import requests
import pandas as pd
from bs4 import BeautifulSoup
import io   
import yfinance as yf
from datetime import datetime
import numpy as np
from statsmodels.tsa.api import Holt
from statsmodels.tsa.arima.model import ARIMA
from statsmodels.graphics.tsaplots import plot_predict

import matplotlib.pyplot as plt, mpld3
from statistics import covariance


import warnings
warnings.filterwarnings("ignore")

def dowanload_data():
    url = 'https://stockmarketmba.com/stocksinthedjia.php'

    req = requests.get(url).text
    soup = BeautifulSoup(req, 'lxml')

    table = soup.find('table', attrs={'id': 'ipos'})
    df = pd.read_html(str(table))[0]
    tickers = df['Symbol'].tolist()+['^DJI']
    stock_final = pd.DataFrame()

    for i in tickers:
        print(i)
        try:
            stock = []
            stock = yf.download(i, start=datetime(2017, 10, 31), end=datetime(2022, 10, 31), progress=False)
            
            if len(stock) == 0:
                None

            else:
                stock['Name'] = i
                stock_final = stock_final.append(stock, sort=False)
        except:
            pass

    stock_final.to_csv('djia_2017-2022.csv')


def main(ticker):
    df = pd.read_csv('djia_2017-2022.csv')
    df = df[df['Name']==ticker].dropna(how='any')
    x = np.array(df.dropna()['Date'])
    y = np.array(df.dropna()['Close'])

    model = ARIMA(y, order=(1,1,2))
    model_fit = model.fit()
    print(model_fit.summary())
    plot_predict(model_fit, dynamic=False)

    data = pd.Series(y, x)
    fit1 = Holt(data).fit(smoothing_level=0.1, smoothing_slope=0.1, optimized=False)

    # plt.plot(fit1.fittedvalues, marker="o", color="blue", label='smoothing')

    plt.plot(x, y, label='actual')
    plt.legend(loc="upper left")
    step = 10
    plt.xticks([x[i+step] for i in range(-step, len(x), step) if i+step < len(x)], rotation=90)
    plt.title('ARIMA forecast model vs. actual for {}'.format(ticker))
    mpld3.show()


def stock_covariance(stocks):
    df = pd.read_csv('djia_2017-2022.csv')
    x = df[df['Name']==stocks[0]].dropna(how='any')['Close']
    y = df[df['Name']==stocks[0]].dropna(how='any')['Close']

    cov = covariance(x, y)
    return cov

def dji_covariance(stock):
    df = pd.read_csv('djia_2017-2022.csv')
    x = df[df['Name']=='^DJI'].dropna(how='any')['Close']
    y = df[df['Name']==stock].dropna(how='any')['Close']

    cov = covariance(x, y)
    return cov




if __name__ == "__main__":
    main('IBM')
    # dowanload_data()