{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"execution":{"iopub.status.busy":"2022-08-12T04:46:31.963614Z","iopub.execute_input":"2022-08-12T04:46:31.964678Z","iopub.status.idle":"2022-08-12T04:46:31.973833Z","shell.execute_reply.started":"2022-08-12T04:46:31.964635Z","shell.execute_reply":"2022-08-12T04:46:31.972699Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train = pd.read_csv(\"../input/project1/train_fillna_Eun.csv\")\ntest = pd.read_csv(\"../input/project1/test.csv\")\nsubmission = pd.read_csv(\"../input/tabular-playground-series-aug-2022/sample_submission.csv\")\n\ndisplay(train.head())\ndisplay(test.head())\ndisplay(submission.head())                         \n","metadata":{"execution":{"iopub.status.busy":"2022-08-12T04:46:36.020919Z","iopub.execute_input":"2022-08-12T04:46:36.021999Z","iopub.status.idle":"2022-08-12T04:46:36.303188Z","shell.execute_reply.started":"2022-08-12T04:46:36.021956Z","shell.execute_reply":"2022-08-12T04:46:36.302115Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train.info()","metadata":{"execution":{"iopub.status.busy":"2022-08-12T04:46:39.297512Z","iopub.execute_input":"2022-08-12T04:46:39.297927Z","iopub.status.idle":"2022-08-12T04:46:39.319455Z","shell.execute_reply.started":"2022-08-12T04:46:39.297891Z","shell.execute_reply":"2022-08-12T04:46:39.318119Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nimport seaborn as sns\nsns.set(style='darkgrid', font_scale=1.4)\nimport matplotlib.pyplot as plt\n%matplotlib inline\n\nfrom itertools import combinations\nimport math\nimport statistics\n\nfrom scipy import stats\nfrom scipy.stats import pearsonr\nfrom scipy.stats import chi2\nfrom scipy.stats import poisson\n\nimport time\n\nfrom datetime import datetime\nimport matplotlib.dates as mdates\nimport plotly.express as px\nimport lightgbm as lgbm\nfrom termcolor import colored\nimport itertools\nimport warnings\nwarnings.filterwarnings(\"ignore\")\n\nimport sklearn\nfrom sklearn.decomposition import PCA\nfrom sklearn.manifold import TSNE\nfrom sklearn.discriminant_analysis import LinearDiscriminantAnalysis as LDA\nfrom sklearn.cluster import KMeans\nfrom sklearn.model_selection import train_test_split, StratifiedKFold, GridSearchCV, TimeSeriesSplit, GroupKFold, cross_validate\nfrom sklearn.preprocessing import StandardScaler, RobustScaler, PowerTransformer, OneHotEncoder, LabelEncoder\nfrom sklearn.impute import SimpleImputer, KNNImputer\nfrom sklearn.experimental import enable_iterative_imputer\nfrom sklearn.impute import IterativeImputer\nfrom sklearn.pipeline import make_pipeline\nfrom sklearn.compose import make_column_transformer\nfrom sklearn.metrics import confusion_matrix, ConfusionMatrixDisplay, accuracy_score, roc_auc_score\nfrom sklearn.ensemble import RandomForestClassifier\nfrom sklearn.linear_model import LinearRegression, Ridge\nfrom sklearn.mixture import GaussianMixture, BayesianGaussianMixture\n\n# UMAP\nimport umap\nimport umap.plot\n\n# Models\nfrom sklearn.linear_model import LinearRegression, LogisticRegression, Lasso, Ridge\nfrom sklearn.neighbors import KNeighborsClassifier\nfrom sklearn.svm import SVC\nfrom sklearn.tree import DecisionTreeClassifier\nfrom sklearn.ensemble import RandomForestClassifier\nfrom xgboost import XGBClassifier, XGBRegressor\nfrom lightgbm import early_stopping\nfrom lightgbm import LGBMClassifier, LGBMRegressor\n\nfrom catboost import CatBoostClassifier\nfrom sklearn.naive_bayes import GaussianNB\n\nfrom sklearn.ensemble import RandomForestClassifier\nfrom sklearn.ensemble import RandomForestRegressor\nfrom lightgbm.sklearn import LGBMClassifier\nfrom lightgbm.sklearn import LGBMRegressor\n\n# 상관관계 분석, VIF : 다중공선성 제거\nfrom statsmodels.stats.outliers_influence import variance_inflation_factor\n\n# KFold(CV), partial : optuna를 사용하기 위함\nfrom sklearn.model_selection import KFold\nfrom functools import partial\n\n# hyper-parameter tuning을 위한 라이브러리, optuna\nimport optuna\n\n# sklearn에서 배웠던 분류 모델들을 불러와봅니다.