diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000000000000000000000000000000000000..d44086f2550ddf318e30c29d156b10bee1d43c02 --- /dev/null +++ b/.gitignore @@ -0,0 +1,3 @@ +/data +/__pycache__ + diff --git a/LICENCE b/LICENCE new file mode 100644 index 0000000000000000000000000000000000000000..1232db2da35c4deb2d8872b7f9f96ae933c93215 --- /dev/null +++ b/LICENCE @@ -0,0 +1,201 @@ + Apache License + Version 2.0, January 2004 + http://www.apache.org/licenses/ + + TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION + + 1. Definitions. + + "License" shall mean the terms and conditions for use, reproduction, + and distribution as defined by Sections 1 through 9 of this document. + + "Licensor" shall mean the copyright owner or entity authorized by + the copyright owner that is granting the License. + + "Legal Entity" shall mean the union of the acting entity and all + other entities that control, are controlled by, or are under common + control with that entity. For the purposes of this definition, + "control" means (i) the power, direct or indirect, to cause the + direction or management of such entity, whether by contract or + otherwise, or (ii) ownership of fifty percent (50%) or more of the + outstanding shares, or (iii) beneficial ownership of such entity. + + "You" (or "Your") shall mean an individual or Legal Entity + exercising permissions granted by this License. + + "Source" form shall mean the preferred form for making modifications, + including but not limited to software source code, documentation + source, and configuration files. + + "Object" form shall mean any form resulting from mechanical + transformation or translation of a Source form, including but + not limited to compiled object code, generated documentation, + and conversions to other media types. + + "Work" shall mean the work of authorship, whether in Source or + Object form, made available under the License, as indicated by a + copyright notice that is included in or attached to the work + (an example is provided in the Appendix below). + + "Derivative Works" shall mean any work, whether in Source or Object + form, that is based on (or derived from) the Work and for which the + editorial revisions, annotations, elaborations, or other modifications + represent, as a whole, an original work of authorship. For the purposes + of this License, Derivative Works shall not include works that remain + separable from, or merely link (or bind by name) to the interfaces of, + the Work and Derivative Works thereof. + + "Contribution" shall mean any work of authorship, including + the original version of the Work and any modifications or additions + to that Work or Derivative Works thereof, that is intentionally + submitted to Licensor for inclusion in the Work by the copyright owner + or by an individual or Legal Entity authorized to submit on behalf of + the copyright owner. For the purposes of this definition, "submitted" + means any form of electronic, verbal, or written communication sent + to the Licensor or its representatives, including but not limited to + communication on electronic mailing lists, source code control systems, + and issue tracking systems that are managed by, or on behalf of, the + Licensor for the purpose of discussing and improving the Work, but + excluding communication that is conspicuously marked or otherwise + designated in writing by the copyright owner as "Not a Contribution." + + "Contributor" shall mean Licensor and any individual or Legal Entity + on behalf of whom a Contribution has been received by Licensor and + subsequently incorporated within the Work. + + 2. Grant of Copyright License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + copyright license to reproduce, prepare Derivative Works of, + publicly display, publicly perform, sublicense, and distribute the + Work and such Derivative Works in Source or Object form. + + 3. Grant of Patent License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + (except as stated in this section) patent license to make, have made, + use, offer to sell, sell, import, and otherwise transfer the Work, + where such license applies only to those patent claims licensable + by such Contributor that are necessarily infringed by their + Contribution(s) alone or by combination of their Contribution(s) + with the Work to which such Contribution(s) was submitted. If You + institute patent litigation against any entity (including a + cross-claim or counterclaim in a lawsuit) alleging that the Work + or a Contribution incorporated within the Work constitutes