{"cells":[{"metadata":{},"cell_type":"markdown","source":"# Hello World! \nThis is my very first machine learning project. So I expect a lot of warnings, errors and absolute-piece-of-shit validation scores. Here we go.","execution_count":null},{"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)\nfrom sklearn.model_selection import train_test_split\nfrom tensorflow import keras\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\n\nimg_rows, img_cols = 28, 28\nnum_classes = 10\n\ndef prep_data(raw):\n    y = raw[:, 0]\n    out_y = keras.utils.to_categorical(y, num_classes)\n    \n    x = raw[:,1:]\n    num_images = raw.shape[0]\n    out_x = x.reshape(num_images, img_rows, img_cols, 1)\n    out_x = out_x / 255\n    return out_x, out_y\n\nfile = \"/kaggle/input/digit-recognizer/train.csv\"\ndata = np.loadtxt(file, skiprows=1, delimiter=',')\nx, y = prep_data(data)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Building The Model","execution_count":null},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"from tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Dense, Flatten, Conv2D, Dropout\n\nmodel = Sequential()\nmodel.add(Conv2D(12, kernel_size=(3,3), activation='relu', input_shape=(img_rows, img_cols, 1)))\nmodel.add(Conv2D(12, kernel_size=(3,3), activation='relu'))\nmodel.add(Conv2D(12, kernel_size=(3,3), activation='relu'))\nmodel.add(Conv2D(12, kernel_size=(3,3), activation='relu'))\nmodel.add(Flatten())\nmodel.add(Dense(100, activation='relu'))\nmodel.add(Dense(num_classes, activation='softmax'))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Compiling","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Fitting","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"model.fit(x, y, batch_size=100, epochs=25, validation_split=0.2)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Validation Score","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"score = model.evaluate(x, y, verbose=0)\nprint(f'Test loss: {score[0]} / Test accuracy: {score[1]}')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Preparing Test Data","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"def prep_test_data(raw):\n    x = raw[:,0:]\n    num_images = raw.shape[0]\n    out_x = x.reshape(num_images, img_rows, img_cols, 1)\n    out_x = out_x / 255\n    return out_x\n\nval_file = \"/kaggle/input/digit-recognizer/test.csv\"\nval_data = np.loadtxt(val_file, skiprows=1, delimiter=',')\nx_test = prep_test_data(val_data)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Predicting & Saving","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"predictions = model.predict_classes(x_test)\n\nindexes = [i for i in range(1,len(val_data)+1)]\noutput = pd.DataFrame({'ImageId': indexes,'Label': predictions})\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":4}