bugfixing

This commit is contained in:
MuslemRahimi 2024-08-09 16:19:09 +02:00
parent be2fbd03a2
commit 21ba8b8a5b
2 changed files with 20 additions and 5 deletions

View File

@ -380,15 +380,15 @@ def create_dataset():
con = sqlite3.connect('stocks.db') con = sqlite3.connect('stocks.db')
cursor = con.cursor() cursor = con.cursor()
cursor.execute("PRAGMA journal_mode = wal") cursor.execute("PRAGMA journal_mode = wal")
cursor.execute("SELECT DISTINCT symbol, name FROM stocks WHERE marketCap >= 10E9 AND symbol NOT LIKE '%.%' AND symbol NOT LIKE '%-%'") cursor.execute("SELECT DISTINCT symbol, name FROM stocks WHERE symbol NOT LIKE '%.%' AND symbol NOT LIKE '%-%'")
stock_data = [{'symbol': row[0], 'name': row[1]} for row in cursor.fetchall()] stock_data = [{'symbol': row[0], 'name': row[1]} for row in cursor.fetchall()]
print(f"Total stocks: {len(stock_data)}") print(f"Total stocks: {len(stock_data)}")
con.close() con.close()
batch_size = 3 batch_size = 5
stock_batches = [stock_data[i:i+batch_size] for i in range(0, len(stock_data), batch_size)] stock_batches = [stock_data[i:i+batch_size] for i in range(0, len(stock_data), batch_size)]
with concurrent.futures.ProcessPoolExecutor(max_workers=4) as executor: with concurrent.futures.ProcessPoolExecutor(max_workers=5) as executor:
futures = [executor.submit(process_stocks_batch, batch, csv_files, reports_folder, threshold) for batch in stock_batches] futures = [executor.submit(process_stocks_batch, batch, csv_files, reports_folder, threshold) for batch in stock_batches]
for future in concurrent.futures.as_completed(futures): for future in concurrent.futures.as_completed(futures):

View File

@ -8,7 +8,7 @@ import pytz
import time import time
import os import os
from dotenv import load_dotenv from dotenv import load_dotenv
from datetime import datetime, timedelta from datetime import datetime, timedelta, date
import sqlite3 import sqlite3
@ -34,6 +34,20 @@ async def save_json(data):
ujson.dump(data, file) ujson.dump(data, file)
def parse_time(time_str):
try:
# Try parsing as full datetime
return datetime.strptime(time_str, '%Y-%m-%d %H:%M:%S')
except ValueError:
try:
# Try parsing as time only
time_obj = datetime.strptime(time_str, '%H:%M:%S').time()
# Combine with today's date
return datetime.combine(date.today(), time_obj)
except ValueError:
# If all else fails, return a default datetime
return datetime.min
def remove_duplicates(elements): def remove_duplicates(elements):
seen = set() seen = set()
unique_elements = [] unique_elements = []
@ -151,7 +165,8 @@ async def get_recent_earnings(session):
except Exception as e: except Exception as e:
pass pass
res_list = remove_duplicates(res_list) res_list = remove_duplicates(res_list)
res_list.sort(key=lambda x: x['marketCap'], reverse=True) #res_list.sort(key=lambda x: x['marketCap'], reverse=True)
res_list.sort(key=lambda x: (-parse_time(x['time']).timestamp(), -x['marketCap']))
res_list = [{k: v for k, v in d.items() if k != 'marketCap'} for d in res_list] res_list = [{k: v for k, v in d.items() if k != 'marketCap'} for d in res_list]
return res_list[0:5] return res_list[0:5]