\n \ucd5c\uadfc \uae08\uc735 \uc2dc\uc7a5\uc5d0\uc11c \uc54c\uace0\ub9ac\uc998 \ud2b8\ub808\uc774\ub529\uc774 \uae09\uaca9\ud788 \ubc1c\uc804\ud558\uba74\uc11c \ub2e4\uc591\ud55c \uba38\uc2e0\ub7ec\ub2dd \ubc0f \ub525\ub7ec\ub2dd \uae30\ubc95\uc774 \ud22c\uc790 \uc804\ub7b5\uc5d0 \ub3c4\uc785\ub418\uace0 \uc788\uc2b5\ub2c8\ub2e4. \ubcf8 \uac15\uc88c\uc5d0\uc11c\ub294 Sklearn<\/strong>\uc744 \uc0ac\uc6a9\ud574 \ubb38\uc11c \ub2e8\uc5b4 \ud589\ub82c(DTM, Document-Term Matrix)\uc744 \uc0dd\uc131\ud558\ub294 \uacfc\uc815\uacfc \uc774\ub97c \uae30\ubc18\uc73c\ub85c \ud55c \uba38\uc2e0\ub7ec\ub2dd \ubaa8\ub378\uc744 \ud65c\uc6a9\ud55c \ud2b8\ub808\uc774\ub529 \uc804\ub7b5\uc744 \uc218\ub9bd\ud558\ub294 \ubc29\ubc95\uc5d0 \ub300\ud574 \uc54c\uc544\ubcf4\uaca0\uc2b5\ub2c8\ub2e4.\n<\/p>\n \n \uc54c\uace0\ub9ac\uc998 \ud2b8\ub808\uc774\ub529\uc740 \uc8fc\uc2dd, \uc678\ud658, \uc554\ud638\ud654\ud3d0 \ub4f1 \ub2e4\uc591\ud55c \uae08\uc735 \uc790\uc0b0\uc744 \ub9e4\ub9e4\ud558\ub294 \uacfc\uc815\uc744 \uc790\ub3d9\ud654\ud558\ub294 \uae30\uc220\uc785\ub2c8\ub2e4. \ub370\uc774\ud130 \ubd84\uc11d, \uc804\ub7b5 \uc218\ub9bd, \ub9e4\ub9e4 \uc2e4\ud589 \ub4f1\uc774 \ud3ec\ud568\ub418\uba70, \uadf8 \uacfc\uc815\uc5d0\uc11c \uba38\uc2e0\ub7ec\ub2dd \uae30\ubc95\uc774 \uc911\uc694\ud55c \uc5ed\ud560\uc744 \uc218\ud589\ud558\uace0 \uc788\uc2b5\ub2c8\ub2e4.\n<\/p>\n \n \uba38\uc2e0\ub7ec\ub2dd\uc740 \ub370\uc774\ud130\uc5d0\uc11c \ud328\ud134\uc744 \ud559\uc2b5\ud558\uace0 \uc608\uce21\ud558\ub294 \uc54c\uace0\ub9ac\uc998\uc744 \uc0ac\uc6a9\ud558\ub294 \uc778\uacf5\uc9c0\ub2a5\uc758 \ud55c \ubd84\uc57c\uc785\ub2c8\ub2e4. \uc785\ub825 \ub370\uc774\ud130\uc640 \ucd9c\ub825 \ub370\uc774\ud130\ub97c \ubc14\ud0d5\uc73c\ub85c \ubaa8\ub378\uc744 \ud559\uc2b5\ud558\uc5ec \ubbf8\uc9c0\uc758 \ub370\uc774\ud130\uc5d0 \ub300\ud55c \uc608\uce21\uc744 \uac00\ub2a5\ud558\uac8c \ud569\ub2c8\ub2e4.\n<\/p>\n \n \ub525\ub7ec\ub2dd\uc740 \uba38\uc2e0\ub7ec\ub2dd\uc758 \ud55c \uac08\ub798\ub85c, \uc778\uacf5\uc2e0\uacbd\ub9dd\uc744 \uae30\ubc18\uc73c\ub85c \ud55c \ud559\uc2b5 \ubc29\uc2dd\uc785\ub2c8\ub2e4. \ud2b9\ud788, \ub300\ub7c9\uc758 \ub370\uc774\ud130\uc640 \ubcf5\uc7a1\ud55c \uad6c\uc870\ub97c \ucc98\ub9ac\ud558\uae30\uc5d0 \ub6f0\uc5b4\ub09c \uc131\ub2a5\uc744 \ubcf4\uc785\ub2c8\ub2e4.