Charlotte Vedrines, finished part B

numpy_questions.py

@@ -16,6 +16,7 @@
 errors by calling `flake8` at the root of the repo.
 """
 import numpy as np
+import math
 
 
 def max_index(X):
@@ -37,12 +38,30 @@ 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")
 
-    # TODO
+    elif X.size == 0:
+        raise ValueError("X must be 2D")
 
-    return i, j
+    elif len(X.shape) != 2:
+        raise ValueError("X must be 2D")
+
+    else:
+
+        i = 0
+        j = 0
+
+        max = 0
+        n_samples, n_features = X.shape
+        for s in range(n_samples):
+            for f in range(n_features):
+                if X[s][f] > max:
+                    max = X[s][f]
+                    i = s
+                    j = f
+
+        return (i, j)
 
 
 def wallis_product(n_terms):
@@ -62,6 +81,17 @@ 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:
+        L = []
+
+        for i in range(1, n_terms+1):
+            temp = (2*i/(2*i-1))*(2*i/(2*i+1))
+            L.append(temp)
+
+        # Multiplies all the elements in the list
+        pi = 2 * math.prod(L)
+
+        return pi

sklearn_questions.py

@@ -25,51 +25,93 @@
 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
+from sklearn.utils.validation import validate_data
 
 
 class OneNearestNeighbor(ClassifierMixin, BaseEstimator):
-    "OneNearestNeighbor classifier."
+    """OneNearestNeighbor classifier."""
 
     def __init__(self):  # noqa: D107
         pass
 
     def fit(self, X, y):
-        """Write docstring.
+        """Prepare the data.
+
+        Parameters
+        ----------
+        X : ndarray of shape (n_samples, n_features)
+            The input array.
+        y : ndarray of shape (n_features,)
+            The label array.
+
+        Returns
+        -------
+        self : OneNearestNeighbor
+            The fitted estimator.
 
-        And describe parameters
         """
+        # reset = True: it writes n_features_in_ onto the estimator
+        X, y = validate_data(self, X, y, reset=True)
         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_train_ = X
+        self.y_train_ = y
+
         return self
 
     def predict(self, X):
-        """Write docstring.
+        """Predicts the samples' one nearest neighbour.
+
+        Parameters
+        ----------
+        X : ndarray of shape (n_samples, n_features)
+            The input array.
 
-        And describe parameters
+        Returns
+        -------
+        y_pred : ndarray of shape (n_features,)
+            The predicted nearest neighbour for each sample.
         """
         check_is_fitted(self)
+
+        # reset = False: reads n_features_in_ back from the estimator
+        # and compares it with the number of columns in the new X
+        X = validate_data(self, X, reset=False)
+
         X = check_array(X)
         y_pred = np.full(
             shape=len(X), fill_value=self.classes_[0],
             dtype=self.classes_.dtype
         )
 
-        # XXX fix
+        for i in range(X.shape[0]):
+            distances = np.sqrt(np.sum((self.X_train_ - X[i, :])**2, axis=1))
+            y_pred[i] = self.y_train_[np.argmin(distances)]
+
         return y_pred
 
     def score(self, X, y):
-        """Write docstring.
-
-        And describe parameters
+        """Calculate the accuracy of the predictions.
+
+        Parameters
+        ----------
+        X : ndarray of shape (n_samples, n_features)
+            The input array.
+        y : ndarray of shape (n_features,)
+            The label array.
+
+        Returns
+        -------
+        accuracy : float
+            The ratio of correctly predicted samples.
         """
         X, y = check_X_y(X, y)
         y_pred = self.predict(X)
 
-        # XXX fix
-        return y_pred.sum()
+        accuracy = np.mean(y_pred == y)
+
+        return accuracy