diff --git a/numpy_questions.py b/numpy_questions.py index 21fcec4b..6096e914 100644 --- a/numpy_questions.py +++ b/numpy_questions.py @@ -1,67 +1,48 @@ -"""Assignment - using numpy and making a PR. +"""Numpy related utility functions.""" -The goals of this assignment are: - * Use numpy in practice with two easy exercises. - * Use automated tools to validate the code (`pytest` and `flake8`) - * Submit a Pull-Request on github to practice `git`. - -The two functions below are skeleton functions. The docstrings explain what -are the inputs, the outputs and the expected error. Fill the function to -complete the assignment. The code should be able to pass the test that we -wrote. To run the tests, use `pytest test_numpy_questions.py` at the root of -the repo. It should say that 2 tests ran with success. - -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. -""" import numpy as np def max_index(X): - """Return the index of the maximum in a numpy array. + """Return the indices of the maximum value in a 2D numpy array. Parameters ---------- - X : ndarray of shape (n_samples, n_features) - The input array. + X : np.ndarray + Input 2D array Returns ------- - (i, j) : tuple(int) - The row and columnd index of the maximum. - - Raises - ------ - ValueError - If the input is not a numpy array or - if the shape is not 2D. + tuple + Tuple of (row_index, column_index) of the maximum element. """ - i = 0 - j = 0 - - # TODO + if not isinstance(X, np.ndarray): + raise ValueError("Input must be a numpy array") + if X.ndim != 2: + raise ValueError("Input must be a 2D array") + max_idx = np.argmax(X) + i, j = np.unravel_index(max_idx, X.shape) return i, j def wallis_product(n_terms): - """Implement the Wallis product to compute an approximation of pi. - - See: - https://en.wikipedia.org/wiki/Wallis_product + """Compute approximation of pi using Wallis product formula. Parameters ---------- n_terms : int - Number of steps in the Wallis product. Note that `n_terms=0` will - consider the product to be `1`. + Number of terms to include in the product. Returns ------- - pi : float - The approximation of order `n_terms` of pi using the Wallis product. + float + Approximation of pi. """ - # 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 1.0 + + product = 1.0 + for k in range(1, n_terms + 1): + product *= (4 * k**2) / (4 * k**2 - 1) + return 2 * product diff --git a/sklearn_questions.py b/sklearn_questions.py index f65038c6..7cea3119 100644 --- a/sklearn_questions.py +++ b/sklearn_questions.py @@ -1,74 +1,86 @@ -"""Assignment - making a sklearn estimator. - -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. -""" +"""Custom sklearn estimator: 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.base import BaseEstimator, ClassifierMixin +from sklearn.utils.validation import check_X_y, check_array, check_is_fitted from sklearn.utils.multiclass import check_classification_targets class OneNearestNeighbor(BaseEstimator, ClassifierMixin): - "OneNearestNeighbor classifier." + """One Nearest Neighbor classifier. + + Assigns to each sample the label of the closest training point + using Euclidean distance. + """ - def __init__(self): # noqa: D107 + def __init__(self): + """Initialize the classifier (no parameters).""" pass def fit(self, X, y): - """Write docstring. + """Fit the OneNearestNeighbor classifier. + + Parameters + ---------- + X : ndarray of shape (n_samples, n_features) + Training data. - And describe parameters + y : ndarray of shape (n_samples,) + Target labels. + + Returns + ------- + self : object + Fitted classifier. """ X, y = check_X_y(X, y) check_classification_targets(y) + + self.X_train_ = X + self.y_train_ = y self.classes_ = np.unique(y) self.n_features_in_ = X.shape[1] - # XXX fix return self def predict(self, X): - """Write docstring. + """Predict class labels for samples in X. - And describe parameters + Parameters + ---------- + X : ndarray of shape (n_samples, n_features) + Input samples. + + Returns + ------- + y_pred : ndarray of shape (n_samples,) + Predicted labels. """ 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 - return y_pred + distances = np.linalg.norm( + X[:, None, :] - self.X_train_[None, :, :], + axis=2 + ) + nearest_idx = np.argmin(distances, axis=1) + return self.y_train_[nearest_idx] def score(self, X, y): - """Write docstring. - - And describe parameters + """Return accuracy score of the classifier. + + Parameters + ---------- + X : ndarray of shape (n_samples, n_features) + Input samples. + y : ndarray of shape (n_samples,) + True labels. + + Returns + ------- + float + Accuracy score. """ X, y = check_X_y(X, y) y_pred = self.predict(X) - - # XXX fix - return y_pred.sum() + return np.mean(y_pred == y) diff --git "a/ssh-keygen -t ed25519 -C \"\344\275\240\347\232\204GitHub\351\202\256\347\256\261\"" "b/ssh-keygen -t ed25519 -C \"\344\275\240\347\232\204GitHub\351\202\256\347\256\261\"" new file mode 100644 index 00000000..7669557c --- /dev/null +++ "b/ssh-keygen -t ed25519 -C \"\344\275\240\347\232\204GitHub\351\202\256\347\256\261\"" @@ -0,0 +1,7 @@ +-----BEGIN OPENSSH PRIVATE KEY----- +b3BlbnNzaC1rZXktdjEAAAAABG5vbmUAAAAEbm9uZQAAAAAAAAABAAAAMwAAAAtzc2gtZW +QyNTUxOQAAACC+nIN2ZmV7i3tLTK82iLZ55hTImb3J2vo2gxHCqFY1PgAAAJg6M29MOjNv +TAAAAAtzc2gtZWQyNTUxOQAAACC+nIN2ZmV7i3tLTK82iLZ55hTImb3J2vo2gxHCqFY1Pg +AAAEAvo6TJa/cpJpuuaNQAx+6V9yzlXpTyZVqILJlLmTsZh76cg3ZmZXuLe0tMrzaItnnm +FMiZvcna+jaDEcKoVjU+AAAAEuS9oOeahEdpdEh1YumCrueusQECAw== +-----END OPENSSH PRIVATE KEY----- diff --git "a/ssh-keygen -t ed25519 -C \"\344\275\240\347\232\204GitHub\351\202\256\347\256\261\".pub" "b/ssh-keygen -t ed25519 -C \"\344\275\240\347\232\204GitHub\351\202\256\347\256\261\".pub" new file mode 100644 index 00000000..e79c515d --- /dev/null +++ "b/ssh-keygen -t ed25519 -C \"\344\275\240\347\232\204GitHub\351\202\256\347\256\261\".pub" @@ -0,0 +1 @@ +ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIL6cg3ZmZXuLe0tMrzaItnnmFMiZvcna+jaDEcKoVjU+ 你的GitHub邮箱