Python\u306e\u6a5f\u68b0\u5b66\u7fd2\u30e9\u30a4\u30d6\u30e9\u30eascikit-learn\u306f\u3001\u8c4a\u5bcc\u306a\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u3068\u4f7f\u3044\u3084\u3059\u3044API\u3067\u4eba\u6c17\u3092\u96c6\u3081\u3066\u3044\u307e\u3059\u3002\u672c\u8a18\u4e8b\u3067\u306f\u3001scikit-learn\u306e\u57fa\u672c\u7684\u306a\u4f7f\u3044\u65b9\u304b\u3089\u3001\u56de\u5e30\u5206\u6790\u3001\u5206\u985e\u3001\u30af\u30e9\u30b9\u30bf\u30ea\u30f3\u30b0\u306a\u3069\u306e\u5b9f\u8df5\u7684\u306a\u30c6\u30af\u30cb\u30c3\u30af\u307e\u3067\u3001\u5b9f\u4f8b\u3092\u4ea4\u3048\u3066\u8a73\u3057\u304f\u89e3\u8aac\u3057\u307e\u3059\u3002\u6a5f\u68b0\u5b66\u7fd2\u306e\u5165\u9580\u304b\u3089\u5fdc\u7528\u307e\u3067\u3001scikit-learn\u3092\u6d3b\u7528\u3059\u308b\u305f\u3081\u306e\u77e5\u8b58\u304c\u8eab\u306b\u3064\u304f\u3067\u3057\u3087\u3046\u3002<\/p>\n\n\n\n
\u76ee\u6b21 <\/p>\n
scikit-learn\uff08\u30b5\u30a4\u30ad\u30c3\u30c8\u30fb\u30e9\u30fc\u30f3\uff09\u306f\u3001\u6a5f\u68b0\u5b66\u7fd2\u306e\u305f\u3081\u306ePython\u30e9\u30a4\u30d6\u30e9\u30ea\u3067\u3059\u3002\u30b7\u30f3\u30d7\u30eb\u3067\u52b9\u7387\u7684\u306a\u6a5f\u68b0\u5b66\u7fd2\u30c4\u30fc\u30eb\u3092\u63d0\u4f9b\u3059\u308b\u3053\u3068\u3092\u76ee\u7684\u306b\u958b\u767a\u3055\u308c\u3001NumPy\u3084SciPy\u306a\u3069\u306e\u79d1\u5b66\u8a08\u7b97\u30e9\u30a4\u30d6\u30e9\u30ea\u3092\u57fa\u76e4\u3068\u3057\u3066\u3044\u307e\u3059\u3002\u30aa\u30fc\u30d7\u30f3\u30bd\u30fc\u30b9\u3067\u63d0\u4f9b\u3055\u308c\u3066\u3044\u308b\u305f\u3081\u3001\u8ab0\u3067\u3082\u7121\u6599\u3067\u5229\u7528\u3059\u308b\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\n
scikit-learn\u306f\u3001\u6559\u5e2b\u3042\u308a\u5b66\u7fd2\uff08\u56de\u5e30\u3001\u5206\u985e\uff09\u3084\u6559\u5e2b\u306a\u3057\u5b66\u7fd2\uff08\u30af\u30e9\u30b9\u30bf\u30ea\u30f3\u30b0\u3001\u6b21\u5143\u524a\u6e1b\uff09\u306a\u3069\u3001\u69d8\u3005\u306a\u6a5f\u68b0\u5b66\u7fd2\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u3092\u7db2\u7f85\u3057\u3066\u3044\u307e\u3059\u3002\u307e\u305f\u3001\u4ea4\u5dee\u691c\u8a3c\u3084\u30b0\u30ea\u30c3\u30c9\u30b5\u30fc\u30c1\u306b\u3088\u308b\u30cf\u30a4\u30d1\u30fc\u30d1\u30e9\u30e1\u30fc\u30bf\u6700\u9069\u5316\u306e\u6a5f\u80fd\u3082\u63d0\u4f9b\u3057\u3066\u304a\u308a\u3001\u9ad8\u5ea6\u306a\u30e2\u30c7\u30eb\u30c1\u30e5\u30fc\u30cb\u30f3\u30b0\u3092\u884c\u3046\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002\u5927\u898f\u6a21\u306a\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u306b\u3082\u5bfe\u5fdc\u3057\u3066\u3044\u308b\u305f\u3081\u3001\u5b9f\u7528\u7684\u306a\u6a5f\u68b0\u5b66\u7fd2\u30bf\u30b9\u30af\u306b\u9069\u7528\u3057\u3084\u3059\u3044\u306e\u304c\u7279\u5fb4\u3067\u3059\u3002<\/p>\n\n\n\n
scikit-learn\u306e\u5927\u304d\u306a\u5229\u70b9\u306f\u3001\u7d71\u4e00\u3055\u308c\u305f\u30b7\u30f3\u30d7\u30eb\u306aAPI\u306b\u3042\u308a\u307e\u3059\u3002\u4e00\u5ea6\u4f7f\u3044\u65b9\u3092\u899a\u3048\u3066\u3057\u307e\u3048\u3070\u3001\u69d8\u3005\u306a\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u3092\u540c\u3058\u611f\u899a\u3067\u6271\u3046\u3053\u3068\u304c\u3067\u304d\u308b\u305f\u3081\u3001\u5b66\u7fd2\u30b3\u30b9\u30c8\u304c\u975e\u5e38\u306b\u4f4e\u304f\u306a\u3063\u3066\u3044\u307e\u3059\u3002\u307e\u305f\u3001\u9ad8\u901f\u306a\u5b9f\u88c5\u306b\u3088\u308a\u3001\u5927\u898f\u6a21\u30c7\u30fc\u30bf\u306e\u51e6\u7406\u306b\u3082\u9069\u3057\u3066\u3044\u307e\u3059\u3002\u8c4a\u5bcc\u306a\u30c9\u30ad\u30e5\u30e1\u30f3\u30c8\u3068\u30e6\u30fc\u30b6\u30fc\u30b3\u30df\u30e5\u30cb\u30c6\u30a3\u306b\u3088\u308b\u30b5\u30dd\u30fc\u30c8\u3082\u3001scikit-learn\u306e\u9b45\u529b\u306e\u4e00\u3064\u3068\u8a00\u3048\u308b\u3067\u3057\u3087\u3046\u3002<\/p>\n\n\n\n
\u4e00\u65b9\u3067\u3001scikit-learn\u306b\u3082\u6b20\u70b9\u3084\u6ce8\u610f\u70b9\u304c\u3042\u308a\u307e\u3059\u3002\u6df1\u5c64\u5b66\u7fd2\u306b\u306f\u5bfe\u5fdc\u3057\u3066\u304a\u3089\u305a\u3001\u30cb\u30e5\u30fc\u30e9\u30eb\u30cd\u30c3\u30c8\u30ef\u30fc\u30af\u3092\u6271\u3046\u306b\u306fKeras, TensorFlow\u306a\u3069\u306e\u5225\u306e\u30e9\u30a4\u30d6\u30e9\u30ea\u3092\u4f7f\u3046\u5fc5\u8981\u304c\u3042\u308a\u307e\u3059\u3002\u307e\u305f\u3001\u4e00\u90e8\u306e\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u306b\u3064\u3044\u3066\u306f\u3001\u4ed6\u306e\u30e9\u30a4\u30d6\u30e9\u30ea\u306e\u5b9f\u88c5\u306b\u53ca\u3070\u306a\u3044\u5834\u5408\u3082\u3042\u308a\u307e\u3059\u3002\u72ec\u81ea\u306e\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u3092\u7d44\u307f\u8fbc\u3080\u306e\u3082\u3001\u4ed6\u306e\u30e9\u30a4\u30d6\u30e9\u30ea\u3068\u6bd4\u3079\u308b\u3068\u96e3\u3057\u3044\u304b\u3082\u3057\u308c\u307e\u305b\u3093\u3002<\/p>\n\n\n\n
\u3068\u306f\u3044\u3048\u3001\u6a5f\u68b0\u5b66\u7fd2\u306e\u5165\u9580\u304b\u3089\u5b9f\u8df5\u307e\u3067\u3092\u30ab\u30d0\u30fc\u3059\u308b\u3001\u975e\u5e38\u306b\u6709\u7528\u306a\u30e9\u30a4\u30d6\u30e9\u30ea\u3067\u3042\u308b\u3053\u3068\u306b\u5909\u308f\u308a\u306f\u3042\u308a\u307e\u305b\u3093\u3002\u672c\u8a18\u4e8b\u3067\u306f\u3001scikit-learn\u306e\u57fa\u672c\u7684\u306a\u4f7f\u3044\u65b9\u304b\u3089\u767a\u5c55\u7684\u306a\u30c6\u30af\u30cb\u30c3\u30af\u307e\u3067\u3001\u5b9f\u4f8b\u3092\u4ea4\u3048\u3066\u8a73\u3057\u304f\u89e3\u8aac\u3057\u3066\u3044\u304d\u307e\u3059\u3002\u6a5f\u68b0\u5b66\u7fd2\u3092\u5b66\u3076\u4e0a\u3067\u3001\u305c\u3072\u62bc\u3055\u3048\u3066\u304a\u304d\u305f\u3044\u30e9\u30a4\u30d6\u30e9\u30ea\u3068\u8a00\u3048\u308b\u3067\u3057\u3087\u3046\u3002<\/p>\n\n\n\n
\u3053\u3053\u304b\u3089\u306f\u3001scikit-learn\u3092\u5b9f\u969b\u306b\u4f7f\u3063\u3066\u307f\u307e\u3057\u3087\u3046\u3002\u307e\u305a\u306f\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u304b\u3089\u59cb\u3081\u307e\u3059\u3002<\/p>\n\n\n\n
scikit-learn\u306e\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u306f\u3001pip\u3092\u4f7f\u3046\u306e\u304c\u6700\u3082\u7c21\u5358\u3067\u3059\u3002\u4ee5\u4e0b\u306e\u30b3\u30de\u30f3\u30c9\u3092\u5b9f\u884c\u3059\u308b\u3053\u3068\u3067\u3001\u6700\u65b0\u7248\u306escikit-learn\u304c\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u3055\u308c\u307e\u3059\u3002<\/p>\n\n\n\n
pip install scikit-learn<\/pre>\n\n\n\nAnaconda\u3092\u4f7f\u3063\u3066\u3044\u308b\u5834\u5408\u306f\u3001\u4ee5\u4e0b\u306e\u30b3\u30de\u30f3\u30c9\u3067\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\n
conda install scikit-learn<\/pre>\n\n\n\n\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u304c\u5b8c\u4e86\u3057\u305f\u3089\u3001\u4ee5\u4e0b\u306e\u3088\u3046\u306b\u30d0\u30fc\u30b8\u30e7\u30f3\u3092\u78ba\u8a8d\u3057\u3066\u304a\u304d\u307e\u3057\u3087\u3046\u3002<\/p>\n\n\n\n
import sklearn\nprint(sklearn.__version__)<\/pre>\n\n\n\n\u5b66\u7fd2\u30c7\u30fc\u30bf\u3068\u30c6\u30b9\u30c8\u30c7\u30fc\u30bf\u306e\u5206\u5272\u65b9\u6cd5<\/h3>\n\n\n\n
\u6a5f\u68b0\u5b66\u7fd2\u3067\u306f\u3001\u30c7\u30fc\u30bf\u3092\u5b66\u7fd2\u7528\u3068\u30c6\u30b9\u30c8\u7528\u306b\u5206\u5272\u3059\u308b\u306e\u304c\u4e00\u822c\u7684\u3067\u3059\u3002scikit-learn\u3067\u306f\u3001
