{"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)\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 all files under the input directory\n\n# import os\n# os.listdir('../input/digit-recognizer')\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"from tensorflow import keras\n\n#variables\nnum_classes = 10\nimg_rows, img_cols = 28, 28\n\n#obtaining and preprocessing data\ninput_path = '../input/digit-recognizer/'\ndataset = pd.read_csv(input_path + 'train.csv')\n#number of rows in dataset\nnum_images = dataset.shape[0]\nX = dataset.values[:,1:].reshape(num_images, img_rows, img_cols, 1) / 255\n#use onehotencoding on output\ny = keras.utils.to_categorical(dataset.label, num_classes)\n\n#organising test data\ntest_dataset = pd.read_csv(input_path + 'test.csv')\ntest_num_images = test_dataset.shape[0]\ntest_X = test_dataset.values[:, :].reshape(test_num_images, img_rows, img_cols, 1) / 255","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#creating the NN model\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Dense, Conv2D, Flatten, Dropout\n\nclassifier = Sequential()\nclassifier.add(Conv2D(32, kernel_size = (3, 3), activation='relu',\n                      input_shape = (img_rows, img_cols, 1)))\nclassifier.add(Dropout(0.5))\nclassifier.add(Conv2D(64, kernel_size = (3, 3), activation='relu'))\nclassifier.add(Dropout(0.5))\nclassifier.add(Flatten())\nclassifier.add(Dense(128, activation='relu'))\nclassifier.add(Dense(num_classes, activation='softmax'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#fitting and training model\nclassifier.compile(optimizer='adam', loss='categorical_crossentropy',\n                  metrics=['accuracy'])\nclassifier.fit(X, y,\n              batch_size=128,\n              epochs=2,\n              validation_split=0.2)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#prediction on test data and formatting\npreds = classifier.predict(test_X)\nresults = np.argmax(preds, axis=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#creating output\noutput = pd.DataFrame({'ImageId': range(1, 28001),\n                       'Label': results})\noutput.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":1}