from sklearn.pipeline import Pipeline from sklearn.model_selection import train_test_split from sklearn.preprocessing import LabelEncoder from sklearn.model_selection import GridSearchCV, KFold, cross_val_predict, cross_val_score, StratifiedKFold from sklearn.feature_selection import SelectKBest, SelectPercentile from sklearn.feature_selection import f_classif, mutual_info_classif from sklearn.compose import TransformedTargetRegressor import load_data_ST import save_output import GSCV name_clf = 'SVMR_linear_STDS' #load data data_train, labels_train, data_test, labels_test = load_data_ST.function_load_data_ST( ) #Scalers from sklearn.preprocessing import StandardScaler, RobustScaler, MinMaxScaler scalers_to_test = [StandardScaler(), RobustScaler(), MinMaxScaler()] df = pd.DataFrame() #Designate distributions to sample hyperparameters from C_range = np.power(2, np.arange(-10, 8, dtype=float)) n_features_to_test = [0.85, 0.9, 0.95] clf = TransformedTargetRegressor(regressor=SVR(kernel='linear'), transformer=MinMaxScaler())
from sklearn.model_selection import train_test_split from sklearn.preprocessing import LabelEncoder from sklearn.model_selection import GridSearchCV from sklearn.model_selection import RandomizedSearchCV from sklearn.ensemble import RandomForestClassifier from sklearn.compose import TransformedTargetRegressor from sklearn.linear_model import LinearRegression import load_data_ST import save_output import nested_cv_ST name_clf = 'LinearRegression' #load data data, labels = load_data_ST.function_load_data_ST() #Scalers from sklearn.preprocessing import StandardScaler, RobustScaler, MinMaxScaler scalers_to_test = [StandardScaler(), RobustScaler(), MinMaxScaler(), None] df = pd.DataFrame() # Designate distributions to sample hyperparameters from n_features_to_test = [0.85, 0.9, 0.95] clf = TransformedTargetRegressor(regressor=LinearRegression(), transformer=MinMaxScaler()) #LinearRegression
from sklearn.ensemble import RandomForestRegressor from sklearn.preprocessing import StandardScaler, RobustScaler, MinMaxScaler from sklearn.linear_model import LinearRegression from sklearn.svm import SVR import load_data_ST import os regr_RF_name = 'RandomForestRegressor' regr_svml_name = 'SVR linear' regr_rbf_name = 'SVR rbf' regr_sig_name = 'SVR sigmoid' #load data pu_data, pu_labels, pa_data, pa_labels = load_data_ST.function_load_data_ST() regr_RF = RandomForestRegressor(n_estimators=100, max_depth=10, criterion='mae', random_state=503) regr_svml = LinearRegression() regr_rbf = SVR(kernel='rbf', C=0.25, gamma=0.0078125) regr_sig = SVR(kernel='sigmoid', C=0.0625, gamma=125) clf_RF = TransformedTargetRegressor(regressor=regr_RF, transformer=MinMaxScaler())
from sklearn.compose import TransformedTargetRegressor from sklearn.ensemble import RandomForestRegressor from sklearn.preprocessing import StandardScaler, RobustScaler, MinMaxScaler from sklearn.preprocessing import LabelEncoder from sklearn.metrics import roc_auc_score, classification_report, accuracy_score, balanced_accuracy_score import seaborn as sns import load_data_ST import os name_clf = 'RandomForestRegressor' #load data pu_data, pu_labels, PA_data, PA_labels = load_data_ST.function_load_data_ST() # Designate distributions to sample hyperparameters from n_features_to_test = [0.85, 0.9, 0.95] n_tree = [15, 30, 45, 60, 75, 90, 105, 120, 135, 150, 165, 180] depth = [ 2, 5, 10, 15, 20, 30, 45, 60, 75] regr_RF = RandomForestRegressor(criterion='mae', random_state=503) pca = PCA(random_state=42, n_components=0.85) #clf