train_test_split<\/code>\u95a2\u6570\u3092\u4f7f\u3063\u3066\u30c7\u30fc\u30bf\u3092\u7c21\u5358\u306b\u5206\u5272\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\nfrom sklearn.model_selection import train_test_split\n\nX_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)<\/pre>\n\n\n\n\u4e0a\u8a18\u306e\u4f8b\u3067\u306f\u3001\u30c7\u30fc\u30bf
X<\/code>\u3068\u30e9\u30d9\u30eby<\/code>\u30928:2\u306e\u6bd4\u7387\u3067\u5b66\u7fd2\u7528\u3068\u30c6\u30b9\u30c8\u7528\u306b\u5206\u5272\u3057\u3066\u3044\u307e\u3059\u3002random_state<\/code>\u3092\u6307\u5b9a\u3059\u308b\u3053\u3068\u3067\u3001\u4e71\u6570\u30b7\u30fc\u30c9\u3092\u56fa\u5b9a\u3057\u3001\u518d\u73fe\u6027\u3092\u78ba\u4fdd\u3057\u3066\u3044\u307e\u3059\u3002<\/p>\n\n\n\n\u30e2\u30c7\u30eb\u306e\u5b66\u7fd2\u3068\u8a55\u4fa1\u306e\u65b9\u6cd5<\/h3>\n\n\n\n
scikit-learn\u3067\u30e2\u30c7\u30eb\u3092\u5b66\u7fd2\u3059\u308b\u306b\u306f\u3001\u4ee5\u4e0b\u306e\u624b\u9806\u3092\u8e0f\u307f\u307e\u3059\u3002<\/p>\n\n\n\n
\n
- \u30e2\u30c7\u30eb\u306e\u30a4\u30f3\u30b9\u30bf\u30f3\u30b9\u5316<\/li>\n\n\n\n
- \u5b66\u7fd2\u30c7\u30fc\u30bf\u3092\u4f7f\u3063\u3066\u30e2\u30c7\u30eb\u3092\u5b66\u7fd2\uff08
fit<\/code>\u95a2\u6570\uff09<\/li>\n\n\n\n- \u30c6\u30b9\u30c8\u30c7\u30fc\u30bf\u3092\u4f7f\u3063\u3066\u4e88\u6e2c\u3092\u884c\u3046\uff08
predict<\/code>\u95a2\u6570\uff09<\/li>\n\n\n\n- \u4e88\u6e2c\u7d50\u679c\u3092\u8a55\u4fa1\u3059\u308b\uff08
score<\/code>\u95a2\u6570\uff09<\/li>\n<\/ol>\n\n\n\n\u4f8b\u3048\u3070\u3001\u7dda\u5f62\u56de\u5e30\u30e2\u30c7\u30eb\u3092\u5b66\u7fd2\u3059\u308b\u306b\u306f\u4ee5\u4e0b\u306e\u3088\u3046\u306b\u3057\u307e\u3059\u3002<\/p>\n\n\n\n
from sklearn.linear_model import LinearRegression\n\nmodel = LinearRegression() # \u30e2\u30c7\u30eb\u306e\u30a4\u30f3\u30b9\u30bf\u30f3\u30b9\u5316\nmodel.fit(X_train, y_train) # \u5b66\u7fd2\u30c7\u30fc\u30bf\u3092\u4f7f\u3063\u3066\u5b66\u7fd2\ny_pred = model.predict(X_test) # \u30c6\u30b9\u30c8\u30c7\u30fc\u30bf\u3092\u4f7f\u3063\u3066\u4e88\u6e2c\nscore = model.score(X_test, y_test) # \u4e88\u6e2c\u7d50\u679c\u3092\u8a55\u4fa1\nprint(f\"Score: {score:.2f}\")<\/pre>\n\n\n\n\u30cf\u30a4\u30d1\u30fc\u30d1\u30e9\u30e1\u30fc\u30bf\u306e\u63a2\u7d22\u65b9\u6cd5<\/h3>\n\n\n\n
\u30e2\u30c7\u30eb\u306e\u6027\u80fd\u3092\u6700\u5927\u9650\u306b\u5f15\u304d\u51fa\u3059\u306b\u306f\u3001\u30cf\u30a4\u30d1\u30fc\u30d1\u30e9\u30e1\u30fc\u30bf\u306e\u8abf\u6574\u304c\u91cd\u8981\u3067\u3059\u3002scikit-learn\u3067\u306f\u3001
GridSearchCV<\/code>\u3084RandomizedSearchCV<\/code>\u3092\u4f7f\u3063\u3066\u30cf\u30a4\u30d1\u30fc\u30d1\u30e9\u30e1\u30fc\u30bf\u306e\u63a2\u7d22\u3092\u884c\u3046\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\nfrom sklearn.model_selection import GridSearchCV\n\nparam_grid = {'C': [0.1, 1, 10], 'kernel': ['linear', 'rbf']}\ngrid_search = GridSearchCV(SVC(), param_grid, cv=5)\ngrid_search.fit(X_train, y_train)\nprint(f\"Best parameters: {grid_search.best_params_}\")\nprint(f\"Best score: {grid_search.best_score_:.2f}\")<\/pre>\n\n\n\n\u4e0a\u8a18\u306e\u4f8b\u3067\u306f\u3001SVM\u306e\u30cf\u30a4\u30d1\u30fc\u30d1\u30e9\u30e1\u30fc\u30bf\u3067\u3042\u308b
C<\/code>\u3068kernel<\/code>\u306b\u3064\u3044\u3066\u3001\u30b0\u30ea\u30c3\u30c9\u30b5\u30fc\u30c1\u3092\u884c\u3063\u3066\u3044\u307e\u3059\u3002cv<\/code>\u3067\u30af\u30ed\u30b9\u30d0\u30ea\u30c7\u30fc\u30b7\u30e7\u30f3\u306e\u5206\u5272\u6570\u3092\u6307\u5b9a\u3059\u308b\u3053\u3068\u3067\u3001\u6c4e\u5316\u6027\u80fd\u3092\u8a55\u4fa1\u3057\u306a\u304c\u3089\u6700\u9069\u306a\u30cf\u30a4\u30d1\u30fc\u30d1\u30e9\u30e1\u30fc\u30bf\u3092\u63a2\u7d22\u3057\u307e\u3059\u3002<\/p>\n\n\n\nscikit-learn\u3092\u4f7f\u3048\u3070\u3001\u3053\u306e\u3088\u3046\u306b\u30c7\u30fc\u30bf\u306e\u6e96\u5099\u304b\u3089\u30e2\u30c7\u30eb\u306e\u8a55\u4fa1\u307e\u3067\u3001\u4e00\u9023\u306e\u6a5f\u68b0\u5b66\u7fd2\u306e\u6d41\u308c\u3092\u7c21\u5358\u306b\u5b9f\u88c5\u3059\u308b\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002\u6b21\u7bc0\u4ee5\u964d\u3067\u306f\u3001\u56de\u5e30\u3001\u5206\u985e\u3001\u30af\u30e9\u30b9\u30bf\u30ea\u30f3\u30b0\u306a\u3069\u3001\u4ee3\u8868\u7684\u306a\u30bf\u30b9\u30af\u306b\u3064\u3044\u3066\u3088\u308a\u8a73\u3057\u304f\u898b\u3066\u3044\u304d\u307e\u3057\u3087\u3046\u3002<\/p>\n\n\n\n
scikit-learn\u3092\u4f7f\u3063\u305f\u56de\u5e30\u5206\u6790\u306e\u5b9f\u8df5<\/h2>\n\n\n\n
\u56de\u5e30\u5206\u6790\u306f\u3001\u8aac\u660e\u5909\u6570\u304b\u3089\u76ee\u7684\u5909\u6570\u306e\u5024\u3092\u4e88\u6e2c\u3059\u308b\u305f\u3081\u306e\u624b\u6cd5\u3067\u3059\u3002\u3053\u3053\u3067\u306f\u3001scikit-learn\u3092\u4f7f\u3063\u3066\u56de\u5e30\u5206\u6790\u3092\u5b9f\u8df5\u7684\u306b\u884c\u3046\u65b9\u6cd5\u3092\u898b\u3066\u3044\u304d\u307e\u3057\u3087\u3046\u3002<\/p>\n\n\n\n
\u7dda\u5f62\u56de\u5e30\u3068\u975e\u7dda\u5f62\u56de\u5e30<\/h3>\n\n\n\n
\u56de\u5e30\u5206\u6790\u306b\u306f\u3001\u5927\u304d\u304f\u5206\u3051\u3066\u7dda\u5f62\u56de\u5e30\u3068\u975e\u7dda\u5f62\u56de\u5e30\u306e2\u7a2e\u985e\u304c\u3042\u308a\u307e\u3059\u3002\u7dda\u5f62\u56de\u5e30\u306f\u3001\u8aac\u660e\u5909\u6570\u3068\u76ee\u7684\u5909\u6570\u306e\u95a2\u4fc2\u304c\u76f4\u7dda\u7684\u3067\u3042\u308b\u3068\u4eee\u5b9a\u3057\u305f\u30e2\u30c7\u30eb\u3067\u3059\u3002\u4e00\u65b9\u3001\u975e\u7dda\u5f62\u56de\u5e30\u306f\u3001\u8aac\u660e\u5909\u6570\u3068\u76ee\u7684\u5909\u6570\u306e\u95a2\u4fc2\u304c\u975e\u7dda\u5f62\u3067\u3042\u308b\u3068\u3057\u3066\u30e2\u30c7\u30eb\u5316\u3057\u307e\u3059\u3002\u591a\u9805\u5f0f\u56de\u5e30\u3084\u6c7a\u5b9a\u6728\u3001\u30b5\u30dd\u30fc\u30c8\u30d9\u30af\u30bf\u30fc\u30de\u30b7\u30f3\uff08SVR\uff09\u306a\u3069\u304c\u4ee3\u8868\u7684\u306a\u975e\u7dda\u5f62\u56de\u5e30\u30e2\u30c7\u30eb\u3067\u3059\u3002<\/p>\n\n\n\n
scikit-learn\u3067\u306f\u3001\u4ee5\u4e0b\u306e\u3088\u3046\u306b\u7dda\u5f62\u56de\u5e30\u3068\u975e\u7dda\u5f62\u56de\u5e30\u3092\u5b9f\u88c5\u3059\u308b\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\n
from sklearn.linear_model import LinearRegression\nfrom sklearn.tree import DecisionTreeRegressor\n\n# \u7dda\u5f62\u56de\u5e30\nlinear_model = LinearRegression()\nlinear_model.fit(X_train, y_train)\n\n# \u6c7a\u5b9a\u6728\u306b\u3088\u308b\u975e\u7dda\u5f62\u56de\u5e30\ntree_model = DecisionTreeRegressor(max_depth=3)\ntree_model.fit(X_train, y_train)<\/pre>\n\n\n\n\u6b63\u5247\u5316\u624b\u6cd5\u306e\u4f7f\u3044\u65b9<\/h3>\n\n\n\n
\u904e\u5b66\u7fd2\u3092\u9632\u3050\u305f\u3081\u306b\u3001\u6b63\u5247\u5316\u624b\u6cd5\u304c\u3088\u304f\u7528\u3044\u3089\u308c\u307e\u3059\u3002\u4ee3\u8868\u7684\u306a\u6b63\u5247\u5316\u624b\u6cd5\u3068\u3057\u3066\u3001L1\u6b63\u5247\u5316\uff08Lasso\uff09\u3068L2\u6b63\u5247\u5316\uff08Ridge\uff09\u304c\u3042\u308a\u307e\u3059\u3002L1\u6b63\u5247\u5316\u306f\u4e00\u90e8\u306e\u4fc2\u6570\u30920\u306b\u3059\u308b\u3053\u3068\u3067\u5909\u6570\u9078\u629e\u3092\u884c\u3044\u3001L2\u6b63\u5247\u5316\u306f\u4fc2\u6570\u306e\u5927\u304d\u3055\u3092\u6291\u3048\u308b\u3053\u3068\u3067\u904e\u5b66\u7fd2\u3092\u9632\u304e\u307e\u3059\u3002\u307e\u305f\u3001ElasticNet\u306fL1\u6b63\u5247\u5316\u3068L2\u6b63\u5247\u5316\u3092\u7d44\u307f\u5408\u308f\u305b\u305f\u624b\u6cd5\u3067\u3059\u3002<\/p>\n\n\n\n
