airflow1.py

# -*- coding: utf-8 -*-
"""
@author: KGarg
"""
import pandas as pd
def get_stock_price():
    import requests
    
    data_dict={}  
    symbols = ['MSFT','AAPL','NFLX']
    path = r"stocks.csv"
    
    for symbol in symbols:
        url=f"https://query1.finance.yahoo.com/v7/finance/download/{symbol}?period1=1673783050&period2=1705319050&interval=1d&events=history&includeAdjustedClose=True"
        headers = {'User-Agent': 'Mozilla/5.0'}  
        response = requests.get(url, headers=headers)  
        data = response.text 
        df = pd.DataFrame(map(lambda x:x.split(","), data.split("\n")[1:]),columns=data.split("\n")[0].split(","))
        
        data_dict[symbol]=df['Close']
    pd.DataFrame(data_dict).to_csv(path,index=False)
    return path
    
def clean(file_path):
    df = pd.read_csv(file_path)
    df = df.dropna()
    df.to_csv(file_path,index=False)
    return file_path

def compute(file_path):    
    output = r'corr.csv'
    df = pd.read_csv(file_path)
    for column in df.columns:
        df[column] = df[column].astype(float)
    
    corr = df.corr()
    corr.to_csv(output,index=False)
    return output