{"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\nfrom sklearn.neighbors import KNeighborsClassifier\nfrom sklearn.model_selection import train_test_split\nimport numpy as np\nimport cv2 \nimport os\nimport pandas as pd\n\nfrom sklearn.svm import SVC\nfrom sklearn.decomposition import PCA as PCA\nfrom sklearn.model_selection import GridSearchCV\nfrom sklearn.pipeline import make_pipeline\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### 학습 데이터 준비"},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"dataset_train = \"../input/2019-fall-pr-project/train/train/\"\ntrain_data = [dataset_train + i for i in os.listdir(dataset_train)]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"images = []  #images\nlabels = []  #labels\n\nfor i in train_data:\n  image = cv2.imread(i)\n  image = cv2.resize(image, (32,32))\n  images.append(image)\n\nfor i in train_data:\n  if 'cat' in i:\n    labels.append(0)\n  elif 'dog' in i:\n    labels.append(1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X = np.array(images)\ny = np.array(labels)\nX = X.reshape(20001, -1)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### 데이터 셋 서브 샘플링 & Train-Validation 나누기"},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train, X_valid, y_train, y_valid = train_test_split(X, y, test_size=0.1, random_state=42)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### 학습 기반 분류기 설계"},{"metadata":{"trusted":true},"cell_type":"code","source":"pca = PCA(n_components=150, whiten=True, random_state=42)\nsvc = SVC(kernel='rbf', class_weight='balanced')\nmodel = make_pipeline(pca, svc)\n\nparam_grid = {'svc__C': [1, 5, 10, 50],\n              'svc__gamma': [0.0005, 0.001, 0.005, 0.01]}\ngrid = GridSearchCV(model, param_grid)\n\n%time grid.fit(X_train, y_train)\nprint(grid.best_params_)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### 테스트 데이터 준비"},{"metadata":{"trusted":true},"cell_type":"code","source":"dataset_test = \"../input/2019-fall-pr-project/test1/test1/\"\ntest_data = [dataset_test + i for i in os.listdir(dataset_test)]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"images = []\nlabels = []\n\nfor i in test_data:\n  image = cv2.imread(i)\n  image = cv2.resize(image, (32,32))\n  images.append(image)\n\nfor i in test_data:\n  if 'cat' in i:\n    labels.append(0)\n  elif 'dog' in i:\n    labels.append(1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_test = np.array(images)\ny_test = np.array(labels)\nX_test = X_test.reshape(5000, -1)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### 학습한 모델을 이용하여 테스트 데이터의 라벨 구하기"},{"metadata":{"trusted":true},"cell_type":"code","source":"model = grid.best_estimator_\nresult = model.predict(X_test)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### 결과 파일로 저장하여 Kaggle 제출 준비"},{"metadata":{"trusted":true},"cell_type":"code","source":"# numpy 를 Pandas 이용하여 결과 파일로 저장\n\nimport pandas as pd\n\nprint(result.shape)\ndf = pd.DataFrame(data=result, index=range(1,5001), columns=['label'])\ndf = df.replace('dog',1)\ndf = df.replace('cat',0)\n\ndf.to_csv('result.csv',index=True, header=True, index_label='id')","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}