{"id":3570,"date":"2023-07-16T18:41:15","date_gmt":"2023-07-16T18:41:15","guid":{"rendered":"https:\/\/statorials.org\/ko\/%e1%84%90%e1%85%a9%e1%86%bc%e1%84%80%e1%85%a8%e1%84%86%e1%85%a9%e1%84%83%e1%85%a6%e1%86%af%e1%84%8b%e1%85%b3%e1%86%ab-%e1%84%8b%e1%85%a8%e1%84%8e%e1%85%b3%e1%86%a8%e1%84%92%e1%85%a1%e1%86%ab%e1%84%83\/"},"modified":"2023-07-16T18:41:15","modified_gmt":"2023-07-16T18:41:15","slug":"%e1%84%90%e1%85%a9%e1%86%bc%e1%84%80%e1%85%a8%e1%84%86%e1%85%a9%e1%84%83%e1%85%a6%e1%86%af%e1%84%8b%e1%85%b3%e1%86%ab-%e1%84%8b%e1%85%a8%e1%84%8e%e1%85%b3%e1%86%a8%e1%84%92%e1%85%a1%e1%86%ab%e1%84%83","status":"publish","type":"post","link":"https:\/\/statorials.org\/ko\/%e1%84%90%e1%85%a9%e1%86%bc%e1%84%80%e1%85%a8%e1%84%86%e1%85%a9%e1%84%83%e1%85%a6%e1%86%af%e1%84%8b%e1%85%b3%e1%86%ab-%e1%84%8b%e1%85%a8%e1%84%8e%e1%85%b3%e1%86%a8%e1%84%92%e1%85%a1%e1%86%ab%e1%84%83\/","title":{"rendered":"Statsmodels\uc5d0\uc11c \ud68c\uadc0 \ubaa8\ub378\uc744 \uc0ac\uc6a9\ud558\uc5ec \uc608\uce21\ud558\ub294 \ubc29\ubc95"},"content":{"rendered":"

<\/p>\n

\n

\ub2e4\uc74c \uae30\ubcf8 \uad6c\ubb38\uc744 \uc0ac\uc6a9\ud558\uba74 Python\uc758 statsmodels<\/a> \ubaa8\ub4c8\uc744 \uc0ac\uc6a9\ud558\uc5ec \ud68c\uadc0 \ubaa8\ub378 \ud53c\ud305\uc744 \uc0ac\uc6a9\ud558\uc5ec \uc0c8\ub85c\uc6b4 \uad00\ucc30\uc5d0 \ub300\ud574 \uc608\uce21\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/span><\/p>\n

