{"cells":[{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"# Data manipulation/analysis\nimport numpy as np\nimport keras \nimport pandas as pd\nimport tensorflow as tf\n\n#Processing input\nfrom keras.utils.np_utils import to_categorical\nfrom sklearn.model_selection import train_test_split\nfrom keras.preprocessing.image import ImageDataGenerator\n\n# Modelling\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Dense, Conv2D, Flatten, Dropout, MaxPooling2D, BatchNormalization\nfrom keras.initializers import glorot_uniform\nfrom keras.optimizers import SGD , Adam\nfrom keras.callbacks import LearningRateScheduler\n\n#Visualization\nimport seaborn as sns\n%matplotlib inline\nsns.set(style='white', context='notebook', palette='deep')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# **Loading and understanding data**"},{"metadata":{"trusted":true},"cell_type":"code","source":"train_data = pd.read_csv('../input/digit-recognizer/train.csv')\ntest_data = pd.read_csv('../input/digit-recognizer/test.csv')\nprint(train_data.head())","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# **Spitting train data into input and labels**"},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train = train_data.drop('label',axis = 1)\nY_train = train_data['label']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"distribution = sns.countplot(Y_train)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# **Reshaping and normalizing input data**"},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train = X_train.values.reshape(-1,28,28,1)\nX_test = test_data.values.reshape(-1,28,28,1)\n\nprint(X_train.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train = X_train / 255.0\nX_test = X_test / 255.0","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# **Label Encoding**"},{"metadata":{"trusted":true},"cell_type":"code","source":"Y_train = to_categorical(Y_train, num_classes = 10)\nprint(Y_train.shape)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# **Splitting data to obtain the validation data set**"},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train, X_val, Y_train, Y_val = train_test_split(X_train, Y_train, test_size = 0.1)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# **Data augmentation**"},{"metadata":{"trusted":true},"cell_type":"code","source":"data_aug = ImageDataGenerator(rotation_range=10,zoom_range = 0.1, width_shift_range=0.1, height_shift_range=0.1)  \n\ndata_aug.fit(X_train)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# **Creating the CNN**"},{"metadata":{"trusted":true},"cell_type":"code","source":"model = keras.Sequential([\n    tf.keras.layers.Conv2D(16, (3,3), activation='relu', input_shape=(28,28, 1)),\n    tf.keras.layers.BatchNormalization(),\n    tf.keras.layers.Conv2D(16, (3,3), activation='relu'),\n    tf.keras.layers.BatchNormalization(),\n    tf.keras.layers.Conv2D(16, (3,3), activation='relu'),\n    tf.keras.layers.BatchNormalization(),\n    tf.keras.layers.Conv2D(16, (3,3), activation='relu'),\n    tf.keras.layers.BatchNormalization(),\n    tf.keras.layers.MaxPooling2D(2,2),\n    tf.keras.layers.Dropout(0.25),\n    \n    tf.keras.layers.Conv2D(32, (3,3), activation='relu'),\n    tf.keras.layers.BatchNormalization(),\n    tf.keras.layers.Conv2D(32, (3,3), activation='relu'),\n    tf.keras.layers.BatchNormalization(),\n    tf.keras.layers.Conv2D(32, (3,3), activation='relu'),\n    tf.keras.layers.BatchNormalization(),\n    tf.keras.layers.Conv2D(32, (3,3), activation='relu'),\n    tf.keras.layers.BatchNormalization(),\n    tf.keras.layers.MaxPooling2D(2,2),\n    tf.keras.layers.Dropout(0.3),\n    \n    tf.keras.layers.Flatten(),    \n    tf.keras.layers.Dense(512,activation= 'relu'),\n    tf.keras.layers.Dropout(0.3),\n    tf.keras.layers.Dense(1024,activation= 'relu'),\n    tf.keras.layers.Dropout(0.4),\n    tf.keras.layers.Dense(10,activation= 'softmax')])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.compile(loss='categorical_crossentropy', optimizer = Adam(lr=1e-4), metrics=[\"accuracy\"])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"annealer = LearningRateScheduler(lambda x: 1e-3 * 0.9 ** x)\nhistory = model.fit_generator(data_aug.flow(X_train, Y_train, batch_size=16),steps_per_epoch=500,epochs=20, verbose=2, validation_data=(X_val,Y_val),callbacks=[annealer])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# **Submission**"},{"metadata":{"trusted":true},"cell_type":"code","source":"output = model.predict(X_test, batch_size=64)\nY_pred = np.argmax(output,axis=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"results = pd.Series(Y_pred,name=\"Label\")\n\nsubmission = 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}