{"id":3027,"date":"2023-07-19T13:46:31","date_gmt":"2023-07-19T13:46:31","guid":{"rendered":"https:\/\/statorials.org\/ko\/%e1%84%8b%e1%85%a7%e1%84%85%e1%85%a5-%e1%84%80%e1%85%a9%e1%86%a8%e1%84%89%e1%85%a5%e1%86%ab-%e1%84%80%e1%85%b3%e1%84%85%e1%85%b5%e1%84%80%e1%85%b5-roc-python\/"},"modified":"2023-07-19T13:46:31","modified_gmt":"2023-07-19T13:46:31","slug":"%e1%84%8b%e1%85%a7%e1%84%85%e1%85%a5-%e1%84%80%e1%85%a9%e1%86%a8%e1%84%89%e1%85%a5%e1%86%ab-%e1%84%80%e1%85%b3%e1%84%85%e1%85%b5%e1%84%80%e1%85%b5-roc-python","status":"publish","type":"post","link":"https:\/\/statorials.org\/ko\/%e1%84%8b%e1%85%a7%e1%84%85%e1%85%a5-%e1%84%80%e1%85%a9%e1%86%a8%e1%84%89%e1%85%a5%e1%86%ab-%e1%84%80%e1%85%b3%e1%84%85%e1%85%b5%e1%84%80%e1%85%b5-roc-python\/","title":{"rendered":"Python\uc5d0\uc11c \uc5ec\ub7ec roc \uace1\uc120\uc744 \uadf8\ub9ac\ub294 \ubc29\ubc95(\uc608\uc81c \ud3ec\ud568)"},"content":{"rendered":"

<\/p>\n

\n

\uae30\uacc4 \ud559\uc2b5\uc5d0\uc11c \ubd84\ub958 \ubaa8\ub378<\/a> \uc758 \uc131\ub2a5\uc744 \uc2dc\uac01\ud654\ud558\ub294 \ud55c \uac00\uc9c0 \ubc29\ubc95\uc740 “\uc218\uc2e0\uae30 \uc791\ub3d9 \ud2b9\uc131” \uace1\uc120\uc744 \ub098\ud0c0\ub0b4\ub294 ROC \uace1\uc120\uc744<\/strong> \ub9cc\ub4dc\ub294 \uac83\uc785\ub2c8\ub2e4.<\/span><\/p>\n

\uc885\uc885 \uc5ec\ub7ec \ubd84\ub958 \ubaa8\ub378\uc744 \ub2e8\uc77c \ub370\uc774\ud130 \uc138\ud2b8\uc5d0 \ub9de\ucd94\uace0 \uac01 \ubaa8\ub378\uc5d0 \ub300\ud55c ROC \uace1\uc120\uc744 \ub9cc\ub4e4\uc5b4 \uc5b4\ub5a4 \ubaa8\ub378\uc774 \ub370\uc774\ud130\uc5d0\uc11c \uac00\uc7a5 \uc798 \uc791\ub3d9\ud558\ub294\uc9c0 \uc2dc\uac01\ud654\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/span><\/p>\n

\ub2e4\uc74c \ub2e8\uacc4\ubcc4 \uc608\uc81c\uc5d0\uc11c\ub294 Python\uc5d0\uc11c \uc5ec\ub7ec ROC \uace1\uc120\uc744 \uadf8\ub9ac\ub294 \ubc29\ubc95\uc744 \ubcf4\uc5ec\uc90d\ub2c8\ub2e4.<\/span><\/p>\n

1\ub2e8\uacc4: \ud544\uc694\ud55c \ud328\ud0a4\uc9c0 \uac00\uc838\uc624\uae30<\/strong><\/span><\/h3>\n

\uba3c\uc800, \uba87 \uac00\uc9c0 \ud544\uc218 \ud328\ud0a4\uc9c0\ub97c Python\uc73c\ub85c \uac00\uc838\uc635\ub2c8\ub2e4.<\/span><\/p>\n