 model. predict<\/span> (df_new)\n<\/strong><\/pre>\n
 \uc774 \ud2b9\uc815 \uad6c\ubb38\uc740 model<\/strong> \uc774\ub77c\ub294 \ud1b5\uacc4 \ubaa8\ub378\uc5d0 \uc801\ud569\ud55c \ud68c\uadc0 \ubaa8\ub378\uc744 \uc0ac\uc6a9\ud558\uc5ec df_new<\/strong> \ub77c\ub294 \uc0c8 DataFrame\uc758 \uac01 \ud589\uc5d0 \ub300\ud55c \uc608\uce21 \uc751\ub2f5 \uac12\uc744 \uacc4\uc0b0\ud569\ub2c8\ub2e4.<\/span><\/p>\n
 \ub2e4\uc74c \uc608\uc5d0\uc11c\ub294 \uc2e4\uc81c\ub85c \uc774 \uad6c\ubb38\uc744 \uc0ac\uc6a9\ud558\ub294 \ubc29\ubc95\uc744 \ubcf4\uc5ec\uc90d\ub2c8\ub2e4.<\/span><\/p>\n
 \uc608: Statsmodels\uc758 \ud68c\uadc0 \ubaa8\ub378\uc744 \uc0ac\uc6a9\ud558\uc5ec \uc608\uce21\ud558\uae30<\/strong><\/span><\/h2>\n
 \ud559\uc2b5 \uc2dc\uac04, \uc751\uc2dc\ud55c \uc900\ube44 \uc2dc\ud5d8, \ud2b9\uc815 \uc218\uc5c5\uc758 \ud559\uc0dd\ub4e4\uc774 \ubc1b\uc740 \ucd5c\uc885 \uc131\uc801\uc5d0 \ub300\ud55c \uc815\ubcf4\uac00 \ud3ec\ud568\ub41c \ub2e4\uc74c\uacfc \uac19\uc740 pandas DataFrame\uc774 \uc788\ub2e4\uace0 \uac00\uc815\ud569\ub2c8\ub2e4.<\/span><\/p>\n
 import<\/span> pandas as<\/span> pd\n\n#createDataFrame\n<\/span>df = pd. DataFrame<\/span> ({' hours<\/span> ': [1, 2, 2, 4, 2, 1, 5, 4, 2, 4, 4, 3, 6],\n                   ' exams<\/span> ': [1, 3, 3, 5, 2, 2, 1, 1, 0, 3, 4, 3, 2],\n                   ' score<\/span> ': [76, 78, 85, 88, 72, 69, 94, 94, 88, 92, 90, 75, 96]})\n\n#view head of DataFrame\n<\/span>df. head<\/span> ()\n\n\thours exam score\n0 1 1 76\n1 2 3 78\n2 2 3 85\n3 4 5 88\n4 2 2 72<\/strong><\/pre>\n
 import<\/span> statsmodels. api<\/span> as<\/span> sm\n\n#define predictor and response variables\n<\/span>y = df[' score<\/span> ']\nx = df[[' hours<\/span> ', ' exams<\/span> ']]\n\n#add constant to predictor variables\n<\/span>x = sm. add_constant<\/span> (x)\n\n#fit linear regression model\n<\/span>model = sm. OLS<\/span> (y,x). fit<\/span> ()\n\n#view model summary\n<\/span>print<\/span> ( model.summary<\/span> ())\n\n                            OLS Regression Results                            \n==================================================== ============================\nDept. Variable: R-squared score: 0.718\nModel: OLS Adj. R-squared: 0.661\nMethod: Least Squares F-statistic: 12.70\nDate: Fri, 05 Aug 2022 Prob (F-statistic): 0.00180\nTime: 09:24:38 Log-Likelihood: -38.618\nNo. Observations: 13 AIC: 83.24\nDf Residuals: 10 BIC: 84.93\nDf Model: 2                                         \nCovariance Type: non-robust                                         \n==================================================== ============================\n                 coef std err t P>|t| [0.025 0.975]\n-------------------------------------------------- ----------------------------\nconst 71.4048 4.001 17.847 0.000 62.490 80.319\nhours 5.1275 1.018 5.038 0.001 2.860 7.395\nexams -1.2121 1.147 -1.057 0.315 -3.768 1.344\n==================================================== ============================\nOmnibus: 1,103 Durbin-Watson: 1,248\nProb(Omnibus): 0.576 Jarque-Bera (JB): 0.803\nSkew: -0.289 Prob(JB): 0.669\nKurtosis: 1.928 Cond. No. 11.7\n==================================================== ============================\n<\/strong><\/pre>\n
 \ucd9c\ub825\uc758 coef<\/strong> \uc5f4\uc5d0\uc11c \uc801\ud569 \ud68c\uadc0 \ubaa8\ub378\uc744 \uc791\uc131\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/span><\/p>\n
 \uc810\uc218 = 71.4048 + 5.1275(\uc2dc\uac04) \u2013 1.2121(\uc2dc\ud5d8)<\/span><\/p>\n
 \uc774\uc81c \uc801\ud569 \ud68c\uadc0 \ubaa8\ub378\uc744 \uc0ac\uc6a9\ud558\uc5ec 5\uba85\uc758 \uc2e0\uc785\uc0dd\uc758 “\uc810\uc218”\ub97c \uc608\uce21\ud55c\ub2e4\uace0 \uac00\uc815\ud574 \ubcf4\uaca0\uc2b5\ub2c8\ub2e4.<\/span><\/p>\n
 \uba3c\uc800 5\uac1c\uc758 \uc0c8\ub85c\uc6b4 \uad00\uce21\uac12\uc744 \ubcf4\uad00\ud560 DataFrame\uc744 \ub9cc\ub4e4\uc5b4 \ubcf4\uaca0\uc2b5\ub2c8\ub2e4.<\/span><\/p>\n
 #create new DataFrame\ndf_new = pd. DataFrame<\/span> ({' hours<\/span> ': [1, 2, 2, 4, 5],\n                       ' exams<\/span> ': [1, 1, 4, 3, 3]})<\/span>\n\n#add column for constant\ndf_new = sm. add_constant<\/span> (df_new)\n<\/span>\n#view new DataFrame\nprint<\/span> (df_new)\n\n   const hours exams\n0 1.0 1 1\n1 1.0 2 1\n2 1.0 2 4\n3 1.0 4 3\n4 1.0 5 3<\/span><\/span><\/strong><\/pre>\n
 \ub2e4\uc74c\uc73c\ub85c, \uc801\ud569 \ud68c\uadc0 \ubaa8\ub378\uc758 \uc608\uce21 \ubcc0\uc218\uc5d0 \ub300\ud55c \uac12\uc73c\ub85c “\uc2dc\uac04”\uacfc “\uc2dc\ud5d8”\uc744 \uc0ac\uc6a9\ud558\uc5ec \uc608\uce21()<\/strong> \ud568\uc218\ub97c \uc0ac\uc6a9\ud558\uc5ec \uac01 \ud559\uc0dd\uc758 “\uc810\uc218”\ub97c \uc608\uce21\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/span><\/span><\/p>\n
 #predict scores for the five new students<\/span>\nmodel. predict<\/span> (df_new)\n\n0 75.320242\n1 80.447734\n2 76.811480\n3 88.278550\n4 93.406042\ndtype:float64\n<\/strong><\/pre>\n
 \uacb0\uacfc\ub97c \ud574\uc11d\ud558\ub294 \ubc29\ubc95\uc740 \ub2e4\uc74c\uacfc \uac19\uc2b5\ub2c8\ub2e4.<\/span><\/p>\n
 statsmodels \ubaa8\ub4c8\uc758 OLS()<\/strong> \ud568\uc218\ub97c \uc0ac\uc6a9\ud558\uc5ec “\uc2dc\uac04”\uacfc “\uc2dc\ud5d8”\uc744 \uc608\uce21 \ubcc0\uc218\ub85c \uc0ac\uc6a9\ud558\uace0 “\uc810\uc218”\ub97c \uc751\ub2f5 \ubcc0\uc218\ub85c \uc0ac\uc6a9\ud558\uc5ec \ub2e4\uc911 \uc120\ud615 \ud68c\uadc0 \ubaa8\ub378<\/a> \uc5d0 \ub9de\ucd9c \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/span><\/p>\n