\ub525\ub7ec\ub2dd \ubaa8\ub378\uc758 \uc131\ub2a5\uc740 \ub370\uc774\ud130\uc758 \ud488\uc9c8\uc5d0 \ud06c\uac8c \uc88c\uc6b0\ub429\ub2c8\ub2e4. \ub530\ub77c\uc11c \ub370\uc774\ud130 \uc804\ucc98\ub9ac\ub294 \ub525\ub7ec\ub2dd \ubaa8\ub378\uc744 \uad6c\ucd95\ud558\ub294 \ub370 \uc788\uc5b4 \uac00\uc7a5 \uc911\uc694\ud55c \uacfc\uc815 \uc911 \ud558\ub098\uc785\ub2c8\ub2e4. \ubcf8 \uac15\uc88c\uc5d0\uc11c\ub294 \ud30c\uc774\ud1a0\uce58(Pytorch)\ub97c \uc0ac\uc6a9\ud558\uc5ec \ub370\uc774\ud130 \uc804\ucc98\ub9ac\ub97c \uc218\ud589\ud558\uace0, \ub370\uc774\ud130\uc14b\uc5d0\uc11c \uacb0\uce21\uce58\ub97c \ud655\uc778\ud558\ub294 \ubc29\ubc95\uc5d0 \ub300\ud574 \uc124\uba85\ud558\uaca0\uc2b5\ub2c8\ub2e4.<\/p>\n
\ub370\uc774\ud130 \uc804\ucc98\ub9ac(Data Preprocessing)\ub294 \uc6d0\ubcf8 \ub370\uc774\ud130\ub97c \ubd84\uc11d\ud558\uae30 \uc801\ud569\ud55c \ud615\ud0dc\ub85c \ubcc0\ud658\ud558\ub294 \uacfc\uc815\uc785\ub2c8\ub2e4. \uc774 \uacfc\uc815\uc740 \uc5ec\ub7ec \ub2e8\uacc4\ub97c \ud3ec\ud568\ud560 \uc218 \uc788\uc73c\uba70, \uc77c\ubc18\uc801\uc73c\ub85c \ub2e4\uc74c\uacfc \uac19\uc740 \uc791\uc5c5\uc744 \ud3ec\ud568\ud569\ub2c8\ub2e4.<\/p>\n
\uacb0\uce21\uce58(Missing Value)\ub294 \ub370\uc774\ud130\uc14b\uc5d0\uc11c \ud2b9\uc815 \uac12\uc774 \ube44\uc5b4\uc788\ub294 \uc0c1\ud0dc\ub97c \uc758\ubbf8\ud569\ub2c8\ub2e4. \uacb0\uce21\uce58\ub294 \ubd84\uc11d \uacb0\uacfc\uc5d0 \ubd80\uc815\uc801\uc778 \uc601\ud5a5\uc744 \ubbf8\uce60 \uc218 \uc788\uc73c\ubbc0\ub85c, \uc801\uc808\ud55c \ubc29\ubc95\uc73c\ub85c \ucc98\ub9ac\ud574\uc57c \ud569\ub2c8\ub2e4. \uacb0\uce21\uce58\ub97c \ucc98\ub9ac\ud558\ub294 \ubc29\ubc95\uc5d0\ub294 \uc5ec\ub7ec \uac00\uc9c0\uac00 \uc788\uc73c\uba70, \ub300\ud45c\uc801\uc778 \ubc29\ubc95\uc740 \ub2e4\uc74c\uacfc \uac19\uc2b5\ub2c8\ub2e4.<\/p>\n
\uc774\uc81c \ud30c\uc774\ud1a0\uce58\ub97c \uc0ac\uc6a9\ud558\uc5ec \uc2e4\uc81c \ub370\uc774\ud130 \uc804\ucc98\ub9ac \ubc0f \uacb0\uce21\uce58 \ud655\uc778\uc744 \ud574\ubcf4\uaca0\uc2b5\ub2c8\ub2e4. \uba3c\uc800 \ud544\uc694\ud55c \ub77c\uc774\ube0c\ub7ec\ub9ac\ub97c \uc784\ud3ec\ud2b8\ud569\ub2c8\ub2e4.<\/p>\n
import numpy as np\nimport pandas as pd\nimport torch\nfrom torch.utils.data import Dataset, DataLoader<\/code><\/pre>\n3.1 \ub370\uc774\ud130\uc14b \uc0dd\uc131<\/h3>\n\uc608\uc2dc\ub85c \uc0ac\uc6a9\ud560 \ub370\uc774\ud130\uc14b\uc744 \uc0dd\uc131\ud574 \ubcf4\uaca0\uc2b5\ub2c8\ub2e4. \uc774 \ub370\uc774\ud130\uc14b\uc5d0\ub294 \uc77c\ubd80 \uacb0\uce21\uce58\uac00 \ud3ec\ud568\ub418\uc5b4 \uc788\uc2b5\ub2c8\ub2e4.<\/p>\ndata = {\n 'feature_1': [1.0, 2.5, np.nan, 4.5, 5.0],\n 'feature_2': [np.nan, 1.5, 2.0, 2.5, 3.0],\n 'label': [0, 1, 0, 1, 0]\n}\n\ndf = pd.DataFrame(data)\nprint(df)<\/code><\/pre>\n3.2 \uacb0\uce21\uce58 \ud655\uc778\ud558\uae30<\/h3>\nPandas\ub97c \uc0ac\uc6a9\ud558\uc5ec \uacb0\uce21\uce58\ub97c \ud655\uc778\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4. isnull()<\/code> \uba54\uc11c\ub4dc\ub97c \uc0ac\uc6a9\ud558\uba74 \uacb0\uce21\uce58\uac00 \uc788\ub294\uc9c0 \ud655\uc778\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/p>\n# \uacb0\uce21\uce58 \ud655\uc778\nmissing_values = df.isnull().sum()\nprint(\"\uac01 \uc5f4\uc758 \uacb0\uce21\uce58 \uac1c\uc218:\\n\", missing_values)<\/code><\/pre>\n3.3 \uacb0\uce21\uce58 \ucc98\ub9ac\ud558\uae30<\/h3>\n\uacb0\uce21\uce58\ub97c \ucc98\ub9ac\ud558\ub294 \ubc29\ubc95\uc744 \uc0b4\ud3b4\ubcf4\uaca0\uc2b5\ub2c8\ub2e4. \uc5ec\uae30\uc11c\ub294 \ud3c9\uade0\uc73c\ub85c \uacb0\uce21\uce58\ub97c \ub300\uccb4\ud558\ub294 \ubc29\ubc95\uc744 \uc0ac\uc6a9\ud569\ub2c8\ub2e4.