scikit-learn\u3067\u306f\u3001\u4ee5\u4e0b\u306e\u3088\u3046\u306b\u6b63\u5247\u5316\u624b\u6cd5\u3092\u9069\u7528\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\n
from sklearn.linear_model import Lasso, Ridge, ElasticNet\n\n# L1\u6b63\u5247\u5316\uff08Lasso\uff09\nlasso_model = Lasso(alpha=0.1)\nlasso_model.fit(X_train, y_train)\n\n# L2\u6b63\u5247\u5316\uff08Ridge\uff09\nridge_model = Ridge(alpha=0.1)\nridge_model.fit(X_train, y_train)\n\n# ElasticNet\nelastic_model = ElasticNet(alpha=0.1, l1_ratio=0.5)\nelastic_model.fit(X_train, y_train)<\/pre>\n\n\n\n\u30e2\u30c7\u30eb\u306e\u89e3\u91c8\u65b9\u6cd5<\/h3>\n\n\n\n
\u56de\u5e30\u30e2\u30c7\u30eb\u3092\u89e3\u91c8\u3059\u308b\u306b\u306f\u3001\u4fc2\u6570\u306e\u5927\u304d\u3055\u3068\u7b26\u53f7\u306b\u7740\u76ee\u3057\u307e\u3059\u3002\u4fc2\u6570\u306e\u5927\u304d\u3055\u306f\u3001\u305d\u306e\u8aac\u660e\u5909\u6570\u306e\u5f71\u97ff\u5ea6\u3092\u8868\u3057\u3001\u7b26\u53f7\u306f\u6b63\u306e\u5f71\u97ff\u304b\u8ca0\u306e\u5f71\u97ff\u304b\u3092\u793a\u3057\u307e\u3059\u3002\u305f\u3060\u3057\u3001\u8aac\u660e\u5909\u6570\u9593\u306b\u76f8\u95a2\u304c\u3042\u308b\u5834\u5408\u3001\u5358\u7d14\u306a\u4fc2\u6570\u306e\u89e3\u91c8\u3067\u306f\u4e0d\u5341\u5206\u3067\u3059\u3002<\/p>\n\n\n\n
\u3053\u306e\u5834\u5408\u3001\u504f\u56de\u5e30\u4fc2\u6570\u3092\u4f7f\u3063\u3066\u3001\u4ed6\u306e\u5909\u6570\u306e\u5f71\u97ff\u3092\u8abf\u6574\u3057\u305f\u5f71\u97ff\u5ea6\u3092\u8a08\u7b97\u3059\u308b\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002scikit-learn\u3067\u306f\u3001\u4ee5\u4e0b\u306e\u3088\u3046\u306b\u504f\u56de\u5e30\u4fc2\u6570\u3092\u8a08\u7b97\u3057\u3001\u53ef\u8996\u5316\u3059\u308b\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\n
from sklearn.linear_model import LinearRegression\nimport statsmodels.api as sm\n\nmodel = LinearRegression()\nmodel.fit(X_train, y_train)\n\nX_train_sm = sm.add_constant(X_train)\nmodel_sm = sm.OLS(y_train, X_train_sm).fit()\nprint(model_sm.summary())\n\nsm.graphics.plot_partregress_grid(model_sm)<\/pre>\n\n\n\n\u307e\u305f\u3001\u90e8\u5206\u4f9d\u5b58\u6027\u30d7\u30ed\u30c3\u30c8\u3092\u4f7f\u3046\u3053\u3068\u3067\u3001\u8aac\u660e\u5909\u6570\u3068\u76ee\u7684\u5909\u6570\u306e\u95a2\u4fc2\u3092\u8996\u899a\u7684\u306b\u7406\u89e3\u3059\u308b\u3053\u3068\u3082\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\n
\u6642\u7cfb\u5217\u30c7\u30fc\u30bf\u3078\u306e\u56de\u5e30\u5206\u6790\u306e\u9069\u7528<\/h3>\n\n\n\n
\u6642\u7cfb\u5217\u30c7\u30fc\u30bf\u306b\u56de\u5e30\u5206\u6790\u3092\u9069\u7528\u3059\u308b\u5834\u5408\u3001\u904e\u53bb\u306e\u6642\u7cfb\u5217\u30c7\u30fc\u30bf\u3092\u30b7\u30d5\u30c8\u3057\u3066\u8aac\u660e\u5909\u6570\u3068\u3057\u3066\u5229\u7528\u3057\u307e\u3059\u3002\u3053\u308c\u3092\u30e9\u30b0\u4ed8\u304d\u5909\u6570\u3068\u547c\u3073\u307e\u3059\u3002\u4f8b\u3048\u3070\u3001\u4ee5\u4e0b\u306e\u3088\u3046\u306b\u30e9\u30b0\u4ed8\u304d\u5909\u6570\u3092\u4f5c\u6210\u3057\u3001\u30e2\u30c7\u30eb\u3092\u69cb\u7bc9\u3059\u308b\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\n
from sklearn.linear_model import LinearRegression\n\nX_lag = pd.concat([X.shift(1), X.shift(2), X.shift(3)], axis=1)\nX_lag = X_lag.dropna()\ny_lag = y[3:]\n\nmodel = LinearRegression()\nmodel.fit(X_lag, y_lag)<\/pre>\n\n\n\n\u3055\u3089\u306b\u3001\u81ea\u5df1\u56de\u5e30\u30e2\u30c7\u30eb\uff08AR\uff09\u3084\u81ea\u5df1\u56de\u5e30\u548c\u5206\u79fb\u52d5\u5e73\u5747\u30e2\u30c7\u30eb\uff08ARIMA\uff09\u306a\u3069\u3001\u6642\u7cfb\u5217\u30c7\u30fc\u30bf\u306b\u7279\u5316\u3057\u305f\u30e2\u30c7\u30eb\u3092\u4f7f\u3046\u3053\u3068\u3082\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\n
\u4ee5\u4e0a\u306e\u3088\u3046\u306b\u3001scikit-learn\u3092\u4f7f\u3046\u3053\u3068\u3067\u3001\u56de\u5e30\u5206\u6790\u3092\u5b9f\u8df5\u7684\u306b\u884c\u3046\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002\u7dda\u5f62\u56de\u5e30\u3068\u975e\u7dda\u5f62\u56de\u5e30\u306e\u9078\u629e\u3001\u6b63\u5247\u5316\u624b\u6cd5\u306e\u9069\u7528\u3001\u30e2\u30c7\u30eb\u306e\u89e3\u91c8\u3001\u6642\u7cfb\u5217\u30c7\u30fc\u30bf\u3078\u306e\u9069\u7528\u306a\u3069\u3001\u69d8\u3005\u306a\u5834\u9762\u3067\u6d3b\u7528\u3067\u304d\u308b\u624b\u6cd5\u3092\u62bc\u3055\u3048\u3066\u304a\u304d\u307e\u3057\u3087\u3046\u3002<\/p>\n\n\n\n
scikit-learn\u3092\u4f7f\u3063\u305f\u5206\u985e\u30bf\u30b9\u30af\u306e\u5b9f\u8df5<\/h2>\n\n\n\n
\u5206\u985e\u306f\u3001\u4e0e\u3048\u3089\u308c\u305f\u30c7\u30fc\u30bf\u3092\u3042\u3089\u304b\u3058\u3081\u5b9a\u7fa9\u3055\u308c\u305f\u30af\u30e9\u30b9\u306b\u5272\u308a\u5f53\u3066\u308b\u30bf\u30b9\u30af\u3067\u3059\u3002\u3053\u3053\u3067\u306f\u3001scikit-learn\u3092\u4f7f\u3063\u3066\u5206\u985e\u30bf\u30b9\u30af\u3092\u5b9f\u8df5\u7684\u306b\u884c\u3046\u65b9\u6cd5\u3092\u898b\u3066\u3044\u304d\u307e\u3057\u3087\u3046\u3002<\/p>\n\n\n\n
2\u30af\u30e9\u30b9\u5206\u985e\u3068\u591a\u30af\u30e9\u30b9\u5206\u985e<\/h3>\n\n\n\n
\u5206\u985e\u30bf\u30b9\u30af\u306f\u3001\u76ee\u7684\u5909\u6570\u306e\u30af\u30e9\u30b9\u6570\u306b\u3088\u3063\u30662\u30af\u30e9\u30b9\u5206\u985e\u3068\u591a\u30af\u30e9\u30b9\u5206\u985e\u306b\u5206\u3051\u3089\u308c\u307e\u3059\u30022\u30af\u30e9\u30b9\u5206\u985e\u306f\u3001\u76ee\u7684\u5909\u6570\u304c2\u3064\u306e\u30af\u30e9\u30b9\u3092\u6301\u3064\u5834\u5408\u3067\u3001\u4f8b\u3048\u3070\u30e1\u30fc\u30eb\u306e\u30b9\u30d1\u30e0\u5224\u5b9a\u306a\u3069\u304c\u8a72\u5f53\u3057\u307e\u3059\u3002\u4e00\u65b9\u3001\u591a\u30af\u30e9\u30b9\u5206\u985e\u306f\u3001\u76ee\u7684\u5909\u6570\u304c3\u3064\u4ee5\u4e0a\u306e\u30af\u30e9\u30b9\u3092\u6301\u3064\u5834\u5408\u3067\u3001\u624b\u66f8\u304d\u6587\u5b57\u306e\u8b58\u5225\u306a\u3069\u304c\u4ee3\u8868\u7684\u306a\u4f8b\u3067\u3059\u3002<\/p>\n\n\n\n
scikit-learn\u3067\u306f\u3001\u4ee5\u4e0b\u306e\u3088\u3046\u306b2\u30af\u30e9\u30b9\u5206\u985e\u3068\u591a\u30af\u30e9\u30b9\u5206\u985e\u3092\u5b9f\u88c5\u3059\u308b\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\n
from sklearn.linear_model import LogisticRegression\nfrom sklearn.ensemble import RandomForestClassifier\n\n# 2\u30af\u30e9\u30b9\u5206\u985e\uff08\u30ed\u30b8\u30b9\u30c6\u30a3\u30c3\u30af\u56de\u5e30\uff09\nlr_model = LogisticRegression()\nlr_model.fit(X_train, y_train)\n\n# \u591a\u30af\u30e9\u30b9\u5206\u985e\uff08\u30e9\u30f3\u30c0\u30e0\u30d5\u30a9\u30ec\u30b9\u30c8\uff09\nrf_model = RandomForestClassifier()\nrf_model.fit(X_train, y_train)<\/pre>\n\n\n\nSVM\u3068\u30ed\u30b8\u30b9\u30c6\u30a3\u30c3\u30af\u56de\u5e30<\/h3>\n\n\n\n
