{"id":1495,"date":"2019-06-29T15:53:23","date_gmt":"2019-06-29T06:53:23","guid":{"rendered":"https:\/\/tnishimaki.com\/?p=1495"},"modified":"2025-06-12T19:32:08","modified_gmt":"2025-06-12T10:32:08","slug":"python%e3%81%ab%e3%82%88%e3%82%8b%e5%9b%9e%e5%b8%b0%e5%88%86%e6%9e%90%e3%80%9c%e3%83%87%e3%83%bc%e3%82%bf%e8%aa%ad%e3%81%bf%e8%be%bc%e3%81%bf%e3%81%8b%e3%82%89%e3%82%b0%e3%83%a9%e3%83%95%e5%8c%96","status":"publish","type":"post","link":"https:\/\/analysis-navi.com\/?p=1495","title":{"rendered":"Python\u306b\u3088\u308b\u56de\u5e30\u5206\u6790\u3068\u7d50\u679c\u306e\u53ef\u8996\u5316"},"content":{"rendered":"\n

Python\u3092\u4f7f\u3063\u3066\u56de\u5e30\u5206\u6790\u3092\u884c\u3063\u3066\u307f\u307e\u3057\u3087\u3046\u3002
\u7406\u8ad6\u3084\u7528\u8a9e\u306b\u3064\u3044\u3066\u306f\u3053\u3061\u3089<\/a>\u3092\u3054\u89a7\u304f\u3060\u3055\u3044\u3002<\/p>\n\n\n\n

\nhttps:\/\/analysis-navi.com\/?p=1217\n<\/div><\/figure>\n\n\n\n\n\n\n

\u30c7\u30fc\u30bf\u306e\u8aad\u307f\u8fbc\u307f<\/h2>\n\n\n\n

\u307e\u305a\u306f\u4f55\u306f\u3068\u3082\u3042\u308c\u3001\u30c7\u30fc\u30bf\u3092\u8aad\u307f\u8fbc\u307f\u307e\u3059\u3002
\u4eca\u56de\u306f\u300c\u6c17\u6e29\u3068\u30a2\u30a4\u30b9\u30af\u30ea\u30fc\u30e0\u306e\u58f2\u4e0a\u300d\u30c7\u30fc\u30bf\u3092\u8aad\u307f\u8fbc\u307f\u3001\u305d\u306e\u95a2\u4fc2\u6027\u3092\u8abf\u3079\u3066\u307f\u307e\u3059\u3002<\/span><\/strong>
\u305d\u3057\u3066\u3001\u305d\u308c\u306b\u57fa\u3065\u3044\u3066\u7fcc\u65e5\u4ee5\u964d\u306e\u4e88\u60f3\u6c17\u6e29\u304b\u3089\u30a2\u30a4\u30b9\u30af\u30ea\u30fc\u30e0\u306e\u58f2\u4e0a\u3092\u4e88\u6e2c\u3057\u3066\u307f\u307e\u3057\u3087\u3046\u3002<\/p>\n\n\n\n

\u3061\u306a\u307f\u306b\u3001\u30d5\u30a1\u30a4\u30eb\u306f\u4ee5\u4e0b\u306e\u3088\u3046\u306a\u5f62\u5f0f\u306b\u306a\u3063\u3066\u3044\u307e\u3059\u3002
– \u65e2\u77e5\u306e\u30c7\u30fc\u30bf(sales_data.csv)<\/strong>
\"\"<\/p>\n\n\n\n

– \u4e88\u6e2c\u5bfe\u8c61\u30c7\u30fc\u30bf(sales_future.csv)<\/strong>
\"\"<\/p>\n\n\n\n

\u305d\u308c\u3067\u306f\u3001\u4ee5\u4e0b\u306e\u901a\u308a2\u3064\u306ecsv\u3092\u8aad\u307f\u8fbc\u307f\u307e\u3059\u3002<\/p>\n\n\n\n

df = pd.read_csv(\"sales_data.csv\")\ndf_test = pd.read_csv(\"sales_future.csv\")<\/pre>\n\n\n\n
\u7d9a\u3044\u3066\u306fsales_data.csv\u306b\u57fa\u3065\u3044\u3066\u56de\u5e30\u5206\u6790\u3092\u884c\u3044\u3001sales_future.csv\u306b\u5bfe\u3057\u3066\u58f2\u4e0a\u4e88\u6e2c\u3092\u3057\u3066\u307f\u307e\u3059\u3002<\/p>\n\n\n\n
\u56de\u5e30\u5206\u6790\u306e\u5b9f\u884c<\/h2>\n\n\n\n
Python\u3067\u56de\u5e30\u5206\u6790\u3092\u5b9f\u884c\u3059\u308b\u305f\u3081\u306e\u30d1\u30c3\u30b1\u30fc\u30b8\u306b\u306f\u5e7e\u3064\u304b\u3042\u308b\u306e\u3067\u3059\u304c\u3001\u500b\u4eba\u7684\u306b\u306f\u56de\u5e30\u5206\u6790\u306e\u5b9f\u884c\u7d50\u679c\u304c\u8a73\u7d30\u306b\u78ba\u8a8d\u3067\u304d\u308b\u300cstatsmodels\u300d\u3092\u30aa\u30b9\u30b9\u30e1\u3057\u307e\u3059\u3002<\/span><\/strong>
