{"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":"import pandas as pd\nimport numpy as np\nimport cv2\nimport matplotlib.pyplot as plt\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import accuracy_score\nfrom sys import getsizeof","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train = pd.read_csv('../input/ava/train.csv', index_col=0)\ntest = pd.read_csv('../input/ava/test.csv', index_col=0)\ntrain","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train = train['image'].values\ny_train = train['label'].values\nX_test = test['image'].values","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"shapes = []\nfor i in range(len(X_train)):\n    path = '../input/ava/dataset/dataset/'+str(X_train[i])+'.jpg'\n    img = cv2.imread(path)\n    shapes.append(img.shape)\nshapes = np.array(shapes[:])\nprint(np.mean(shapes[:,0]), np.mean(shapes[:,1]), np.mean(shapes[:,2]))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"img_number = np.random.randint(len(X_train))\npath = '../input/ava/dataset/dataset/'+str(X_train[img_number])+'.jpg'\nimg = cv2.imread(path)\nimg = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)\nimg2 = cv2.resize(img, (500, 500), interpolation = cv2.INTER_AREA)\nfig, m_axs = plt.subplots(1, 2, figsize=(12, 5))\nax1, ax2 = m_axs\n\nax1.set_title('Original Image')\nax1.imshow(img, cmap='gray')\nax2.set_title('resized '+ str(y_train[img_number]))\nax2.imshow(img2);","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def get_feature(img):\n    img = cv2.resize(img, (32, 32), interpolation = cv2.INTER_AREA)\n    return np.array(img).flatten()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def create_features_data(image_names):\n    FEATURES = []\n    for i in range(len(image_names)):\n        path = '../input/ava/dataset/dataset/'+str(image_names[i])+'.jpg'\n        img = cv2.imread(path)\n        FEATURES.append(get_feature(img))\n    return np.array(FEATURES)\nfeatures_train = create_features_data(X_train)\nfeatures_test = create_features_data(X_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\nlr = LogisticRegression()\nlr.fit(features_train,y_train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# accuracy_score(lr.predict(features_test), y_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"prediction = pd.DataFrame()\nprediction['labels'] = lr.predict(features_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"prediction","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"prediction.to_csv(\"submittion.csv\", index_label='id')","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}