\u30b5\u30dd\u30fc\u30c8\u30d9\u30af\u30bf\u30fc\u30de\u30b7\u30f3\uff08SVM\uff09\u3068\u30ed\u30b8\u30b9\u30c6\u30a3\u30c3\u30af\u56de\u5e30\u306f\u3001\u3069\u3061\u3089\u3082\u5206\u985e\u30bf\u30b9\u30af\u3067\u3088\u304f\u4f7f\u308f\u308c\u308b\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u3067\u3059\u3002SVM\u306f\u3001\u30ab\u30fc\u30cd\u30eb\u30c8\u30ea\u30c3\u30af\u3092\u4f7f\u3063\u3066\u975e\u7dda\u5f62\u306e\u6c7a\u5b9a\u5883\u754c\u3092\u5b66\u7fd2\u3059\u308b\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002\u4e00\u65b9\u3001\u30ed\u30b8\u30b9\u30c6\u30a3\u30c3\u30af\u56de\u5e30\u306f\u3001\u30b7\u30b0\u30e2\u30a4\u30c9\u95a2\u6570\u3092\u4f7f\u3063\u3066\u4e8b\u5f8c\u78ba\u7387\u3092\u8a08\u7b97\u3057\u3001\u95be\u5024\u3092\u8a2d\u5b9a\u3059\u308b\u3053\u3068\u3067\u30af\u30e9\u30b9\u5206\u985e\u3092\u884c\u3044\u307e\u3059\u3002<\/p>\n\n\n\n
scikit-learn\u3067\u306f\u3001\u4ee5\u4e0b\u306e\u3088\u3046\u306bSVM\u3068\u30ed\u30b8\u30b9\u30c6\u30a3\u30c3\u30af\u56de\u5e30\u3092\u5b9f\u88c5\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\n
from sklearn.svm import SVC\nfrom sklearn.linear_model import LogisticRegression\n\n# SVM\nsvm_model = SVC(kernel='rbf', C=1.0)\nsvm_model.fit(X_train, y_train)\n\n# \u30ed\u30b8\u30b9\u30c6\u30a3\u30c3\u30af\u56de\u5e30\nlr_model = LogisticRegression(C=1.0)\nlr_model.fit(X_train, y_train)<\/pre>\n\n\n\n\u6c7a\u5b9a\u6728\u3068\u30e9\u30f3\u30c0\u30e0\u30d5\u30a9\u30ec\u30b9\u30c8<\/h3>\n\n\n\n
\u6c7a\u5b9a\u6728\u306f\u3001\u8aac\u660e\u5909\u6570\u306e\u5024\u306b\u57fa\u3065\u3044\u3066\u5206\u5c90\u3092\u7e70\u308a\u8fd4\u3057\u3001\u6700\u7d42\u7684\u306b\u5404\u8449\u30ce\u30fc\u30c9\u3067\u30af\u30e9\u30b9\u5206\u985e\u3092\u884c\u3046\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u3067\u3059\u3002\u30e9\u30f3\u30c0\u30e0\u30d5\u30a9\u30ec\u30b9\u30c8\u306f\u3001\u8907\u6570\u306e\u6c7a\u5b9a\u6728\u3092\u7d44\u307f\u5408\u308f\u305b\u305f\u96c6\u56e3\u5b66\u7fd2\u30e2\u30c7\u30eb\u3067\u3042\u308a\u3001\u904e\u5b66\u7fd2\u3092\u6291\u3048\u3064\u3064\u9ad8\u3044\u7cbe\u5ea6\u3092\u5b9f\u73fe\u3057\u307e\u3059\u3002<\/p>\n\n\n\n
scikit-learn\u3067\u306f\u3001\u4ee5\u4e0b\u306e\u3088\u3046\u306b\u6c7a\u5b9a\u6728\u3068\u30e9\u30f3\u30c0\u30e0\u30d5\u30a9\u30ec\u30b9\u30c8\u3092\u5b9f\u88c5\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\n
from sklearn.tree import DecisionTreeClassifier\nfrom sklearn.ensemble import RandomForestClassifier\n\n# \u6c7a\u5b9a\u6728\ndt_model = DecisionTreeClassifier(max_depth=3)\ndt_model.fit(X_train, y_train)\n\n# \u30e9\u30f3\u30c0\u30e0\u30d5\u30a9\u30ec\u30b9\u30c8\nrf_model = RandomForestClassifier(n_estimators=100, max_depth=3)\nrf_model.fit(X_train, y_train)<\/pre>\n\n\n\n\u7570\u5e38\u691c\u77e5\u3078\u306e\u5206\u985e\u306e\u9069\u7528<\/h3>\n\n\n\n
\u5206\u985e\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u306f\u3001\u7570\u5e38\u691c\u77e5\u306b\u3082\u5fdc\u7528\u3059\u308b\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002One-Class SVM\u306f\u3001\u6b63\u5e38\u30c7\u30fc\u30bf\u306e\u307f\u3092\u5b66\u7fd2\u3057\u3001\u5916\u308c\u5024\u3092\u7570\u5e38\u3068\u3057\u3066\u691c\u77e5\u3057\u307e\u3059\u3002Isolation Forest\u306f\u3001\u7570\u5e38\u30c7\u30fc\u30bf\u307b\u3069\u5c11\u306a\u3044\u5206\u5272\u3067\u5b64\u7acb\u3059\u308b\u3068\u3044\u3046\u6027\u8cea\u3092\u5229\u7528\u3057\u3066\u7570\u5e38\u3092\u691c\u77e5\u3057\u307e\u3059\u3002\u307e\u305f\u3001Local Outlier Factor (LOF)\u306f\u3001\u5bc6\u5ea6\u306e\u4f4e\u3044\u9818\u57df\u306b\u3042\u308b\u5916\u308c\u5024\u3092\u7570\u5e38\u3068\u3057\u3066\u691c\u77e5\u3057\u307e\u3059\u3002<\/p>\n\n\n\n
scikit-learn\u3067\u306f\u3001\u4ee5\u4e0b\u306e\u3088\u3046\u306b\u7570\u5e38\u691c\u77e5\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u3092\u5b9f\u88c5\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\n
from sklearn.svm import OneClassSVM\nfrom sklearn.ensemble import IsolationForest\nfrom sklearn.neighbors import LocalOutlierFactor\n\n# One-Class SVM\nocsvm_model = OneClassSVM(kernel='rbf', nu=0.1)\nocsvm_model.fit(X_train)\n\n# Isolation Forest\nif_model = IsolationForest(n_estimators=100, contamination=0.1)\nif_model.fit(X_train)\n\n# Local Outlier Factor\nlof_model = LocalOutlierFactor(n_neighbors=20, contamination=0.1)\nlof_model.fit(X_train)<\/pre>\n\n\n\n\u5206\u985e\u30bf\u30b9\u30af\u3092\u5b9f\u8df5\u3059\u308b\u4e0a\u3067\u306f\u3001\u30c7\u30fc\u30bf\u306e\u7279\u6027\u306b\u5fdc\u3058\u3066\u9069\u5207\u306a\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u3092\u9078\u629e\u3059\u308b\u3053\u3068\u304c\u91cd\u8981\u3067\u3059\u3002\u307e\u305f\u3001\u8a55\u4fa1\u6307\u6a19\u3084\u4e0d\u5747\u8861\u30c7\u30fc\u30bf\u3078\u306e\u5bfe\u51e6\u6cd5\u306b\u3064\u3044\u3066\u3082\u7406\u89e3\u3092\u6df1\u3081\u3066\u304a\u304f\u5fc5\u8981\u304c\u3042\u308a\u307e\u3059\u3002\u7570\u5e38\u691c\u77e5\u3078\u306e\u5fdc\u7528\u3082\u542b\u3081\u3066\u3001scikit-learn\u3092\u6d3b\u7528\u3059\u308b\u3053\u3068\u3067\u3001\u69d8\u3005\u306a\u5206\u985e\u30bf\u30b9\u30af\u306b\u53d6\u308a\u7d44\u3080\u3053\u3068\u304c\u3067\u304d\u308b\u3067\u3057\u3087\u3046\u3002<\/p>\n\n\n\n
scikit-learn\u3092\u4f7f\u3063\u305f\u30af\u30e9\u30b9\u30bf\u30ea\u30f3\u30b0\u306e\u5b9f\u8df5<\/h2>\n\n\n\n
\u30af\u30e9\u30b9\u30bf\u30ea\u30f3\u30b0\u306f\u3001\u6559\u5e2b\u306a\u3057\u5b66\u7fd2\u306e\u4ee3\u8868\u7684\u306a\u624b\u6cd5\u3067\u3042\u308a\u3001\u30c7\u30fc\u30bf\u306e\u69cb\u9020\u3092\u63a2\u7d22\u7684\u306b\u7406\u89e3\u3059\u308b\u305f\u3081\u306b\u7528\u3044\u3089\u308c\u307e\u3059\u3002\u3053\u3053\u3067\u306f\u3001scikit-learn\u3092\u4f7f\u3063\u3066\u30af\u30e9\u30b9\u30bf\u30ea\u30f3\u30b0\u3092\u5b9f\u8df5\u7684\u306b\u884c\u3046\u65b9\u6cd5\u3092\u898b\u3066\u3044\u304d\u307e\u3057\u3087\u3046\u3002<\/p>\n\n\n\n
K-means\u3068Hierarchical Clustering<\/h3>\n\n\n\n
K-means\u306f\u3001\u30c7\u30fc\u30bf\u70b9\u3068\u30af\u30e9\u30b9\u30bf\u4e2d\u5fc3\u3068\u306e\u8ddd\u96e2\u306e\u7dcf\u548c\u304c\u6700\u5c0f\u306b\u306a\u308b\u3088\u3046\u306b\u30af\u30e9\u30b9\u30bf\u3092\u5f62\u6210\u3059\u308b\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u3067\u3059\u3002\u4e00\u65b9\u3001\u968e\u5c64\u7684\u30af\u30e9\u30b9\u30bf\u30ea\u30f3\u30b0\uff08Hierarchical Clustering\uff09\u306f\u3001\u30c7\u30fc\u30bf\u70b9\u9593\u306e\u8ddd\u96e2\u306b\u57fa\u3065\u3044\u3066\u3001\u30af\u30e9\u30b9\u30bf\u3092\u968e\u5c64\u7684\u306b\u5f62\u6210\u3057\u307e\u3059\u3002<\/p>\n\n\n\n
scikit-learn\u3067\u306f\u3001\u4ee5\u4e0b\u306e\u3088\u3046\u306bK-means\u3068\u968e\u5c64\u7684\u30af\u30e9\u30b9\u30bf\u30ea\u30f3\u30b0\u3092\u5b9f\u88c5\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\n
from sklearn.cluster import KMeans\nfrom sklearn.cluster import AgglomerativeClustering\n\n# K-means\nkmeans_model = KMeans(n_clusters=3, random_state=42)\nkmeans_model.fit(X)\n\n# \u968e\u5c64\u7684\u30af\u30e9\u30b9\u30bf\u30ea\u30f3\u30b0\nhc_model = AgglomerativeClustering(n_clusters=3, linkage='ward')\nhc_model.fit(X)<\/pre>\n\n\n\nDBSCAN\u3068Gaussian Mixture<\/h3>\n\n\n\n
