{"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\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\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":"route = '../input/digit-recognizer/'\ntrain = pd.read_csv(f'{route}train.csv')\ntest = pd.read_csv(f'{route}test.csv')\nprint(train.shape)\nprint(test.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"label = train.label\ntrain = train.drop('label', axis=1)\ntrain.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.model_selection import train_test_split\nX_train, X_test, y_train, y_test = train_test_split(train, label, random_state=0)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#labelのone-hot-encoder\nfrom keras.utils import to_categorical\ny_train = to_categorical(y_train, 10)\ny_test = to_categorical(y_test, 10)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(X_train.shape)\nprint(X_test.shape)\nprint(y_train.shape)\nprint(y_test.shape)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## モデルの作成"},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.layers import Dense, Dropout\nfrom keras.models import Sequential\nfrom keras.metrics import accuracy\n\nmodel = Sequential()\nmodel.add(Dense(64, activation='relu', input_shape=(784,)))\nmodel.add(Dropout(0.2))\nmodel.add(Dense(32, activation='relu'))\nmodel.add(Dense(10, activation='softmax'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# モデルの学習\nhistory = model.fit(X_train, y_train, epochs=30, batch_size=128, verbose=1,\n                   validation_data=(X_test, y_test))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import matplotlib.pyplot as plt\nloss = history.history['loss']\nval_loss = history.history['val_loss']\n\nnum_epoch = len(loss)\nplt.plot(range(num_epoch), loss, marker='.', label='loss')\nplt.plot(range(num_epoch), val_loss, marker='.', label='val_loss')\nplt.legend(loc='best')\nplt.grid()\nplt.xlabel('epoch')\nplt.ylabel('loss')\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"accuracy = history.history['accuracy']\nval_accuracy = history.history['val_accuracy']\n\nnum_epoch = len(accuracy)\nplt.plot(range(num_epoch), accuracy, marker='.', label='accuracy')\nplt.plot(range(num_epoch), val_accuracy, marker='.', label='val_accuracy')\nplt.legend(loc='best')\nplt.grid()\nplt.xlabel('epoch')\nplt.ylabel('accuracy')\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test = pd.read_csv(f'{route}test.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_pred = model.predict_classes(test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission = pd.read_csv(f'{route}sample_submission.csv')\nsubmission.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission['Label'] = test_pred\nsubmission.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission.to_csv('ANSWER.csv',header=True, 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}