<\/p>\n# \ud3c9\uade0\uc73c\ub85c \uacb0\uce21\uce58 \ub300\uccb4\ndf['feature_1'].fillna(df['feature_1'].mean(), inplace=True)\ndf['feature_2'].fillna(df['feature_2'].mean(), inplace=True)\nprint(\"\uacb0\uce21\uce58 \ub300\uccb4 \ud6c4:\\n\", df)<\/code><\/pre>\n4. \ub370\uc774\ud130\uc14b\uc744 \ud30c\uc774\ud1a0\uce58 Dataset\uc73c\ub85c \ubcc0\ud658<\/h3>\n\ub370\uc774\ud130 \uc804\ucc98\ub9ac\uac00 \ub05d\ub098\uba74, \ub370\uc774\ud130\uc14b\uc744 \ud30c\uc774\ud1a0\uce58\uc758 Dataset<\/code> \ud074\ub798\uc2a4\ub97c \uc0c1\uc18d\ud558\uc5ec \ubcc0\ud658\ud569\ub2c8\ub2e4.<\/p>\nclass MyDataset(Dataset):\n def __init__(self, dataframe):\n self.dataframe = dataframe\n \n def __len__(self):\n return len(self.dataframe)\n\n def __getitem__(self, idx):\n return torch.tensor(self.dataframe.iloc[idx, :-1].values, dtype=torch.float32), \\\n torch.tensor(self.dataframe.iloc[idx, -1], dtype=torch.long)\n\ndataset = MyDataset(df)\ndataloader = DataLoader(dataset, batch_size=2, shuffle=True)<\/code><\/pre>\n5. \uacb0\ub860<\/h3>\n\ubcf8 \uac15\uc88c\uc5d0\uc11c\ub294 \ub525\ub7ec\ub2dd\uc5d0\uc11c \ub370\uc774\ud130 \uc804\ucc98\ub9ac\uc758 \uc911\uc694\uc131 \ubc0f \uacb0\uce21\uce58 \ucc98\ub9ac \ubc29\ubc95\uc5d0 \ub300\ud574 \uc54c\uc544\ubcf4\uc558\uc2b5\ub2c8\ub2e4. \ud30c\uc774\ud1a0\uce58\ub97c \uc774\uc6a9\ud558\uc5ec \uacb0\uce21\uce58\ub97c \ud655\uc778\ud558\uace0 \ucc98\ub9ac\ud558\ub294 \uacfc\uc815\uc744 \uc2e4\uc2b5\ud558\uc600\uc73c\uba70, \uc774\ub97c \ud1b5\ud574 \ub370\uc774\ud130\uc14b\uc744 \ud6a8\uacfc\uc801\uc73c\ub85c \uc900\ube44\ud560 \uc218 \uc788\ub294 \ubc29\ubc95\uc744 \ubc30\uc6b8 \uc218 \uc788\uc5c8\uc2b5\ub2c8\ub2e4. \ub370\uc774\ud130 \uc804\ucc98\ub9ac\ub294 \ub525\ub7ec\ub2dd \ubaa8\ub378\uc758 \uc131\ub2a5\uc744 \ub192\uc774\ub294 \uc911\uc694\ud55c \ub2e8\uacc4\uc774\ubbc0\ub85c, \ubc18\ub4dc\uc2dc \uc798 \uc774\ud574\ud558\uace0 \ud65c\uc6a9\ud574\uc57c \ud569\ub2c8\ub2e4.<\/p>\n\ucc38\uace0 \uc790\ub8cc<\/h2>\n\ub2e4\uc74c\uc758 \uc790\ub8cc\ub97c \ud1b5\ud574 \ub354 \ub9ce\uc740 \uc815\ubcf4\ub97c \uc5bb\uc744 \uc218 \uc788\uc2b5\ub2c8\ub2e4:<\/p>\n\nPytorch Documentation<\/a><\/li>\nPandas Documentation<\/a><\/li>\nScikit-learn Documentation<\/a><\/li>\n<\/ul>\n
\uc608\uc2dc\ub85c \uc0ac\uc6a9\ud560 \ub370\uc774\ud130\uc14b\uc744 \uc0dd\uc131\ud574 \ubcf4\uaca0\uc2b5\ub2c8\ub2e4. \uc774 \ub370\uc774\ud130\uc14b\uc5d0\ub294 \uc77c\ubd80 \uacb0\uce21\uce58\uac00 \ud3ec\ud568\ub418\uc5b4 \uc788\uc2b5\ub2c8\ub2e4.<\/p>\n
data = {\n 'feature_1': [1.0, 2.5, np.nan, 4.5, 5.0],\n 'feature_2': [np.nan, 1.5, 2.0, 2.5, 3.0],\n 'label': [0, 1, 0, 1, 0]\n}\n\ndf = pd.DataFrame(data)\nprint(df)<\/code><\/pre>\n3.2 \uacb0\uce21\uce58 \ud655\uc778\ud558\uae30<\/h3>\nPandas\ub97c \uc0ac\uc6a9\ud558\uc5ec \uacb0\uce21\uce58\ub97c \ud655\uc778\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4. isnull()<\/code> \uba54\uc11c\ub4dc\ub97c \uc0ac\uc6a9\ud558\uba74 \uacb0\uce21\uce58\uac00 \uc788\ub294\uc9c0 \ud655\uc778\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/p>\n# \uacb0\uce21\uce58 \ud655\uc778\nmissing_values = df.isnull().sum()\nprint(\"\uac01 \uc5f4\uc758 \uacb0\uce21\uce58 \uac1c\uc218:\\n\", missing_values)<\/code><\/pre>\n3.3 \uacb0\uce21\uce58 \ucc98\ub9ac\ud558\uae30<\/h3>\n\uacb0\uce21\uce58\ub97c \ucc98\ub9ac\ud558\ub294 \ubc29\ubc95\uc744 \uc0b4\ud3b4\ubcf4\uaca0\uc2b5\ub2c8\ub2e4. \uc5ec\uae30\uc11c\ub294 \ud3c9\uade0\uc73c\ub85c \uacb0\uce21\uce58\ub97c \ub300\uccb4\ud558\ub294 \ubc29\ubc95\uc744 \uc0ac\uc6a9\ud569\ub2c8\ub2e4.