statsmodels\u3092\u4f7f\u3046\u3068\u3001\u4ee5\u4e0b\u306e\u3088\u3046\u306b\u56de\u5e30\u5206\u6790\u304c\u7c21\u5358\u306b\u5b9f\u884c\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\n
#x\u3068y\u306b\u5206\u96e2\nx_name = \"temperature\" \ny_name = \"sales\"\nx = df[x_name]\ny = df[y_name]\n\n#\u56de\u5e30\u5206\u6790\u306e\u5b9f\u884c\nimport statsmodels.api as sm\nmodel = sm.OLS(y, sm.add_constant(x))\nresult = model.fit(disp=0)\nprint(result.summary())<\/pre>\n\n\n\n
\u307e\u305a\u306f\u8aad\u307f\u8fbc\u3093\u3060csv\u3092x\u3068y\u306b\u5206\u96e2\u3057\u307e\u3059\u3002
\u6c42\u3081\u305f\u3044\u3082\u306e(\u76ee\u7684\u5909\u6570)\u304c\u300cy\u300d\u3067\u3001\u305d\u306e\u8a08\u7b97\u306b\u4f7f\u3046\u3082\u306e(\u8aac\u660e\u5909\u6570)\u304c\u300cx\u300d<\/span><\/strong>\u3067\u3059\u3002
\u3053\u308c\u306b\u95a2\u3057\u3066\u306f\u4eba\u9593\u304c\u6307\u5b9a\u3057\u3066\u3042\u3052\u308b\u5fc5\u8981\u304c\u3042\u308a\u307e\u3059\u3002<\/p>\n\n\n\n
\u3061\u306a\u307f\u306b\u3001\u300cadd_constant\u300d\u306f\u3001\u5207\u7247\u3092\u4f7f\u3046\u5834\u5408\u306b\u6307\u5b9a\u3057\u307e\u3059\u3002\u3064\u307e\u308a\\(y=ax+b\\)\u306e\\(b\\)\u306e\u9805\u3092\u4f7f\u3046\u5834\u5408\u306b\u306f\u4ed8\u3051\u307e\u3059\u3002<\/span><\/strong>\u591a\u304f\u306e\u5834\u5408\u306f\u4f7f\u3046\u304b\u306a\u3068\u3002
\u305d\u3057\u3066\u3001\u6700\u5f8c\u306bresult.summary()\u3092print\u3059\u308b\u3068\u4ee5\u4e0b\u304c\u8868\u793a\u3055\u308c\u307e\u3059\u3002<\/p>\n\n\n\n
                            OLS Regression Results                            \n==============================================================================\nDep. Variable:                  sales   R-squared:                       0.808\nModel:                            OLS   Adj. R-squared:                  0.803\nMethod:                 Least Squares   F-statistic:                     143.2\nDate:                Sun, 23 Jun 2019   Prob (F-statistic):           9.68e-14\nTime:                        17:18:11   Log-Likelihood:                -228.93\nNo. Observations:                  36   AIC:                             461.9\nDf Residuals:                      34   BIC:                             465.0\nDf Model:                           1                                         \nCovariance Type:            nonrobust                                         \n===============================================================================\n                  coef    std err          t      P>|t|      [0.025      0.975]\n-------------------------------------------------------------------------------\nconst         106.7334     58.138      1.836      0.075     -11.417     224.884\ntemperature    39.1031      3.267     