{"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 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\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\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":"\nfrom sklearn.neighbors import KNeighborsClassifier\nfrom sklearn.model_selection import train_test_split\n\nimport numpy as np\n\nimport cv2 \nimport os","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import matplotlib.pyplot as plt\nimport os\nfrom tqdm import tqdm\nimport scipy.misc\n\ndataset_train = \"/kaggle/input/2019-fall-pr-project/train/train/\"\nfilename = os.listdir(dataset_train)\n\nfilename.sort()\n\n#k = plt.imread(dataset_train)\nX = np.zeros([len(filename),32*32*3])\n\n\nfor i, name in tqdm(enumerate(filename), desc='Loading..'):\n    \n    \n    image = plt.imread(dataset_train + name)\n    \n    image = cv2.resize(image,dsize=(32,32), interpolation=cv2.INTER_LANCZOS4)\n    #image = np.resize(image,[32,32,3])\n    image = image.reshape(-1)\n    X[i] = image","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"labeling = np.zeros_like(filename)\n\nfor i, name in tqdm(enumerate(filename), desc='Loading..'):\n    \n    if name.split('.')[0] == 'cat':\n        labeling[i] = 0\n    elif name.split('.')[0] == 'dog':\n        labeling[i] = 1\n    else:\n        break","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"labeling[:]\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X = cv2.GaussianBlur(X,(5,5),0)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.preprocessing import StandardScaler\n\nscaler = StandardScaler()\nscaler.fit(X)\nX_norm = scaler.transform(X)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_norm.shape\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.svm import SVC\nfrom sklearn.decomposition import PCA as RandomizedPCA\nfrom sklearn.metrics import classification_report\nimport time\nfrom sklearn.model_selection import GridSearchCV\nfrom sklearn import metrics \nfrom sklearn.pipeline import make_pipeline\n\npca = RandomizedPCA(n_components=32, whiten=True, random_state=42)\nsvc = SVC(kernel='rbf', class_weight='balanced')\nmodel = make_pipeline(pca, svc)\n\n\nfrom sklearn.model_selection import GridSearchCV\n\nparam_grid = {'svc__C':[1,5,10,50],\n             'svc__gamma':[1E-4,5E-4,1E-3,5E-3]}\ngrid = GridSearchCV(model, param_grid)\n\n%time grid.fit(X_norm, labeling)\nprint(grid.best_params_)\nmodel = grid.best_estimator_","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"ans_rbf=model.predict(X_norm)\n#print(\"training Runtime: %0.20f Seconds\"%(time.time()-start))\n\nprint(classification_report(labeling, ans_rbf))\n\n\n\n# 분류 결과 시각화를 원하면 주석을 삭제 할 것\nprint(\"Confusion matrix:\\n%s\" % metrics.confusion_matrix(labeling, ans_rbf))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"dataset_test = \"/kaggle/input/2019-fall-pr-project/test1/test1/\"\n\n\nfilename_test = os.listdir(dataset_test)\n\n\n\n#k = plt.imread(dataset_train)\nX_test = np.zeros([len(filename_test),32*32*3])\n\n\nfor i, name_t in tqdm(enumerate(filename_test), desc='Loading..'):\n    \n    image = plt.imread(dataset_test + name_t)\n    \n    image = cv2.resize(image,dsize=(32,32), interpolation=cv2.INTER_LANCZOS4)\n    #image = np.resize(image,[32,32,3])\n    image = image.reshape(-1)\n    X_test[i] = image","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_test = cv2.GaussianBlur(X_test,(5,5),0)\n\nfrom sklearn.preprocessing import StandardScaler\n\n\nscaler = StandardScaler()\nscaler.fit(X_test)\nX_norm_t = scaler.transform(X_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_norm_t","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\nresult = model.predict(X_norm_t)\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"result.reshape(-1,1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import pandas as pd\n\n\nresult = result.reshape(-1,1)\nprint(result.shape)\ndf = pd.DataFrame(result, columns=[\"label\"])\ndf.index = np.arange(1,len(df)+1)\ndf.index.name = 'id'\n\ndf.to_csv('results-jwon-v2.csv',index=True, header=True)\n!kaggle competitions submit -c 2019-fall-pr-project -f results-jwon-v2.csv -m \"jwon-181029\"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","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}