<\/p>\n# \ud3c9\uade0\uc73c\ub85c \uacb0\uce21\uce58 \ub300\uccb4\ndf['feature_1'].fillna(df['feature_1'].mean(), inplace=True)\ndf['feature_2'].fillna(df['feature_2'].mean(), inplace=True)\nprint(\"\uacb0\uce21\uce58 \ub300\uccb4 \ud6c4:\\n\", df)<\/code><\/pre>\n4. \ub370\uc774\ud130\uc14b\uc744 \ud30c\uc774\ud1a0\uce58 Dataset\uc73c\ub85c \ubcc0\ud658<\/h3>\n\ub370\uc774\ud130 \uc804\ucc98\ub9ac\uac00 \ub05d\ub098\uba74, \ub370\uc774\ud130\uc14b\uc744 \ud30c\uc774\ud1a0\uce58\uc758 Dataset<\/code> \ud074\ub798\uc2a4\ub97c \uc0c1\uc18d\ud558\uc5ec \ubcc0\ud658\ud569\ub2c8\ub2e4.<\/p>\nclass MyDataset(Dataset):\n def __init__(self, dataframe):\n self.dataframe = dataframe\n \n def __len__(self):\n return len(self.dataframe)\n\n def __getitem__(self, idx):\n return torch.tensor(self.dataframe.iloc[idx, :-1].values, dtype=torch.float32), \\\n torch.tensor(self.dataframe.iloc[idx, -1], dtype=torch.long)\n\ndataset = MyDataset(df)\ndataloader = DataLoader(dataset, batch_size=2, shuffle=True)<\/code><\/pre>\n5. \uacb0\ub860<\/h3>\n\ubcf8 \uac15\uc88c\uc5d0\uc11c\ub294 \ub525\ub7ec\ub2dd\uc5d0\uc11c \ub370\uc774\ud130 \uc804\ucc98\ub9ac\uc758 \uc911\uc694\uc131 \ubc0f \uacb0\uce21\uce58 \ucc98\ub9ac \ubc29\ubc95\uc5d0 \ub300\ud574 \uc54c\uc544\ubcf4\uc558\uc2b5\ub2c8\ub2e4. \ud30c\uc774\ud1a0\uce58\ub97c \uc774\uc6a9\ud558\uc5ec \uacb0\uce21\uce58\ub97c \ud655\uc778\ud558\uace0 \ucc98\ub9ac\ud558\ub294 \uacfc\uc815\uc744 \uc2e4\uc2b5\ud558\uc600\uc73c\uba70, \uc774\ub97c \ud1b5\ud574 \ub370\uc774\ud130\uc14b\uc744 \ud6a8\uacfc\uc801\uc73c\ub85c \uc900\ube44\ud560 \uc218 \uc788\ub294 \ubc29\ubc95\uc744 \ubc30\uc6b8 \uc218 \uc788\uc5c8\uc2b5\ub2c8\ub2e4. \ub370\uc774\ud130 \uc804\ucc98\ub9ac\ub294 \ub525\ub7ec\ub2dd \ubaa8\ub378\uc758 \uc131\ub2a5\uc744 \ub192\uc774\ub294 \uc911\uc694\ud55c \ub2e8\uacc4\uc774\ubbc0\ub85c, \ubc18\ub4dc\uc2dc \uc798 \uc774\ud574\ud558\uace0 \ud65c\uc6a9\ud574\uc57c \ud569\ub2c8\ub2e4.<\/p>\n\ucc38\uace0 \uc790\ub8cc<\/h2>\n\ub2e4\uc74c\uc758 \uc790\ub8cc\ub97c \ud1b5\ud574 \ub354 \ub9ce\uc740 \uc815\ubcf4\ub97c \uc5bb\uc744 \uc218 \uc788\uc2b5\ub2c8\ub2e4:<\/p>\n\nPytorch Documentation<\/a><\/li>\nPandas Documentation<\/a><\/li>\nScikit-learn Documentation<\/a><\/li>\n<\/ul>\n
Pandas\ub97c \uc0ac\uc6a9\ud558\uc5ec \uacb0\uce21\uce58\ub97c \ud655\uc778\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4. isnull()<\/code> \uba54\uc11c\ub4dc\ub97c \uc0ac\uc6a9\ud558\uba74 \uacb0\uce21\uce58\uac00 \uc788\ub294\uc9c0 \ud655\uc778\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/p>\n# \uacb0\uce21\uce58 \ud655\uc778\nmissing_values = df.isnull().sum()\nprint(\"\uac01 \uc5f4\uc758 \uacb0\uce21\uce58 \uac1c\uc218:\\n\", missing_values)<\/code><\/pre>\n3.3 \uacb0\uce21\uce58 \ucc98\ub9ac\ud558\uae30<\/h3>\n\uacb0\uce21\uce58\ub97c \ucc98\ub9ac\ud558\ub294 \ubc29\ubc95\uc744 \uc0b4\ud3b4\ubcf4\uaca0\uc2b5\ub2c8\ub2e4. \uc5ec\uae30\uc11c\ub294 \ud3c9\uade0\uc73c\ub85c \uacb0\uce21\uce58\ub97c \ub300\uccb4\ud558\ub294 \ubc29\ubc95\uc744 \uc0ac\uc6a9\ud569\ub2c8\ub2e4.