def get_results(X):
categoricals = X.select_dtypes(include='object')
categoricals = categoricals.astype(str)
categoricals = categoricals.apply(label.fit_transform)
label_encoding = categoricals['country']
categoricals.drop(['country'], axis=1, inplace=True)
X_one = enc.transform(categoricals)
encoded_data = pd.DataFrame(X_one.todense())
encoded_data.reset_index(drop=True, inplace=True)
categoricals.reset_index(drop=True, inplace=True)
original_numeric = X.select_dtypes(include='number')
original_numeric.reset_index(drop=True, inplace=True)
X = pd.concat([original_numeric, encoded_data, label_encoding],
axis=1).values
Xp = pca.transform(X)
clf = XGBClassifier()
booster = Booster()
booster.load_model('xgb.model')
clf._Booster = booster
classes = clf.predict_proba(Xp)
y_pred = [0 if c[0] > 0.5 else 1 for c in classes]
return y_pred
def analyze(self, event):
array_list = [
"lepJet_llpdnnx_-1_isLLP_QMU_QQMU",
"lepJet_llpdnnx_0_isLLP_QMU_QQMU",
"lepJet_llpdnnx_1_isLLP_QMU_QQMU",
"lepJet_llpdnnx_2_isLLP_QMU_QQMU", "dimuon_mass", "dimuon_deltaR",
"lepJet_pt", "lepJet_eta", "lepJet_deltaR", "MET_pt", "MET_phi",
"looseMuons_pt", "looseMuons_eta", "looseMuons_dxy",
"tightMuons_pt", "tightMuons_eta", "tightMuons_dxy"
]
data = pd.DataFrame(data={
"lepJet_llpdnnx_-1_isLLP_QMU_QQMU":
getattr(event, "lepJet_llpdnnx_-1_isLLP_QMU_QQMU"),
"lepJet_llpdnnx_0_isLLP_QMU_QQMU":
event.lepJet_llpdnnx_0_isLLP_QMU_QQMU,
"lepJet_llpdnnx_1_isLLP_QMU_QQMU":
event.lepJet_llpdnnx_1_isLLP_QMU_QQMU,
"lepJet_llpdnnx_2_isLLP_QMU_QQMU":
event.lepJet_llpdnnx_2_isLLP_QMU_QQMU,
"dimuon_mass":
event.dimuon_mass,
"dimuon_deltaR":
event.dimuon_deltaR,
"lepJet_pt":
event.lepJet_pt,
"lepJet_eta":
event.lepJet_eta,
"lepJet_deltaR":
event.lepJet_deltaR,
"MET_pt":
event.MET_pt,
"MET_phi":
event.MET_phi,
"looseMuons_pt":
event.looseMuons_pt,
"looseMuons_eta":
event.looseMuons_eta,
"looseMuons_dxy":
event.looseMuons_dxy,
"tightMuons_pt":
event.tightMuons_pt,
"tightMuons_eta":
event.tightMuons_eta,
"tightMuons_dxy":
event.tightMuons_dxy,
},
columns=array_list,
index=[0])
model = XGBClassifier()
booster = Booster()
#model._le = LabelEncoder().fit([1])
booster.load_model(self.modelPath)
booster.feature_names = array_list
model._Booster = booster
bdt_score = model.predict_proba(data)
setattr(event, "bdt_score", bdt_score[:, 1])
return True
from xgboost import XGBClassifier, Booster
model = XGBClassifier()
booster = Booster()
booster.load_model('model.pkl')
model._Booster = booster
print(model.predict([[0, 0, 0, 0, 0, 00]]))
def load_model(model_path):
clf = XGBClassifier()
booster = Booster()
booster.load_model(model_path)
clf._Booster = booster
return clf
from sklearn.preprocessing import LabelEncoder
from process_data import process_input
# For logging
import logging
import traceback
from logging.handlers import RotatingFileHandler
from time import strftime, time
app = Flask(__name__)
xgb_ClaimInd_model = XGBClassifier()
booster = xgb.Booster()
booster.load_model('models/xgb_ClaimInd_model')
xgb_ClaimInd_model._Booster = booster
xgb_ClaimInd_model._le = LabelEncoder().fit([0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10])
# Logging
handler = RotatingFileHandler('app.log', maxBytes=100000, backupCount=5)
logger = logging.getLogger(__name__)
logger.setLevel(logging.INFO)
logger.addHandler(handler)
@app.route("/")
def index():
return "RenataTNT API"