{"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)\nfrom sklearn.model_selection import train_test_split\nimport tensorflow as tf\nfrom tensorflow import keras\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Dense, Dropout, Flatten, Conv2D, MaxPool2D\nfrom tensorflow.keras.optimizers import RMSprop\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom tensorflow.keras.utils import to_categorical\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\ntrain=pd.read_csv(\"/kaggle/input/digit-recognizer/train.csv\")\ntest=pd.read_csv(\"/kaggle/input/digit-recognizer/test.csv\")\n# Any results you write to the current directory are saved as output.\n","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"Ytrain=train[\"label\"]\nXtrain=train.drop(labels=[\"label\"],axis=1)\nYtrain.value_counts()\ntrain.info()\nXtrain.isnull().any().describe()\ntest.isnull().any().describe()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Xtrain=Xtrain/255\ntest=test/255\nYtrain=keras.utils.to_categorical(Ytrain,num_classes=10)\n\nXtrain = Xtrain.values.reshape(-1,28,28,1)\ntest = test.values.reshape(-1,28,28,1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"random_seed = 1\nXtrain, Xval, Ytrain, Yval = train_test_split(Xtrain, Ytrain, test_size = 0.1, random_state=random_seed)\nprint(Xtrain.shape)\nprint(Ytrain.shape)\nprint(Xval.shape)\nprint(Yval.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_datagen = ImageDataGenerator(\n    rotation_range=10,\n    width_shift_range=0.1,\n    height_shift_range=0.1,\n    shear_range=0.1,\n    zoom_range = 0.1,\n    horizontal_flip=True)\n\ntrain_datagen.fit(Xtrain)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = keras.Sequential()\n\nmodel.add(Conv2D(filters = 32, kernel_size = (3,3),padding = 'Same', \n                 activation ='relu', input_shape = (28,28,1)))\n\nmodel.add(MaxPool2D(pool_size=(2,2)))\nmodel.add(Dropout(0.20))\n\nmodel.add(Conv2D(filters = 64, kernel_size = (3,3),padding = 'Same', \n                 activation ='relu'))\n\n\nmodel.add(MaxPool2D(pool_size=(2,2), strides=(2,2)))\nmodel.add(Dropout(0.20))\n\nmodel.add(Conv2D(filters = 64, kernel_size = (3,3),activation ='relu'))\nmodel.add(Conv2D(filters = 64, kernel_size = (3,3),padding = 'Same', \n                 activation ='relu'))\nmodel.add(Dropout(0.20))\n\nmodel.add(Flatten())\nmodel.add(Dense(256, activation = \"relu\"))\nmodel.add(Dropout(0.5))\nmodel.add(Dense(10, activation = \"softmax\"))\n\nmodel.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.compile(optimizer = tf.optimizers.Adam(),\n              loss = 'categorical_crossentropy',\n              metrics=['accuracy'])\nbatch_size = 64\nepochs=30\n# history = model.fit(Xtrain, Ytrain, batch_size = batch_size, epochs = epochs, \n#           validation_data = (Xval, Yval), verbose = 2)\n\nhistory = model.fit_generator(train_datagen.flow(Xtrain,Ytrain, batch_size=batch_size),\n                              epochs = epochs, validation_data = (Xval,Yval),\n                              verbose = 2)\nplt.plot(history.history['accuracy'])\nplt.plot(history.history['val_accuracy'])\nplt.title('model accuracy')\nplt.ylabel('accuracy')\nplt.xlabel('epoch')\nplt.legend(['train', 'test'], loc='upper left')\nplt.show()\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\n# predict results\nresults = model.predict(test)\n\n# select the indix with the maximum probability\nresults = np.argmax(results,axis = 1)\n\nresults = pd.Series(results,name=\"Label\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission = pd.concat([pd.Series(range(1,28001),name = \"ImageId\"),results],axis = 1)\n\nsubmission.to_csv(\"cnn_mnist_datagen.csv\",index=False)","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}