import streamlit as st
import re
import numpy as np
import pandas as pd
import sklearn
import xgboost
seed=42

data = pd.read_csv("annotations_dataset.csv")
data = data.set_index("Gene")

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
]

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(columns=["BPlabel_encoded","BPlabel"])
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))
predictions = [round(item, 2) for item in predictions]

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

df_total = df_total[['XGB_Score', 'mousescore_Exomiser',
 'SDI', 'Liver_GTExTPM',  'pLI_ExAC',
 'HIPred',
 'Cells - EBV-transformed lymphocytes_GTExTPM',
 'Pituitary_GTExTPM',
 'IPA_BP_annotation']]


st.title('Blood Pressure Gene Prioritisation Post-GWAS')
st.markdown("""
A machine learning pipeline for predicting disease-causing genes post-genome-wide association study in blood pressure.
""")

#gene_input = st.text_input('Input Single HGNC Gene:') 
#df = df_total[df_total.index == gene_input] 
#st.dataframe(df)


collect_genes = lambda x : [str(i) for i in re.split(",", x) if i != ""]

input_genes = st.text_input("List of HGNC Genes (enter comma separated)")
#gene_list = st.write(collect_genes(input_genes))
gene_list = collect_genes(input_genes)
if gene_list:
    df = df_total[df_total.index.isin(gene_list)]
    st.dataframe(df)
else:
    pass

st.markdown("""
Total Gene Prioritisation Results:
""")

st.dataframe(df_total)