{"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\nimport matplotlib.pyplot as plt\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":{"trusted":true},"cell_type":"code","source":"WIDTH=137\nHEIGHT=236\nBATCHSIZE = 36\nVALIDATION_SIZE = .2","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"train = pd.read_csv(\"/kaggle/input/bengaliai-cv19/train.csv\")\np1 = pd.read_parquet(\"/kaggle/input/bengaliai-cv19/test_image_data_0.parquet\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"parquet_file = \"/kaggle/input/bengaliai-cv19/train_image_data_1.parquet\"\n\n# def process_parquet(parquet_file):\nparquet = pd.read_parquet(parquet_file).iloc[:,:]\n# print(parquet.shape)\nlabels = pd.DataFrame(parquet.iloc[:,0]).merge(train, on = 'image_id', how = 'left')\nimg = parquet.iloc[:,1:].values.reshape(-1, WIDTH, HEIGHT)#.astype(float)\n\nprint(img.shape)\nprint(labels.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"rows = 3\ncolumns = 3\nn_plots = rows*columns\n\nf, ax = plt.subplots(rows,columns, figsize = [25,15])\nfor i, img_i in enumerate(np.random.choice(img.shape[0], n_plots)):\n    ax = plt.subplot(rows, columns, i+1)\n    ax.imshow(img[img_i,:,:], cmap='gray', vmin=0, vmax=255)\n    ax.set_title(\" \".join([f\"{x1}: {x2}\\n\" for x1,x2 in labels.iloc[img_i,:].to_dict().items()]))\nplt.tight_layout(pad=0)\nplt.show()","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":4}