docstring.
-
-        And describe parameters
-        """
+    def score(self, X, y):  # noqa: D400, D401
+        """Here we compute the accuracy by comparing the prediction with the actual y"""  # noqa: E501
         X, y = check_X_y(X, y)
         y_pred = self.predict(X)
+        accuracy = np.mean(y_pred == y)
 
-        # XXX fix
-        return y_pred.sum()
+        return accuracy