Wrap in a class and set function as static

datapuller.py

@@ -1,16 +1,20 @@
 import yfinance as yf
 import pandas as pd
 
-# Import the S&P 500 symbols
+class DataPuller:
-symbols = pd.read_excel("./data/stock_symbols.xlsx")
-symbols.columns = symbols.columns.str.strip()
-tickers = symbols['Symbol'].tolist()
 
-# Scrape the data
+    @staticmethod
-all_data = []
+    def pull():
-for i, symbol in enumerate(tickers): # Try first 20
+        # Import the S&P 500 symbols
+        symbols = pd.read_excel("./data/stock_symbols.xlsx")
+        symbols.columns = symbols.columns.str.strip()
+        tickers = symbols['Symbol'].tolist()
+
+        # Scrape the data
+        all_data = []
+        for i, symbol in enumerate(tickers): # Try first 20
             print(f"Processing: {i} of {len(tickers)}")
-    df = yf.download(symbol, period="max")
+            df = yf.download(symbol, period="max", auto_adjust=True)
             if not df.empty:
                 # Remove the ticker column
                 df.columns = df.columns.get_level_values(0)
@@ -37,13 +41,13 @@ for i, symbol in enumerate(tickers): # Try first 20
 
                 all_data.append(df)
 
-# Concatinate into a combined list and cache
+        # Concatinate into a combined list and cache
-print("Processing data")
+        print("Processing data")
-final_df = pd.concat(all_data)
+        final_df = pd.concat(all_data)
 
-# Drop rows with null values
+        # Drop rows with null values
-final_df.dropna(inplace=True)
+        final_df.dropna(inplace=True)
 
-print("Writing data to file")
+        print("Writing data to file")
-final_df.to_parquet("./data/stocks.parquet")
+        final_df.to_parquet("./data/stocks.parquet")
-final_df.head(200).to_csv("./data/stocks_preview.csv")
+        final_df.head(200).to_csv("./data/stocks_preview.csv")