{"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":{"trusted":true},"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom tensorflow.keras.layers import Conv2D, MaxPool2D, BatchNormalization, Dropout, GlobalAveragePooling2D, GlobalAveragePooling2D, Dense\nfrom tqdm import tqdm\nfrom tensorflow.keras.models import Model\n\nfrom tensorflow.keras.losses import categorical_crossentropy, sparse_categorical_crossentropy, categorical_crossentropy\nfrom tensorflow.keras.optimizers import Adam\nfrom tensorflow.keras.callbacks import EarlyStopping, ModelCheckpoint, ReduceLROnPlateau\n\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.utils import shuffle\nimport cv2\nimport gc","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"_kg_hide-output":true,"trusted":true},"cell_type":"code","source":"\n# for i in range(1):\n#     df_test1 = pd.read_parquet(\"test_image_data_0.parquet\")\n#     df_test2 = pd.read_parquet(\"test_image_data_1.parquet\")\n\n#     df_test3 = pd.read_parquet(\"test_image_data_2.parquet\")\n\n#     df_test4  = pd.read_parquet(\"test_image_data_3.parquet\")\n# df_test = pd.concat([df_test1, df_test2, df_test3, df_test4 ], axis = 0)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_class_map = pd.read_csv(\"/kaggle/input/bengaliai-cv19/\" + \"class_map.csv\")\ndf_test_csv = pd.read_csv(\"/kaggle/input/bengaliai-cv19/\"+ \"test.csv\")\ndf_train_csv = pd.read_csv(\"/kaggle/input/bengaliai-cv19/\" + \"train.csv\")\ndf_submission = pd.read_csv(\"/kaggle/input/bengaliai-cv19/\" + \"sample_submission.csv\")","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"Temp = np.empty((0, 64, 64,1))\nTemp_Label = np.empty((0,1))\n\n\ndef Train_Data_Prepration(Temp = Temp, Temp_Label = Temp_Label):\n\n    for i in [\"train_image_data_0.parquet\", \"train_image_data_1.parquet\", \"train_image_data_2.parquet\", \"train_image_data_3.parquet\"]:\n        \n        df_train1 = pd.read_parquet(\"/kaggle/input/bengaliai-cv19/\" + i)\n\n        df_train1 = shuffle(df_train1)\n\n        Label = df_train1[['image_id']]\n                                    \n        df_train = df_train1.iloc[:, 1:].values\n\n        del df_train1\n        gc.collect()\n\n        Array = np.empty((len(df_train), 64, 64,1))\n\n        for i in tqdm(range(len(df_train))):\n            a = df_train[i, :].reshape(137,236)#\n            b = a.copy()\n            a[a > 230] = 255\n            b = b[:, ~np.all(a[1:] == a[:-1], axis=0)]\n            b = b.T\n            a = a[:, ~np.all(a[1:] == a[:-1], axis=0)]\n            a = a.T\n            b = b[:, ~np.all(a[1:] == a[:-1], axis=0)]\n            b = b.T\n            Array[i,:,:,0] = cv2.resize(b , (64,64))\n\n        del a, b, df_train\n        gc.collect()\n\n        Temp = np.concatenate((Temp, Array), axis = 0)\n\n        Temp_Label = np.concatenate((Temp_Label, Label.values), axis = 0)\n        \n    return Temp, Temp_Label\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Temp, Temp_Label = Train_Data_Prepration()\nTemp = Temp.astype('uint8')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Final_data1 = np.concatenate((Temp, Temp, Temp), axis = 3)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_y = pd.DataFrame(Temp_Label, columns = ['image_id'])\n\ndf_y_new = pd.merge(df_y, df_train_csv, on = 'image_id', how = 'left')\n\ny_train_168 = df_y_new.grapheme_root\n\ny_train_11 = df_y_new.vowel_diacritic\ny_train_7 = df_y_new.consonant_diacritic\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_y_new.to_csv(\"Label.csv\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_y_new.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"np.save('Y_train.npy', Temp_Label)\nnp.save('X_train2_3_Channel.npy', Final_data1)\n","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}