{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 5GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import pandas as pd\nfrom PIL import Image\nimport numpy as np\nimport os\nfrom sklearn.neighbors import KNeighborsClassifier","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# **Unzipping the train.7z file and storing kaggle/working/train folder**","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"#!pip install py7zr\nimport py7zr\nwith py7zr.SevenZipFile('/kaggle/input/cifar-10/train.7z', mode='r') as z:\n    z.extractall(path='/kaggle/working')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"* ** Creating the DataFrame for test, train**\n* **train_labels,test_labels will give information of target label for each image in test and train datasets based on id as index**","execution_count":null},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"train_labels = pd.read_csv('/kaggle/input/cifar-10/trainLabels.csv')\ntrain_images = pd.DataFrame(columns = ['id','pixel_array','label'])\n\ntest_labels = pd.read_csv('/kaggle/input/cifar-10/sampleSubmission.csv')\ntest_images = pd.DataFrame(columns = ['id','pixel_array','label'])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Converting Image to Pixel array using numpy\n .ravel() - is used to flatten the array resulting 1-D array**","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"base_path = '/kaggle/working/train/'\nr = '.png'\nimg_a = []\nfor i in range(0,50000):\n    img = Image.open(base_path + str(i+1) + r)\n    arr = np.array(img)\n    arr = arr.ravel()\n    train_images = train_images.append([{ 'id':train_labels['id'].iloc[i],'pixel_array': arr, 'label':train_labels['label'].iloc[i]}])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"rm -r /kaggle/working/train","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"with py7zr.SevenZipFile('/kaggle/input/cifar-10/test.7z', mode='r') as z:\n    z.extractall(path='/kaggle/working')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"base_path = '/kaggle/working/test/'\nr = '.png'\nimg_a = []\nfor i in range(0,300000):\n    img = Image.open(base_path + str(i+1) + r)\n    arr = np.array(img)\n    arr = arr.ravel()\n    test_images = test_images.append([{ 'id':test_labels['id'].iloc[i],'pixel_array': arr, 'label':test_labels['label'].iloc[i]}])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"rm -r /kaggle/working/test","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"knnc = KNeighborsClassifier(n_neighbors=3,algorithm = 'brute').fit(np.vstack(train_images['pixel_array']),train_images['label'])\ntest_images['predict_labels'] = knnc.predict(np.vstack(test_images['pixel_array']))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.metrics import accuracy_score\naccuracy_score(test_images['label'],test_images['predict_labels'])","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat":4,"nbformat_minor":4}