<\/p>\n# \ud3c9\uade0\uc73c\ub85c \uacb0\uce21\uce58 \ub300\uccb4\ndf['feature_1'].fillna(df['feature_1'].mean(), inplace=True)\ndf['feature_2'].fillna(df['feature_2'].mean(), inplace=True)\nprint(\"\uacb0\uce21\uce58 \ub300\uccb4 \ud6c4:\\n\", df)<\/code><\/pre>\n4. \ub370\uc774\ud130\uc14b\uc744 \ud30c\uc774\ud1a0\uce58 Dataset\uc73c\ub85c \ubcc0\ud658<\/h3>\n\ub370\uc774\ud130 \uc804\ucc98\ub9ac\uac00 \ub05d\ub098\uba74, \ub370\uc774\ud130\uc14b\uc744 \ud30c\uc774\ud1a0\uce58\uc758 Dataset<\/code> \ud074\ub798\uc2a4\ub97c \uc0c1\uc18d\ud558\uc5ec \ubcc0\ud658\ud569\ub2c8\ub2e4.<\/p>\nclass MyDataset(Dataset):\n def __init__(self, dataframe):\n self.dataframe = dataframe\n \n def __len__(self):\n return len(self.dataframe)\n\n def __getitem__(self, idx):\n return torch.tensor(self.dataframe.iloc[idx, :-1].values, dtype=torch.float32), \\\n torch.tensor(self.dataframe.iloc[idx, -1], dtype=torch.long)\n\ndataset = MyDataset(df)\ndataloader = DataLoader(dataset, batch_size=2, shuffle=True)<\/code><\/pre>\n5. \uacb0\ub860<\/h3>\n\ubcf8 \uac15\uc88c\uc5d0\uc11c\ub294 \ub525\ub7ec\ub2dd\uc5d0\uc11c \ub370\uc774\ud130 \uc804\ucc98\ub9ac\uc758 \uc911\uc694\uc131 \ubc0f \uacb0\uce21\uce58 \ucc98\ub9ac \ubc29\ubc95\uc5d0 \ub300\ud574 \uc54c\uc544\ubcf4\uc558\uc2b5\ub2c8\ub2e4. \ud30c\uc774\ud1a0\uce58\ub97c \uc774\uc6a9\ud558\uc5ec \uacb0\uce21\uce58\ub97c \ud655\uc778\ud558\uace0 \ucc98\ub9ac\ud558\ub294 \uacfc\uc815\uc744 \uc2e4\uc2b5\ud558\uc600\uc73c\uba70, \uc774\ub97c \ud1b5\ud574 \ub370\uc774\ud130\uc14b\uc744 \ud6a8\uacfc\uc801\uc73c\ub85c \uc900\ube44\ud560 \uc218 \uc788\ub294 \ubc29\ubc95\uc744 \ubc30\uc6b8 \uc218 \uc788\uc5c8\uc2b5\ub2c8\ub2e4. \ub370\uc774\ud130 \uc804\ucc98\ub9ac\ub294 \ub525\ub7ec\ub2dd \ubaa8\ub378\uc758 \uc131\ub2a5\uc744 \ub192\uc774\ub294 \uc911\uc694\ud55c \ub2e8\uacc4\uc774\ubbc0\ub85c, \ubc18\ub4dc\uc2dc \uc798 \uc774\ud574\ud558\uace0 \ud65c\uc6a9\ud574\uc57c \ud569\ub2c8\ub2e4.<\/p>\n\ucc38\uace0 \uc790\ub8cc<\/h2>\n\ub2e4\uc74c\uc758 \uc790\ub8cc\ub97c \ud1b5\ud574 \ub354 \ub9ce\uc740 \uc815\ubcf4\ub97c \uc5bb\uc744 \uc218 \uc788\uc2b5\ub2c8\ub2e4:<\/p>\n\nPytorch Documentation<\/a><\/li>\nPandas Documentation<\/a><\/li>\nScikit-learn Documentation<\/a><\/li>\n<\/ul>\n
isnull()<\/code> \uba54\uc11c\ub4dc\ub97c \uc0ac\uc6a9\ud558\uba74 \uacb0\uce21\uce58\uac00 \uc788\ub294\uc9c0 \ud655\uc778\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/p>\n# \uacb0\uce21\uce58 \ud655\uc778\nmissing_values = df.isnull().sum()\nprint(\"\uac01 \uc5f4\uc758 \uacb0\uce21\uce58 \uac1c\uc218:\\n\", missing_values)<\/code><\/pre>\n3.3 \uacb0\uce21\uce58 \ucc98\ub9ac\ud558\uae30<\/h3>\n\uacb0\uce21\uce58\ub97c \ucc98\ub9ac\ud558\ub294 \ubc29\ubc95\uc744 \uc0b4\ud3b4\ubcf4\uaca0\uc2b5\ub2c8\ub2e4. \uc5ec\uae30\uc11c\ub294 \ud3c9\uade0\uc73c\ub85c \uacb0\uce21\uce58\ub97c \ub300\uccb4\ud558\ub294 \ubc29\ubc95\uc744 \uc0ac\uc6a9\ud569\ub2c8\ub2e4.<\/p>\n# \ud3c9\uade0\uc73c\ub85c \uacb0\uce21\uce58 \ub300\uccb4\ndf['feature_1'].fillna(df['feature_1'].mean(), inplace=True)\ndf['feature_2'].fillna(df['feature_2'].mean(), inplace=True)\nprint(\"\uacb0\uce21\uce58 \ub300\uccb4 \ud6c4:\\n\", df)<\/code><\/pre>\n4. \ub370\uc774\ud130\uc14b\uc744 \ud30c\uc774\ud1a0\uce58 Dataset\uc73c\ub85c \ubcc0\ud658<\/h3>\n\ub370\uc774\ud130 \uc804\ucc98\ub9ac\uac00 \ub05d\ub098\uba74, \ub370\uc774\ud130\uc14b\uc744 \ud30c\uc774\ud1a0\uce58\uc758 Dataset<\/code> \ud074\ub798\uc2a4\ub97c \uc0c1\uc18d\ud558\uc5ec \ubcc0\ud658\ud569\ub2c8\ub2e4.