{"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","collapsed":true,"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":false},"cell_type":"code","source":"import pandas as pd\nimport numpy as np\n\nimport torch\nimport torchvision.datasets as data\nimport torchvision.transforms as transforms\nimport random","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"device = 'cuda' if torch.cuda.is_available() else 'cpu'\n\nrandom.seed(777)\ntorch.manual_seed(777)\nif device == 'cuda':\n  torch.cuda.manual_seed_all(777)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learning_rate = 0.0003\ntraining_epochs = 15\nbatch_size = 100","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_data=pd.read_csv('mnist_train_label.csv',header=None,usecols=range(0,785))\ntest_data=pd.read_csv('mnist_test.csv',header=None, usecols=range(0,784))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train_data=train_data.loc[:,1:784]\ny_train_data=train_data.loc[:,0]\nprint(y_train_data)\n\nx_train_data=np.array(x_train_data)\ny_train_data=np.array(y_train_data)\n\nx_train_data=torch.FloatTensor(x_train_data)\ny_train_data=torch.LongTensor(y_train_data)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_dataset = torch.utils.data.TensorDataset(x_train_data, y_train_data)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data_loader = torch.utils.data.DataLoader(dataset=train_dataset,\n                                          batch_size=batch_size,\n                                          shuffle=True,\n                                          drop_last=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"linear1 = torch.nn.Linear(784,10,bias=True) #layer in784 out 10 단층 설계","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"torch.nn.init.xavier_uniform_(linear1.weight)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = torch.nn.Sequential(linear1).to(device)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"loss = torch.nn.CrossEntropyLoss().to(device)\noptimizer = torch.optim.SGD(model.parameters(), lr=learning_rate) # SGD모델","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"total_batch = len(data_loader)\nfor epoch in range(training_epochs):\n    avg_cost = 0\n\n    for X, Y in data_loader:\n\n        # (1000, 1, 28, 28) 크기의 텐서를 (1000, 784) 크기의 텐서로 변형\n        X = X.view(-1, 28 * 28).to(device)\n        # one-hot encoding되어 있지 않음\n        Y = Y.to(device)\n        #%debug\n\n        # 그래디언트 초기화\n        optimizer.zero_grad()\n        # Forward 계산\n        hypothesis = model(X)\n        # Error 계산\n        cost = loss(hypothesis, Y)\n        # Backparopagation\n        cost.backward()\n        # 가중치 갱신\n        optimizer.step()\n\n        # 평균 Error 계산\n        avg_cost += cost / total_batch\n\n    print('Epoch:', '%04d' % (epoch + 1), 'cost =', '{:.9f}'.format(avg_cost))\n\nprint('Learning finished')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"with torch.no_grad():\n\n  x_test_data=test_data.loc[:,:]\n  print(x_test_data)\n  x_test_data=np.array(x_test_data)\n  x_test_data=torch.from_numpy(x_test_data).float().to(device)\n\n  prediction = model(x_test_data)\n  correct_prediction = torch.argmax(prediction, 1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"correct_prediction = correct_prediction.cpu().numpy().reshape(-1,1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submit=pd.read_csv('submission.csv')\nfor i in range(len(correct_prediction)):\n  submit['Category'][i]=correct_prediction[i].item()\n\nsubmit","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","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}