11.969      0.000      32.463      45.743\n==============================================================================\nOmnibus:                        3.479   Durbin-Watson:                   1.573\nProb(Omnibus):                  0.176   Jarque-Bera (JB):                1.602\nSkew:                           0.110   Prob(JB):                        0.449\nKurtosis:                       1.990   Cond. No.                         43.3\n==============================================================================<\/pre>\n\n\n\n
\u4f55\u3084\u3089\u8272\u3005\u51fa\u3066\u304d\u307e\u3057\u305f\u3002
\u52ff\u8ad6\u3059\u3079\u3066\u5927\u4e8b\u306a\u6307\u6a19\u306a\u306e\u3067\u3059\u304c\u3001\u3068\u308a\u3042\u3048\u305a\\(a\\)\u3068\\(b\\)\u3068\\(R^2\\)\u5024\u306f\u78ba\u8a8d\u3057\u3066\u304a\u304d\u307e\u3057\u3087\u3046\u3002
\u4e2d\u6bb5\u306b\u3042\u308b\u300ccoef\u300d\u3068\u300cconst\u300d\u304c\u4ea4\u308f\u3063\u305f\u6240\u306b\u3042\u308b\u6570\u5b57\u304c\u5207\u7247<\/span><\/strong>\u3067\u3059\u3002\u4eca\u56de\u306e\u4f8b\u3067\u306f106.7334\u3067\u3059\u3002
\u300ccoef\u300d\u3068\u300ctemperature\u300d\u304c\u4ea4\u308f\u3063\u305f\u3068\u3053\u308d\u306b\u3042\u308b\u6570\u5b57\u304c\u50be\u304d<\/span><\/strong>\u3067\u3059\u3002\u4eca\u56de\u306e\u4f8b\u3067\u306f39.1031\u3067\u3059\u3002
\u305d\u3057\u3066\u3001\u53f3\u4e0a\u306b\u3042\u308b\u300cR-squared\u300d\u304c\\(R^2\\)\u5024<\/span><\/strong>\u306b\u306a\u308a\u307e\u3059\u3002\u4eca\u56de\u306e\u4f8b\u3067\u306f0.808\u306a\u306e\u3067\u3001\u305d\u3053\u305d\u3053\u4fe1\u7528\u306b\u5024\u3059\u308b\u7d50\u679c\u306b\u306a\u3063\u3066\u3044\u305d\u3046\u3067\u3059\u3002
\u3044\u305a\u308c\u3082Excel\u3067\u5b9f\u884c\u3057\u305f\u6642<\/a>\u3068\u540c\u3058\u7d50\u679c\u304c\u5f97\u3089\u308c\u3066\u3044\u308b\u3088\u3046\u3067\u3059\u3002<\/p>\n\n\n\n
\u7d50\u679c\u3068\u3057\u3066\u3001\u30a2\u30a4\u30b9\u30af\u30ea\u30fc\u30e0\u306e\u58f2\u4e0a\u3092\\(y\\)\u3001\u6c17\u6e29\u3092\\(x\\)\u3068\u3059\u308b\u3068\u3001\\(y=106.7x+39.1\\)\u3068\u3044\u3046\u95a2\u4fc2\u304c\u3042\u308b<\/span><\/strong>\u3068\u3044\u3046\u7b54\u3048\u304c\u51fa\u307e\u3057\u305f\u3002<\/p>\n\n\n\n
\u672a\u77e5\u306e\u30c7\u30fc\u30bf\u306e\u63a8\u6e2c<\/h2>\n\n\n\n
\u3055\u3066\u3001\u56de\u5e30\u5206\u6790\u304c\u51fa\u6765\u305f\u6240\u3067\u3001\u304a\u6b21\u306f\u660e\u65e5\u4ee5\u964d\u306e\u4e88\u60f3\u6c17\u6e29\u3092\u3082\u3068\u306b\u30a2\u30a4\u30b9\u30af\u30ea\u30fc\u30e0\u306e\u58f2\u4e0a\u3092\u4e88\u6e2c\u3057\u3066\u307f\u307e\u3059\u3002
\u307e\u3042\u3001\u5148\u7a0b\u8a08\u7b97\u3067\u304d\u305f\u5f0f\u306e\\(x\\)\u306b\u6570\u5024\u3092\u5165\u308c\u3066\u8a08\u7b97\u3059\u308b\u3060\u3051\u3067\u306f\u3042\u308a\u307e\u3059\u304c\u30fb\u30fb\u30fb\u3002<\/p>\n\n\n\n
