From 6903e9acd3c3dcd2e93e62895f06d124734e90ca Mon Sep 17 00:00:00 2001
From: MuslemRahimi <moslem_rahimi@hotmail.de>
Date: Wed, 26 Jun 2024 20:57:14 +0200
Subject: [PATCH] update clinical trial

---
 app/cron_clinical_trial.py | 58 +++++++++++++++++++++++---------------
 1 file changed, 36 insertions(+), 22 deletions(-)

diff --git a/app/cron_clinical_trial.py b/app/cron_clinical_trial.py
index 7a03743..95b110b 100644
--- a/app/cron_clinical_trial.py
+++ b/app/cron_clinical_trial.py
@@ -12,33 +12,47 @@ import pandas as pd
 import time
 
 
+
+# Function to extract the string after the first 'DRUG:'
+def extract_drug(string):
+    parts = string.split('|')
+    for part in parts:
+        if part.startswith('DRUG:'):
+            return part.split(': ', 1)[1].strip()  # Extract the part after 'DRUG:'
+    return ''  # Return empty string if no 'DRUG:' found
+
+
 ct = ClinicalTrials()
 
 async def get_data(company_name):
-    try:
-    	get_ct_data = ct.get_study_fields(
+	try:
+
+		company_name = company_name.replace('&','and')
+		get_ct_data = ct.get_study_fields(
 		    search_expr=f"{company_name}",
-		    fields=["Study Results","Funder Type","Start Date", "Completion Date","Study Status","Study Title", 'Phases', 'Brief Summary', 'Age','Sex', 'Enrollment','Study Type','Sponsor','Study URL','NCT Number'],
+		    fields=["Study Results","Interventions","Funder Type","Start Date", "Completion Date","Study Status","Study Title", 'Phases', 'Brief Summary', 'Age','Sex', 'Enrollment','Study Type','Sponsor','Study URL','NCT Number'],
 		    max_studies=1000,
 		    )
-    	df = pd.DataFrame.from_records(get_ct_data[1:], columns=get_ct_data[0])
-    	df['Completion Date'] = pd.to_datetime(df['Completion Date'],errors='coerce')
-    	df_sorted = df.sort_values(by='Completion Date', ascending=False)
-    	# Convert 'Completion Date' back to string format
-    	df_sorted['Completion Date'] = df_sorted['Completion Date'].apply(lambda x: x.strftime('%Y-%m-%d') if pd.notnull(x) else None)
-    	df_sorted['Phases'] = df_sorted['Phases'].replace('PHASE2|PHASE3', 'Phase 2/3')
-    	df_sorted['Phases'] = df_sorted['Phases'].replace('PHASE1|PHASE2', 'Phase 1/2')
-    	df_sorted['Phases'] = df_sorted['Phases'].replace('EARLY_PHASE1', 'Phase 1')
+		df = pd.DataFrame.from_records(get_ct_data[1:], columns=get_ct_data[0])
+		df['Start Date'] = pd.to_datetime(df['Start Date'],errors='coerce')
+		df_sorted = df.sort_values(by='Start Date', ascending=False)
 
-    	df_sorted['Study Status'] = df_sorted['Study Status'].replace('ACTIVE_NOT_RECRUITING', 'Active')
-    	df_sorted['Study Status'] = df_sorted['Study Status'].replace('NOT_YET_RECRUITING', 'Active')
-    	df_sorted['Study Status'] = df_sorted['Study Status'].replace('UNKNOWN', '-')
+		df_sorted['Start Date'] = df_sorted['Start Date'].apply(lambda x: x.strftime('%Y-%m-%d') if pd.notnull(x) else None)
+		df_sorted['Phases'] = df_sorted['Phases'].replace('PHASE2|PHASE3', 'Phase 2/3')
+		df_sorted['Phases'] = df_sorted['Phases'].replace('PHASE1|PHASE2', 'Phase 1/2')
+		df_sorted['Phases'] = df_sorted['Phases'].replace('EARLY_PHASE1', 'Phase 1')
 
-    	data = df_sorted.to_dict('records')
-    	return data
-    except Exception as e:
-        print(f"Error fetching data for {ticker}: {e}")
-        return []
+		df_sorted['Study Status'] = df_sorted['Study Status'].replace('ACTIVE_NOT_RECRUITING', 'Active')
+		df_sorted['Study Status'] = df_sorted['Study Status'].replace('NOT_YET_RECRUITING', 'Active')
+		df_sorted['Study Status'] = df_sorted['Study Status'].replace('UNKNOWN', '-')
+
+		df_sorted['Interventions'] = df_sorted['Interventions'].apply(extract_drug)
+		data = df_sorted.to_dict('records')
+		return data
+	
+	except Exception as e:
+		print(f"Error fetching data for {company_name}: {e}")
+		return []
 
 async def save_json(symbol, data):
     # Use async file writing to avoid blocking the event loop
@@ -56,12 +70,12 @@ async def run():
 
     cursor = con.cursor()
     cursor.execute("PRAGMA journal_mode = wal")
-    cursor.execute("SELECT DISTINCT symbol, name FROM stocks WHERE industry = 'Biotechnology' AND symbol NOT LIKE '%.%'")
+    cursor.execute("SELECT DISTINCT symbol, name FROM stocks WHERE (industry = 'Biotechnology' OR industry LIKE '%Drug%') AND symbol NOT LIKE '%.%'")
     company_data = [{'symbol': row[0], 'name': row[1]} for row in cursor.fetchall()]
     con.close()
     #test mode
-    #company_data = [{'symbol': 'DSGN', 'name': 'Design Therapeutics, Inc.'}]
-    
+    #company_data = [{'symbol': 'MRK', 'name': 'Merck & Co. Inc.'}]
+    print(len(company_data))
     async with aiohttp.ClientSession() as session:
         tasks = []
         for item in company_data: