{"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 20GB 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":"train = pd.read_csv('/kaggle/input/digit-recognizer/train.csv')\ntest = pd.read_csv('/kaggle/input/digit-recognizer/test.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import tensorflow as tf\nfrom tensorflow.keras import layers\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x = np.array(train.drop('label', axis=1))/255\ny = np.array(train['label'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x=x.reshape((-1,28,28,1))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.model_selection import train_test_split\n\nx_train,x_test,y_train,y_test = train_test_split(x,y,test_size=0.2)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data_gen = ImageDataGenerator(\n            rotation_range=12,\n            width_shift_range=0.12,\n            height_shift_range=0.12,\n            shear_range=0.12,\n            validation_split=0.2,)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"training_generator = data_gen.flow(x_train,y_train,batch_size=32,subset='training')\nvalidation_generator = data_gen.flow(x_test,y_test,batch_size=32,subset='validation')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import matplotlib.pyplot as plt\n\nplt.figure(figsize=(10,5))\nfor i in range(6):\n    plt.subplot(2,3,i+1)\n    for x,y in training_generator:\n        plt.imshow((x[0]/255).reshape(28,28),cmap='gray')\n        plt.title('y={}'.format(y[0]))\n        plt.axis('off')\n        break\nplt.tight_layout()\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Convolutional Neural Network"},{"metadata":{"trusted":true},"cell_type":"code","source":"cnn = tf.keras.Sequential([\n    \n    layers.Conv2D(32,(3,3),input_shape=(28,28,1),padding='same',activation='relu'),\n    layers.BatchNormalization(),\n    layers.MaxPool2D(2,2),\n    layers.Dropout(0.3),\n    \n    layers.Conv2D(64,(3,3),activation='relu',padding='same'),\n    layers.BatchNormalization(),\n    layers.MaxPool2D(2,2),\n    layers.Dropout(0.3),\n    \n    layers.Conv2D(128,(3,3),activation='relu',padding='same'),\n    layers.BatchNormalization(),\n    layers.MaxPool2D(2,2),\n    layers.Dropout(0.3),\n    \n    layers.Conv2D(256,(3,3),activation='relu',padding='same'),\n    layers.BatchNormalization(),\n    layers.MaxPool2D(2,2),\n    layers.Dropout(0.5),\n    \n    layers.Flatten(),\n    layers.Dense(256,activation='relu'),\n    layers.BatchNormalization(),\n    layers.Dropout(0.5),\n    layers.Dense(10,activation='softmax')\n])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"cnn.compile(optimizer='adam',\n            loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),\n            metrics=['accuracy']\n           )","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"history_cnn = cnn.fit_generator(training_generator,epochs=100,validation_data=validation_generator)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.plot(history_cnn.history['accuracy'])\nplt.plot(history_cnn.history['val_accuracy'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.plot(history_cnn.history['loss'])\nplt.plot(history_cnn.history['val_loss'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"cnn.evaluate( x_test, y_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pred_test_data = np.array(test).reshape((-1,28,28,1))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"predictions_cnn = cnn.predict_classes(pred_test_data)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submit_cnn = pd.DataFrame({'ImageId':range(1,len(predictions_cnn)+1),'Label':predictions_cnn})\n\nsubmit_cnn.to_csv('submission_cnn.csv',index=False)\n","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}