shashankvemuri

# View Data 
news['Date'] = pd.to_datetime(news.Date).dt.date

unique_ticker = news['Ticker'].unique().tolist()
news_dict = {name: news.loc[news['Ticker'] == name] for name in unique_ticker}

values = []
for ticker in tickers: 
    dataframe = news_dict[ticker]
    dataframe = dataframe.set_index('Ticker')

shashankvemuri

# Import libraries
import pandas as pd
from bs4 import BeautifulSoup
import matplotlib.pyplot as plt
from urllib.request import urlopen, Request
from nltk.sentiment.vader import SentimentIntensityAnalyzer

# Parameters 
n = 3 #the # of article headlines displayed per ticker
tickers = ['AAPL', 'TSLA', 'AMZN']

shashankvemuri

import talib
import smtplib
import datetime
import numpy as np
import pandas as pd
from email.mime.text import MIMEText
from yahoo_fin import stock_info as si
from pandas_datareader import DataReader
from email.mime.multipart import MIMEMultipart
from bs4 import BeautifulSoup

shashankvemuri

def sendMessage(text):
    message = text

    email = ""
    password = ""
    sms_gateway = ''
    smtp = "smtp.gmail.com" 
    port = 587
    
    server = smtplib.SMTP(smtp,port)

shashankvemuri

def getData(list_of_stocks):
    for stock in list_of_stocks:
        df = DataReader(stock, 'yahoo', start, end)
        print (stock)
        
        # Current Price 
        price = si.get_live_price('{}'.format(stock))
        price = round(price, 2)
        
        # Sharpe Ratio

shashankvemuri

import talib
import smtplib
import datetime
import numpy as np
import pandas as pd
from email.mime.text import MIMEText
from yahoo_fin import stock_info as si
from pandas_datareader import DataReader
from email.mime.multipart import MIMEMultipart
from bs4 import BeautifulSoup

shashankvemuri

#import the libraries
import math
import warnings
import datetime 
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from tensorflow.keras import Sequential
from pandas_datareader import DataReader
from sklearn.preprocessing import MinMaxScaler

shashankvemuri

df = DataReader(stock, "yahoo", start_date, end_date)
data = df.filter(['Close'])
dataset = data.values
train_data_len = math.ceil(len(dataset)*.8)

#scale the data
scaler = MinMaxScaler(feature_range=(0,1))
scaled_data = scaler.fit_transform(dataset)

#create the training dataset

shashankvemuri

#build LSTM model
model = Sequential()
model.add(LSTM(50, return_sequences=True, input_shape=(x_train.shape[1],1)))
model.add(LSTM(50,return_sequences=False))

model.add(Dense(25))
model.add(Dense(1))

#compile the model
model.compile(optimizer='adam', loss='mean_squared_error', metrics=['accuracy'])

shashankvemuri

#get the root mean squared error (RMSE)
rmse = np.sqrt(np.mean((predictions-y_test)**2))

#plot the data
train = data[:train_data_len]
valid = data[train_data_len:]
valid['Predictions'] = predictions
plt.figure(figsize=(16,8))
plt.title('Model for {}'.format(stock.upper()))
plt.xlabel('Date', fontsize=16)