\n<\/p>\n \n \ubb38\uc11c \ub2e8\uc5b4 \ud589\ub82c(DTM)\uc740 \uc790\uc5f0\uc5b4 \ucc98\ub9ac(NLP) \ubd84\uc57c\uc5d0\uc11c \uc0ac\uc6a9\ub418\ub294 \ub370\uc774\ud130 \uad6c\uc870\ub85c, \ud14d\uc2a4\ud2b8 \ubb38\uc11c\uc758 \ub0b4\uc6a9\uc744 \uc218\uce58\ud654\ud558\ub294 \ubc29\ubc95\uc785\ub2c8\ub2e4. \uac01 \ud589\uc740 \ubb38\uc11c\ub97c, \uac01 \uc5f4\uc740 \ub2e8\uc5b4\ub97c \ub098\ud0c0\ub0b4\uba70, \ud589\ub82c\uc758 \uac01 \uc694\uc18c\ub294 \ud2b9\uc815 \ubb38\uc11c\uc5d0\uc11c \ud574\ub2f9 \ub2e8\uc5b4\uac00 \uc5bc\ub9c8\ub098 \ub4f1\uc7a5\ud558\ub294\uc9c0\ub97c \ub098\ud0c0\ub0c5\ub2c8\ub2e4.\n<\/p>\n \n DTM\uc744 \uc0dd\uc131\ud558\ub294 \uacfc\uc815\uc740 \uc8fc\ub85c \ub2e4\uc74c\uacfc \uac19\uc740 \ub2e8\uacc4\ub85c \uc9c4\ud589\ub429\ub2c8\ub2e4:<\/p>\n \n \uc774\uc81c Sklearn<\/strong> \ub77c\uc774\ube0c\ub7ec\ub9ac\ub97c \uc0ac\uc6a9\ud558\uc5ec DTM\uc744 \uc0dd\uc131\ud558\ub294 \ubc29\ubc95\uc744 \uc0b4\ud3b4\ubcf4\uaca0\uc2b5\ub2c8\ub2e4. Sklearn\uc740 \ud30c\uc774\uc36c\uc758 \uba38\uc2e0\ub7ec\ub2dd \ub77c\uc774\ube0c\ub7ec\ub9ac\ub85c, \ub2e4\uc591\ud55c \uc54c\uace0\ub9ac\uc998 \ubc0f \uc720\ud2f8\ub9ac\ud2f0 \ud568\uc218\ub4e4\uc744 \uc81c\uacf5\ud569\ub2c8\ub2e4.\n<\/p>\n \n DTM \uc0dd\uc131\uc744 \uc704\ud574 \ud544\uc694\ud55c \ub77c\uc774\ube0c\ub7ec\ub9ac\ub97c \uc124\uce58\ud569\ub2c8\ub2e4. \ub2e4\uc74c\uacfc \uac19\uc740 \uba85\ub839\uc5b4\ub97c \uc0ac\uc6a9\ud569\ub2c8\ub2e4:\n<\/p>\n \n \ud14d\uc2a4\ud2b8 \ub370\uc774\ud130\ub97c \uc218\uc9d1\ud558\ub294 \ubc29\ubc95\uc740 \ub2e4\uc591\ud569\ub2c8\ub2e4. \uc608\ub97c \ub4e4\uc5b4, \uc6f9 \uc2a4\ud06c\ub798\ud551\uc744 \ud1b5\ud574 \ub274\uc2a4 \uae30\uc0ac\ub97c \uc218\uc9d1\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4. \ud558\uc9c0\ub9cc \uc774\ubc88 \uac15\uc88c\uc5d0\uc11c\ub294 \uc608\uc2dc \ub370\uc774\ud130\ub97c \uc0ac\uc6a9\ud55c\ub2e4\uace0 \uac00\uc815\ud558\uaca0\uc2b5\ub2c8\ub2e4.\n<\/p>\n \n \uc774\uc81c Scikit-learn\uc744 \uc0ac\uc6a9\ud558\uc5ec DTM\uc744 \uc0dd\uc131\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4. \n DTM\uc744 \uc0dd\uc131\ud55c \ud6c4, \uc774\ub97c \uba38\uc2e0\ub7ec\ub2dd \ubaa8\ub378\uc5d0 \uc801\uc6a9\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4. \ub2e4\uc591\ud55c \uba38\uc2e0\ub7ec\ub2dd \uae30\ubc95 \uc911, \uc608\ub97c \ub4e4\uc5b4, \ub85c\uc9c0\uc2a4\ud2f1 \ud68c\uadc0, \uc11c\ud3ec\ud2b8 \ubca1\ud130 \uba38\uc2e0(SVM), \ub79c\ub364 \ud3ec\ub808\uc2a4\ud2b8\uc640 \uac19\uc740 \ubd84\ub958 \uc54c\uace0\ub9ac\uc998\uc744 \uc0ac\uc6a9\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.\n<\/p>\n \n DTM\uc744 \uae30\ubc18\uc73c\ub85c \ub370\uc774\ud130\ub97c \ud6c8\ub828\ud560 \uc900\ube44\uac00 \uc644\ub8cc\ub418\uc5c8\uc2b5\ub2c8\ub2e4. \ub370\uc774\ud130\ud504\ub808\uc784\uc758 \ud615\ud0dc\ub85c \ub808\uc774\ube14\uc744 \ucd94\uac00\ud558\uace0 \ud6c8\ub828 \ub370\uc774\ud130\ub97c \uc900\ube44\ud569\ub2c8\ub2e4.