direct + or contributory patent infringement, then any patent licenses + granted to You under this License for that Work shall terminate + as of the date such litigation is filed. + + 4. Redistribution. You may reproduce and distribute copies of the + Work or Derivative Works thereof in any medium, with or without + modifications, and in Source or Object form, provided that You + meet the following conditions: + + (a) You must give any other recipients of the Work or + Derivative Works a copy of this License; and + + (b) You must cause any modified files to carry prominent notices + stating that You changed the files; and + + (c) You must retain, in the Source form of any Derivative Works + that You distribute, all copyright, patent, trademark, and + attribution notices from the Source form of the Work, + excluding those notices that do not pertain to any part of + the Derivative Works; and + + (d) If the Work includes a "NOTICE" text file as part of its + distribution, then any Derivative Works that You distribute must + include a readable copy of the attribution notices contained + within such NOTICE file, excluding those notices that do not + pertain to any part of the Derivative Works, in at least one + of the following places: within a NOTICE text file distributed + as part of the Derivative Works; within the Source form or + documentation, if provided along with the Derivative Works; or, + within a display generated by the Derivative Works, if and + wherever such third-party notices normally appear. The contents + of the NOTICE file are for informational purposes only and + do not modify the License. You may add Your own attribution + notices within Derivative Works that You distribute, alongside + or as an addendum to the NOTICE text from the Work, provided + that such additional attribution notices cannot be construed + as modifying the License. + + You may add Your own copyright statement to Your modifications and + may provide additional or different license terms and conditions + for use, reproduction, or distribution of Your modifications, or + for any such Derivative Works as a whole, provided Your use, + reproduction, and distribution of the Work otherwise complies with + the conditions stated in this License. + + 5. Submission of Contributions. Unless You explicitly state otherwise, + any Contribution intentionally submitted for inclusion in the Work + by You to the Licensor shall be under the terms and conditions of + this License, without any additional terms or conditions. + Notwithstanding the above, nothing herein shall supersede or modify + the terms of any separate license agreement you may have executed + with Licensor regarding such Contributions. + + 6. Trademarks. This License does not grant permission to use the trade + names, trademarks, service marks, or product names of the Licensor, + except as required for reasonable and customary use in describing the + origin of the Work and reproducing the content of the NOTICE file. + + 7. Disclaimer of Warranty. Unless required by applicable law or + agreed to in writing, Licensor provides the Work (and each + Contributor provides its Contributions) on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or + implied, including, without limitation, any warranties or conditions + of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A + PARTICULAR PURPOSE. You are solely responsible for determining the + appropriateness of using or redistributing the Work and assume any + risks associated with Your exercise of permissions under this License. + + 8. Limitation of Liability. In no event and under no legal theory, + whether in tort (including negligence), contract, or otherwise, + unless required by applicable law (such as deliberate and grossly + negligent acts) or agreed to in writing, shall any Contributor be + liable to You for damages, including any direct, indirect, special, + incidental, or consequential damages of any character arising as a + result of this License or out of the use or inability to use the + Work (including but not limited to damages for loss of goodwill, + work stoppage, computer failure or malfunction, or any and all + other commercial damages or losses), even if such Contributor + has been advised of the possibility of such damages. + + 9. Accepting Warranty or Additional Liability. While redistributing + the Work or Derivative Works thereof, You may choose to offer, + and charge a fee for, acceptance of support, warranty, indemnity, + or other liability obligations and/or rights consistent with this + License. However, in