DBSCAN\u306f\u3001\u30c7\u30fc\u30bf\u70b9\u306e\u5bc6\u5ea6\u306b\u57fa\u3065\u3044\u3066\u30af\u30e9\u30b9\u30bf\u3092\u5f62\u6210\u3057\u3001\u5916\u308c\u5024\u3092\u691c\u51fa\u3059\u308b\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u3067\u3059\u3002Gaussian Mixture Model\uff08GMM\uff09\u306f\u3001\u30c7\u30fc\u30bf\u304c\u8907\u6570\u306e\u30ac\u30a6\u30b9\u5206\u5e03\u306e\u6df7\u5408\u30e2\u30c7\u30eb\u304b\u3089\u751f\u6210\u3055\u308c\u308b\u3068\u4eee\u5b9a\u3057\u3066\u30af\u30e9\u30b9\u30bf\u30ea\u30f3\u30b0\u3092\u884c\u3044\u307e\u3059\u3002<\/p>\n\n\n\n
scikit-learn\u3067\u306f\u3001\u4ee5\u4e0b\u306e\u3088\u3046\u306bDBSCAN\u3068GMM\u3092\u5b9f\u88c5\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\n
from sklearn.cluster import DBSCAN\nfrom sklearn.mixture import GaussianMixture\n\n# DBSCAN\ndbscan_model = DBSCAN(eps=0.5, min_samples=5)\ndbscan_model.fit(X)\n\n# Gaussian Mixture Model\ngmm_model = GaussianMixture(n_components=3, random_state=42)\ngmm_model.fit(X)<\/pre>\n\n\n\n\u7279\u5fb4\u91cf\u306e\u6a19\u6e96\u5316\u3068\u30b9\u30b1\u30fc\u30ea\u30f3\u30b0<\/h3>\n\n\n\n
\u30af\u30e9\u30b9\u30bf\u30ea\u30f3\u30b0\u3092\u884c\u3046\u524d\u306b\u3001\u7279\u5fb4\u91cf\u306e\u524d\u51e6\u7406\u3092\u884c\u3046\u3053\u3068\u304c\u91cd\u8981\u3067\u3059\u3002\u6a19\u6e96\u5316\u306f\u3001\u30c7\u30fc\u30bf\u306e\u5e73\u5747\u30920\u3001\u5206\u6563\u30921\u306b\u5909\u63db\u3059\u308b\u64cd\u4f5c\u3067\u3042\u308a\u3001\u30b9\u30b1\u30fc\u30ea\u30f3\u30b0\u306f\u3001\u30c7\u30fc\u30bf\u306e\u5024\u3092\u4e00\u5b9a\u306e\u7bc4\u56f2\uff08\u4f8b: 0\u301c1\uff09\u306b\u5909\u63db\u3059\u308b\u64cd\u4f5c\u3067\u3059\u3002<\/p>\n\n\n\n
scikit-learn\u3067\u306f\u3001\u4ee5\u4e0b\u306e\u3088\u3046\u306b\u6a19\u6e96\u5316\u3068\u30b9\u30b1\u30fc\u30ea\u30f3\u30b0\u3092\u5b9f\u88c5\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\n
from sklearn.preprocessing import StandardScaler, MinMaxScaler\n\n# \u6a19\u6e96\u5316\nscaler = StandardScaler()\nX_scaled = scaler.fit_transform(X)\n\n# \u30b9\u30b1\u30fc\u30ea\u30f3\u30b0\nscaler = MinMaxScaler()\nX_scaled = scaler.fit_transform(X)<\/pre>\n\n\n\n\u6b21\u5143\u524a\u6e1b\u3068\u30af\u30e9\u30b9\u30bf\u30ea\u30f3\u30b0\u306e\u7d44\u307f\u5408\u308f\u305b<\/h3>\n\n\n\n
\u9ad8\u6b21\u5143\u306e\u30c7\u30fc\u30bf\u306b\u5bfe\u3057\u3066\u30af\u30e9\u30b9\u30bf\u30ea\u30f3\u30b0\u3092\u9069\u7528\u3059\u308b\u5834\u5408\u3001\u6b21\u5143\u524a\u6e1b\u3068\u7d44\u307f\u5408\u308f\u305b\u308b\u3053\u3068\u3067\u3001\u3088\u308a\u52b9\u679c\u7684\u306a\u5206\u6790\u304c\u53ef\u80fd\u306b\u306a\u308a\u307e\u3059\u3002PCA\u3084t-SNE\u3092\u4f7f\u3063\u3066\u6b21\u5143\u524a\u6e1b\u3092\u884c\u3063\u305f\u5f8c\u3001\u30af\u30e9\u30b9\u30bf\u30ea\u30f3\u30b0\u3092\u9069\u7528\u3059\u308b\u65b9\u6cd5\u3068\u3001\u30af\u30e9\u30b9\u30bf\u30ea\u30f3\u30b0\u306e\u7d50\u679c\u3092\u3082\u3068\u306b\u6b21\u5143\u524a\u6e1b\u3057\u3066\u53ef\u8996\u5316\u3059\u308b\u65b9\u6cd5\u304c\u3042\u308a\u307e\u3059\u3002<\/p>\n\n\n\n
scikit-learn\u3067\u306f\u3001\u4ee5\u4e0b\u306e\u3088\u3046\u306bPCA\u3068t-SNE\u3092\u5b9f\u88c5\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\n
from sklearn.decomposition import PCA\nfrom sklearn.manifold import TSNE\n\n# PCA\npca = PCA(n_components=2)\nX_pca = pca.fit_transform(X)\n\n# t-SNE\ntsne = TSNE(n_components=2, random_state=42)\nX_tsne = tsne.fit_transform(X)<\/pre>\n\n\n\n\u30af\u30e9\u30b9\u30bf\u30ea\u30f3\u30b0\u306f\u3001\u30c7\u30fc\u30bf\u306e\u69cb\u9020\u3092\u7406\u89e3\u3059\u308b\u305f\u3081\u306e\u5f37\u529b\u306a\u30c4\u30fc\u30eb\u3067\u3059\u3002scikit-learn\u3092\u4f7f\u3046\u3053\u3068\u3067\u3001\u69d8\u3005\u306a\u30af\u30e9\u30b9\u30bf\u30ea\u30f3\u30b0\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u3092\u7c21\u5358\u306b\u5b9f\u88c5\u3059\u308b\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002\u7279\u5fb4\u91cf\u306e\u524d\u51e6\u7406\u3084\u6b21\u5143\u524a\u6e1b\u3068\u306e\u7d44\u307f\u5408\u308f\u305b\u306b\u3064\u3044\u3066\u3082\u7406\u89e3\u3092\u6df1\u3081\u3001\u5b9f\u8df5\u7684\u306a\u30c7\u30fc\u30bf\u5206\u6790\u30b9\u30ad\u30eb\u3092\u8eab\u306b\u3064\u3051\u307e\u3057\u3087\u3046\u3002<\/p>\n\n\n\n
scikit-learn\u3068\u30c7\u30fc\u30bf\u524d\u51e6\u7406\u30fb\u30e2\u30c7\u30eb\u8a55\u4fa1<\/h2>\n\n\n\n
\u6a5f\u68b0\u5b66\u7fd2\u30e2\u30c7\u30eb\u3092\u69cb\u7bc9\u3059\u308b\u4e0a\u3067\u3001\u30c7\u30fc\u30bf\u306e\u524d\u51e6\u7406\u3068\u30e2\u30c7\u30eb\u306e\u8a55\u4fa1\u306f\u6b20\u304b\u305b\u306a\u3044\u8981\u7d20\u3067\u3059\u3002\u3053\u3053\u3067\u306f\u3001scikit-learn\u3092\u4f7f\u3063\u305f\u30c7\u30fc\u30bf\u524d\u51e6\u7406\u3068\u30e2\u30c7\u30eb\u8a55\u4fa1\u306e\u5b9f\u8df5\u7684\u306a\u65b9\u6cd5\u3092\u898b\u3066\u3044\u304d\u307e\u3057\u3087\u3046\u3002<\/p>\n\n\n\n
\u6b20\u640d\u5024\u306e\u6271\u3044\u65b9<\/h3>\n\n\n\n
\u6b20\u640d\u5024\u3092\u542b\u3080\u30c7\u30fc\u30bf\u3092\u6271\u3046\u969b\u306b\u306f\u3001\u307e\u305a\u6b20\u640d\u5024\u306e\u5b58\u5728\u3092\u7279\u5b9a\u3059\u308b\u5fc5\u8981\u304c\u3042\u308a\u307e\u3059\u3002\u305d\u306e\u5f8c\u3001\u6b20\u640d\u5024\u3092\u524a\u9664\u3059\u308b\u65b9\u6cd5\uff08\u30ea\u30b9\u30c8\u30ef\u30a4\u30ba\u524a\u9664\u3001\u30da\u30a2\u30ef\u30a4\u30ba\u524a\u9664\uff09\u3068\u3001\u6b20\u640d\u5024\u3092\u88dc\u5b8c\u3059\u308b\u65b9\u6cd5\uff08\u5e73\u5747\u5024\u3001\u4e2d\u592e\u5024\u3001\u6700\u983b\u5024\u3001KNN\u6cd5\u306a\u3069\uff09\u304c\u3042\u308a\u307e\u3059\u3002<\/p>\n\n\n\n
scikit-learn\u3067\u306f\u3001\u4ee5\u4e0b\u306e\u3088\u3046\u306b\u6b20\u640d\u5024\u3092\u88dc\u5b8c\u3059\u308b\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\n
from sklearn.impute import SimpleImputer\n\n# \u6b20\u640d\u5024\u3092\u5e73\u5747\u5024\u3067\u88dc\u5b8c\nimputer = SimpleImputer(strategy='mean')\nX_imputed = imputer.fit_transform(X)<\/pre>\n\n\n\n\u30ab\u30c6\u30b4\u30ea\u5909\u6570\u306e\u30a8\u30f3\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0<\/h3>\n\n\n\n
\u30ab\u30c6\u30b4\u30ea\u5909\u6570\u3092\u6570\u5024\u5316\u3059\u308b\u969b\u306b\u306f\u3001One-Hot Encoding\u3001Label Encoding\u3001Ordinal Encoding\u306a\u3069\u306e\u624b\u6cd5\u304c\u3042\u308a\u307e\u3059\u3002One-Hot Encoding\u306f\u30ab\u30c6\u30b4\u30ea\u5909\u6570\u3092\u30d0\u30a4\u30ca\u30ea\u5909\u6570\u306b\u5909\u63db\u3057\u3001Label Encoding\u306f\u6574\u6570\u306b\u5909\u63db\u3057\u307e\u3059\u3002Ordinal Encoding\u306f\u9806\u5e8f\u95a2\u4fc2\u3092\u8003\u616e\u3057\u3066\u6574\u6570\u306b\u5909\u63db\u3057\u307e\u3059\u3002<\/p>\n\n\n\n
scikit-learn\u3067\u306f\u3001\u4ee5\u4e0b\u306e\u3088\u3046\u306b\u30ab\u30c6\u30b4\u30ea\u5909\u6570\u3092\u30a8\u30f3\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\n
from sklearn.preprocessing import OneHotEncoder, LabelEncoder, OrdinalEncoder\n\n# One-Hot Encoding\nonehot_encoder = OneHotEncoder()\nX_onehot = onehot_encoder.fit_transform(X)\n\n# Label Encoding\nlabel_encoder = LabelEncoder()\nX_label = label_encoder.fit_transform(X)\n\n# Ordinal Encoding\nordinal_encoder = OrdinalEncoder()\nX_ordinal = ordinal_encoder.fit_transform(X)<\/pre>\n\n\n\n\u4ea4\u5dee\u691c\u8a3c\u3068\u30b0\u30ea\u30c3\u30c9\u30b5\u30fc\u30c1<\/h3>\n\n\n\n
