Ayush Singh Part B

numpy_questions.py

@@ -29,20 +29,29 @@ def max_index(X):
     Returns
     -------
     (i, j) : tuple(int)
-        The row and columnd index of the maximum.
+        The row and column index of the maximum.
 
     Raises
     ------
     ValueError
         If the input is not a numpy array or
         if the shape is not 2D.
     """
-    i = 0
-    j = 0
+    # Validate input type
+    if not isinstance(X, np.ndarray):
+        raise ValueError("X must be a numpy ndarray")
 
-    # TODO
+    # Validate shape
+    if X.ndim != 2:
+        raise ValueError("X must be a 2D array")
 
-    return i, j
+    # Find flat index of maximum value
+    flat_idx = np.argmax(X)
+
+    # Convert flat index to (row, col)
+    i, j = np.unravel_index(flat_idx, X.shape)
+
+    return int(i), int(j)
 
 
 def wallis_product(n_terms):
@@ -62,6 +71,19 @@ 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 not isinstance(n_terms, int):
+        raise ValueError("n_terms must be an integer")
+    if n_terms < 0:
+        raise ValueError("n_terms must be non-negative")
+
+    # Special case as required by the tests
+    if n_terms == 0:
+        return 1.0
+
+    product = 1.0
+    for n in range(1, n_terms + 1):
+        # term = (4 n^2) / (4 n^2 - 1)
+        product *= (4.0 * n * n) / (4.0 * n * n - 1.0)
+
+    # Wallis product converges to π/2
+    return 2.0 * product

sklearn_questions.py

@@ -2,73 +2,124 @@
 
 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.
 """
 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_is_fitted,
+    validate_data,
+)
 from sklearn.utils.multiclass import check_classification_targets
 
+class OneNearestNeighbor(ClassifierMixin, BaseEstimator):
+    """One Nearest Neighbor classifier.
+
+    This classifier predicts the class of a sample based on the class
+    of its nearest neighbor in the training set, using Euclidean distance
+    as the proximity metric.
+
+    Attributes
+    ----------
+    classes_ : ndarray of shape (n_classes,)
+        The unique class labels in the training data.
+    n_features_in_ : int
+        The number of features seen during fit.
+    X_ : ndarray of shape (n_samples, n_features)
+        The training input samples.
+    y_ : ndarray of shape (n_samples,)
+        The training target values.
 
-class OneNearestNeighbor(BaseEstimator, ClassifierMixin):
-    "OneNearestNeighbor classifier."
+    """
 
     def __init__(self):  # noqa: D107
         pass
 
     def fit(self, X, y):
-        """Write docstring.
+        """Fit the OneNearestNeighbor classifier.
+
+        This method stores the training data for later use during prediction.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            The training input samples.
+        y : array-like of shape (n_samples,)
+            The target values (class labels).
+
+        Returns
+        -------
+        self : object
+            Returns self to allow method chaining.
 
-        And describe parameters
         """
-        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_ = X
+        self.y_ = y
         return self
 
     def predict(self, X):
-        """Write docstring.
+        """Predict class labels for samples in X.
+
+        For each sample in X, finds the nearest neighbor in the training
+        set and returns its class label.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            The input samples to predict.
+
+        Returns
+        -------
+        y_pred : ndarray of shape (n_samples,)
+            The predicted class labels.
 
-        And describe parameters
         """
         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],
             dtype=self.classes_.dtype
         )
-
-        # XXX fix
+        for i, x in enumerate(X):
+            distances = np.sqrt(np.sum((self.X_ - x) ** 2, axis=1))
+            nearest_idx = np.argmin(distances)
+            y_pred[i] = self.y_[nearest_idx]
         return y_pred
 
     def score(self, X, y):
-        """Write docstring.
+        """Calculate the accuracy score.
+
+        Computes the mean accuracy of predictions on the given test data.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            The input samples.
+        y : array-like of shape (n_samples,)
+            The true class labels.
+
+        Returns
+        -------
+        score : float
+            The mean accuracy of the classifier on the given data.
 
-        And describe parameters
         """
         X, y = check_X_y(X, y)
         y_pred = self.predict(X)
-
-        # XXX fix
-        return y_pred.sum()
+        return np.mean(y_pred == y)

students.txt

@@ -78,7 +78,11 @@ Perrotton	Pauline  X
 Rouzou	Julia     X
 Sekri	Juliette     
 Seugnet	Alec     
+<<<<<<< HEAD
+Singh	Ayush  X  
+=======
 Singh	Ayush  X
+>>>>>>> upstream/main
 Smith	Oliver X     
 Söhnchen	Vincent  X 
 Soro	Nangounon Mohamed   X