{"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_minor":4,"nbformat":4,"cells":[{"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\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nimport tensorflow as tf\nfrom tensorflow import keras\nfrom tensorflow.keras import layers\nfrom tensorflow.keras.models import Sequential\nfrom keras.models import Sequential\nfrom keras.layers import Dense,Dropout,Flatten,Conv2D,MaxPool2D\nimport seaborn as sns\nimport matplotlib.pyplot as plt\nfrom keras.utils.np_utils import to_categorical\nfrom keras.optimizers import RMSprop\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom keras.callbacks import ReduceLROnPlateau\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import confusion_matrix\nimport itertools\n\n# Input data files are available in the read-only \"../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# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session.\n\ntrain = pd.read_csv(\"/kaggle/input/digit-recognizer/train.csv\")\n\nY_train = train[\"label\"]\nX_train = train.drop(labels = [\"label\"],axis = 1) \n\nX_train = X_train / 255.0\n\nX_train=X_train.values.reshape(-1,28,28,1)\n\nY_train=to_categorical(Y_train, num_classes=10)\n\nrandom_seed=213\n\nX_train,X_val,Y_train,Y_val = train_test_split(X_train,Y_train,test_size=0.15,random_state=random_seed)\n\nmodel = Sequential([\n    layers.Conv2D(16, kernel_size=(3, 3), padding='same', activation='relu', input_shape=(28, 28, 1)),\n    layers.Conv2D(32,  kernel_size=(3, 3), padding='same', activation='relu'),\n    layers.Conv2D(32,  kernel_size=(3, 3), padding='same', activation='relu'),\n    \n    layers.Flatten(),\n    layers.Dense(128, activation='relu'),\n    layers.Dropout(0.25, seed=213),\n    layers.Dense(128, activation='relu'),\n    layers.Dropout(0.25, seed=426),\n    layers.Dense(10, activation='softmax')\n])\n\noptimizer = RMSprop(lr=0.001)\n\nmodel.compile(optimizer=optimizer, loss=\"mse\", metrics=['mse', 'mae'])\n\ncallbacks = [tf.keras.callbacks.EarlyStopping(patience=10, monitor='val_loss')]\n\nhistory = model.fit(x=X_train, y=Y_train, batch_size=1000, epochs=100, validation_data=(X_val, Y_val), callbacks=callbacks)\n\nhist = pd.DataFrame(history.history)\nhist['epoch'] = history.epoch\n\nplt.figure()\nplt.xlabel('Epoch')\nplt.ylabel('MAE')\nplt.plot(hist['epoch'], hist['mae'],\n         label='Train Error')\nplt.plot(hist['epoch'], hist['val_mae'],\n         label='Val Error')\nplt.ylim([0, 100])\nplt.legend()\n\nplt.figure()\nplt.xlabel('Epoch')\nplt.ylabel('MSE')\nplt.plot(hist['epoch'], hist['mse'],\n         label='Train Error')\nplt.plot(hist['epoch'], hist['val_mse'],\n         label='Val Error')\nplt.ylim([0, 5000])\nplt.legend()\nplt.show()\n\ntest_df = pd.read_csv('/kaggle/input/digit-recognizer/test.csv')\ntest_X = np.array(test_df)\ntest_X = test_X / 255\n\ntest_X = test_X.reshape(-1,28,28,1)\nfinal_pred = model.predict(test_X)\n\nnumbers = final_pred.argmax(axis=1)\n\nfinal_df = pd.DataFrame(numbers, columns=['Label'])\nImageId = np.array(final_df.index) + 1\nfinal_df['ImageId'] = ImageId\n\nfinal_df.to_csv('final.csv', index=False)","metadata":{"execution":{"iopub.status.busy":"2021-09-04T09:27:11.088126Z","iopub.execute_input":"2021-09-04T09:27:11.088851Z","iopub.status.idle":"2021-09-04T10:10:00.926246Z","shell.execute_reply.started":"2021-09-04T09:27:11.088792Z","shell.execute_reply":"2021-09-04T10:10:00.924811Z"},"trusted":true},"execution_count":null,"outputs":[]}]}