[조예인] week9_2024_GDG_ML입문스터디

week4/[MLNovice]조예인_week4-3.ipynb

@@ -0,0 +1 @@
+{"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"provenance":[],"authorship_tag":"ABX9TyPUgi5jqCh/hYdCIXBtzPFS"},"kernelspec":{"name":"python3","display_name":"Python 3"},"language_info":{"name":"python"}},"cells":[{"cell_type":"markdown","source":["# 랜덤포레스트"],"metadata":{"id":"tC1gC_UpQLSI"}},{"cell_type":"markdown","source":["랜덤하게 선택한 샘플과 특성을 사용, 과대적합 방지"],"metadata":{"id":"A7lbQiqyQSY8"}},{"cell_type":"code","source":["import numpy as np\n","import pandas as pd\n","from sklearn.model_selection import train_test_split\n","\n","wine = pd.read_csv('https://bit.ly/wine_csv_data')\n","\n","data = wine[['alcohol', 'sugar', 'pH']].to_numpy()\n","target = wine['class'].to_numpy()\n","\n","train_input, test_input, train_target, test_target = train_test_split(data, target, test_size=0.2, random_state=42)"],"metadata":{"id":"37pYe1ZaQOjF","executionInfo":{"status":"ok","timestamp":1730121396466,"user_tz":-540,"elapsed":8417,"user":{"displayName":"조예인","userId":"17650117334011908449"}}},"execution_count":1,"outputs":[]},{"cell_type":"code","source":["from sklearn.model_selection import cross_validate\n","from sklearn.ensemble import RandomForestClassifier\n","\n","rf = RandomForestClassifier(n_jobs=-1, random_state=42)\n","scores = cross_validate(rf, train_input, train_target, return_train_score=True, n_jobs=-1)\n","\n","print(np.mean(scores['train_score']), np.mean(scores['test_score']))"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"Imb0lJQiRTBG","executionInfo":{"status":"ok","timestamp":1730121412462,"user_tz":-540,"elapsed":14959,"user":{"displayName":"조예인","userId":"17650117334011908449"}},"outputId":"d6cfa960-0f05-4f32-d1d4-e8f0c689e34b"},"execution_count":2,"outputs":[{"output_type":"stream","name":"stdout","text":["0.9973541965122431 0.8905151032797809\n"]}]},{"cell_type":"code","source":["rf.fit(train_input, train_target)\n","print(rf.feature_importances_)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"Z747U4MLRWWt","executionInfo":{"status":"ok","timestamp":1730121415947,"user_tz":-540,"elapsed":2506,"user":{"displayName":"조예인","userId":"17650117334011908449"}},"outputId":"33b13d5e-c62c-47e1-88c0-a4b302c1a682"},"execution_count":3,"outputs":[{"output_type":"stream","name":"stdout","text":["[0.23167441 0.50039841 0.26792718]\n"]}]},{"cell_type":"markdown","source":["OOB 샘플 : 부트스트랩 샘플에 포함되지 않고 남는 샘플"],"metadata":{"id":"LlJdVIYERyVP"}},{"cell_type":"code","source":["rf = RandomForestClassifier(oob_score=True, n_jobs=-1, random_state=42)\n","\n","rf.fit(train_input, train_target)\n","print(rf.oob_score_)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"xrEHEv34RZ-T","executionInfo":{"status":"ok","timestamp":1730121418242,"user_tz":-540,"elapsed":2297,"user":{"displayName":"조예인","userId":"17650117334011908449"}},"outputId":"f0ac9025-7163-41cf-93cc-2f967d5d3f4e"},"execution_count":4,"outputs":[{"output_type":"stream","name":"stdout","text":["0.8934000384837406\n"]}]},{"cell_type":"markdown","source":["# 엑스트라트리"],"metadata":{"id":"TJmnAK8XRdcO"}},{"cell_type":"markdown","source":["부트스트랩 샘플을 사용하지 않고, 전체 훈련 세트를 사용.\n","\n","전체 특성 중에 일부를 랜덤하게 선택."],"metadata":{"id":"MURdvvOERwoK"}},{"cell_type":"code","source":["from sklearn.ensemble import ExtraTreesClassifier\n","\n","et = ExtraTreesClassifier(n_jobs=-1, random_state=42)\n","scores = cross_validate(et, train_input, train_target, return_train_score=True, n_jobs=-1)\n","\n","print(np.mean(scores['train_score']), np.mean(scores['test_score']))"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"R9S_rCyWRbfc","executionInfo":{"status":"ok","timestamp":1730121443354,"user_tz":-540,"elapsed":6116,"user":{"displayName":"조예인","userId":"17650117334011908449"}},"outputId":"81a2ceef-5899-452a-b548-2ff69028c596"},"execution_count":5,"outputs":[{"output_type":"stream","name":"stdout","text":["0.9974503966084433 0.8887848893166506\n"]}]},{"cell_type":"code","source":["et.fit(train_input, train_target)\n","print(et.feature_importances_)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"BflR_pWwRg35","executionInfo":{"status":"ok","timestamp":1730121444652,"user_tz":-540,"elapsed":1301,"user":{"displayName":"조예인","userId":"17650117334011908449"}},"outputId":"3be41869-474a-4a13-a062-d5b4b35805de"},"execution_count":6,"outputs":[{"output_type":"stream","name":"stdout","text":["[0.20183568 0.52242907 0.27573525]\n"]}]},{"cell_type":"markdown","source":["# 그레이디언트 부스팅"],"metadata":{"id":"zNZbGelsRn1v"}},{"cell_type":"code","source":["from