\u305d\u308c\u3067\u306f\u5192\u982d\u3067\u8aad\u307f\u8fbc\u3093\u3060df_test\u3092\u547c\u3073\u51fa\u3057\u3001\u305d\u308c\u3068\u5148\u7a0b\u8a08\u7b97\u3057\u305f\\(a\\)\u3068\\(b\\)\u306e\u5024\u3092\u7528\u3044\u3066\u4e88\u6e2c\u58f2\u4e0a\u3092\u8a08\u7b97\u3057\u3066\u307f\u307e\u3057\u3087\u3046\u3002<\/p>\n\n\n\n
y_result=[]\nfor i in range(len(df_test.index)):\n    y_tmp = result.params.const + result.params[x_name] * df_test[x_name][i]\n    y_result.append(y_tmp)\nprint(y_result)<\/pre>\n\n\n\n
result.params.const\u306b\u306f\u5207\u7247\u304c\u3001result.params[\u25cf]\u306b\u306f\u25cf\u306e\u50be\u304d\u304c\u683c\u7d0d\u3055\u308c\u3066\u3044\u307e\u3059\u3002<\/span><\/strong>
\u4e0a\u8a18\u306e\u30d7\u30ed\u30b0\u30e9\u30e0\u3092\u5b9f\u884c\u3059\u308b\u3068\u30fb\u30fb\u30fb<\/p>\n\n\n\n
[599.4330734770003, 837.9622816650826, 505.58551615709916, 697.1909456852309, 908.3479496550086]<\/pre>\n\n\n\n
df_test\u306e\u4e0a\u304b\u3089\u9806\u756a\u306b\\(y\\)\u304c\u8a08\u7b97\u3055\u308c\u307e\u3057\u305f\u3002
\u3042\u3068\u306f\u4ee5\u4e0b\u306e\u3088\u3046\u306b\u3059\u308c\u3070\u3001Excel\u306b\u63a8\u6e2c\u7d50\u679c\u3092\u66f8\u304d\u51fa\u3059\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\n
df_test_y = pd.DataFrame(y_result,columns=[\"y\"])\ndf_result = pd.concat([df_test,df_test_y],axis=1)\ndf_result.to_csv(\"result.csv\")<\/pre>\n\n\n\n
\u5192\u982d\u3067\u8aad\u307f\u8fbc\u3093\u3060\u30d5\u30a1\u30a4\u30eb\u306b\u3001\\(y\\)\u304c\u8ffd\u8a18\u3055\u308c\u305fresult.csv\u304c\u51fa\u6765\u307e\u3057\u305f\u3002
\"\"<\/p>\n\n\n\n
\u56de\u5e30\u5206\u6790\u7d50\u679c\u306e\u30b0\u30e9\u30d5\u5316<\/h2>\n\n\n\n
\u6298\u89d2\u306a\u306e\u3067\u3001\u30b0\u30e9\u30d5\u3082\u66f8\u3044\u3066\u307f\u307e\u3057\u3087\u3046\u3002<\/p>\n\n\n\n
import matplotlib.pyplot as plt\nplt.plot(x, y, 'o')\nplt.plot(x, result.params.const+result.params[x_name]*x)\nplt.show()<\/pre>\n\n\n\n
\"\"<\/figure>\n\n\n\n\n\n\n\n
\u305d\u3053\u305d\u3053\u826f\u3044\u56de\u5e30\u5206\u6790\u304c\u51fa\u6765\u3066\u3044\u305d\u3046\u3067\u3059\u306d\u3002
\u5358\u56de\u5e30\u5206\u6790\u3067\u3042\u308c\u3070\u3001\u4f55\u306f\u3068\u3082\u3042\u308c\u30b0\u30e9\u30d5\u3092\u66f8\u3044\u3066\u307f\u308b\u3068\u3001\u56de\u5e30\u5206\u6790\u306e\u7cbe\u5ea6\u304c\u76f4\u611f\u7684\u306b\u5206\u304b\u308a\u3084\u3059\u304f\u306a\u3063\u3066\u826f\u3044\u3068\u601d\u3044\u307e\u3059\u3002<\/p>\n\n\n\n
\u307e\u3068\u3081<\/h2>\n\n\n\n
\u3055\u3066\u3001\u4eca\u56de\u306fPython\u3067\u56de\u5e30\u5206\u6790\u3092\u884c\u3063\u3066\u307f\u307e\u3057\u305f\u3002
\u6d41\u308c\u3068\u3057\u3066\u306f\u3001\u307e\u305a\u4eba\u9593\u306f\u30c7\u30fc\u30bf\u3092\u8aad\u307f\u8fbc\u307e\u305b\u3066\u3001\\(x\\)\u3068\\(y\\)\u3092\u6307\u5b9a<\/span><\/strong>\u3057\u3066\u3042\u3052\u308b\u3002