 from<\/span> sklearn import<\/span> metrics\nfrom<\/span> sklearn import<\/span> datasets\nfrom<\/span> sklearn. model_selection<\/span> import<\/span> train_test_split\nfrom<\/span> sklearn. linear_model<\/span> import<\/span> LogisticRegression\nfrom<\/span> sklearn. set<\/span> import<\/span> GradientBoostingClassifier\nimport<\/span> numpy as<\/span> np\nimport<\/span> matplotlib. pyplot<\/span> as<\/span> plt\n<\/strong><\/span><\/pre>\n
 2\ub2e8\uacc4: \uac00\uc9dc \ub370\uc774\ud130 \uc0dd\uc131<\/strong><\/span><\/h3>\n
 \ub2e4\uc74c\uc73c\ub85c sklearn\uc758 make_classification()<\/a> \ud568\uc218\ub97c \uc0ac\uc6a9\ud558\uc5ec 1000\uac1c\uc758 \ud589, 4\uac1c\uc758 \uc608\uce21 \ubcc0\uc218 \ubc0f \uc774\uc9c4 \uc751\ub2f5 \ubcc0\uc218\uac00 \uc788\ub294 \uac00\uc9dc \ub370\uc774\ud130 \uc138\ud2b8\ub97c \ub9cc\ub4ed\ub2c8\ub2e4.<\/span><\/p>\n
 #create fake dataset\n<\/span>X, y = datasets. make_classification<\/span> (n_samples= 1000<\/span> ,\n                                    n_features= 4<\/span> ,\n                                    n_informative= 3<\/span> ,\n                                    n_redundant= 1<\/span> ,\n                                    random_state= 0<\/span> )\n\n#split dataset into training and testing set\n<\/span>X_train, X_test, y_train, y_test = train_test_split(X, y, test_size= .3<\/span> , random_state= 0<\/span> )<\/strong><\/span><\/pre>\n
 3\ub2e8\uacc4: \uc5ec\ub7ec \ubaa8\ub378\uc744 \ud53c\ud305\ud558\uace0 ROC \uace1\uc120 \uadf8\ub9ac\uae30<\/strong><\/span><\/h3>\n
 \ub2e4\uc74c\uc73c\ub85c, \ub85c\uc9c0\uc2a4\ud2f1 \ud68c\uadc0 \ubaa8\ub378\uc744 \uc801\uc6a9\ud55c \ub2e4\uc74c \uacbd\uc0ac \uac15\ud654 \ubaa8\ub378\uc744 \ub370\uc774\ud130\uc5d0 \uc801\uc6a9\ud558\uace0 \ub3d9\uc77c\ud55c \ud50c\ub86f\uc5d0 \uac01 \ubaa8\ub378\uc5d0 \ub300\ud55c ROC \uace1\uc120\uc744 \uadf8\ub9bd\ub2c8\ub2e4.<\/span> <\/p>\n
 #set up plotting area\n<\/span>plt. Figure<\/span> (0). clf<\/span> ()\n\n#fit logistic regression model and plot ROC curve\n<\/span>model = LogisticRegression()\nmodel. fit<\/span> (X_train, y_train)\ny_pred = model. predict_proba<\/span> (X_test)[:, 1]\nfpr, tpr, _ = metrics. roc_curve<\/span> (y_test, y_pred)\nauc = round(metrics. roc_auc_score<\/span> (y_test, y_pred), 4)\nplt. plot<\/span> (fpr,tpr,label=\"Logistic Regression, AUC=\"+str(auc))\n\n#fit gradient boosted model and plot ROC curve\n<\/span>model = GradientBoostingClassifier()\nmodel. fit<\/span> (X_train, y_train)\ny_pred = model. predict_proba<\/span> (X_test)[:, 1]\nfpr, tpr, _ = metrics. roc_curve<\/span> (y_test, y_pred)\nauc = round(metrics. roc_auc_score<\/span> (y_test, y_pred), 4)\nplt. plot<\/span> (fpr,tpr,label=\"Gradient Boosting, AUC=\"+str(auc))\n\n#add legend\n<\/span>plt. legend<\/span> ()<\/strong><\/span> <\/pre>\n
\"Python\uc5d0\uc11c<\/p>\n
 \ud30c\ub780\uc0c9 \uc120\uc740 \ub85c\uc9c0\uc2a4\ud2f1 \ud68c\uadc0 \ubaa8\ub378\uc758 ROC \uace1\uc120\uc744 \ub098\ud0c0\ub0b4\uace0 \uc8fc\ud669\uc0c9 \uc120\uc740 \uadf8\ub798\ub514\uc5b8\ud2b8 \ubd80\uc2a4\ud305 \ubaa8\ub378\uc758 ROC \uace1\uc120\uc744 \ub098\ud0c0\ub0c5\ub2c8\ub2e4.<\/span><\/p>\n
 ROC \uace1\uc120\uc774 \ud50c\ub86f\uc758 \uc67c\ucabd \uc0c1\ub2e8 \ubaa8\uc11c\ub9ac\uc5d0 \uac00\uae4c\uc6b8\uc218\ub85d \ubaa8\ub378\uc774 \ub370\uc774\ud130\ub97c \ubc94\uc8fc\ub85c \ub354 \uc798 \ubd84\ub958\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/span><\/p>\n
 \uc774\ub97c \uc815\ub7c9\ud654\ud558\uae30 \uc704\ud574 \uace1\uc120 \uc544\ub798\uc5d0 \uc788\ub294 \ud50c\ub86f\uc758 \uc591\uc744 \uc54c\ub824\uc8fc\ub294 AUC(\uace1\uc120 \uc544\ub798 \uc601\uc5ed)\ub97c \uacc4\uc0b0\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/span><\/p>\n
 AUC\uac00 1\uc5d0 \uac00\uae4c\uc6b8\uc218\ub85d \ubaa8\ub378\uc774 \ub354 \uc88b\uc2b5\ub2c8\ub2e4.<\/span><\/p>\n
 \ucc28\ud2b8\uc5d0\uc11c \uac01 \ubaa8\ub378\uc5d0 \ub300\ud55c \ub2e4\uc74c AUC \uce21\uc815\ud56d\ubaa9\uc744 \ubcfc \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/span><\/p>\n