{"id":2457,"date":"2023-07-22T04:29:06","date_gmt":"2023-07-22T04:29:06","guid":{"rendered":"https:\/\/statorials.org\/ja\/python%e3%81%a6%e3%82%99%e3%81%ae%e4%ba%8c%e5%a4%89%e9%87%8f%e8%a7%a3%e6%9e%90\/"},"modified":"2023-07-22T04:29:06","modified_gmt":"2023-07-22T04:29:06","slug":"python%e3%81%a6%e3%82%99%e3%81%ae%e4%ba%8c%e5%a4%89%e9%87%8f%e8%a7%a3%e6%9e%90","status":"publish","type":"post","link":"https:\/\/statorials.org\/ja\/python%e3%81%a6%e3%82%99%e3%81%ae%e4%ba%8c%e5%a4%89%e9%87%8f%e8%a7%a3%e6%9e%90\/","title":{"rendered":"Python \u3067\u4e8c\u5909\u91cf\u5206\u6790\u3092\u5b9f\u884c\u3059\u308b\u65b9\u6cd5: \u4f8b\u4ed8\u304d"},"content":{"rendered":"

<\/p>\n

\n

\u4e8c\u5909\u91cf\u5206\u6790<\/strong>\u3068\u3044\u3046\u7528\u8a9e\u306f\u30012 \u3064\u306e\u5909\u6570\u306e\u5206\u6790\u3092\u6307\u3057\u307e\u3059\u3002\u63a5\u982d\u8f9e\u300cbi\u300d\u306f\u300c2\u300d\u3092\u610f\u5473\u3059\u308b\u306e\u3067\u3001\u3053\u308c\u3092\u899a\u3048\u3066\u304a\u304f\u3068\u3088\u3044\u3067\u3057\u3087\u3046\u3002<\/span><\/p>\n

\u4e8c\u5909\u91cf\u89e3\u6790\u306e\u76ee\u6a19\u306f\u30012 \u3064\u306e\u5909\u6570\u9593\u306e\u95a2\u4fc2\u3092\u7406\u89e3\u3059\u308b\u3053\u3068\u3067\u3059\u3002<\/span><\/p>\n

\u4e8c\u5909\u91cf\u89e3\u6790\u3092\u5b9f\u884c\u3059\u308b\u306b\u306f\u3001\u6b21\u306e 3 \u3064\u306e\u4e00\u822c\u7684\u306a\u65b9\u6cd5\u304c\u3042\u308a\u307e\u3059\u3002<\/span><\/p>\n

1.<\/strong>\u70b9\u7fa4<\/span><\/p>\n

2.<\/strong>\u76f8\u95a2\u4fc2\u6570<\/span><\/p>\n

3.<\/strong>\u5358\u7d14\u306a\u7dda\u5f62\u56de\u5e30<\/span><\/p>\n

\u6b21\u306e\u4f8b\u306f\u30012 \u3064\u306e\u5909\u6570\u306b\u95a2\u3059\u308b\u60c5\u5831\u3092\u542b\u3080\u6b21\u306e pandas DataFrame \u3092\u4f7f\u7528\u3057\u3066\u3001Python \u3067\u3053\u308c\u3089\u306e\u30bf\u30a4\u30d7\u306e\u4e8c\u5909\u91cf\u5206\u6790\u3092\u5b9f\u884c\u3059\u308b\u65b9\u6cd5\u3092\u793a\u3057\u3066\u3044\u307e\u3059: (1)<\/strong>\u52c9\u5f37\u306b\u8cbb\u3084\u3057\u305f\u6642\u9593\u3001\u304a\u3088\u3073(2)<\/strong> 20 \u4eba\u306e\u7570\u306a\u308b\u5b66\u751f\u304c\u53d6\u5f97\u3057\u305f\u8a66\u9a13\u306e\u30b9\u30b3\u30a2\u3002<\/span><\/p>\n