<\/p>\nclass MyDataset(Dataset):\n def __init__(self, dataframe):\n self.dataframe = dataframe\n \n def __len__(self):\n return len(self.dataframe)\n\n def __getitem__(self, idx):\n return torch.tensor(self.dataframe.iloc[idx, :-1].values, dtype=torch.float32), \\\n torch.tensor(self.dataframe.iloc[idx, -1], dtype=torch.long)\n\ndataset = MyDataset(df)\ndataloader = DataLoader(dataset, batch_size=2, shuffle=True)<\/code><\/pre>\n5. \uacb0\ub860<\/h3>\n\ubcf8 \uac15\uc88c\uc5d0\uc11c\ub294 \ub525\ub7ec\ub2dd\uc5d0\uc11c \ub370\uc774\ud130 \uc804\ucc98\ub9ac\uc758 \uc911\uc694\uc131 \ubc0f \uacb0\uce21\uce58 \ucc98\ub9ac \ubc29\ubc95\uc5d0 \ub300\ud574 \uc54c\uc544\ubcf4\uc558\uc2b5\ub2c8\ub2e4. \ud30c\uc774\ud1a0\uce58\ub97c \uc774\uc6a9\ud558\uc5ec \uacb0\uce21\uce58\ub97c \ud655\uc778\ud558\uace0 \ucc98\ub9ac\ud558\ub294 \uacfc\uc815\uc744 \uc2e4\uc2b5\ud558\uc600\uc73c\uba70, \uc774\ub97c \ud1b5\ud574 \ub370\uc774\ud130\uc14b\uc744 \ud6a8\uacfc\uc801\uc73c\ub85c \uc900\ube44\ud560 \uc218 \uc788\ub294 \ubc29\ubc95\uc744 \ubc30\uc6b8 \uc218 \uc788\uc5c8\uc2b5\ub2c8\ub2e4. \ub370\uc774\ud130 \uc804\ucc98\ub9ac\ub294 \ub525\ub7ec\ub2dd \ubaa8\ub378\uc758 \uc131\ub2a5\uc744 \ub192\uc774\ub294 \uc911\uc694\ud55c \ub2e8\uacc4\uc774\ubbc0\ub85c, \ubc18\ub4dc\uc2dc \uc798 \uc774\ud574\ud558\uace0 \ud65c\uc6a9\ud574\uc57c \ud569\ub2c8\ub2e4.<\/p>\n\ucc38\uace0 \uc790\ub8cc<\/h2>\n\ub2e4\uc74c\uc758 \uc790\ub8cc\ub97c \ud1b5\ud574 \ub354 \ub9ce\uc740 \uc815\ubcf4\ub97c \uc5bb\uc744 \uc218 \uc788\uc2b5\ub2c8\ub2e4:<\/p>\n\nPytorch Documentation<\/a><\/li>\nPandas Documentation<\/a><\/li>\nScikit-learn Documentation<\/a><\/li>\n<\/ul>\n
# \uacb0\uce21\uce58 \ud655\uc778\nmissing_values = df.isnull().sum()\nprint(\"\uac01 \uc5f4\uc758 \uacb0\uce21\uce58 \uac1c\uc218:\\n\", missing_values)<\/code><\/pre>\n3.3 \uacb0\uce21\uce58 \ucc98\ub9ac\ud558\uae30<\/h3>\n\uacb0\uce21\uce58\ub97c \ucc98\ub9ac\ud558\ub294 \ubc29\ubc95\uc744 \uc0b4\ud3b4\ubcf4\uaca0\uc2b5\ub2c8\ub2e4. \uc5ec\uae30\uc11c\ub294 \ud3c9\uade0\uc73c\ub85c \uacb0\uce21\uce58\ub97c \ub300\uccb4\ud558\ub294 \ubc29\ubc95\uc744 \uc0ac\uc6a9\ud569\ub2c8\ub2e4.<\/p>\n# \ud3c9\uade0\uc73c\ub85c \uacb0\uce21\uce58 \ub300\uccb4\ndf['feature_1'].fillna(df['feature_1'].mean(), inplace=True)\ndf['feature_2'].fillna(df['feature_2'].mean(), inplace=True)\nprint(\"\uacb0\uce21\uce58 \ub300\uccb4 \ud6c4:\\n\", df)<\/code><\/pre>\n4. \ub370\uc774\ud130\uc14b\uc744 \ud30c\uc774\ud1a0\uce58 Dataset\uc73c\ub85c \ubcc0\ud658<\/h3>\n\ub370\uc774\ud130 \uc804\ucc98\ub9ac\uac00 \ub05d\ub098\uba74, \ub370\uc774\ud130\uc14b\uc744 \ud30c\uc774\ud1a0\uce58\uc758 Dataset<\/code> \ud074\ub798\uc2a4\ub97c \uc0c1\uc18d\ud558\uc5ec \ubcc0\ud658\ud569\ub2c8\ub2e4.