\u305d\u3057\u3066\u56de\u5e30\u5206\u6790\u81ea\u4f53\u306f\u30b3\u30f3\u30d4\u30e5\u30fc\u30bf\u306b\u3084\u3089\u305b\u3066\u3001\u51fa\u3066\u304d\u305f\u7d50\u679c\u3092\u3069\u3046\u89e3\u91c8\u3059\u308b\u304b\u3092\u4eba\u9593\u304c\u8003\u3048\u308b\u3002<\/span><\/strong>
\u30fb\u30fb\u30fb\u304a\u304a\u3088\u305d\u3053\u3046\u3044\u3063\u305f\u6d41\u308c\u3068\u306a\u3063\u3066\u3044\u307e\u3059\u3002<\/p>\n\n\n\n
\u3061\u306a\u307f\u306b\u91cd\u56de\u5e30\u5206\u6790\u3082\u3001x\u306e\u5217\u304c\u5897\u3048\u308b\u3060\u3051\u306e\u8a71\u3067\u3059\u306e\u3067\u3001\u307b\u307c\u540c\u69d8\u306e\u624b\u7d9a\u304d\u3067\u884c\u3046\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"
Python\u3092\u4f7f\u3063\u3066\u56de\u5e30\u5206\u6790\u3092\u884c\u3063\u3066\u307f\u307e\u3057\u3087\u3046\u3002\u7406\u8ad6\u3084\u7528\u8a9e\u306b\u3064\u3044\u3066\u306f\u3053\u3061\u3089\u3092\u3054\u89a7\u304f\u3060\u3055\u3044\u3002 \u30c7\u30fc\u30bf\u306e\u8aad\u307f\u8fbc\u307f \u307e\u305a\u306f\u4f55\u306f\u3068\u3082\u3042\u308c\u3001\u30c7\u30fc\u30bf\u3092\u8aad\u307f\u8fbc\u307f\u307e\u3059\u3002\u4eca\u56de\u306f\u300c\u6c17\u6e29\u3068\u30a2\u30a4\u30b9\u30af\u30ea\u30fc\u30e0\u306e\u58f2\u4e0a\u300d\u30c7\u30fc\u30bf\u3092\u8aad\u307f\u8fbc\u307f\u3001\u305d\u306e\u95a2\u4fc2\u6027\u3092\u8abf […]<\/p>\n","protected":false},"author":1,"featured_media":5082,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"inline_featured_image":false,"swell_btn_cv_data":"","vkexunit_cta_each_option":"","footnotes":""},"categories":[129],"tags":[101,131,134],"class_list":["post-1495","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-study","tag-ml","tag-stats","tag-python"],"_links":{"self":[{"href":"https:\/\/analysis-navi.com\/index.php?rest_route=\/wp\/v2\/posts\/1495","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/analysis-navi.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/analysis-navi.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/analysis-navi.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/analysis-navi.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=1495"}],"version-history":[{"count":22,"href":"https:\/\/analysis-navi.com\/index.php?rest_route=\/wp\/v2\/posts\/1495\/revisions"}],"predecessor-version":[{"id":5165,"href":"https:\/\/analysis-navi.com\/index.php?rest_route=\/wp\/v2\/posts\/1495\/revisions\/5165"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/analysis-navi.com\/index.php?rest_route=\/wp\/v2\/media\/5082"}],"wp:attachment":[{"href":"https:\/\/analysis-navi.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=1495"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/analysis-navi.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=1495"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/analysis-navi.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=1495"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}