{"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 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","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import matplotlib.pyplot as plt\nimport seaborn as sns\nimport numpy as np\nimport pandas as pd\nimport os\n\nprint(os.listdir('/kaggle/input/digit-recognizer'))","execution_count":null,"outputs":[]},{"metadata":{"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":"train.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train = train.drop('label', axis=1)\ny_train = train['label'].astype('int32')\nprint('x_train shape: ', x_train.shape)\nprint('y_train shape: ', y_train.shape)\nprint('test shape: ', test.shape)\nprint('\\nsamples in test: ', test.shape[0])\nprint('samples in train: ', x_train.shape[0])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print('Number of Examples Per Digit:\\n', y_train.value_counts())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.countplot(y_train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train /= 255.0\ntest /= 255.0\nx_train = x_train.values.reshape(x_train.shape[0], 28, 28, 1)\ntest = test.values.reshape(test.shape[0], 28, 28, 1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print('x_train shape: ', x_train.shape)\nprint('y_train shape: ', y_train.shape)\nprint('test shape: ', test.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.figure(figsize=(12,10))\nfor img in range(10):\n    plt.subplot(5, 5, img+1)\n    plt.imshow(x_train[img].reshape((28, 28)), cmap='binary_r')\n    plt.axis('off')\n    plt.title('Label: ' + y_train[img].astype('str'))\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import keras\nfrom keras.models import Sequential\nfrom keras.layers import Dense, Dropout, Flatten, Conv2D, MaxPooling2D\nfrom keras.utils import to_categorical\nfrom sklearn.model_selection import train_test_split","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_train = to_categorical(y_train, 10)\nx_train, x_test, y_train, y_test = train_test_split(x_train, y_train, test_size = 0.1, random_state=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = Sequential()\nmodel.add(Conv2D(32, kernel_size=(3, 3), activation='relu', input_shape=(28,28,1)))\nmodel.add(Conv2D(64, (3, 3), activation='relu'))\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\nmodel.add(Dropout(0.25))\nmodel.add(Conv2D(64, (3, 3), activation='relu'))\nmodel.add(Conv2D(128, (3, 3), activation='relu'))\nmodel.add(Dropout(0.25))\nmodel.add(Flatten())\nmodel.add(Dense(128, activation='relu'))\nmodel.add(Dropout(0.5))\nmodel.add(Dense(10, activation='softmax'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.compile(loss='categorical_crossentropy', optimizer='Adadelta', metrics=['accuracy'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.fit(x_train, y_train, batch_size=128, epochs=12, verbose=1,\n          validation_data=(x_test, y_test))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"loss, accuracy = model.evaluate(x_test, y_test, verbose=0)\ntrain_stat = model.evaluate(x_train, y_train, verbose=0)\nprint('Train Loss:     ', round(train_stat[0], 5))\nprint('Train Accuracy: ', round(train_stat[1]*100, 4), '%')\nprint('Test Loss:      ', round(loss, 5))\nprint('Test Accuracy:  ', round(accuracy*100, 4), '%')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"predictions = model.predict(x_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"results = np.argmax(predictions, axis = 1)\nresults = pd.Series(results, name=\"Label\")\nsubmission = pd.concat([pd.Series(range(1,28001),name = \"ImageId\"),results],axis = 1)\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}