{"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)\nimport seaborn as sns\nimport matplotlib.pyplot as plt \nimport warnings \nwarnings.filterwarnings('ignore')\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 the files in the input directory\n\nimport os\nprint(os.listdir(\"../input\"))\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"train = pd.read_csv(\"../input/train.csv\")\nprint(train.shape)\ntrain.head(10)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test = pd.read_csv(\"../input/test.csv\")\nprint(test.shape)\ntest.head(10)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_train = train[\"label\"]\nx_train = train.drop(labels = [\"label\"],axis=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train = x_train/255.0\ntest = test/255.0","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(\"x_train shape\",x_train.shape)\nprint(\"test shape\",test.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train = x_train.values.reshape(-1,28,28,1)\ntest = test.values.reshape(-1,28,28,1)\nprint(\"x_train shape\",x_train.shape)\nprint(\"test shape\",test.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.utils.np_utils import to_categorical\ny_train = to_categorical(y_train,num_classes = 10)\nprint(y_train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.model_selection import train_test_split\nx_train,x_val,y_train,y_val = train_test_split(x_train,y_train,test_size=0.15,random_state=2)\nprint(\"x_train shape\",x_train.shape)\nprint(\"x_test shape\",x_val.shape)\nprint(\"y_train shape\",y_train.shape)\nprint(\"y_test shape\",y_val.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.imshow(x_train[4][:,:,0],cmap = 'gray')\nplt.show()\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.metrics import confusion_matrix\nimport itertools\nfrom keras.utils.np_utils import to_categorical \nfrom keras.models import Sequential\nfrom keras.layers import Dense,Dropout,Flatten,Conv2D,MaxPool2D\nfrom keras.optimizers import RMSprop,Adam\nfrom keras.callbacks import ReduceLROnPlateau\nfrom keras.preprocessing.image import ImageDataGenerator\n\nmodel = Sequential()\nmodel.add(Conv2D(filters=8,kernel_size=(5,5),padding = 'Same',activation='relu',input_shape=(28,28,1)))\nmodel.add(MaxPool2D(pool_size=(2,2)))\nmodel.add(Dropout(0.25))\n\nmodel.add(Conv2D(filters = 16, kernel_size = (3,3),padding='Same',activation='relu'))\nmodel.add(MaxPool2D(pool_size=(2,2),strides=(2,2)))\nmodel.add(Dropout(0.25))\n\nmodel.add(Flatten())\nmodel.add(Dense(256,activation=\"relu\"))\nmodel.add(Dropout(0.5))\nmodel.add(Dense(10,activation=\"softmax\"))\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"optimizer = Adam(lr = 0.001,beta_1 =0.9,beta_2=0.999)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.compile(optimizer=optimizer,loss = \"categorical_crossentropy\",metrics=[\"accuracy\"])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"epochs = 20\nbatch_size = 250","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"datagen = ImageDataGenerator()\ndatagen.fit(x_train)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"history = model.fit_generator(datagen.flow(x_train,y_train, batch_size=batch_size),\n                              epochs = epochs, validation_data = (x_val,y_val), steps_per_epoch=x_train.shape[0] // batch_size)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.plot(history.history['val_loss'],color = 'r',label = \"validation loss\")\nplt.title(\"Validation loss\")\nplt.xlabel(\"Epochs\")\nplt.ylabel(\"Loss\")\nplt.legend()\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"raw","source":""}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.4","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}