<\/p>\nclass MyDataset(Dataset):\n def __init__(self, dataframe):\n self.dataframe = dataframe\n \n def __len__(self):\n return len(self.dataframe)\n\n def __getitem__(self, idx):\n return torch.tensor(self.dataframe.iloc[idx, :-1].values, dtype=torch.float32), \\\n torch.tensor(self.dataframe.iloc[idx, -1], dtype=torch.long)\n\ndataset = MyDataset(df)\ndataloader = DataLoader(dataset, batch_size=2, shuffle=True)<\/code><\/pre>\n5. \uacb0\ub860<\/h3>\n\ubcf8 \uac15\uc88c\uc5d0\uc11c\ub294 \ub525\ub7ec\ub2dd\uc5d0\uc11c \ub370\uc774\ud130 \uc804\ucc98\ub9ac\uc758 \uc911\uc694\uc131 \ubc0f \uacb0\uce21\uce58 \ucc98\ub9ac \ubc29\ubc95\uc5d0 \ub300\ud574 \uc54c\uc544\ubcf4\uc558\uc2b5\ub2c8\ub2e4. \ud30c\uc774\ud1a0\uce58\ub97c \uc774\uc6a9\ud558\uc5ec \uacb0\uce21\uce58\ub97c \ud655\uc778\ud558\uace0 \ucc98\ub9ac\ud558\ub294 \uacfc\uc815\uc744 \uc2e4\uc2b5\ud558\uc600\uc73c\uba70, \uc774\ub97c \ud1b5\ud574 \ub370\uc774\ud130\uc14b\uc744 \ud6a8\uacfc\uc801\uc73c\ub85c \uc900\ube44\ud560 \uc218 \uc788\ub294 \ubc29\ubc95\uc744 \ubc30\uc6b8 \uc218 \uc788\uc5c8\uc2b5\ub2c8\ub2e4. \ub370\uc774\ud130 \uc804\ucc98\ub9ac\ub294 \ub525\ub7ec\ub2dd \ubaa8\ub378\uc758 \uc131\ub2a5\uc744 \ub192\uc774\ub294 \uc911\uc694\ud55c \ub2e8\uacc4\uc774\ubbc0\ub85c, \ubc18\ub4dc\uc2dc \uc798 \uc774\ud574\ud558\uace0 \ud65c\uc6a9\ud574\uc57c \ud569\ub2c8\ub2e4.<\/p>\n\ucc38\uace0 \uc790\ub8cc<\/h2>\n\ub2e4\uc74c\uc758 \uc790\ub8cc\ub97c \ud1b5\ud574 \ub354 \ub9ce\uc740 \uc815\ubcf4\ub97c \uc5bb\uc744 \uc218 \uc788\uc2b5\ub2c8\ub2e4:<\/p>\n\nPytorch Documentation<\/a><\/li>\nPandas Documentation<\/a><\/li>\nScikit-learn Documentation<\/a><\/li>\n<\/ul>\n
\uacb0\uce21\uce58\ub97c \ucc98\ub9ac\ud558\ub294 \ubc29\ubc95\uc744 \uc0b4\ud3b4\ubcf4\uaca0\uc2b5\ub2c8\ub2e4. \uc5ec\uae30\uc11c\ub294 \ud3c9\uade0\uc73c\ub85c \uacb0\uce21\uce58\ub97c \ub300\uccb4\ud558\ub294 \ubc29\ubc95\uc744 \uc0ac\uc6a9\ud569\ub2c8\ub2e4.<\/p>\n
# \ud3c9\uade0\uc73c\ub85c \uacb0\uce21\uce58 \ub300\uccb4\ndf['feature_1'].fillna(df['feature_1'].mean(), inplace=True)\ndf['feature_2'].fillna(df['feature_2'].mean(), inplace=True)\nprint(\"\uacb0\uce21\uce58 \ub300\uccb4 \ud6c4:\\n\", df)<\/code><\/pre>\n4. \ub370\uc774\ud130\uc14b\uc744 \ud30c\uc774\ud1a0\uce58 Dataset\uc73c\ub85c \ubcc0\ud658<\/h3>\n\ub370\uc774\ud130 \uc804\ucc98\ub9ac\uac00 \ub05d\ub098\uba74, \ub370\uc774\ud130\uc14b\uc744 \ud30c\uc774\ud1a0\uce58\uc758 Dataset<\/code> \ud074\ub798\uc2a4\ub97c \uc0c1\uc18d\ud558\uc5ec \ubcc0\ud658\ud569\ub2c8\ub2e4.<\/p>\nclass MyDataset(Dataset):\n def __init__(self, dataframe):\n self.dataframe = dataframe\n \n def __len__(self):\n return len(self.dataframe)\n\n def __getitem__(self, idx):\n return torch.tensor(self.dataframe.iloc[idx, :-1].values, dtype=torch.float32), \\\n torch.tensor(self.dataframe.iloc[idx, -1], dtype=torch.long)\n\ndataset = MyDataset(df)\ndataloader = DataLoader(dataset, batch_size=2, shuffle=True)<\/code><\/pre>\n5. \uacb0\ub860<\/h3>\n\ubcf8 \uac15\uc88c\uc5d0\uc11c\ub294 \ub525\ub7ec\ub2dd\uc5d0\uc11c \ub370\uc774\ud130 \uc804\ucc98\ub9ac\uc758 \uc911\uc694\uc131 \ubc0f \uacb0\uce21\uce58 \ucc98\ub9ac \ubc29\ubc95\uc5d0 \ub300\ud574 \uc54c\uc544\ubcf4\uc558\uc2b5\ub2c8\ub2e4. \ud30c\uc774\ud1a0\uce58\ub97c \uc774\uc6a9\ud558\uc5ec \uacb0\uce21\uce58\ub97c \ud655\uc778\ud558\uace0 \ucc98\ub9ac\ud558\ub294 \uacfc\uc815\uc744 \uc2e4\uc2b5\ud558\uc600\uc73c\uba70, \uc774\ub97c \ud1b5\ud574 \ub370\uc774\ud130\uc14b\uc744 \ud6a8\uacfc\uc801\uc73c\ub85c \uc900\ube44\ud560 \uc218 \uc788\ub294 \ubc29\ubc95\uc744 \ubc30\uc6b8 \uc218 \uc788\uc5c8\uc2b5\ub2c8\ub2e4. \ub370\uc774\ud130 \uc804\ucc98\ub9ac\ub294 \ub525\ub7ec\ub2dd \ubaa8\ub378\uc758 \uc131\ub2a5\uc744 \ub192\uc774\ub294 \uc911\uc694\ud55c \ub2e8\uacc4\uc774\ubbc0\ub85c, \ubc18\ub4dc\uc2dc \uc798 \uc774\ud574\ud558\uace0 \ud65c\uc6a9\ud574\uc57c \ud569\ub2c8\ub2e4.