accepting such obligations, You may act only + on Your own behalf and on Your sole responsibility, not on behalf + of any other Contributor, and only if You agree to indemnify, + defend, and hold each Contributor harmless for any liability + incurred by, or claims asserted against, such Contributor by reason + of your accepting any such warranty or additional liability. + + END OF TERMS AND CONDITIONS + + APPENDIX: How to apply the Apache License to your work. + + To apply the Apache License to your work, attach the following + boilerplate notice, with the fields enclosed by brackets "[]" + replaced with your own identifying information. (Don't include + the brackets!) The text should be enclosed in the appropriate + comment syntax for the file format. We also recommend that a + file or class name and description of purpose be included on the + same "printed page" as the copyright notice for easier + identification within third-party archives. + + Copyright [2022] [CHOUKRI] + + Licensed under the Apache License, Version 2.0 (the "License"); + you may not use this file except in compliance with the License. + You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, software + distributed under the License is distributed on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + See the License for the specific language governing permissions and + limitations under the License. \ No newline at end of file diff --git a/knn.py b/knn.py new file mode 100644 index 0000000000000000000000000000000000000000..9da45fbe8f17a5a97342fd64518f68b64367d091 --- /dev/null +++ b/knn.py @@ -0,0 +1,162 @@ +# K-nearest-neighbors + +# 1. function distance_matrix + +import matplotlib.pyplot as plt +import numpy as np +from scipy.optimize.slsqp import concatenate + +from read_cifar import read_cifar, split_dataset + +path = "data/cifar-10-batches-py/" + + +# first we write the function that calculate the distance between two matrix +# we will use this function to compute the distance between two matrix with equal shape +def equal_shape_distance_matrix(X, V): + """ + compute the Euclidean distance between two matrix with equal shape + + :param + X: first matrix + V: second matrix + :return: + the Euclidean distance between X and V + """ + return ( + np.dot(X, X.transpose()) + + np.dot(V, V.transpose()) + - 2 * np.dot(X, V.transpose()) + ) + + +# distance_matrix function between two matrix of any shape + + +def distance_matrix(data_train, data_test): + + """ + compute the Euclidean distance between two matrix + + :param + data_train: the data_train matrix that contains the training data + data_test: the data_test matrix that contains the test data + :return: + dist: the Euclidean distance between data_train and data_test as a matrix + """ + # we compute the first distance with equal shapes + dist = equal_shape_distance_matrix(data_train[: data_test.shape[0]], data_test) + + # we compute the distance between the test set and the p part of the training data + p = int(data_train.shape[0] / data_test.shape[0]) + for i in range(1, p): + sub_dist = equal_shape_distance_matrix( + data_train[data_test.shape[0] * i : data_test.shape[0] * (i + 1)], data_test + ) + dist = np.concatenate((dist, sub_dist), axis=1) + return dist + + +# 2. the function Knn_predict + + +def knn_predict(labels_train, dists, k): + + """ + compute the predicted labels for the data_test + + :param + labels_train: the labels of the training_data with whom we will compare the predicted labels + dists: the distance matrix that contains the euclidean distances between the data_train and the test_train + k = number of neighbors + :return: + lables_predicted: the predicted labels for the data_test + + """ + # we initialize the matrix of predicted labels + num_test = dists.shape[0] + lables_predicted = np.zeros(num_test) + for i in range(num_test): + closest_labels = [] + + # list des indices des plus petites distances + sorted_dist = np.argsort(dists[i]) + + # les k premiers labels qui correspondent au data_train qui ont la plus petite distance avec les data_test + closest_labels = list(labels_train[sorted_dist[0:k]]) + + pass + # les labels prédits pour les data_tets + lables_predicted[i] = np.argmax(np.bincount(closest_labels)) + + pass + return lables_predicted + + +# 4. evaluate_knn + + +def evaluate_knn(data_train, labels_train, data_test, labels_test, k): + + """ + evaluate the accuracy of our prediction model + + :param + data_train: the data of the training set + labels_train: the labels of the data_train + data_test: the data of the test set + labels_test: