numpy_questions - Arnaud Cazanave

numpy_questions.py

@@ -37,12 +37,19 @@ def max_index(X):
         If the input is not a numpy array or
         if the shape is not 2D.
     """
-    i = 0
-    j = 0
+    if type(X) is not np.ndarray:
 
-    # TODO
+        raise ValueError("X must be a numpy array")
 
-    return i, j
+    if len(X.shape) != 2:
+
+        raise ValueError("X must be a 2 dimensional array")
+
+    index_array = np.where(X == np.max(X))
+
+    result = tuple(x[0].item() for x in index_array)
+
+    return result
 
 
 def wallis_product(n_terms):
@@ -64,4 +71,18 @@ 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
+    n = 1
+
+    if n_terms == 0:
+
+        return pi
+
+    while n <= n_terms:
+
+        pi = pi * (4*n**2 / (4*n**2-1))
+
+        n += 1
+
+    return 2*pi

sklearn_questions.py

@@ -19,57 +19,95 @@
 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
+from sklearn.utils.validation import validate_data
 
 
 class OneNearestNeighbor(ClassifierMixin, BaseEstimator):
-    "OneNearestNeighbor classifier."
+    """One-nearest-neighbor classifier."""
 
     def __init__(self):  # noqa: D107
         pass
 
     def fit(self, X, y):
-        """Write docstring.
-
-        And describe parameters
+        """Fit the classifier to the training data.
+
+        Parameters
+        ----------
+        X : ndarray of shape (n_samples, n_features)
+            Training feature matrix.
+        y : ndarray of shape (n_samples,)
+            Training class labels.
+
+        Returns
+        -------
+        self : OneNearestNeighbor
+            Fitted classifier.
         """
-        X, y = check_X_y(X, y)
+        X, y = validate_data(self, 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.
+        """Predict class labels using the nearest neighbor.
 
-        And describe parameters
+        Parameters
+        ----------
+        X : ndarray of shape (n_samples, n_features)
+            Observations to classify.
+
+        Returns
+        -------
+        y_pred : ndarray of shape (n_samples,)
+            Predicted class labels.
         """
         check_is_fitted(self)
-        X = check_array(X)
+        X = validate_data(self, X, reset=False)
+
         y_pred = np.full(
-            shape=len(X), fill_value=self.classes_[0],
+            shape=len(X),
+            fill_value=self.classes_[0],
             dtype=self.classes_.dtype
         )
 
-        # XXX fix
+        for i, x in enumerate(X):
+            distances = np.linalg.norm(self.X_train_ - x, axis=1)
+            index = np.argmin(distances)
+            y_pred[i] = self.y_train_[index]
+
         return y_pred
 
     def score(self, X, y):
-        """Write docstring.
-
-        And describe parameters
+        """Compute the classification accuracy.
+
+        Parameters
+        ----------
+        X : ndarray of shape (n_samples, n_features)
+            Observations to classify.
+        y : ndarray of shape (n_samples,)
+            True class labels.
+
+        Returns
+        -------
+        score : float
+            Proportion of correctly classified observations.
         """
         X, y = check_X_y(X, y)
         y_pred = self.predict(X)
 
-        # XXX fix
+        y_pred = (y_pred == y) / len(y)
+
         return y_pred.sum()