{"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_minor":4,"nbformat":4,"cells":[{"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","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2022-04-23T19:28:42.664215Z","iopub.execute_input":"2022-04-23T19:28:42.664982Z","iopub.status.idle":"2022-04-23T19:28:42.67602Z","shell.execute_reply.started":"2022-04-23T19:28:42.664934Z","shell.execute_reply":"2022-04-23T19:28:42.675179Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from keras.datasets import mnist\nfrom keras.utils import np_utils\nfrom keras.layers import Input, Dense, Dropout, Conv2D\nfrom keras.models import Model, Sequential","metadata":{"execution":{"iopub.status.busy":"2022-04-23T19:28:42.747912Z","iopub.execute_input":"2022-04-23T19:28:42.74887Z","iopub.status.idle":"2022-04-23T19:28:42.753786Z","shell.execute_reply.started":"2022-04-23T19:28:42.748831Z","shell.execute_reply":"2022-04-23T19:28:42.752898Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data_train = pd.read_csv(\"/kaggle/input/digit-recognizer/train.csv\")\ndata_train = np.array(data_train)\ndata_test = pd.read_csv(\"/kaggle/input/digit-recognizer/test.csv\")\nprint(data_test)\ndata_test = np.array(data_test)\nprint(data_test.shape)\ny_train, x_train = data_train[:,0], data_train[:, 1:]\nx_test = data_test\n\nx_train = x_train.astype('float32') / 255.\nx_test = x_test.astype('float32') / 255\n\ny_train = np_utils.to_categorical(y_train,10)\nprint(x_test)","metadata":{"execution":{"iopub.status.busy":"2022-04-23T19:28:42.835352Z","iopub.execute_input":"2022-04-23T19:28:42.836262Z","iopub.status.idle":"2022-04-23T19:28:47.698673Z","shell.execute_reply.started":"2022-04-23T19:28:42.836204Z","shell.execute_reply":"2022-04-23T19:28:47.698095Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model = Sequential([\n        Dense(units=200, input_dim=784, bias_initializer='one', activation='tanh'),\n        Dropout(0.4),\n        Dense(units=100, bias_initializer='one', activation='tanh'),\n        Dropout(0.4),\n        Dense(units=10, bias_initializer='one', activation='softmax')\n    ])\n","metadata":{"execution":{"iopub.status.busy":"2022-04-23T19:28:47.699962Z","iopub.execute_input":"2022-04-23T19:28:47.700282Z","iopub.status.idle":"2022-04-23T19:28:47.737589Z","shell.execute_reply.started":"2022-04-23T19:28:47.700254Z","shell.execute_reply":"2022-04-23T19:28:47.736819Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.compile(\n\n    loss = 'categorical_crossentropy',\n    metrics = ['accuracy']\n)\nmodel.summary()\nmodel.fit(x_train, y_train, batch_size=32, epochs=10)\n\n","metadata":{"execution":{"iopub.status.busy":"2022-04-23T19:28:47.74141Z","iopub.execute_input":"2022-04-23T19:28:47.742191Z","iopub.status.idle":"2022-04-23T19:29:32.289687Z","shell.execute_reply.started":"2022-04-23T19:28:47.742149Z","shell.execute_reply":"2022-04-23T19:29:32.288258Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"Label_pre = model.predict(x_test, batch_size=32)\nLabel_pre = np.argmax(Label_pre, axis = -1)\nList_x = range(1,28001)\nsub = pd.DataFrame({ 'ImageId': List_x, 'Label': Label_pre })\nsub.to_csv(\"Chenyang_WANG.csv\", index=False)","metadata":{"execution":{"iopub.status.busy":"2022-04-23T19:29:50.514328Z","iopub.execute_input":"2022-04-23T19:29:50.515267Z","iopub.status.idle":"2022-04-23T19:29:51.738005Z","shell.execute_reply.started":"2022-04-23T19:29:50.515217Z","shell.execute_reply":"2022-04-23T19:29:51.73716Z"},"trusted":true},"execution_count":null,"outputs":[]}]}