\nfrom sklearn.linear_model import SGDClassifier      # 1. Linear Classifier\nfrom sklearn.linear_model import LogisticRegression # 2. Logistic Regression\nfrom sklearn.tree import DecisionTreeClassifier     # 3. Decision Tree\nfrom sklearn.ensemble import RandomForestClassifier # 4. Random Forest\n\n# 평가 지표\nfrom sklearn.metrics import accuracy_score","metadata":{"execution":{"iopub.status.busy":"2022-08-12T04:46:41.658538Z","iopub.execute_input":"2022-08-12T04:46:41.658979Z","iopub.status.idle":"2022-08-12T04:46:41.683847Z","shell.execute_reply.started":"2022-08-12T04:46:41.658939Z","shell.execute_reply":"2022-08-12T04:46:41.682811Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_OHE = pd.get_dummies(train,columns=[\"attribute_0\",\"attribute_1\"])\ntrain_OHE","metadata":{"execution":{"iopub.status.busy":"2022-08-12T04:46:47.190546Z","iopub.execute_input":"2022-08-12T04:46:47.191349Z","iopub.status.idle":"2022-08-12T04:46:47.244102Z","shell.execute_reply.started":"2022-08-12T04:46:47.191306Z","shell.execute_reply":"2022-08-12T04:46:47.242648Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X = train_OHE.drop(columns=[\"failure\",\"product_code\"]) # input matrix\n\ny = train_OHE.failure                 # target vector\n\nX","metadata":{"execution":{"iopub.status.busy":"2022-08-12T04:46:50.080622Z","iopub.execute_input":"2022-08-12T04:46:50.081451Z","iopub.status.idle":"2022-08-12T04:46:50.120370Z","shell.execute_reply.started":"2022-08-12T04:46:50.081403Z","shell.execute_reply":"2022-08-12T04:46:50.119126Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"clf = SGDClassifier()\nclf2 = LogisticRegression()\nclf3 = DecisionTreeClassifier()\nclf4 = RandomForestClassifier()\nclf5 = LinearRegression()\nclf6 = Lasso()\nclf7 = Ridge()\nclf8 = XGBClassifier()\nclf9 = XGBRegressor()\n#clf10 = LGBMClassifier()\n#clf11 = LGBMRegressor()\n\nclf.fit(X, y)\nclf2.fit(X, y)\nclf3.fit(X, y)\nclf4.fit(X, y)\nclf5.fit(X, y)\nclf6.fit(X, y)\nclf7.fit(X, y)\nclf8.fit(X, y)\nclf9.fit(X, y)\n#clf10.fit(X, y)\n#clf11.fit(X, y)\n\npred = clf.predict(X)\npred2 = clf2.predict(X)\npred3 = clf3.predict(X)\npred4 = clf4.predict(X)\npred5 = clf.predict(X)\npred6 = clf.predict(X)\npred7 = clf.predict(X)\npred8 = clf.predict(X)\npred9 = clf.predict(X)\n#pred10 = clf.predict(X)\n#pred11 = clf.predict(X)","metadata":{"execution":{"iopub.status.busy":"2022-08-12T04:46:52.758058Z","iopub.execute_input":"2022-08-12T04:46:52.758477Z","iopub.status.idle":"2022-08-12T04:47:20.631865Z","shell.execute_reply.started":"2022-08-12T04:46:52.758435Z","shell.execute_reply":"2022-08-12T04:47:20.630538Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(\"1. SGDClassifier, Accuracy for training : %.4f\" % accuracy_score(y, pred))\nprint(\"2. LogisticRegression, Accuracy for training : %.4f\" % accuracy_score(y, pred2))\nprint(\"3. DecisionTreeClassifie, Accuracy for training : %.4f\" % accuracy_score(y, pred3))\nprint(\"4. RandomForestClassifier, Accuracy for training : %.4f\" % accuracy_score(y, pred4))\nprint(\"5. LinearRegression, Accuracy for training : %.4f\" % accuracy_score(y, pred5))\nprint(\"6. Lasso, Accuracy for training : %.4f\" % accuracy_score(y, pred6))\nprint(\"7. Ridge, Accuracy for training : %.4f\" % accuracy_score(y, pred7))\nprint(\"8. XGBClassifier, Accuracy for training : %.4f\" % accuracy_score(y, pred8))\nprint(\"9. XGBRegressor, Accuracy for training : %.4f\" % accuracy_score(y, pred9))\n#print(\"10. LGBMClassifier, Accuracy for training : %.4f\" % accuracy_score(y, pred10))\n#print(\"11. LGBMRegressor, Accuracy for training : %.4f\" % accuracy_score(y, pred11))\n\n","metadata":{"execution":{"iopub.status.busy":"2022-08-12T04:47:43.299579Z","iopub.execute_input":"2022-08-12T04:47:43.300004Z","iopub.status.idle":"2022-08-12T04:47:43.332556Z","shell.execute_reply.started":"2022-08-12T04:47:43.299970Z","shell.execute_reply":"2022-08-12T04:47:43.331756Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test","metadata":{"execution":{"iopub.status.busy":"2022-08-12T04:47:46.837348Z","iopub.execute_input":"2022-08-12T04:47:46.837786Z","iopub.status.idle":"2022-08-12T04:47:46.877031Z","shell.execute_reply.started":"2022-08-12T04:47:46.837750Z","shell.execute_reply":"2022-08-12T04:47:46.876155Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_OHE = pd.get_dummies(test,columns=[\"attribute_0\",\"attribute_1\"])\ntest_OHE = test_OHE.drop(columns=[\"product_code\"])\n\n\n\ntest_OHE","metadata":{"execution":{"iopub.status.busy":"2022-08-12T04:48:06.519276Z","iopub.execute_input":"2022-08-12T04:48:06.519719Z","iopub.status.idle":"2022-08-12T04:48:06.569325Z","shell.execute_reply.started":"2022-08-12T04:48:06.519669Z","shell.execute_reply":"2022-08-12T04:48:06.568409Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# prediction\n#result = clf.predict(test_OHE)\nresult2 = clf2.predict(test_OHE)\nresult3 = clf3.predict(test_OHE)\nresult4 = clf4.predict(test_OHE)\nresult5 = clf5.predict(test_OHE)\nresult6 = clf6.predict(test_OHE)\nresult7 = clf7.predict(test_OHE)\nresult8 = clf8.predict(test_OHE)\nresult9 = clf9.predict(test_OHE)\n","metadata":{"execution":{"iopub.status.busy":"2022-08-12T04:48:09.284823Z","iopub.execute_input":"2022-08-12T04:48:09.285241Z","iopub.status.idle":"2022-08-12T04:48:09.980214Z","shell.execute_reply.started":"2022-08-12T04:48:09.285203Z","shell.execute_reply":"2022-08-12T04:48:09.979240Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"len(result4)","metadata":{"execution":{"iopub.status.busy":"2022-08-12T04:44:30.554651Z","iopub.execute_input":"2022-08-12T04:44:30.555819Z","iopub.status.idle":"2022-08-12T04:44:30.562197Z","shell.execute_reply.started":"2022-08-12T04:44:30.555765Z","shell.execute_reply":"2022-08-12T04:44:30.561051Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\nsubmission[\"failure\"] = result3\nsubmission","metadata":{"execution":{"iopub.status.busy":"2022-08-12T05:09:23.563608Z","iopub.execute_input":"2022-08-12T05:09:23.564557Z","iopub.status.idle":"2022-08-12T05:09:23.577358Z","shell.execute_reply.started":"2022-08-12T05:09:23.564519Z","shell.execute_reply":"2022-08-12T05:09:23.576239Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission.reset_index(drop=True).to_csv(\"submission.csv\", index=False)","metadata":{"execution":{"iopub.status.busy":"2022-08-12T05:09:28.746326Z","iopub.execute_input":"2022-08-12T05:09:28.747044Z","iopub.status.idle":"2022-08-12T05:09:28.776398Z","shell.execute_reply.started":"2022-08-12T05:09:28.746995Z","shell.execute_reply":"2022-08-12T05:09:28.775420Z"},"trusted":true},"execution_count":null,"outputs":[]}]}