{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"'''import os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))'''","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# IMPORTING LIBRARIES","execution_count":null},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nimport matplotlib.pyplot as plt\n%matplotlib inline\nimport seaborn as sns\nimport tensorflow as tf","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# LOADING DATA","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"df_train = pd.read_csv(\"/kaggle/input/digit-recognizer/train.csv\") #../input/digit-recognizer/train.csv\ndf_test = pd.read_csv(\"/kaggle/input/digit-recognizer/test.csv\")\ndf_submission = pd.read_csv(\"/kaggle/input/digit-recognizer/sample_submission.csv\")","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## -> GETTING VIEW OF SUBMISSION FILE","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"df_submission","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# EDA","execution_count":null},{"metadata":{},"cell_type":"markdown","source":"#### Looking into data","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"display(\"Train File\", df_train.head())\ndisplay(\"Test File\", df_test.head())","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"#### Shape of files","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"print(\"Train File\", df_train.shape)\nprint(\"Test File\", df_test.shape)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"#### Checking for NULL values","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"print(\"Train File\", df_train.isnull().any().sum())\nprint(\"Test File\", df_test.isnull().any().sum())","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"#### Data description","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"display(\"Train File\", df_train.describe())\ndisplay(\"Test File\", df_test.describe())","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"#### Label plot","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.countplot(df_train['label'])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Preprocessing","execution_count":null},{"metadata":{},"cell_type":"markdown","source":"#### Segregating Data","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"y_train = df_train['label'].astype('float32')\nX_train = df_train.drop(['label'], axis=1).astype('int32')\nX_test = df_test.astype('float32')\nX_train.shape, y_train.shape, X_test.shape","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"#### Normalizing Data","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train = X_train/255\nX_test = X_test/255","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"#### Reshaping data(as images)","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train = X_train.values.reshape(-1,28,28,1)\nX_test = X_test.values.reshape(-1,28,28,1)\nX_train.shape , X_test.shape","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"#### One Hot Encoding","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.utils.np_utils import to_categorical\ny_train = to_categorical(y_train, num_classes = 10)\ny_train.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.model_selection import train_test_split\nX_train, X_cv, y_train, y_cv = train_test_split(X_train, y_train, test_size = 0.1, random_state=42)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"#### Model Preparation Libraries","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.layers import Input,InputLayer, Dense, Activation, ZeroPadding2D, BatchNormalization, Flatten, Conv2D\nfrom keras.layers import AveragePooling2D, MaxPooling2D, Dropout\nfrom keras.models import Sequential,Model\nfrom keras.optimizers import SGD\nfrom keras.callbacks import ModelCheckpoint,LearningRateScheduler\nimport keras\nfrom keras import backend as K","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"#### Model Layers","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"# Building a CNN model\ninput_shape = (28,28,1)\nX_input = Input(input_shape)\n\n# layer 1\nx = Conv2D(64,(3,3),strides=(1,1),name='layer_conv1',padding='same')(X_input)\nx = BatchNormalization()(x)\nx = Activation('relu')(x)\nx = MaxPooling2D((2,2),name='maxPool1')(x)\n# layer 2\nx = Conv2D(32,(3,3),strides=(1,1),name='layer_conv2',padding='same')(x)\nx = BatchNormalization()(x)\nx = Activation('relu')(x)\nx = MaxPooling2D((2,2),name='maxPool2')(x)\n# layer 3\nx = Conv2D(32,(3,3),strides=(1,1),name='conv3',padding='same')(x)\nx = BatchNormalization()(x)\nx = Activation('relu')(x)\nx = MaxPooling2D((2,2), name='maxPool3')(x)\n# fc\nx = Flatten()(x)\nx = Dense(64,activation ='relu',name='fc0')(x)\nx = Dropout(0.25)(x)\nx = Dense(32,activation ='relu',name='fc1')(x)\nx = Dropout(0.25)(x)\nx = Dense(10,activation ='softmax',name='fc2')(x)\n\nconv_model = Model(inputs=X_input, outputs=x, name='Predict')\nconv_model.summary()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"#### Adam Optimizer (it converges more efficiently)","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"# Adam optimizer\nconv_model.compile(optimizer='adam',loss='categorical_crossentropy',metrics=['accuracy'])\nconv_model.fit(X_train, y_train, epochs=10, batch_size=100, validation_data=(X_cv,y_cv))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"#### Predicting labels and saving in csv file","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"y_pred = conv_model.predict(X_test)\ny_pred = np.argmax(y_pred,axis=1)\nmy_submission = pd.DataFrame({'ImageId': list(range(1, len(y_pred)+1)), 'Label': y_pred})\nmy_submission.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}