\u30e2\u30c7\u30eb\u306e\u6c4e\u5316\u6027\u80fd\u3092\u8a55\u4fa1\u3059\u308b\u305f\u3081\u306b\u3001\u4ea4\u5dee\u691c\u8a3c\u304c\u7528\u3044\u3089\u308c\u307e\u3059\u3002K-\u5206\u5272\u4ea4\u5dee\u691c\u8a3c\u306f\u3001\u30c7\u30fc\u30bf\u3092K\u500b\u306e\u30b5\u30d6\u30bb\u30c3\u30c8\u306b\u5206\u5272\u3057\u3001\u9806\u756a\u306b\u691c\u8a3c\u3092\u884c\u3046\u624b\u6cd5\u3067\u3059\u3002\u5c64\u5316K-\u5206\u5272\u4ea4\u5dee\u691c\u8a3c\u306f\u3001\u30af\u30e9\u30b9\u6bd4\u7387\u3092\u4fdd\u6301\u3057\u306a\u304c\u3089K-\u5206\u5272\u4ea4\u5dee\u691c\u8a3c\u3092\u884c\u3044\u307e\u3059\u3002<\/p>\n\n\n\n
\u30b0\u30ea\u30c3\u30c9\u30b5\u30fc\u30c1\u306f\u3001\u30cf\u30a4\u30d1\u30fc\u30d1\u30e9\u30e1\u30fc\u30bf\u306e\u5019\u88dc\u5024\u3092\u6307\u5b9a\u3057\u3001\u4ea4\u5dee\u691c\u8a3c\u3092\u7528\u3044\u3066\u5404\u7d44\u307f\u5408\u308f\u305b\u3092\u8a55\u4fa1\u3059\u308b\u3053\u3068\u3067\u3001\u6700\u9069\u306a\u30cf\u30a4\u30d1\u30fc\u30d1\u30e9\u30e1\u30fc\u30bf\u3092\u63a2\u7d22\u3059\u308b\u624b\u6cd5\u3067\u3059\u3002<\/p>\n\n\n\n
scikit-learn\u3067\u306f\u3001\u4ee5\u4e0b\u306e\u3088\u3046\u306b\u4ea4\u5dee\u691c\u8a3c\u3068\u30b0\u30ea\u30c3\u30c9\u30b5\u30fc\u30c1\u3092\u5b9f\u88c5\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\n
from sklearn.model_selection import KFold, StratifiedKFold, GridSearchCV\n\n# K-\u5206\u5272\u4ea4\u5dee\u691c\u8a3c\nkf = KFold(n_splits=5, shuffle=True, random_state=42)\n\n# \u5c64\u5316K-\u5206\u5272\u4ea4\u5dee\u691c\u8a3c\nskf = StratifiedKFold(n_splits=5, shuffle=True, random_state=42)\n\n# \u30b0\u30ea\u30c3\u30c9\u30b5\u30fc\u30c1\nparam_grid = {'C': [0.1, 1, 10], 'kernel': ['linear', 'rbf']}\ngrid_search = GridSearchCV(SVC(), param_grid, cv=5)\ngrid_search.fit(X_train, y_train)<\/pre>\n\n\n\n\u9069\u5207\u306a\u8a55\u4fa1\u6307\u6a19\u306e\u9078\u3073\u65b9<\/h3>\n\n\n\n
\u30e2\u30c7\u30eb\u306e\u8a55\u4fa1\u306b\u306f\u3001\u554f\u984c\u306e\u7a2e\u985e\u306b\u5fdc\u3058\u3066\u9069\u5207\u306a\u8a55\u4fa1\u6307\u6a19\u3092\u9078\u3076\u5fc5\u8981\u304c\u3042\u308a\u307e\u3059\u3002\u56de\u5e30\u554f\u984c\u3067\u306f\u3001MAE\u3001MSE\u3001RMSE\u3001R^2\u306a\u3069\u306e\u6307\u6a19\u304c\u7528\u3044\u3089\u308c\u307e\u3059\u3002\u5206\u985e\u554f\u984c\u3067\u306f\u3001\u6b63\u89e3\u7387\u3001\u9069\u5408\u7387\u3001\u518d\u73fe\u7387\u3001F1\u30b9\u30b3\u30a2\u3001AUC\u306a\u3069\u304c\u4f7f\u308f\u308c\u307e\u3059\u3002\u30af\u30e9\u30b9\u30bf\u30ea\u30f3\u30b0\u3067\u306f\u3001\u30b7\u30eb\u30a8\u30c3\u30c8\u4fc2\u6570\u3001Davies-Bouldin Index\u3001Calinski-Harabasz Index\u306a\u3069\u304c\u7528\u3044\u3089\u308c\u307e\u3059\u3002<\/p>\n\n\n\n
scikit-learn\u3067\u306f\u3001\u4ee5\u4e0b\u306e\u3088\u3046\u306b\u8a55\u4fa1\u6307\u6a19\u3092\u8a08\u7b97\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\n
from sklearn.metrics import mean_absolute_error, mean_squared_error, r2_score\nfrom sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score, roc_auc_score\nfrom sklearn.metrics import silhouette_score, davies_bouldin_score, calinski_harabasz_score\n\n# \u56de\u5e30\u554f\u984c\u306e\u8a55\u4fa1\u6307\u6a19\nmae = mean_absolute_error(y_test, y_pred)\nmse = mean_squared_error(y_test, y_pred)\nrmse = np.sqrt(mse)\nr2 = r2_score(y_test, y_pred)\n\n# \u5206\u985e\u554f\u984c\u306e\u8a55\u4fa1\u6307\u6a19\naccuracy = accuracy_score(y_test, y_pred)\nprecision = precision_score(y_test, y_pred)\nrecall = recall_score(y_test, y_pred)\nf1 = f1_score(y_test, y_pred)\nauc = roc_auc_score(y_test, y_pred_proba)\n\n# \u30af\u30e9\u30b9\u30bf\u30ea\u30f3\u30b0\u306e\u8a55\u4fa1\u6307\u6a19\nsilhouette = silhouette_score(X, labels)\ndb_index = davies_bouldin_score(X, labels)\nch_index = calinski_harabasz_score(X, labels)<\/pre>\n\n\n\n\u30c7\u30fc\u30bf\u524d\u51e6\u7406\u3068\u30e2\u30c7\u30eb\u8a55\u4fa1\u306f\u3001\u6a5f\u68b0\u5b66\u7fd2\u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u306e\u91cd\u8981\u306a\u8981\u7d20\u3067\u3059\u3002scikit-learn\u3092\u6d3b\u7528\u3059\u308b\u3053\u3068\u3067\u3001\u6b20\u640d\u5024\u306e\u51e6\u7406\u3084\u30ab\u30c6\u30b4\u30ea\u5909\u6570\u306e\u30a8\u30f3\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0\u3001\u4ea4\u5dee\u691c\u8a3c\u3001\u30b0\u30ea\u30c3\u30c9\u30b5\u30fc\u30c1\u3001\u9069\u5207\u306a\u8a55\u4fa1\u6307\u6a19\u306e\u9078\u629e\u306a\u3069\u3001\u4e00\u9023\u306e\u4f5c\u696d\u3092\u52b9\u7387\u7684\u306b\u884c\u3046\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002\u3053\u308c\u3089\u306e\u624b\u6cd5\u3092\u9069\u5207\u306b\u7d44\u307f\u5408\u308f\u305b\u3001\u30e2\u30c7\u30eb\u306e\u6027\u80fd\u3092\u6700\u5927\u9650\u306b\u5f15\u304d\u51fa\u3057\u307e\u3057\u3087\u3046\u3002<\/p>\n\n\n\n
scikit-learn\u306e\u767a\u5c55\u7684\u306a\u4f7f\u3044\u65b9<\/h2>\n\n\n\n
scikit-learn\u3092\u4f7f\u3044\u3053\u306a\u3059\u3053\u3068\u3067\u3001\u3088\u308a\u52b9\u7387\u7684\u3067\u9ad8\u5ea6\u306a\u6a5f\u68b0\u5b66\u7fd2\u3092\u5b9f\u8df5\u3059\u308b\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002\u3053\u3053\u3067\u306f\u3001scikit-learn\u306e\u767a\u5c55\u7684\u306a\u4f7f\u3044\u65b9\u306b\u3064\u3044\u3066\u3001\u5177\u4f53\u7684\u306a\u4f8b\u3092\u4ea4\u3048\u3066\u89e3\u8aac\u3057\u307e\u3059\u3002<\/p>\n\n\n\n
\u30d1\u30a4\u30d7\u30e9\u30a4\u30f3\u306b\u3088\u308b\u51e6\u7406\u306e\u81ea\u52d5\u5316<\/h3>\n\n\n\n
\u30d1\u30a4\u30d7\u30e9\u30a4\u30f3\u3092\u4f7f\u3046\u3053\u3068\u3067\u3001\u30c7\u30fc\u30bf\u524d\u51e6\u7406\u304b\u3089\u30e2\u30c7\u30eb\u69cb\u7bc9\u307e\u3067\u306e\u4e00\u9023\u306e\u6d41\u308c\u3092\u81ea\u52d5\u5316\u3059\u308b\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002\u3053\u308c\u306b\u3088\u308a\u3001\u30b3\u30fc\u30c9\u306e\u53ef\u8aad\u6027\u304c\u5411\u4e0a\u3057\u3001\u518d\u5229\u7528\u6027\u304c\u9ad8\u307e\u308a\u307e\u3059\u3002\u307e\u305f\u3001\u30ab\u30b9\u30bf\u30e0\u30c8\u30e9\u30f3\u30b9\u30d5\u30a9\u30fc\u30de\u30fc\u3092\u4f5c\u6210\u3059\u308b\u3053\u3068\u3067\u3001\u72ec\u81ea\u306e\u524d\u51e6\u7406\u624b\u9806\u3092\u30d1\u30a4\u30d7\u30e9\u30a4\u30f3\u306b\u7d44\u307f\u8fbc\u3080\u3053\u3068\u3082\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\n
scikit-learn\u3067\u306f\u3001\u4ee5\u4e0b\u306e\u3088\u3046\u306b\u30d1\u30a4\u30d7\u30e9\u30a4\u30f3\u3092\u69cb\u7bc9\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\n
from sklearn.pipeline import Pipeline\nfrom sklearn.preprocessing import StandardScaler\nfrom sklearn.linear_model import LogisticRegression\n\npipeline = Pipeline([\n ('scaler', StandardScaler()),\n ('classifier', LogisticRegression())\n])\n\npipeline.fit(X_train, y_train)<\/pre>\n\n\n\n\u30a2\u30f3\u30b5\u30f3\u30d6\u30eb\u5b66\u7fd2\u306e\u5b9f\u88c5\u65b9\u6cd5<\/h3>\n\n\n\n
