Move validation function

validate.py

@@ -3,43 +3,13 @@ from dotenv import load_dotenv
 from langchain_google_genai import ChatGoogleGenerativeAI
 from langchain_openai import ChatOpenAI
 from prompt import *
-from utils import call, permutate
-from io import StringIO
+from utils import *
 
 import os
-import pandas as pd
 import re
-import requests
 
 load_dotenv()
 
-raw_url = "https://www.ebi.ac.uk/gwas/api/search/downloads/alternative"
-gwas_path = "resources/gwas_catalog.tsv"
-
-# Load Raw GWAS files
-if os.path.exists(gwas_path):
-    gwas = pd.read_csv(gwas_path, delimiter='\t')[['DISEASE/TRAIT', 'CHR_ID', 'MAPPED_GENE', 'SNPS', 'P-VALUE', 'OR or BETA']]
-else:
-    data = requests.get(raw_url).content.decode('utf-8')
-    gwas = pd.read_csv(StringIO(data), delimiter='\t')[['DISEASE/TRAIT', 'CHR_ID', 'MAPPED_GENE', 'SNPS', 'P-VALUE', 'OR or BETA']]
-
-# Load Genes and SNPs from GWAS
-gwas_gene_rsid = gwas[['MAPPED_GENE', 'SNPS']]
-gwas_gene_rsid.dropna(inplace=True, ignore_index=True)
-gwas_gene_rsid['MAPPED_GENE'] = gwas_gene_rsid['MAPPED_GENE'].apply(lambda x: x.replace(' ', '').upper())
-
-# Generate Genes and SNPs mapping
-ground_truth = defaultdict(list)
-for i in gwas_gene_rsid.index:
-    gene = gwas_gene_rsid.loc[i, 'MAPPED_GENE']
-    snp = gwas_gene_rsid.loc[i, 'SNPS']
-
-    pattern = r"[,\-]"
-    genes = re.split(pattern, gene)
-    for gene in genes:
-        ground_truth[gene].append(snp)
-        ground_truth[snp].append(gene)
-
 class Validation():
 
     def __init__(self, llm):