 import<\/span> pandas as<\/span> pd\n\n#createDataFrame<\/span>\ndf = pd. DataFrame<\/span> ({' hours<\/span> ': [1, 1, 1, 2, 2, 2, 3, 3, 3, 3,\n                             3, 4, 4, 5, 5, 6, 6, 6, 7, 8],\n                   ' score<\/span> ': [75, 66, 68, 74, 78, 72, 85, 82, 90, 82,\n                             80, 88, 85, 90, 92, 94, 94, 88, 91, 96]})\n\n#view first five rows of DataFrame\n<\/span>df. head<\/span> ()\n\n\thours score\n0 1 75\n1 1 66\n2 1 68\n3 2 74\n4 2 78<\/strong><\/pre>\n
 1. \u70b9\u7fa4<\/strong><\/span><\/h3>\n
\u6b21\u306e\u69cb\u6587\u3092\u4f7f\u7528\u3057\u3066\u3001\u5b66\u7fd2\u6642\u9593\u3068\u8a66\u9a13\u7d50\u679c\u306e\u6563\u5e03\u56f3\u3092\u4f5c\u6210\u3067\u304d\u307e\u3059\u3002<\/span> <\/p>\n
 import<\/span> matplotlib. pyplot<\/span> as<\/span> plt\n\n#create scatterplot of hours vs. score<\/span>\nplt. scatter<\/span> (df. hours<\/span> , df. score<\/span> )\nplt. title<\/span> (' Hours Studied vs. Exam Score<\/span> ')\nplt. xlabel<\/span> (' Hours Studied<\/span> ')\nplt. ylabel<\/span> (' Exam Score<\/span> ')\n<\/strong><\/pre>\n
\"\"<\/p>\n
 X \u8ef8\u306f\u5b66\u7fd2\u6642\u9593\u3092\u793a\u3057\u3001Y \u8ef8\u306f\u8a66\u9a13\u3067\u7372\u5f97\u3057\u305f\u6210\u7e3e\u3092\u793a\u3057\u307e\u3059\u3002<\/span><\/p>\n
\u30b0\u30e9\u30d5\u306f\u30012 \u3064\u306e\u5909\u6570\u306e\u9593\u306b\u6b63\u306e\u95a2\u4fc2\u304c\u3042\u308b\u3053\u3068\u3092\u793a\u3057\u3066\u3044\u307e\u3059\u3002\u5b66\u7fd2\u6642\u9593\u6570\u304c\u5897\u52a0\u3059\u308b\u306b\u3064\u308c\u3066\u3001\u8a66\u9a13\u306e\u30b9\u30b3\u30a2\u3082\u5897\u52a0\u3059\u308b\u50be\u5411\u304c\u3042\u308a\u307e\u3059\u3002<\/span><\/p>\n
 2. \u76f8\u95a2\u4fc2\u6570<\/strong><\/span><\/h3>\n
\u30d4\u30a2\u30bd\u30f3\u76f8\u95a2\u4fc2\u6570\u306f\u30012 \u3064\u306e\u5909\u6570\u9593\u306e\u7dda\u5f62\u95a2\u4fc2\u3092\u5b9a\u91cf\u5316\u3059\u308b\u65b9\u6cd5\u3067\u3059\u3002<\/span><\/p>\n
 pandas \u306ecorr()<\/strong>\u95a2\u6570\u3092\u4f7f\u7528\u3057\u3066\u76f8\u95a2\u884c\u5217\u3092\u4f5c\u6210\u3067\u304d\u307e\u3059\u3002<\/span><\/p>\n
 #create correlation matrix\n<\/span>df. corr<\/span> ()\n\n\thours score\nhours 1.000000 0.891306\nscore 0.891306 1.000000<\/strong><\/pre>\n
\u76f8\u95a2\u4fc2\u6570\u306f0.891<\/strong>\u3067\u3042\u308b\u3053\u3068\u304c\u308f\u304b\u308a\u307e\u3059\u3002\u3053\u308c\u306f\u3001<\/span>\u52c9\u5f37\u6642\u9593\u3068\u8a66\u9a13\u306e\u6210\u7e3e\u306e\u9593\u306b\u5f37\u3044\u6b63\u306e\u76f8\u95a2\u95a2\u4fc2\u304c\u3042\u308b\u3053\u3068\u3092\u793a\u3057\u3066\u3044\u307e\u3059\u3002<\/span><\/p>\n
 3. \u5358\u7d14\u306a\u7dda\u5f62\u56de\u5e30<\/strong><\/span><\/h3>\n
