from sklearn.metrics import make_scorer
from sklearn.preprocessing import StandardScaler
import xgboost as xgb
from sklearn.model_selection import StratifiedKFold, RandomizedSearchCV
from xgboost import XGBClassifier
from sklearn.metrics import confusion_matrix, classification_report, accuracy_score
from lib.read import cost_confusion_matrix, read_data, get_conclusion
X_train, Y_train, X_test, Y_test = read_data()
conclusions = []
basic = XGBClassifier()
basic.name = "basic"
basic.fit(X_train, Y_train)
Y_pred = basic.predict(X_test)
cm = confusion_matrix(Y_test, Y_pred)
cost_confusion_matrix(cm)
row = get_conclusion(Y_test, Y_pred, 'basic')
# "{'subsample': 0.9, 'silent': False, 'reg_lambda': 10.0, 'n_estimators': 100, 'min_child_weight': 0.5, 'max_depth': 10, 'learning_rate': 0.2, 'gamma': 0, 'colsample_bytree': 0.7, 'colsample_bylevel': 0.4}
bestParamsModel = XGBClassifier(subsample=0.9,
silent=False,
reg_lambda=10,
n_estimators=100,
min_child_weight=0.5,
max_depth=10,
learning_rate=0.2,
gamma=0,
from pprint import pprint
from sklearn.feature_selection import SelectFromModel
from sklearn.metrics import make_scorer
import xgboost as xgb
from sklearn.model_selection import StratifiedKFold, RandomizedSearchCV
from xgboost import XGBClassifier
from sklearn.metrics import confusion_matrix, classification_report, accuracy_score
from lib.read import cost_confusion_matrix, read_data, my_scorer
X_train, Y_train, X_test, Y_test = read_data()
basic = XGBClassifier()
basic.name = "basic"
basic.fit(X_train, Y_train)
Y_pred = basic.predict(X_test)
cm = confusion_matrix(Y_test, Y_pred)
cost_confusion_matrix(cm)
param_grid = {
'silent': [False],
'max_depth': [6, 10, 15, 20],
'learning_rate': [0.1, 0.2, 0, 3],
'subsample': [0.5, 0.6, 0.7, 0.8, 0.9, 1.0],
'best_score': [0.5, 0.6, 0.7, 0.8, 0.9, 1.0],
'colsample_bytree': [0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0],
'colsample_bylevel': [0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0],
'min_child_weight': [0.5, 1.0, 3.0, 5.0, 7.0, 10.0],
'gamma': [0, 0.25, 0.5, 1.0],
