Update app.py

app.py

@@ -1,16 +1,37 @@
 import streamlit as st
 import numpy as np
 import pandas as pd
-import pickle
 import sklearn
 import xgboost
 
 data = pd.read_csv("annotations_dataset.csv")
 data = data.set_index("Gene")
 
-model = pickle.load(open('fitted_model.sav', 'rb'))
+training_data = pd.read_csv("selected_features_training_data.csv", header=0)
+training_data.columns = [
+    regex.sub("_", col) if any(x in str(col) for x in set(("[", "]", "<"))) else col
+    for col in training_data.columns.values
+]
 
-predictions = list(model.predict(data))
+training_data["BPlabel_encoded"] = training_data["BPlabel"].map(
+    {"most likely": 1, "probable": 0.75, "least likely": 0.1}
+)
+Y = training_data["BPlabel_encoded"]
+X = training_data.drop("BPlabel_encoded","BPlabel", errors=ignore)
+xgb = xgboost.XGBRegressor(
+    n_estimators=40,
+    learning_rate=0.2,
+    max_depth=4,
+    reg_alpha=1,
+    reg_lambda=1,
+    random_state=seed,
+    objective="reg:squarederror",
+)
+
+
+xgb.fit(X, Y)
+
+predictions = list(xgb.predict(data))
 
 output = pd.Series(data=predictions, index=data.index, name="XGB_Score")
 df_total = pd.concat([data, output], axis=1)