search

enzoampil / fastquant

fastquant — Backtest and optimize your ML trading strategies with only 3 lines of code!
MIT License
1.51k stars 236 forks source link

[FEATURE] Generalize sentiment strategies #122

Open enzoampil opened 4 years ago

jpdeleon commented 4 years ago

guide

models = ['nltk', 'textblob', 'light_nlp_model']
senti_sources = ['disclosures', 'twitter', 'news']

if senti_source=="news":
        df = get_stock_data(...)
    sentiment = get_bt_news(...) 
elif senti_source=="disclosures":
        disclosures = DisclosuresPSE(...)
        df = disclosures.get_pse_data() 
    sentiment = disclosures.get_sentiment() 
else:
    #twitter
        df = get_stock_data(...)
    sentiment = get_twitter_sentiment() 

backtest("sentiment", df, sentiment=sentiment, model="nltk", senti=0.5)