the actual labels (true labels) for the test set + k = number of neighbors + :return: + accuracy: the accuracy of the model + """ + + # we call for distance_matrix and knn_predict + dists = distance_matrix(data_train, data_test) + y_test_pred = knn_predict(labels_train, dists, k) + + # total number of predictions + num_test = dists.shape[0] + # number of correct predictions + correct = np.sum(y_test_pred == labels_test) + # accuracy + accuracy = float(correct) / num_test + print("Got %d / %d correct, accuracy is : %f" % (correct, num_test, accuracy)) + return accuracy + + +if __name__ == "__main__": + + # load data and split it into train and test + + data, labels = read_cifar(path) + + # we choose the split factor 0.9 + data_train, data_test, labels_train, labels_test = split_dataset(data, labels, 0.9) + + print(data_test.shape) + + # we reduce the shape of the test to prevent memory issues + + num_test = 2000 + mask = list(range(num_test)) + data_test = data_test[mask] + labels_test = labels_test[mask] + + # we calcul the accuracy for k from 1 to 20 + + Ks = [] + accuracies = [] + + for k in range(1, 20): + + accuracy = evaluate_knn(data_train, labels_train, data_test, labels_test, k) + Ks.append(k) + accuracies.append(accuracy) + + # we plot the variation of the accuracy as a function of k and save it as knn.png + + plt.plot(Ks, accuracies, "o") + plt.title("Accuracy vs K") + plt.savefig("knn.png", bbox_inches="tight") + plt.show() diff --git a/read_cifar.py b/read_cifar.py new file mode 100644 index 0000000000000000000000000000000000000000..b324313cae738fdeafd63b6fd5ef53cb7fb10578 --- /dev/null +++ b/read_cifar.py @@ -0,0 +1,123 @@ +# prepare the CIFAR dataset + +# 1. we create a folder data in wich we will move the downloaded cifar-10-batches-py folder +# +# 2. function read_cifar_batch + +import os +import pickle + +import numpy as np + +path = "data/cifar-10-batches-py/" + + +def read_cifar_batch(file): + + """ + load single batch of cifar. + + :param + file: the path of the single batch. + + :return: + data: a matrix that contains the data of the batch. + labels: a vector whose values correspond to the class code of the data of the same index in data. + + """ + + with open(file, "rb") as fo: + + dict = pickle.load(fo, encoding="bytes") + data = dict[b"data"] + labels = dict[b"labels"] + data = data.reshape(10000, 3072) + labels = np.array(labels) + + return data, labels + + +# 3. the function read_cifar + + +def read_cifar(path): + + """ + load all batches of cifar including the test batch. + + :param + path: the path of the directory containing the six batches (five data_batch and one test_batch). + + :return: + data: a matrix that contains all data of the batches + labels: a vector whose values correspond to the class code of the data of the same index in data + + """ + + XT = [] + YT = [] + + for i in range(1, 6): + + f = os.path.join(path, "data_batch_%d" % (i,)) + X, Y = read_cifar_batch(f) + XT.append(X) + YT.append(Y) + + T, W = read_cifar_batch(path + "test_batch") + XT.append(T) + YT.append(W) + + data = np.concatenate(XT) + labels = np.concatenate(YT) + + del X, Y + + return data, labels + + +# 4. the function split_dataset + +from sklearn.model_selection import train_test_split + + +def split_dataset(data, labels, split): + + """ + Split the dataset into a training set and a test set + + :param + data: the dataset + labels: the labels corresponding to the dataset + split: a float between 0 and 1 which determines the split factor of the training set with respect to the test set. + :return: + data_train: a matrix that contains the data of the training set + data_test: a matrix that contains the data of the test set + labels_train: a vector whose values correspond to the class code of the data of the same index in data_train + labels_train: a vector whose values correspond to the class code of the data of the same index in data_test + """ + + # shuffle = True means that the data must be shuffled, so that two successive calls shouldn't give the same output. + data_train, data_test, labels_train, labels_test = train_test_split( + data, labels, test_size=split, shuffle=True + ) + + return data_train, data_test, labels_train, labels_test + + +if __name__ == "__main__": + + data, labels = read_cifar_batch(path + "data_batch_1") + print(data.shape) + print(labels.shape) + + data, labels = read_cifar(path) + print(data.shape) + print(labels.shape) + + data_train, data_test, labels_train, labels_test = split_dataset( + data, labels, split=0.2 + ) + + print(data_train.shape) + print(data_test.shape)