import numpy as np
import pandas as pd
import pickle
import sys
#import sklearn
#import sklearn.neighbors._base
#sys.modules['sklearn.neighbors.base'] = sklearn.neighbors._base
import xgboost
#from missingpy import MissForest
import warnings
warnings.simplefilter(action="ignore", category=FutureWarning)
from warnings import filterwarnings

filterwarnings("ignore")
seed=42

data = pd.read_csv("annotations_dataset.csv")
data = data.set_index("Gene")
#imputer = MissForest(random_state=seed)
#data = imputer.fit_transform(data)

model = pickle.load(open('fitted_model.sav', 'rb'))

predictions = list(model.predict(data))

output = pd.Series(data=predictions, index=data.index, name="XGB_Score")
df_total = pd.concat([data, output], axis=1)