Python... it can be unforgiving at times. Especially when it comes to lower and upper case letters. The problem is 'longs' needs to be capitalized. So instead of

    for sec in pipe_results[pipe_results['longs']].index.tolist():

It should be

    for sec in pipe_results[pipe_results['Longs']].index.tolist():

Notice the capitalized 'Longs'. There is also the same problem a few lines after that with 'Shorts'.

    for sec in pipe_results[pipe_results['Shorts']].index.tolist():

However, there is faster way to accomplish this. Use the pandas query method and simply create a list.

    # context.longs = []  
    # no need for the for loop below  
    # just query the dataframe  
    # for sec in pipe_results[pipe_results['longs']].index.tolist():  
    #    if data.can_trade(sec):  
    #        context.longs.append(sec)

    context.longs = pipe_results.query('Longs').index.tolist()

Do something similar for the shorts

    context.shorts = pipe_results.query('Shorts').index.tolist()

Because 'Longs' and 'Shorts' are boolean values, the above is really shorthand for

context.longs = pipe_results.query('Longs == True').index.tolist()  
context.shorts = pipe_results.query('Shorts == True').index.tolist()

I believe the algo runs now.

Silly me! Thank your for such enlightenments and showing me a better way to optimize the algorithm.

I have runned a backtest of the algorithm for the year 2019 and had a poor return comparing to the SPX . My next step would be looking for other factors to test.

Regards,