\n<\/p>\n \n \ud6c8\ub828\ub41c \ubaa8\ub378\uc744 \uc0ac\uc6a9\ud558\uc5ec \ud14c\uc2a4\ud2b8 \ub370\uc774\ud130\uc5d0 \ub300\ud55c \uc608\uce21\uc744 \uc218\ud589\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.\n<\/p>\n \n \ubaa8\ub378\uc758 \uc131\ub2a5\uc744 \ud3c9\uac00\ud558\uae30 \uc704\ud574 \ub2e4\uc591\ud55c \ud3c9\uac00 \uc9c0\ud45c\ub97c \uc0ac\uc6a9\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4. \uc815\ud655\ub3c4, F1-score, \uc815\ubc00\ub3c4, \uc7ac\ud604\uc728 \ub4f1\uc744 \ud65c\uc6a9\ud558\uc5ec \ubaa8\ub378\uc758 \uc608\uce21 \uc131\ub2a5\uc744 \ud3c9\uac00\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.\n<\/p>\n \n \ubcf8 \uac15\uc88c\uc5d0\uc11c\ub294 Sklearn \ub77c\uc774\ube0c\ub7ec\ub9ac\ub97c \uc0ac\uc6a9\ud558\uc5ec \ubb38\uc11c \ub2e8\uc5b4 \ud589\ub82c\uc744 \uc0dd\uc131\ud558\uace0 \uc774\ub97c \uae30\ubc18\uc73c\ub85c \ud55c \uba38\uc2e0\ub7ec\ub2dd \ubaa8\ub378\uc758 \ud6c8\ub828 \ubc0f \ud3c9\uac00 \uacfc\uc815\uc5d0 \ub300\ud574 \uc54c\uc544\ubcf4\uc558\uc2b5\ub2c8\ub2e4. \uc54c\uace0\ub9ac\uc998 \ud2b8\ub808\uc774\ub529\uc5d0\uc11c\ub294 \ud14d\uc2a4\ud2b8 \ub370\uc774\ud130(\ub274\uc2a4, \uc18c\uc15c \ubbf8\ub514\uc5b4 \ub4f1)\ub97c \ubd84\uc11d\ud558\uc5ec \uc2dc\uc7a5\uc758 \ubc29\ud5a5\uc131\uc744 \uc608\uce21\ud558\uace0 \ud2b8\ub808\uc774\ub529 \uc804\ub7b5\uc744 \uc218\ub9bd\ud558\ub294 \ub370 \ub9e4\uc6b0 \uc720\uc6a9\ud569\ub2c8\ub2e4.\n<\/p>\n \n \ud5a5\ud6c4 \uc5f0\uad6c \ubc29\ud5a5\uc73c\ub85c\ub294 \ub525\ub7ec\ub2dd \uae30\ubc95\uc744 \ud65c\uc6a9\ud55c \ubaa8\ub378 \uac1c\uc120, \ub2e4\uc591\ud55c \ub370\uc774\ud130 \uc18c\uc2a4(\uc608: \uc18c\uc15c \ubbf8\ub514\uc5b4, \uacbd\uc81c \uc9c0\ud45c \ub4f1)\uc758 \ud1b5\ud569, \uace0\uae09 \uc790\uc5f0\uc5b4 \ucc98\ub9ac \uae30\ubc95 \ub4f1\uc744 \uace0\ub824\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.\n<\/p>\n \n \ub354 \ub098\uc544\uac00, \uc2e4\uc81c \ud2b8\ub808\uc774\ub529 \uc2dc\uc2a4\ud15c\uc5d0 \ud1b5\ud569\ud558\uae30 \uc704\ud55c \ubaa8\ub378\uc758 \uc2e4\uc6a9\uc131 \ud14c\uc2a4\ud2b8, \uc2e4\uc2dc\uac04 \ub370\uc774\ud130 \ucc98\ub9ac \uae30\ubc95 \ubc0f \ubc31\ud14c\uc2a4\ud305 \ubc29\ubc95\ub860\ub3c4 \uac15\uad6c\ud574\uc57c \ud560 \uac83\uc785\ub2c8\ub2e4.\n<\/p>\n1. \uc54c\uace0\ub9ac\uc998 \ud2b8\ub808\uc774\ub529\uacfc \uba38\uc2e0\ub7ec\ub2dd\uc758 \uac1c\uc694<\/h2>\n
1.1 \uba38\uc2e0\ub7ec\ub2dd \uac1c\uc694<\/h3>\n
1.2 \ub525\ub7ec\ub2dd \uac1c\uc694<\/h3>\n
2. \ubb38\uc11c \ub2e8\uc5b4 \ud589\ub82c(DTM) \uc774\ud574\ud558\uae30<\/h2>\n
