Webscrape and Lin Reg

import yfinance as yf
import pandas as pd
import requests
from bs4 import BeautifulSoup
import plotly.graph_objects as go
from plotly.subplots import make_subplots
from sklearn.linear_model import LinearRegression

#Defining graphing function

def make_graph(stock_data, stock):
    fig = make_subplots(rows=2, cols=1, shared_xaxes=True, subplot_titles=("Historical Share Price", "Time Series Regression"), vertical_spacing = .3)
    stock_data_specific = stock_data[stock_data.Date <= '2021--06-14']
    fig.add_trace(go.Scatter(x=pd.to_datetime(stock_data_specific.Date, infer_datetime_format=True), y=stock_data_specific.Close.astype("float"), name="Share Price"), row=1, col=1)
    
    #Add time series regression line
    X = stock_data_specific.index.values.reshape(-1, 1)
    y = stock_data_specific['Close'].values.reshape(-1, 1)
    reg = LinearRegression().fit(X, y)
    y_pred = reg.predict(X)
    fig.add_trace(go.Scatter(x=stock_data_specific['Date'], y=y_pred.flatten(), name='Time Series Regression'), row=2, col=1)

    fig.update_xaxes(title_text="Date", row=1, col=1)
    fig.update_xaxes(title_text="Date", row=2, col=1)
    fig.update_yaxes(title_text="Price ($US)", row=1, col=1)
    fig.update_layout(showlegend=False,
    height=900,
    title=stock,
    xaxis_rangeslider_visible=True)
    fig.show()
    
#Use yfinance to extract stock data
 
SPY = yf.Ticker("SPY")

SPY_data = SPY.history(period="max")

 #reset the index
SPY_data.reset_index(inplace=True)
SPY_data.head()

#Plots graph with time series regression
make_graph(SPY_data, 'S&P 500')

#end