sklearn.ensemble import GradientBoostingClassifier\n","\n","gb = GradientBoostingClassifier(random_state=42)\n","scores = cross_validate(gb, train_input, train_target, return_train_score=True, n_jobs=-1)\n","\n","print(np.mean(scores['train_score']), np.mean(scores['test_score']))"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"bDf8HwEJRiR4","executionInfo":{"status":"ok","timestamp":1730121482566,"user_tz":-540,"elapsed":2446,"user":{"displayName":"조예인","userId":"17650117334011908449"}},"outputId":"e52cbb07-228b-469e-a3c5-5cf62928e9ff"},"execution_count":7,"outputs":[{"output_type":"stream","name":"stdout","text":["0.8881086892152563 0.8720430147331015\n"]}]},{"cell_type":"code","source":["gb = GradientBoostingClassifier(n_estimators=500, learning_rate=0.2, random_state=42)\n","scores = cross_validate(gb, train_input, train_target, return_train_score=True, n_jobs=-1)\n","\n","print(np.mean(scores['train_score']), np.mean(scores['test_score']))"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"Xh6Upv-7RrRf","executionInfo":{"status":"ok","timestamp":1730121728182,"user_tz":-540,"elapsed":15819,"user":{"displayName":"조예인","userId":"17650117334011908449"}},"outputId":"05a63cf3-3e90-4c05-dd5a-1df26dc4760b"},"execution_count":8,"outputs":[{"output_type":"stream","name":"stdout","text":["0.9464595437171814 0.8780082549788999\n"]}]},{"cell_type":"code","source":["gb.fit(train_input, train_target)\n","print(gb.feature_importances_)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"W7GIVgxeSkUf","executionInfo":{"status":"ok","timestamp":1730121730349,"user_tz":-540,"elapsed":2168,"user":{"displayName":"조예인","userId":"17650117334011908449"}},"outputId":"dfb1d89f-5c40-41ec-82e0-1232c796cfd1"},"execution_count":9,"outputs":[{"output_type":"stream","name":"stdout","text":["[0.15887763 0.6799705  0.16115187]\n"]}]},{"cell_type":"markdown","source":["# 히스토그램 기반 그레이디언트 부스팅"],"metadata":{"id":"qgNC4A6_StEz"}},{"cell_type":"code","source":["from sklearn.ensemble import HistGradientBoostingClassifier\n","\n","hgb = HistGradientBoostingClassifier(random_state=42)\n","scores = cross_validate(hgb, train_input, train_target, return_train_score=True, n_jobs=-1)\n","\n","print(np.mean(scores['train_score']), np.mean(scores['test_score']))"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"aQMMCPRoSv3L","executionInfo":{"status":"ok","timestamp":1730121809503,"user_tz":-540,"elapsed":2381,"user":{"displayName":"조예인","userId":"17650117334011908449"}},"outputId":"5eb52325-8c36-4740-d1f4-246cd39efb2d"},"execution_count":10,"outputs":[{"output_type":"stream","name":"stdout","text":["0.9321723946453317 0.8801241948619236\n"]}]},{"cell_type":"code","source":["from sklearn.inspection import permutation_importance\n","\n","hgb.fit(train_input, train_target)\n","result = permutation_importance(hgb, train_input, train_target, n_repeats=10,\n","                                random_state=42, n_jobs=-1)\n","print(result.importances_mean)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"akYdz-O4S7L1","executionInfo":{"status":"ok","timestamp":1730121816890,"user_tz":-540,"elapsed":5072,"user":{"displayName":"조예인","userId":"17650117334011908449"}},"outputId":"bdfd8ae2-e514-4282-bc2d-55c161597516"},"execution_count":11,"outputs":[{"output_type":"stream","name":"stdout","text":["[0.08876275 0.23438522 0.08027708]\n"]}]},{"cell_type":"code","source":["result = permutation_importance(hgb, test_input, test_target, n_repeats=10,\n","                                random_state=42, n_jobs=-1)\n","print(result.importances_mean)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"4hpfPdzYS8U7","executionInfo":{"status":"ok","timestamp":1730121818528,"user_tz":-540,"elapsed":1095,"user":{"displayName":"조예인","userId":"17650117334011908449"}},"outputId":"4d60af58-557d-4384-ad46-fa1df41a8e65"},"execution_count":12,"outputs":[{"output_type":"stream","name":"stdout","text":["[0.05969231 0.20238462 0.049     ]\n"]}]},{"cell_type":"code","source":["hgb.score(test_input, test_target)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"8gJvPcirS9qh","executionInfo":{"status":"ok","timestamp":1730121820896,"user_tz":-540,"elapsed":394,"user":{"displayName":"조예인","userId":"17650117334011908449"}},"outputId":"681f71f9-b511-463d-ef85-e4420c988cc0"},"execution_count":13,"outputs":[{"output_type":"execute_result","data":{"text/plain":["0.8723076923076923"]},"metadata":{},"execution_count":13}]},{"cell_type":"code","source":[],"metadata":{"id":"GBcMwm77S-ci"},"execution_count":null,"outputs":[]}]}