2.1 DTM \uc0dd\uc131 \ubc29\ubc95<\/h3>\n
\n
3. Sklearn\uc744 \ud65c\uc6a9\ud55c DTM \uc0dd\uc131<\/h2>\n
3.1 \ub77c\uc774\ube0c\ub7ec\ub9ac \uc124\uce58<\/h3>\n
pip install scikit-learn pandas numpy<\/code><\/pre>\n3.2 \ub370\uc774\ud130 \uc218\uc9d1 \ubc0f \uc804\ucc98\ub9ac<\/h3>\n
import pandas as pd\n\n# \uc608\uc2dc \ub370\uc774\ud130 \uc0dd\uc131\ndata = {'document': [\n '\uc8fc\uc2dd \uc2dc\uc7a5\uc774 \uc0c1\uc2b9\ud558\uace0 \uc788\ub2e4.',\n '\uae08\ub9ac \uc778\uc0c1\uc774 \uc608\uc0c1\ub41c\ub2e4.',\n '\uc8fc\uc2dd \ub9e4\ub3c4 \uc2dc\uc810\uc774 \uc911\uc694\ud558\ub2e4.'\n]}\ndf = pd.DataFrame(data)<\/code><\/pre>\n3.3 \ubb38\uc11c \ub2e8\uc5b4 \ud589\ub82c(DTM) \uc0dd\uc131<\/h3>\n
CountVectorizer<\/code> \ub610\ub294 TfidfVectorizer<\/code> \ud568\uc218\ub97c \uc0ac\uc6a9\ud560 \uc218 \uc788\ub294\ub370, \ud6c4\uc790\ub294 TF-IDF\ub97c \uae30\ubc18\uc73c\ub85c DTM\uc744 \uc0dd\uc131\ud569\ub2c8\ub2e4.\n<\/p>\nfrom sklearn.feature_extraction.text import CountVectorizer\n\n# CountVectorizer\ub97c \uc0ac\uc6a9\ud558\uc5ec DTM \uc0dd\uc131\nvectorizer = CountVectorizer()\ndtm = vectorizer.fit_transform(df['document'])\n\n# DTM\uc744 \ub370\uc774\ud130\ud504\ub808\uc784\uc73c\ub85c \ubcc0\ud658\ndtm_df = pd.DataFrame(dtm.toarray(), columns=vectorizer.get_feature_names_out())\nprint(dtm_df)<\/code><\/pre>\n4. \uba38\uc2e0\ub7ec\ub2dd \ubaa8\ub378 \uc801\uc6a9<\/h2>\n
4.1 \ubaa8\ub378 \ud6c8\ub828<\/h3>\n
from sklearn.model_selection import train_test_split\nfrom sklearn.linear_model import LogisticRegression\n\n# \ub808\uc774\ube14 \uc0dd\uc131 (\uc608\uc2dc)\nlabels = [1, 0, 1] # \uac01 \ubb38\uc11c\uc758 \ub808\uc774\ube14\uc744 \uc815\uc758\ndf['label'] = labels\n\n# \ud6c8\ub828\/\ud14c\uc2a4\ud2b8 \ub370\uc774\ud130 \ubd84\ub9ac\nX_train, X_test, y_train, y_test = train_test_split(dtm_df, df['label'], test_size=0.2, random_state=42)\n \n# \ubaa8\ub378 \ud6c8\ub828\nmodel = LogisticRegression()\nmodel.fit(X_train, y_train)<\/code><\/pre>\n4.2 \uc608\uce21 \uc218\ud589<\/h3>\n
predictions = model.predict(X_test)\nprint(predictions)<\/code><\/pre>\n5. \ubaa8\ub378 \ud3c9\uac00<\/h2>\n
from sklearn.metrics import accuracy_score, classification_report\n\n# \uc815\ud655\ub3c4 \ud3c9\uac00\naccuracy = accuracy_score(y_test, predictions)\nprint(f\"Accuracy: {accuracy}\")\n\n# \uc790\uc138\ud55c \ud3c9\uac00 \ub9ac\ud3ec\ud2b8\nreport = classification_report(y_test, predictions)\nprint(report)<\/code><\/pre>\n6. \uacb0\ub860 \ubc0f \ud5a5\ud6c4 \uc5f0\uad6c \ubc29\ud5a5<\/h2>\n
\ucc38\uace0\ubb38\ud5cc<\/h2>\n