MARTIN_assignment

numpy_questions.py

@@ -15,6 +15,8 @@
 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
 
 
@@ -39,9 +41,12 @@ def max_index(X):
     """
     i = 0
     j = 0
-
-    # TODO
-
+    if not isinstance(X, np.ndarray):
+        raise ValueError("Input must be a numpy array")
+    if len(X.shape) != 2:
+        raise ValueError("Input must be a 2D array")
+    id = np.argmax(X)
+    i, j = np.unravel_index(id, X.shape)
     return i, j
 
 
@@ -62,6 +67,9 @@ 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
+    pi = 1
+    for i in range(1, n_terms + 1):
+        pi = pi * (4 * i**2) / (4 * i**2 - 1)
+    return pi * 2

sklearn_questions.py

@@ -28,47 +28,81 @@
 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 according to X, y.
+
+        Parameters
+        ----------
+        X : ndarray of shape (n_samples, n_features)
+            Training data, with n_samples the number of samples and
+            n_features the number of features.
+        y : ndarray of shape (n_samples,)
+            Target data, with n_samples the number of samples
+
+        Returns
+        -------
+        self : object
+            Fitted estimator.
         """
         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.
+        """
+        Predict the labels based on X with the NearestNeighbor Estimator.
+
+        Parameters
+        ----------
+        X : ndarray of shape (n_samples, n_features)
+            Data to predict, with n_samples the number of samples and
+            n_features the number of features.
+
+        Returns
+        -------
+        y_pred : ndarray of shape (n_samples,) with the predicted values.
+                Predicted values for X.
 
-        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
+        for i in range(len(X)):
+            d = np.linalg.norm(self.X_ - X[i, :], axis=1)
+            nearest_index = d.argmin()
+            y_pred[i] = self.y_[nearest_index]
         return y_pred
 
     def score(self, X, y):
-        """Write docstring.
-
-        And describe parameters
+        """
+        Score the prediction with the predict function.
+
+        Parameters
+        ----------
+        X : ndarray of shape (n_sample, n_features)
+            Data to predict.
+        y : ndarray of shape (n_sample, )
+            Targeted data.
+        Returns
+        -------
+        score : float
+            Mean accuracy of the model on the X, y dataset.
         """
         X, y = check_X_y(X, y)
         y_pred = self.predict(X)
-
-        # XXX fix
-        return y_pred.sum()
+        y_pred = (y_pred == y)
+        return y_pred.sum()/len(y_pred)

students.txt

@@ -61,7 +61,7 @@ Liu	Guangyue
 Liu	Yunxian     
 Lucille	Maximilien X     
 Mahé	Blanche     
-Martin	Justin     X
+Martin	Justin X
 Massias	Mathurin     
 Massoud	Alexandre.....X
 Mayette	Scott