<\/p>\n\ucc38\uace0 \uc790\ub8cc<\/h2>\n\ub2e4\uc74c\uc758 \uc790\ub8cc\ub97c \ud1b5\ud574 \ub354 \ub9ce\uc740 \uc815\ubcf4\ub97c \uc5bb\uc744 \uc218 \uc788\uc2b5\ub2c8\ub2e4:<\/p>\n\nPytorch Documentation<\/a><\/li>\nPandas Documentation<\/a><\/li>\nScikit-learn Documentation<\/a><\/li>\n<\/ul>\n
\ub370\uc774\ud130 \uc804\ucc98\ub9ac\uac00 \ub05d\ub098\uba74, \ub370\uc774\ud130\uc14b\uc744 \ud30c\uc774\ud1a0\uce58\uc758 Dataset<\/code> \ud074\ub798\uc2a4\ub97c \uc0c1\uc18d\ud558\uc5ec \ubcc0\ud658\ud569\ub2c8\ub2e4.<\/p>\nclass MyDataset(Dataset):\n def __init__(self, dataframe):\n self.dataframe = dataframe\n \n def __len__(self):\n return len(self.dataframe)\n\n def __getitem__(self, idx):\n return torch.tensor(self.dataframe.iloc[idx, :-1].values, dtype=torch.float32), \\\n torch.tensor(self.dataframe.iloc[idx, -1], dtype=torch.long)\n\ndataset = MyDataset(df)\ndataloader = DataLoader(dataset, batch_size=2, shuffle=True)<\/code><\/pre>\n5. \uacb0\ub860<\/h3>\n\ubcf8 \uac15\uc88c\uc5d0\uc11c\ub294 \ub525\ub7ec\ub2dd\uc5d0\uc11c \ub370\uc774\ud130 \uc804\ucc98\ub9ac\uc758 \uc911\uc694\uc131 \ubc0f \uacb0\uce21\uce58 \ucc98\ub9ac \ubc29\ubc95\uc5d0 \ub300\ud574 \uc54c\uc544\ubcf4\uc558\uc2b5\ub2c8\ub2e4. \ud30c\uc774\ud1a0\uce58\ub97c \uc774\uc6a9\ud558\uc5ec \uacb0\uce21\uce58\ub97c \ud655\uc778\ud558\uace0 \ucc98\ub9ac\ud558\ub294 \uacfc\uc815\uc744 \uc2e4\uc2b5\ud558\uc600\uc73c\uba70, \uc774\ub97c \ud1b5\ud574 \ub370\uc774\ud130\uc14b\uc744 \ud6a8\uacfc\uc801\uc73c\ub85c \uc900\ube44\ud560 \uc218 \uc788\ub294 \ubc29\ubc95\uc744 \ubc30\uc6b8 \uc218 \uc788\uc5c8\uc2b5\ub2c8\ub2e4. \ub370\uc774\ud130 \uc804\ucc98\ub9ac\ub294 \ub525\ub7ec\ub2dd \ubaa8\ub378\uc758 \uc131\ub2a5\uc744 \ub192\uc774\ub294 \uc911\uc694\ud55c \ub2e8\uacc4\uc774\ubbc0\ub85c, \ubc18\ub4dc\uc2dc \uc798 \uc774\ud574\ud558\uace0 \ud65c\uc6a9\ud574\uc57c \ud569\ub2c8\ub2e4.<\/p>\n\ucc38\uace0 \uc790\ub8cc<\/h2>\n\ub2e4\uc74c\uc758 \uc790\ub8cc\ub97c \ud1b5\ud574 \ub354 \ub9ce\uc740 \uc815\ubcf4\ub97c \uc5bb\uc744 \uc218 \uc788\uc2b5\ub2c8\ub2e4:<\/p>\n\nPytorch Documentation<\/a><\/li>\nPandas Documentation<\/a><\/li>\nScikit-learn Documentation<\/a><\/li>\n<\/ul>\n
Dataset<\/code> \ud074\ub798\uc2a4\ub97c \uc0c1\uc18d\ud558\uc5ec \ubcc0\ud658\ud569\ub2c8\ub2e4.<\/p>\nclass MyDataset(Dataset):\n def __init__(self, dataframe):\n self.dataframe = dataframe\n \n def __len__(self):\n return len(self.dataframe)\n\n def __getitem__(self, idx):\n return torch.tensor(self.dataframe.iloc[idx, :-1].values, dtype=torch.float32), \\\n torch.tensor(self.dataframe.iloc[idx, -1], dtype=torch.long)\n\ndataset = MyDataset(df)\ndataloader = DataLoader(dataset, batch_size=2, shuffle=True)<\/code><\/pre>\n5. \uacb0\ub860<\/h3>\n\ubcf8 \uac15\uc88c\uc5d0\uc11c\ub294 \ub525\ub7ec\ub2dd\uc5d0\uc11c \ub370\uc774\ud130 \uc804\ucc98\ub9ac\uc758 \uc911\uc694\uc131 \ubc0f \uacb0\uce21\uce58 \ucc98\ub9ac \ubc29\ubc95\uc5d0 \ub300\ud574 \uc54c\uc544\ubcf4\uc558\uc2b5\ub2c8\ub2e4. \ud30c\uc774\ud1a0\uce58\ub97c \uc774\uc6a9\ud558\uc5ec \uacb0\uce21\uce58\ub97c \ud655\uc778\ud558\uace0 \ucc98\ub9ac\ud558\ub294 \uacfc\uc815\uc744 \uc2e4\uc2b5\ud558\uc600\uc73c\uba70, \uc774\ub97c \ud1b5\ud574 \ub370\uc774\ud130\uc14b\uc744 \ud6a8\uacfc\uc801\uc73c\ub85c \uc900\ube44\ud560 \uc218 \uc788\ub294 \ubc29\ubc95\uc744 \ubc30\uc6b8 \uc218 \uc788\uc5c8\uc2b5\ub2c8\ub2e4. \ub370\uc774\ud130 \uc804\ucc98\ub9ac\ub294 \ub525\ub7ec\ub2dd \ubaa8\ub378\uc758 \uc131\ub2a5\uc744 \ub192\uc774\ub294 \uc911\uc694\ud55c \ub2e8\uacc4\uc774\ubbc0\ub85c, \ubc18\ub4dc\uc2dc \uc798 \uc774\ud574\ud558\uace0 \ud65c\uc6a9\ud574\uc57c \ud569\ub2c8\ub2e4.