Time for action – detecting a trend in QQQ

Often we are more interested in the trend of a data sample than in detrending it. Still we can get the trend back easily after detrending. Let’s do that for 1 year of price data for QQQ:

1. Write code that gets the close price and corresponding dates for QQQ.

   today = date.today()
   start = (today.year - 1, today.month, today.day)
   
   quotes = quotes_historical_yahoo(“QQQ”, start, today)
   quotes = np.array(quotes)
   
   dates = quotes.T[0]
   qqq = quotes.T[4]

2. Detrend the signal.

   y = signal.detrend(qqq)

3. Create month and day locators for the dates.

   alldays = DayLocator()
   months = MonthLocator ()
   

4. Create a date formatter that creates a string of month name and year.

   month_formatter = DateFormatter(“%b %Y”)

5. Create a figure and subplot.

   fig = plt.figure()
   ax = fig.add_subplot(111)

6. Plot the data and underlying trend by subtracting the detrended signal.

   plt.plot(dates, qqq, ‘o’, dates, qqq - y, ‘-’)

7. Set the locators and formatter.

   ax.xaxis.set_minor_locator(alldays)
   ax.xaxis.set_major_locator...