forked from lab/TPM
You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
35 lines
1.2 KiB
35 lines
1.2 KiB
import pandas as pd |
|
import json |
|
import yfinance as yf |
|
import numpy as np |
|
import psycopg2 |
|
from psycopg2.extras import execute_values |
|
from tqdm import tqdm |
|
from config import SQL_CONFIG |
|
|
|
with open('data_init/assets_us.json') as f: |
|
data_us = json.load(f) |
|
|
|
# US Stocks |
|
conn = psycopg2.connect(**SQL_CONFIG) |
|
cursor = conn.cursor() |
|
|
|
# Schema already created by data_init_tw_v0.py, just check connection |
|
cursor.execute("SELECT COUNT(*) FROM stock_price;") |
|
row_count = cursor.fetchone()[0] |
|
if row_count <= 0 : |
|
for ticker in tqdm(data_us): |
|
df = yf.download(ticker, start="2007-01-01", progress=False, threads=False) |
|
if df is None or df.empty: |
|
continue |
|
price_col = 'Close' if 'Close' in df.columns else ('Adj Close' if 'Adj Close' in df.columns else None) |
|
if price_col is None: |
|
continue |
|
value = [(ticker, row.name.strftime('%Y-%m-%d'), float(row[price_col])) for _, row in df.iterrows()] |
|
with conn: |
|
with conn.cursor(cursor_factory=psycopg2.extras.RealDictCursor) as curs: |
|
sql = "insert into stock_price (ticker, date, price) values %s" |
|
execute_values(curs, sql, value) |
|
print("Finish initialize") |
|
else: |
|
print("DB already have data")
|
|
|