<\/p>\n\ucc38\uace0 \uc790\ub8cc<\/h2>\n\ub2e4\uc74c\uc758 \uc790\ub8cc\ub97c \ud1b5\ud574 \ub354 \ub9ce\uc740 \uc815\ubcf4\ub97c \uc5bb\uc744 \uc218 \uc788\uc2b5\ub2c8\ub2e4:<\/p>\n\nPytorch Documentation<\/a><\/li>\nPandas Documentation<\/a><\/li>\nScikit-learn Documentation<\/a><\/li>\n<\/ul>\n
class MyDataset(Dataset):\n def __init__(self, dataframe):\n self.dataframe = dataframe\n \n def __len__(self):\n return len(self.dataframe)\n\n def __getitem__(self, idx):\n return torch.tensor(self.dataframe.iloc[idx, :-1].values, dtype=torch.float32), \\\n torch.tensor(self.dataframe.iloc[idx, -1], dtype=torch.long)\n\ndataset = MyDataset(df)\ndataloader = DataLoader(dataset, batch_size=2, shuffle=True)<\/code><\/pre>\n5. \uacb0\ub860<\/h3>\n\ubcf8 \uac15\uc88c\uc5d0\uc11c\ub294 \ub525\ub7ec\ub2dd\uc5d0\uc11c \ub370\uc774\ud130 \uc804\ucc98\ub9ac\uc758 \uc911\uc694\uc131 \ubc0f \uacb0\uce21\uce58 \ucc98\ub9ac \ubc29\ubc95\uc5d0 \ub300\ud574 \uc54c\uc544\ubcf4\uc558\uc2b5\ub2c8\ub2e4. \ud30c\uc774\ud1a0\uce58\ub97c \uc774\uc6a9\ud558\uc5ec \uacb0\uce21\uce58\ub97c \ud655\uc778\ud558\uace0 \ucc98\ub9ac\ud558\ub294 \uacfc\uc815\uc744 \uc2e4\uc2b5\ud558\uc600\uc73c\uba70, \uc774\ub97c \ud1b5\ud574 \ub370\uc774\ud130\uc14b\uc744 \ud6a8\uacfc\uc801\uc73c\ub85c \uc900\ube44\ud560 \uc218 \uc788\ub294 \ubc29\ubc95\uc744 \ubc30\uc6b8 \uc218 \uc788\uc5c8\uc2b5\ub2c8\ub2e4. \ub370\uc774\ud130 \uc804\ucc98\ub9ac\ub294 \ub525\ub7ec\ub2dd \ubaa8\ub378\uc758 \uc131\ub2a5\uc744 \ub192\uc774\ub294 \uc911\uc694\ud55c \ub2e8\uacc4\uc774\ubbc0\ub85c, \ubc18\ub4dc\uc2dc \uc798 \uc774\ud574\ud558\uace0 \ud65c\uc6a9\ud574\uc57c \ud569\ub2c8\ub2e4.<\/p>\n\ucc38\uace0 \uc790\ub8cc<\/h2>\n\ub2e4\uc74c\uc758 \uc790\ub8cc\ub97c \ud1b5\ud574 \ub354 \ub9ce\uc740 \uc815\ubcf4\ub97c \uc5bb\uc744 \uc218 \uc788\uc2b5\ub2c8\ub2e4:<\/p>\n\nPytorch Documentation<\/a><\/li>\nPandas Documentation<\/a><\/li>\nScikit-learn Documentation<\/a><\/li>\n<\/ul>\n
\ubcf8 \uac15\uc88c\uc5d0\uc11c\ub294 \ub525\ub7ec\ub2dd\uc5d0\uc11c \ub370\uc774\ud130 \uc804\ucc98\ub9ac\uc758 \uc911\uc694\uc131 \ubc0f \uacb0\uce21\uce58 \ucc98\ub9ac \ubc29\ubc95\uc5d0 \ub300\ud574 \uc54c\uc544\ubcf4\uc558\uc2b5\ub2c8\ub2e4. \ud30c\uc774\ud1a0\uce58\ub97c \uc774\uc6a9\ud558\uc5ec \uacb0\uce21\uce58\ub97c \ud655\uc778\ud558\uace0 \ucc98\ub9ac\ud558\ub294 \uacfc\uc815\uc744 \uc2e4\uc2b5\ud558\uc600\uc73c\uba70, \uc774\ub97c \ud1b5\ud574 \ub370\uc774\ud130\uc14b\uc744 \ud6a8\uacfc\uc801\uc73c\ub85c \uc900\ube44\ud560 \uc218 \uc788\ub294 \ubc29\ubc95\uc744 \ubc30\uc6b8 \uc218 \uc788\uc5c8\uc2b5\ub2c8\ub2e4. \ub370\uc774\ud130 \uc804\ucc98\ub9ac\ub294 \ub525\ub7ec\ub2dd \ubaa8\ub378\uc758 \uc131\ub2a5\uc744 \ub192\uc774\ub294 \uc911\uc694\ud55c \ub2e8\uacc4\uc774\ubbc0\ub85c, \ubc18\ub4dc\uc2dc \uc798 \uc774\ud574\ud558\uace0 \ud65c\uc6a9\ud574\uc57c \ud569\ub2c8\ub2e4.<\/p>\n
\ub2e4\uc74c\uc758 \uc790\ub8cc\ub97c \ud1b5\ud574 \ub354 \ub9ce\uc740 \uc815\ubcf4\ub97c \uc5bb\uc744 \uc218 \uc788\uc2b5\ub2c8\ub2e4:<\/p>\n