{"cells":[{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"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 in \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 \"../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\n\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n        \n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"from sklearn.neighbors import KNeighborsClassifier\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import classification_report\nfrom sklearn.svm import SVC\nfrom sklearn.model_selection import GridSearchCV\nimport numpy as np\nimport cv2 \nimport os\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"dataset_train =\"/kaggle/input/2019-fall-pr-project/train/train/\"\n\nimgs = []\nlabels = []\n\nfor img_dir in os.listdir(dataset_train):\n    print(img_dir)\n    if str.find(img_dir, 'cat'):\n        labels.append(0)\n    else:\n        labels.append(1)\n    img = cv2.imread(dataset_train+img_dir)\n    data = cv2.resize(img, (32, 32))\n    data = np.reshape(data, -1)\n    imgs.append(data)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(len(labels[:-1]))\nprint(len(imgs))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train, x_test, y_train, y_test = train_test_split(imgs, labels, test_size=0.25, random_state=42)\n\nfrom sklearn.preprocessing import StandardScaler\n\nscaler = StandardScaler()\nx_train = scaler.fit_transform(x_train)\nx_test = scaler.transform(x_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"clf = SVC(kernel='rbf', class_weight='balanced', random_state=42)\n\n\nparam_grid = {'C':[0.1, 1], 'gamma':[0.0001, 0.001, 0.01]}\n\nclf = GridSearchCV(clf, param_grid, cv=3)\n\n#clf.fit(x_train, y_train)\nclf.fit(x_test, y_test)\n\n\nmodel = clf.best_estimator_\n\nprint(clf.best_params_)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"dataset_test = \"/kaggle/input/2019-fall-pr-project/test1/test1/\"\n\nimgs_test = []\ntest_id = []\n\nfor img_dir in os.listdir(dataset_test):\n    iid, _ = img_dir.split('.')\n    test_id.append(iid)\n    img = cv2.imread(dataset_test+img_dir)\n    data = cv2.resize(img, (32, 32))\n    data = np.reshape(data, -1)\n    imgs_test.append(data)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"imgs_test = scaler.transform(imgs_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_predict = model.predict(imgs_test)\n\n#score = classification_report(y_test, y_predict)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(y_predict)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df = pd.DataFrame([y_predict])\ndf = df.T\ndf","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df.index = np.arange(1,len(df)+1)\ndf.index.name = 'id'\ndf","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":1}