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

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

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

predictions = list(model.predict(data))

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