\u30a2\u30f3\u30b5\u30f3\u30d6\u30eb\u5b66\u7fd2\u306f\u3001\u8907\u6570\u306e\u30e2\u30c7\u30eb\u3092\u7d44\u307f\u5408\u308f\u305b\u308b\u3053\u3068\u3067\u3001\u5358\u4e00\u306e\u30e2\u30c7\u30eb\u3088\u308a\u3082\u9ad8\u3044\u6027\u80fd\u3092\u9054\u6210\u3059\u308b\u624b\u6cd5\u3067\u3059\u3002\u4ee3\u8868\u7684\u306a\u30a2\u30f3\u30b5\u30f3\u30d6\u30eb\u5b66\u7fd2\u3068\u3057\u3066\u3001\u30d0\u30ae\u30f3\u30b0\uff08\u30e9\u30f3\u30c0\u30e0\u30d5\u30a9\u30ec\u30b9\u30c8\uff09\u3001\u30d6\u30fc\u30b9\u30c6\u30a3\u30f3\u30b0\uff08AdaBoost, Gradient Boosting\uff09\u3001\u30b9\u30bf\u30c3\u30ad\u30f3\u30b0\u306a\u3069\u304c\u3042\u308a\u307e\u3059\u3002<\/p>\n\n\n\n
scikit-learn\u3067\u306f\u3001\u4ee5\u4e0b\u306e\u3088\u3046\u306b\u30a2\u30f3\u30b5\u30f3\u30d6\u30eb\u5b66\u7fd2\u3092\u5b9f\u88c5\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\n
from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier, GradientBoostingClassifier\nfrom sklearn.ensemble import StackingClassifier\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn.tree import DecisionTreeClassifier\n\n# \u30e9\u30f3\u30c0\u30e0\u30d5\u30a9\u30ec\u30b9\u30c8\nrf_model = RandomForestClassifier(n_estimators=100, random_state=42)\n\n# AdaBoost\nada_model = AdaBoostClassifier(n_estimators=100, random_state=42)\n\n# Gradient Boosting\ngb_model = GradientBoostingClassifier(n_estimators=100, random_state=42)\n\n# \u30b9\u30bf\u30c3\u30ad\u30f3\u30b0\nestimators = [\n ('rf', RandomForestClassifier(n_estimators=100, random_state=42)),\n ('ada', AdaBoostClassifier(n_estimators=100, random_state=42)),\n ('gb', GradientBoostingClassifier(n_estimators=100, random_state=42))\n]\nstack_model = StackingClassifier(estimators=estimators, final_estimator=LogisticRegression())<\/pre>\n\n\n\nOpenCV\u306a\u3069\u4ed6\u30e9\u30a4\u30d6\u30e9\u30ea\u3068\u306e\u9023\u643a<\/h3>\n\n\n\n
scikit-learn\u306f\u3001OpenCV\u3084XGBoost\u3001LightGBM\u306a\u3069\u306e\u5916\u90e8\u30e9\u30a4\u30d6\u30e9\u30ea\u3068\u9023\u643a\u3059\u308b\u3053\u3068\u3067\u3001\u3088\u308a\u9ad8\u5ea6\u306a\u6a5f\u68b0\u5b66\u7fd2\u30bf\u30b9\u30af\u306b\u5bfe\u5fdc\u3067\u304d\u307e\u3059\u3002OpenCV\u3092\u7528\u3044\u308b\u3053\u3068\u3067\u3001\u753b\u50cf\u51e6\u7406\u3068\u6a5f\u68b0\u5b66\u7fd2\u3092\u7d44\u307f\u5408\u308f\u305b\u305f\u30bf\u30b9\u30af\u306b\u53d6\u308a\u7d44\u3080\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002XGBoost\u3084LightGBM\u306f\u3001\u52fe\u914d\u30d6\u30fc\u30b9\u30c6\u30a3\u30f3\u30b0\u306e\u5b9f\u88c5\u306b\u7279\u5316\u3057\u305f\u30e9\u30a4\u30d6\u30e9\u30ea\u3067\u3042\u308a\u3001\u5927\u898f\u6a21\u30c7\u30fc\u30bf\u3078\u306e\u5bfe\u5fdc\u306b\u512a\u308c\u3066\u3044\u307e\u3059\u3002<\/p>\n\n\n\n
\u4ee5\u4e0b\u306f\u3001OpenCV\u3092\u7528\u3044\u305f\u753b\u50cf\u51e6\u7406\u3068\u6a5f\u68b0\u5b66\u7fd2\u306e\u9023\u643a\u4f8b\u3067\u3059\u3002<\/p>\n\n\n\n
import cv2\nfrom sklearn.svm import SVC\n\n# \u753b\u50cf\u306e\u8aad\u307f\u8fbc\u307f\u3068\u524d\u51e6\u7406\nimg = cv2.imread('image.jpg')\ngray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)\nfeatures = gray.reshape(-1)\n\n# SVM\u3092\u7528\u3044\u305f\u753b\u50cf\u5206\u985e\nsvm_model = SVC()\nsvm_model.fit(X_train, y_train)\nprediction = svm_model.predict([features])<\/pre>\n\n\n\n\u5927\u898f\u6a21\u30c7\u30fc\u30bf\u3078\u306e\u5bfe\u5fdc\u65b9\u6cd5<\/h3>\n\n\n\n
\u5927\u898f\u6a21\u30c7\u30fc\u30bf\u3092\u6271\u3046\u969b\u306b\u306f\u3001\u30e1\u30e2\u30ea\u5236\u7d04\u3084\u30d1\u30d5\u30a9\u30fc\u30de\u30f3\u30b9\u306e\u554f\u984c\u304c\u751f\u3058\u308b\u53ef\u80fd\u6027\u304c\u3042\u308a\u307e\u3059\u3002\u3053\u308c\u306b\u5bfe\u5fdc\u3059\u308b\u305f\u3081\u306b\u3001\u30c7\u30fc\u30bf\u306e\u30c1\u30e3\u30f3\u30af\u5358\u4f4d\u3067\u306e\u8aad\u307f\u8fbc\u307f\u3084\u3001\u7279\u5fb4\u91cf\u306e\u6f38\u9032\u7684\u306a\u9078\u629e\uff08Incremental Feature Selection\uff09\u3001\u30aa\u30f3\u30e9\u30a4\u30f3\u5b66\u7fd2\uff08Online Learning\uff09\u306a\u3069\u306e\u624b\u6cd5\u304c\u7528\u3044\u3089\u308c\u307e\u3059\u3002<\/p>\n\n\n\n
scikit-learn\u3067\u306f\u3001\u4ee5\u4e0b\u306e\u3088\u3046\u306b\u30aa\u30f3\u30e9\u30a4\u30f3\u5b66\u7fd2\u3092\u5b9f\u88c5\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\n
from sklearn.linear_model import SGDClassifier\n\nsgd_model = SGDClassifier()\n\nfor X_batch, y_batch in zip(X_batches, y_batches):\n sgd_model.partial_fit(X_batch, y_batch, classes=np.unique(y))<\/pre>\n\n\n\n\u3053\u306e\u3088\u3046\u306b\u3001scikit-learn\u3092\u767a\u5c55\u7684\u306b\u4f7f\u3044\u3053\u306a\u3059\u3053\u3068\u3067\u3001\u3088\u308a\u5b9f\u8df5\u7684\u3067\u9ad8\u5ea6\u306a\u6a5f\u68b0\u5b66\u7fd2\u3092\u884c\u3046\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002\u30d1\u30a4\u30d7\u30e9\u30a4\u30f3\u3084\u30a2\u30f3\u30b5\u30f3\u30d6\u30eb\u5b66\u7fd2\u3001\u5916\u90e8\u30e9\u30a4\u30d6\u30e9\u30ea\u3068\u306e\u9023\u643a\u3001\u5927\u898f\u6a21\u30c7\u30fc\u30bf\u3078\u306e\u5bfe\u5fdc\u306a\u3069\u3001\u69d8\u3005\u306a\u5834\u9762\u3067\u5fdc\u7528\u529b\u3092\u767a\u63ee\u3057\u307e\u3057\u3087\u3046\u3002scikit-learn\u306e\u53ef\u80fd\u6027\u3092\u6700\u5927\u9650\u306b\u5f15\u304d\u51fa\u3059\u3053\u3068\u3067\u3001\u6a5f\u68b0\u5b66\u7fd2\u306e\u30a8\u30ad\u30b9\u30d1\u30fc\u30c8\u3092\u76ee\u6307\u3059\u3053\u3068\u304c\u3067\u304d\u308b\u3067\u3057\u3087\u3046\u3002<\/p>\n\n\n\n
scikit-learn\u306e\u5b9f\u8df5\u7684\u306a\u9069\u7528\u4f8b<\/h2>\n\n\n\n
\u3053\u3053\u307e\u3067scikit-learn\u306e\u57fa\u672c\u7684\u306a\u4f7f\u3044\u65b9\u304b\u3089\u767a\u5c55\u7684\u306a\u30c6\u30af\u30cb\u30c3\u30af\u307e\u3067\u5b66\u3093\u3067\u304d\u307e\u3057\u305f\u3002\u6700\u5f8c\u306b\u3001scikit-learn\u3092\u5b9f\u969b\u306e\u696d\u52d9\u3067\u6d3b\u7528\u3059\u308b\u969b\u306e\u5177\u4f53\u7684\u306a\u9069\u7528\u4f8b\u3092\u3044\u304f\u3064\u304b\u7d39\u4ecb\u3057\u307e\u3059\u3002<\/p>\n\n\n\n
\u4e0d\u52d5\u7523\u4fa1\u683c\u306e\u4e88\u6e2c\u30e2\u30c7\u30eb<\/h3>\n\n\n\n
\u4e0d\u52d5\u7523\u4fa1\u683c\u306e\u4e88\u6e2c\u306f\u3001scikit-learn\u3092\u7528\u3044\u305f\u56de\u5e30\u5206\u6790\u306e\u4ee3\u8868\u7684\u306a\u9069\u7528\u4f8b\u3067\u3059\u3002\u76ee\u7684\u5909\u6570\u306f\u4e0d\u52d5\u7523\u4fa1\u683c\u3001\u8aac\u660e\u5909\u6570\u306f\u9762\u7a4d\u3001\u7acb\u5730\u3001\u7bc9\u5e74\u6570\u3001\u9593\u53d6\u308a\u306a\u3069\u304c\u8003\u3048\u3089\u308c\u307e\u3059\u3002\u7dda\u5f62\u56de\u5e30\u3084\u30e9\u30f3\u30c0\u30e0\u30d5\u30a9\u30ec\u30b9\u30c8\u3001XGBoost\u306a\u3069\u306e\u624b\u6cd5\u3092\u7528\u3044\u308b\u3053\u3068\u3067\u3001\u4e0d\u52d5\u7523\u4fa1\u683c\u306e\u4e88\u6e2c\u30e2\u30c7\u30eb\u3092\u69cb\u7bc9\u3059\u308b\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\n
\u30e2\u30c7\u30eb\u306e\u8a55\u4fa1\u306b\u306f\u3001MAE\uff08\u5e73\u5747\u7d76\u5bfe\u8aa4\u5dee\uff09\u3001RMSE\uff08\u5e73\u5747\u4e8c\u4e57\u8aa4\u5dee\u306e\u5e73\u65b9\u6839\uff09\u3001R^2\uff08\u6c7a\u5b9a\u4fc2\u6570\uff09\u306a\u3069\u306e\u56de\u5e30\u554f\u984c\u306e\u8a55\u4fa1\u6307\u6a19\u3092\u7528\u3044\u307e\u3059\u3002\u3053\u308c\u3089\u306e\u6307\u6a19\u3092\u7528\u3044\u3066\u3001\u30e2\u30c7\u30eb\u306e\u4e88\u6e2c\u7cbe\u5ea6\u3092\u8a55\u4fa1\u3057\u3001\u6539\u5584\u3057\u3066\u3044\u304d\u307e\u3059\u3002<\/p>\n\n\n\n
