{"cells":[{"metadata":{"trusted":true},"cell_type":"code","source":"! kaggle competitions download -c 2019-fall-pr-project\n\n\nimport zipfile\nimport os\n\nos.mkdir('/content/input2')\n\nzip_ref = zipfile.ZipFile(\"/content/2019-fall-pr-project.zip\", 'r')\nzip_ref.extractall(\"/content/input2\")\nzip_ref.close()","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\nfrom imutils import paths\nimport numpy as np\nimport imutils \nimport cv2 \nimport os\nimport argparse\n\n\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def image_to_feature_vector(image, size=(32, 32)):\n    return cv2.resize(image, size).flatten()\n\ndataset_train = \"/content/input2/train/\"\n\nprint(\"[INFO] describing images...\")\nimagePaths = list(paths.list_images(dataset_train))\n\nprint(len(imagePaths))\n# initialize the raw pixel intensities matrix, the features matrix,\n# and labels list\nrawImages = []\nlabels = []\nfor (i, imagePath) in enumerate(imagePaths):\n\t# load the image and extract the class label (assuming that our\n\t# path as the format: /path/to/dataset/{class}.{image_num}.jpg\n\n    image = cv2.imread(imagePath)\n    label = imagePath.split(os.path.sep)[-1].split(\".\")[0]\n \n# extract raw pixel intensity \"features\", followed by a color\n\t# histogram to characterize the color distribution of the pixels\n\t# in the image\n\n    pixels = image_to_feature_vector(image)\n    \n \n# update the raw images, features, and labels matricies,\n\t# respectively\n    rawImages.append(pixels)\n    labels.append(label)\n \n# show an update every 1,000 images\n    if i > 0 and i % 1000 == 0:\n        print(\"[INFO] processed {}/{}\".format(i, len(imagePaths)))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\nrawImages = np.array(rawImages)\nlabels = np.array(labels)\n\nprint(\"[INFO] pixels matrix: {:.2f}MB\".format(\nrawImages.nbytes / (1024 * 1000.0)))\nbUseCompleteDataset = False\nif bUseCompleteDataset:\n    (trainRI, testRI, trainRL, testRL) = train_test_split(rawImages, labels, test_size=0.25, random_state=42)\nelse:\n    rawImages_subset = rawImages[:2000]\n    labels_subset = labels[:2000]\n    (trainRI, testRI, trainRL, testRL) = train_test_split(rawImages_subset, labels_subset, test_size=0.25, random_state=42)\n\n\n\n\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# train and evaluate a k-NN classifer on the raw pixel intensities\n\nprint(\"[INFO] evaluating raw pixel accuracy...\")\nneighbors = [1, 3, 5, 7, 13]\n\nfor k in neighbors:\n    model = KNeighborsClassifier(n_neighbors= 5)\n    a=model.fit(trainRI, trainRL)\n    acc = model.score(testRI, testRL)\n    print(\"[INFO] raw pixel accuracy: {:.2f}%\".format(acc * 100))\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"dataset_test = \"/content/input2/test1/\"\n\nimagePaths_test=list(paths.list_images(dataset_test))\n\nprint(len(imagePaths_test))\nrawImages_test=[]\nlabels_test=[]\n\nfor(i,imagePath_test) in enumerate(imagePaths_test):\n    image=cv2.imread(imagePath_test)\n    label=imagePath_test.split(os.path.sep)[-1].split(\".\")[0]\n\n    pixels=image_to_feature_vector(image)\n\n    rawImages_test.append(pixels)\n    labels_test.append(label)\n\n\n    if i>0 and i%1000==0:\n      print(\"[INFO] processed {}/{}\".format(i,len(imagePaths_test)))\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = KNeighborsClassifier(n_neighbors= 5)\na=model.fit(trainRI, trainRL)\nresult=a.predict(rawImages_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#numpy 를 Pandas 이용하여 결과 파일로 저장\nimport pandas as pd\n\n\nresult=np.reshape(result,(-1,1))\n\nprint(result.shape)\ndf = pd.DataFrame(result, columns=[\"label\"])\ndf.index.name = 'id'\ndf.index += 1\ndf = df.replace('dog',1)\ndf = df.replace('cat',0)\ndf = df.rename({'1':'id','0':'label'})\ndf.to_csv('sungbin-v2.csv',index=True, header=True)","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}