simple_model.py

import pandas as pd
import numpy as np
import xgboost as xgb
from sklearn.model_selection import train_test_split

data = pd.read_feather('data.feather')
data = pd.get_dummies(data, drop_first=True)
X_train, X_test, y_train, y_test = train_test_split(data.drop('salary', axis = 1),
                                                    np.log1p(data.salary.values),
                                                    test_size =.30,
                                                    random_state=12345)
dtrain = xgb.DMatrix(data = X_train, label=y_train)
dtest = xgb.DMatrix(data = X_test, label=y_test)
param = {'eta':0.1,
         'objective':'reg:linear'}
xgb_model = xgb.train(param, dtrain, num_boost_round=100)
X_test['y_hat_with_bias'] = np.exp(xgb_model.predict(dtest)) - 1