SNS\u306e\u6295\u7a3f\u306e\u611f\u60c5\u5206\u6790<\/h3>\n\n\n\n
SNS\u306e\u6295\u7a3f\u304b\u3089\u3001\u30e6\u30fc\u30b6\u30fc\u306e\u30dd\u30b8\u30c6\u30a3\u30d6\/\u30cd\u30ac\u30c6\u30a3\u30d6\u306a\u611f\u60c5\u3092\u5224\u5b9a\u3059\u308b\u611f\u60c5\u5206\u6790\u3082\u3001scikit-learn\u3092\u6d3b\u7528\u3067\u304d\u308b\u5206\u91ce\u3067\u3059\u3002\u307e\u305a\u3001\u6295\u7a3f\u306e\u30c6\u30ad\u30b9\u30c8\u30c7\u30fc\u30bf\u306b\u5bfe\u3057\u3066\u3001\u30af\u30ea\u30fc\u30cb\u30f3\u30b0\u3084\u3001BoW\uff08Bag of Words\uff09\u3001TF-IDF\uff08Term Frequency-Inverse Document Frequency\uff09\u306a\u3069\u306e\u7279\u5fb4\u91cf\u62bd\u51fa\u3092\u884c\u3044\u307e\u3059\u3002<\/p>\n\n\n\n
\u305d\u306e\u5f8c\u3001\u30ed\u30b8\u30b9\u30c6\u30a3\u30c3\u30af\u56de\u5e30\u3084SVM\uff08\u30b5\u30dd\u30fc\u30c8\u30d9\u30af\u30bf\u30fc\u30de\u30b7\u30f3\uff09\u3001\u30ca\u30a4\u30fc\u30d6\u30d9\u30a4\u30ba\u306a\u3069\u306e\u5206\u985e\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u3092\u7528\u3044\u3066\u3001\u611f\u60c5\u3092\u5224\u5b9a\u3059\u308b\u30e2\u30c7\u30eb\u3092\u69cb\u7bc9\u3057\u307e\u3059\u3002\u9069\u5408\u7387\u3001\u518d\u73fe\u7387\u3001F1\u30b9\u30b3\u30a2\u306a\u3069\u306e\u5206\u985e\u554f\u984c\u306e\u8a55\u4fa1\u6307\u6a19\u3092\u7528\u3044\u3066\u3001\u30e2\u30c7\u30eb\u306e\u6027\u80fd\u3092\u8a55\u4fa1\u3057\u307e\u3059\u3002<\/p>\n\n\n\n
EC\u30b5\u30a4\u30c8\u306e\u8cfc\u8cb7\u4e88\u6e2c<\/h3>\n\n\n\n
EC\u30b5\u30a4\u30c8\u306b\u304a\u3051\u308b\u8cfc\u8cb7\u4e88\u6e2c\u306f\u3001\u30e6\u30fc\u30b6\u30fc\u306e\u8cfc\u8cb7\u884c\u52d5\u3092\u4e88\u6e2c\u3057\u3001\u30d1\u30fc\u30bd\u30ca\u30e9\u30a4\u30ba\u3055\u308c\u305f\u30ec\u30b3\u30e1\u30f3\u30c7\u30fc\u30b7\u30e7\u30f3\u3092\u63d0\u4f9b\u3059\u308b\u305f\u3081\u306b\u91cd\u8981\u3067\u3059\u3002\u8aac\u660e\u5909\u6570\u3068\u3057\u3066\u3001\u904e\u53bb\u306e\u8cfc\u8cb7\u5c65\u6b74\u3001\u95b2\u89a7\u5c65\u6b74\u3001\u5c5e\u6027\u60c5\u5831\u306a\u3069\u3092\u7528\u3044\u308b\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\n
\u5354\u8abf\u30d5\u30a3\u30eb\u30bf\u30ea\u30f3\u30b0\u3084\u30b3\u30f3\u30c6\u30f3\u30c4\u30d9\u30fc\u30b9\u63a8\u85a6\u3001\u30e9\u30f3\u30c0\u30e0\u30d5\u30a9\u30ec\u30b9\u30c8\u306a\u3069\u306e\u624b\u6cd5\u3092\u7528\u3044\u3066\u3001\u8cfc\u8cb7\u4e88\u6e2c\u30e2\u30c7\u30eb\u3092\u69cb\u7bc9\u3057\u307e\u3059\u3002\u6b63\u89e3\u7387\u3001\u9069\u5408\u7387\u3001\u518d\u73fe\u7387\u3001AUC\uff08ROC\u66f2\u7dda\u306e\u4e0b\u9762\u7a4d\uff09\u306a\u3069\u306e\u8a55\u4fa1\u6307\u6a19\u3092\u7528\u3044\u3066\u3001\u30e2\u30c7\u30eb\u306e\u6027\u80fd\u3092\u8a55\u4fa1\u3057\u307e\u3059\u3002<\/p>\n\n\n\n
\u682a\u4fa1\u306e\u5909\u52d5\u4e88\u6e2c\u30e2\u30c7\u30eb<\/h3>\n\n\n\n
\u682a\u4fa1\u306e\u5909\u52d5\u3092\u4e88\u6e2c\u3059\u308b\u3053\u3068\u306f\u3001\u91d1\u878d\u5206\u91ce\u306b\u304a\u3051\u308bscikit-learn\u306e\u91cd\u8981\u306a\u9069\u7528\u4f8b\u306e\u4e00\u3064\u3067\u3059\u3002\u76ee\u7684\u5909\u6570\u306f\u5c06\u6765\u306e\u682a\u4fa1\u306e\u4e0a\u6607\/\u4e0b\u843d\u3001\u8aac\u660e\u5909\u6570\u306f\u904e\u53bb\u306e\u682a\u4fa1\u3001\u51fa\u6765\u9ad8\u3001\u30cb\u30e5\u30fc\u30b9\u8a18\u4e8b\u306e\u611f\u60c5\u6975\u6027\u306a\u3069\u304c\u8003\u3048\u3089\u308c\u307e\u3059\u3002<\/p>\n\n\n\n
\u30ed\u30b8\u30b9\u30c6\u30a3\u30c3\u30af\u56de\u5e30\u3084SVM\u3001LSTM\uff08Long Short-Term Memory\uff09\u306a\u3069\u306e\u624b\u6cd5\u3092\u7528\u3044\u3066\u3001\u682a\u4fa1\u306e\u5909\u52d5\u4e88\u6e2c\u30e2\u30c7\u30eb\u3092\u69cb\u7bc9\u3057\u307e\u3059\u3002\u6b63\u89e3\u7387\u3001\u9069\u5408\u7387\u3001\u518d\u73fe\u7387\u3001AUC\u306a\u3069\u306e\u8a55\u4fa1\u6307\u6a19\u3092\u7528\u3044\u3066\u3001\u30e2\u30c7\u30eb\u306e\u6027\u80fd\u3092\u8a55\u4fa1\u3057\u307e\u3059\u3002<\/p>\n\n\n\n
\u4ee5\u4e0a\u3001scikit-learn\u306e\u5b9f\u8df5\u7684\u306a\u9069\u7528\u4f8b\u30924\u3064\u7d39\u4ecb\u3057\u307e\u3057\u305f\u3002\u305d\u308c\u305e\u308c\u306e\u5206\u91ce\u3067\u3001scikit-learn\u3092\u6d3b\u7528\u3059\u308b\u3053\u3068\u3067\u3001\u30c7\u30fc\u30bf\u304b\u3089\u4fa1\u5024\u3042\u308b\u77e5\u898b\u3092\u5f15\u304d\u51fa\u3059\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002\u9069\u7528\u4f8b\u3067\u5f97\u3089\u308c\u305f\u77e5\u898b\u3092\u30d3\u30b8\u30cd\u30b9\u306b\u6d3b\u304b\u3059\u3053\u3068\u3067\u3001\u4f01\u696d\u306e\u610f\u601d\u6c7a\u5b9a\u306e\u8cea\u3092\u9ad8\u3081\u308b\u3053\u3068\u304c\u3067\u304d\u308b\u3067\u3057\u3087\u3046\u3002<\/p>\n\n\n\n
scikit-learn\u306f\u3001\u69d8\u3005\u306a\u5206\u91ce\u3067\u6d3b\u7528\u3067\u304d\u308b\u5f37\u529b\u306a\u30c4\u30fc\u30eb\u3067\u3059\u3002\u672c\u8a18\u4e8b\u3067\u7d39\u4ecb\u3057\u305f\u5185\u5bb9\u3092\u53c2\u8003\u306b\u3001scikit-learn\u3092\u6d3b\u7528\u3057\u305f\u6a5f\u68b0\u5b66\u7fd2\u306e\u5b9f\u8df5\u306b\u53d6\u308a\u7d44\u3093\u3067\u307f\u3066\u304f\u3060\u3055\u3044\u3002\u5b9f\u52d9\u3067\u306e\u8ab2\u984c\u89e3\u6c7a\u306b\u5f79\u7acb\u3066\u308b\u3053\u3068\u304c\u3067\u304d\u308c\u3070\u5e78\u3044\u3067\u3059\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"
Python\u306e\u6a5f\u68b0\u5b66\u7fd2\u30e9\u30a4\u30d6\u30e9\u30eascikit-learn\u306f\u3001\u8c4a\u5bcc\u306a\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u3068\u4f7f\u3044\u3084\u3059\u3044API\u3067\u4eba\u6c17\u3092\u96c6\u3081\u3066\u3044\u307e\u3059\u3002\u672c\u8a18\u4e8b\u3067\u306f\u3001scikit-learn\u306e\u57fa\u672c\u7684\u306a\u4f7f\u3044\u65b9\u304b\u3089\u3001\u56de\u5e30\u5206\u6790\u3001\u5206\u985e\u3001\u30af\u30e9\u30b9\u30bf\u30ea\u30f3\u30b0\u306a\u3069\u306e\u5b9f\u8df5\u7684\u306a … <\/p>\n","protected":false},"author":1,"featured_media":474,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[4],"tags":[],"class_list":{"0":"post-221","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","7":"category-python"},"_links":{"self":[{"href":"https:\/\/chocottopro.com\/index.php?rest_route=\/wp\/v2\/posts\/221","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/chocottopro.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/chocottopro.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/chocottopro.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/chocottopro.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=221"}],"version-history":[{"count":2,"href":"https:\/\/chocottopro.com\/index.php?rest_route=\/wp\/v2\/posts\/221\/revisions"}],"predecessor-version":[{"id":414,"href":"https:\/\/chocottopro.com\/index.php?rest_route=\/wp\/v2\/posts\/221\/revisions\/414"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/chocottopro.com\/index.php?rest_route=\/wp\/v2\/media\/474"}],"wp:attachment":[{"href":"https:\/\/chocottopro.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=221"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/chocottopro.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=221"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/chocottopro.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=221"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}