\u5358\u7d14\u7dda\u5f62\u56de\u5e30\u306f\u30012 \u3064\u306e\u5909\u6570\u9593\u306e\u95a2\u4fc2\u3092\u5b9a\u91cf\u5316\u3059\u308b\u305f\u3081\u306b\u4f7f\u7528\u3067\u304d\u308b\u7d71\u8a08\u624b\u6cd5\u3067\u3059\u3002<\/span><\/p>\n
 statsmodels \u30d1\u30c3\u30b1\u30fc\u30b8\u306eOLS()<\/strong>\u95a2\u6570\u3092\u4f7f\u7528\u3059\u308b\u3068\u3001\u5b66\u7fd2\u6642\u9593\u3068\u53d7\u3051\u53d6\u3063\u305f\u8a66\u9a13\u7d50\u679c\u306b\u5bfe\u3059\u308b\u5358\u7d14\u306a\u7dda\u5f62\u56de\u5e30\u30e2\u30c7\u30eb\u3092<\/a>\u3059\u3070\u3084\u304f\u5f53\u3066\u306f\u3081\u308b\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002<\/span><\/p>\n
 import<\/span> statsmodels. api<\/span> as<\/span> sm\n\n#define response variable\n<\/span>y = df[' score<\/span> ']\n\n#define explanatory variable\n<\/span>x = df[[' hours<\/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: 0.794\nModel: OLS Adj. R-squared: 0.783\nMethod: Least Squares F-statistic: 69.56\nDate: Mon, 22 Nov 2021 Prob (F-statistic): 1.35e-07\nTime: 16:15:52 Log-Likelihood: -55,886\nNo. Observations: 20 AIC: 115.8\nDf Residuals: 18 BIC: 117.8\nModel: 1                                         \nCovariance Type: non-robust                                         \n==================================================== ============================\n                 coef std err t P>|t| [0.025 0.975]\n-------------------------------------------------- ----------------------------\nconst 69.0734 1.965 35.149 0.000 64.945 73.202\nhours 3.8471 0.461 8.340 0.000 2.878 4.816\n==================================================== ============================\nOmnibus: 0.171 Durbin-Watson: 1.404\nProb(Omnibus): 0.918 Jarque-Bera (JB): 0.177\nSkew: 0.165 Prob(JB): 0.915\nKurtosis: 2.679 Cond. No. 9.37\n==================================================== ============================\n<\/strong><\/pre>\n
\u8fd1\u4f3c\u3055\u308c\u305f\u56de\u5e30\u5f0f\u306f\u6b21\u306e\u3088\u3046\u306b\u306a\u308a\u307e\u3059\u3002<\/span><\/p>\n
\u8a66\u9a13\u30b9\u30b3\u30a2 = 69.0734 + 3.8471*(\u52c9\u5f37\u6642\u9593)<\/span><\/p>\n
\u3053\u308c\u306f\u3001\u5b66\u7fd2\u6642\u9593\u304c\u8ffd\u52a0\u3055\u308c\u308b\u3054\u3068\u306b\u3001\u8a66\u9a13\u30b9\u30b3\u30a2\u304c\u5e73\u57473.8471<\/strong>\u5897\u52a0\u3059\u308b\u3053\u3068\u3092\u793a\u3057\u3066\u3044\u307e\u3059\u3002<\/span><\/p>\n
\u307e\u305f\u3001\u9069\u5408\u56de\u5e30\u5f0f\u3092\u4f7f\u7528\u3057\u3066\u3001\u5408\u8a08\u5b66\u7fd2\u6642\u9593\u6570\u306b\u57fa\u3065\u3044\u3066\u751f\u5f92\u304c\u53d7\u3051\u53d6\u308b\u30b9\u30b3\u30a2\u3092\u4e88\u6e2c\u3059\u308b\u3053\u3068\u3082\u3067\u304d\u307e\u3059\u3002<\/span><\/p>\n
\u305f\u3068\u3048\u3070\u30013 \u6642\u9593\u52c9\u5f37\u3057\u305f\u751f\u5f92\u306f81.6147<\/strong>\u306e\u30b9\u30b3\u30a2\u3092\u53d6\u5f97\u3059\u308b\u5fc5\u8981\u304c\u3042\u308a\u307e\u3059\u3002<\/span><\/p>\n