marcosan93

def fbpPositions(pred_df, short=True):
    """
    Gets positions based on the predictions and the actual values. This
    is the logic of the trading strategy.
    """
    if pred_df['open'] < pred_df['yhat_lower']:
        return 1
    elif pred_df['open'] > pred_df['yhat_upper'] and short:
        return -1
    else:

marcosan93

def runningFBP(prices, forecast_hours, training_hours):
    """
    Runs Facebook Prophet to get predictions over a set period 
    of time. Uses FBP to train and predict every hour and gets the 
    price forecasts in the next N hours.
    """
    # DF for the predicted values
    pred_df = pd.DataFrame()

    # Running the model each day

marcosan93

def fbpTrainPredict(df, forecast_hours):
    """
    Uses FB Prophet and fits to a appropriately formatted DF. Makes a prediction N days into 
    the future based on given forecast period. Returns predicted values as a DF.
    """
    # Setting up prophet
    m = Prophet(
        yearly_seasonality=False,
        weekly_seasonality=False,
        daily_seasonality=False

marcosan93

def getIntradayPrices(crypto, n_hours, training_hours, mov_avg):
    """
    Gets crypto prices from now to N days ago and training amount will be in addition 
    to the number of days to train. (According to the EOD documentation: The maximum 
    periods between ‘from’ and ‘to’ are 120 days for 1-minute interval, 600 days 
    for 5-minute interval and 7200 days for 1 hour interval.)
    
    There also appears to be a time delay on the data of about 15-20 hours, which 
    is added to the from(ago) variable.
    """

marcosan93

# Adding sentiment positions to the forecast DF
positions = pred_df.merge(
    sent_df, 
    right_index=True, 
    left_index=True, 
    how='inner'
)

# Getting forecast prophet positions
positions['fbp_positions'] = positions.apply(

marcosan93

def runningFBP(prices, forecast_period, training_days):
    """
    Runs Facebook Prophet to get predictions over a set period 
    of time. Uses FBP to train and predict every N days and gets the 
    price forecasts.
    """
    # DF for the predicted values
    pred_df = pd.DataFrame()

    # Running the model each day

marcosan93

def getPrices(ticker, training_days, sent_df, mov_avg):
    """
    Using a sentiment DataFrame to find the first day and trains with the previous
    N days to make predictions that coincide with the sentiment date range.
    
    In order to properly backtest with sentiment, a certain amount of training 
    days need to come before the initial date from the sentiment DF.
    
    Also prepares the price data for FBProphet.
    """

marcosan93

def sentimentPositions(val, thresh=0.1, short=True):
    """
    Returns position as 1, -1, or 0 for Buy, Sell, 
    and Do Nothing respectively based on the given 
    sentiment value and threshold.
    """
    if val > thresh:
        return 1
    elif val < -thresh and short:
        return -1

marcosan93

def getNews(ticker, days):
    """
    Retrieves financial news over the course of a specified number of days for
    a given stock ticker.
    """

    # List of news
    news = []
    
    # How many days back to retrieve

marcosan93

def getNewsAndPrices(ticker, days):
    """
    Retrieves financial news and price history over the course of a 
    specified number of days fora given stock ticker.
    """

    # List of news
    news = []
    
    # How many days back to retrieve