{"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\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 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 5GB 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","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import matplotlib.pyplot as plt","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"train = pd.read_csv(\"../input/digit-recognizer/train.csv\")\ntest = pd.read_csv(\"../input/digit-recognizer/test.csv\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_submission = pd.read_csv('../input/digit-recognizer/sample_submission.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train = train.drop(['label'], axis = 1)\ny_train = train['label']\nX_test = test\nX_train = X_train / 255.0\nX_test = X_test / 255.0","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train.shape, y_train.shape, X_test.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train=X_train.values\nX_test=X_test.values\ntest=test.values\n\n\n\nX_train=X_train.reshape(X_train.shape[0], 28, 28, 1)\nX_test=X_test.reshape(X_test.shape[0], 28, 28, 1)\ntest=test.reshape(test.shape[0] , 28 , 28 , 1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train.shape, y_train.shape, X_test.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train.max(), X_train.min()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import tensorflow as tf\nfrom tensorflow.keras.layers import Dense, Flatten, Conv2D, MaxPool2D, Dropout\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.callbacks import EarlyStopping","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"input_shape = X_train[0].shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"early_stop = EarlyStopping(monitor = 'val_loss', mode = 'min', verbose = 2, patience = 0)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model1 = Sequential()\nmodel1.add(Conv2D(filters = 32, kernel_size = (3,3), padding = 'valid', activation = 'relu', input_shape = input_shape))\nmodel1.add(Conv2D(filters = 64, kernel_size = (3,3), padding = 'valid', activation = 'relu'))\nmodel1.add(MaxPool2D(pool_size=(2,2)))\nmodel1.add(Dropout(0.25))\n\nmodel1.add(Conv2D(filters = 96, kernel_size = (3,3), padding = 'valid', activation = 'relu'))\nmodel1.add(Conv2D(filters = 128, kernel_size = (5,5), padding = 'valid', activation = 'relu'))\nmodel1.add(MaxPool2D(pool_size=(3,3)))\nmodel1.add(Dropout(0.33))\n\nmodel1.add(Flatten())\nmodel1.add(Dense(128, activation='relu'))\nmodel1.add(Dropout(0.50))\nmodel1.add(Dense(10, activation='softmax'))\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model1.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model1.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model1.fit(X_train, y_train, epochs = 100, batch_size = 64, verbose = 1, callbacks = [early_stop], shuffle = True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"predictions1 = model1.predict(X_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model2 = Sequential()\nmodel2.add(Conv2D(filters = 32, kernel_size = (3,3), padding = 'valid', activation = 'relu', input_shape = input_shape))\nmodel2.add(MaxPool2D(pool_size=(2,2)))\nmodel2.add(Dropout(0.25))\n\nmodel2.add(Conv2D(filters = 64, kernel_size = (3,3), padding = 'valid', activation = 'relu'))\nmodel2.add(Conv2D(filters = 64, kernel_size = (3,3), padding = 'valid', activation = 'relu'))\nmodel2.add(MaxPool2D(pool_size=(2,2)))\nmodel2.add(Dropout(0.33))\n\nmodel2.add(Conv2D(filters = 128, kernel_size = (3,3), padding = 'valid', activation = 'relu'))\nmodel2.add(MaxPool2D(pool_size=(2,2)))\nmodel2.add(Dropout(0.4))\n\nmodel2.add(Flatten())\nmodel2.add(Dense(1024, activation='relu'))\nmodel2.add(Dropout(0.50))\nmodel2.add(Dense(10, activation='softmax'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model2.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model2.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model2.fit(X_train, y_train, epochs = 100, batch_size = 128, verbose = 1, callbacks = [early_stop], shuffle = True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"predictions2 = model1.predict(X_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model3 = Sequential()\nmodel3.add(Conv2D(filters = 32, kernel_size = (3,3), padding = 'valid', activation = 'relu', input_shape = input_shape))\nmodel3.add(Conv2D(filters = 32, kernel_size = (3,3), padding = 'valid', activation = 'relu'))\nmodel3.add(Dropout(0.25))\n\nmodel3.add(Conv2D(filters = 64, kernel_size = (3,3), padding = 'valid', activation = 'relu'))\nmodel3.add(Conv2D(filters = 64, kernel_size = (3,3), padding = 'valid', activation = 'relu'))\nmodel3.add(MaxPool2D(pool_size=(2,2)))\nmodel3.add(Dropout(0.33))\n\nmodel3.add(Conv2D(filters = 96, kernel_size = (3,3), padding = 'valid', activation = 'relu'))\nmodel3.add(Conv2D(filters = 96, kernel_size = (3,3), padding = 'valid', activation = 'relu'))\nmodel3.add(MaxPool2D(pool_size=(2,2)))\nmodel3.add(Dropout(0.4))\n\nmodel3.add(Flatten())\nmodel3.add(Dense(512, activation='relu'))\nmodel3.add(Dropout(0.50))\nmodel3.add(Dense(1024, activation='relu'))\nmodel3.add(Dropout(0.50))\nmodel3.add(Dense(10, activation='softmax'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model3.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model3.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model3.fit(X_train, y_train, epochs = 100, batch_size = 128, verbose = 1, callbacks = [early_stop], shuffle = True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"predictions3 = model1.predict(X_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"predictions = (predictions1 + predictions2 + predictions3)/3\nPredictions = []\nfor i in range (0, len(predictions)):\n    Predictions.append(predictions[i].argmax())\nid = []\nfor i in range(1, len(Predictions)+1):\n    id.append(i)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"output = pd.DataFrame({'ImageId': id, 'Label': Predictions})\noutput.to_csv('my_submission.csv', index=False)\nprint(\"Your submission was successfully saved!\")\n","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}