{"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":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"#importing necessary libraries\n\nimport pandas as pd\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport matplotlib.image as pltimg\nimport seaborn as sns\nimport missingno as msno\nsns.set()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train = pd.read_csv('/kaggle/input/digit-recognizer/train.csv')\ntest = pd.read_csv('/kaggle/input/digit-recognizer/test.csv')\n\ntrain","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train = train.drop(['label'],axis = 1)\ny_train = train['label']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_test = test","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Checking for null values in train and test set\n\nprint('Number of null values in training set is : ',train.isnull().sum().unique())\nprint('Number of null values in test set is : ',test.isnull().sum().unique())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.figure(figsize = (12,8))\nsns.distplot(y_train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#reshaping\nX_train_reshaped = X_train.values.reshape(-1,28,28,1)\nX_test_reshaped = X_test.values.reshape(-1,28,28,1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Normalising\nX_train_normalised = X_train_reshaped/255.\nX_test_normalised = X_test_reshaped/255.","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.figure(figsize = (15,15))\nfor i in range(25):\n    plt.subplot(5,5,i+1)\n    plt.imshow(X_train_normalised[i][:,:,0], cmap = 'gray')\n    plt.xticks([])\n    plt.yticks([])\n    plt.title('Label {}'.format(y_train[i]))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Encoding","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"from tensorflow.keras.utils import to_categorical","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# one hot encoding\ny_train_encoded = to_categorical(y_train, num_classes = 10)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#splitting the data\nfrom sklearn.model_selection import train_test_split\n\nX_train, X_test, y_train, y_test = train_test_split(X_train_normalised, y_train_encoded, test_size = 0.2, random_state = 42)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Model Building","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"from tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Dense, Conv2D, MaxPool2D\nfrom tensorflow.keras.layers import BatchNormalization,Flatten,Dropout\nfrom tensorflow.keras.callbacks import EarlyStopping,ReduceLROnPlateau","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# CNN\nmodel = Sequential([Conv2D(filters=32, kernel_size=(5,5), \\\n                           activation='relu', input_shape=(28,28,1)),\n    MaxPool2D(pool_size=(2,2)),\n    Conv2D(filters=64, kernel_size=(3,3), \\\n                           activation='relu', input_shape=(28,28,1)),\n    MaxPool2D(pool_size=(2,2), strides=(2,2)),\n    Flatten(),\n    Dense(256, activation='relu'),\n    Dense(10, activation='softmax')\n])\n\nmodel.compile(\n    optimizer='adam',\n    loss='categorical_crossentropy',\n    metrics=['accuracy']\n)\n\nmodel.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"callbacks = [ \n    EarlyStopping(monitor = 'loss', patience = 6), \n    ReduceLROnPlateau(monitor = 'loss', patience = 4)\n]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.fit(X_train,y_train,\n         batch_size = 64,\n         epochs = 100,\n         verbose = 1,\n         validation_data = (X_test,y_test),\n         callbacks = callbacks)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Metric on validation set\nscore = model.evaluate(X_test,y_test,verbose = 0)\nprint('The loss on validation set is {0} and the accuracy is {1}'.format(round(score[0],3),round(score[1],3)))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# predict results\nresults = model.predict(X_test_normalised)\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(\"submission.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}