karishmadudani

## This scripts downloads historical stock prices and Vix Data for a given period. 

import quandl
import pandas as pd
import csv


#Get a list of S&P 500 tickers
Tickers = pd.read_csv("C:\Users\lenovo\Desktop\Karishma\Stocks\SP500_Symbols.csv")

karishmadudani

## This scripts downloads historical stock prices and Vix Data for a given period. 

import quandl
import pandas as pd
import csv


#Get a list of S&P 500 tickers
Tickers = pd.read_csv("C:\Users\lenovo\Desktop\Karishma\Stocks\SP500_Symbols.csv")

karishmadudani

## This scripts downloads historical stock prices for a given period. 

import quandl
import pandas as pd
import csv


#Get a list of S&P 500 tickers
Tickers = pd.read_csv("C:\Users\lenovo\Desktop\Karishma\Stocks\SP500_Symbols.csv")

karishmadudani

## This scripts updates the data for stock prices for the latest date

import quandl
import pandas as pd
import csv
import datetime as DT

#Get a list of S&P 500 tickers
Tickers = pd.read_csv("C:\Users\lenovo\Desktop\Karishma\Stocks\SP500_Symbols.csv")
quandl.ApiConfig.api_key = "xxxxxxxxxxxxxxxx"

karishmadudani

## This script creates new normalized input variables and ML models to be used for prediction

import pandas as pd
import numpy as np
from sklearn import svm
from sklearn.model_selection import train_test_split
from imblearn.over_sampling import RandomOverSampler
from sklearn.metrics import confusion_matrix
from sklearn.metrics import accuracy_score
from sklearn.metrics import precision_score

karishmadudani

#Calculate moving averages and normalize the below variables and add to the dataset 'df'    
            VolumeMA = df['Volume'].rolling(window=50).mean()
            AdjClosedMA_50 = df['Adj. Close'].rolling(window=50).mean()
            AdjClosedMA_200 = df['Adj. Close'].rolling(window=200).mean()
            df['VolumeN']= ((df['Volume']-VolumeMA)/VolumeMA)*100
            df['AdjClosedN_50'] = ((df['Adj. Close']- AdjClosedMA_50)/AdjClosedMA_50)*100
            df['AdjClosedN_200'] = ((df['Adj. Close']- AdjClosedMA_200)/AdjClosedMA_200)*100
                
            #Converting numDays and minProfit to string for the purpose of exporting to csv files
            numDaysF = float(numDays)

karishmadudani

 ## Creating SVM model    
            X = df[['HighN','LowN','OpenN','VolumeN', 'pctChange','AdjClosedN_50', 'AdjClosedN_200']]
            y = df['Class']
            X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.20, random_state = 42)
            ros = RandomOverSampler()
            X_train_oversampled,y_train_oversampled = ros.fit_sample(X_train, y_train)
            clf = svm.SVC()
            clf.fit(X_train_oversampled,y_train_oversampled)
            predict = clf.predict(X_test)
            cm = confusion_matrix(y_test, predict)

karishmadudani

import tweepy
import json
import pandas as pd
from scipy.misc import imread
from wordcloud import WordCloud, STOPWORDS, ImageColorGenerator
import matplotlib as mpl
import csv
import matplotlib.pyplot as plt

import operator

karishmadudani

#Authentication

consumer_key = 'xxxxxxxxxxxxxxxxxxxxxxx'
consumer_secret = 'xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx'
access_token = 'xxxxxxxxxxxxx-xxxxxxxxxxxxxxx'
access_token_secret = 'xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx'

auth = tweepy.OAuthHandler(consumer_key, consumer_secret) #Interacting with twitter's API
auth.set_access_token(access_token, access_token_secret)
api = tweepy.API (auth) #creating the API object

karishmadudani

#Store tweets data in a dataframe

def tweets_df(results):
    id_list = [tweet.id for tweet  in results]
    data_set = pd.DataFrame(id_list, columns = ["id"])
    
    data_set["text"] = [tweet.text for tweet in results]
    data_set["created_at"] = [tweet.created_at for tweet in results]
    data_set["retweet_count"] = [tweet.retweet_count for tweet in results]
    data_set["user_screen_name"] = [tweet.author.screen_name for tweet in results]