train.py 文件源码

def split_into_intervals(data, n):
    """
    Split time series into n minute intervals
    """
    # Throw away time, bid/ask numbers
    prices =  [x[1] for x in data]

    # create a len n-1 array of price differences (10 second increments)
    price_diffs = np.diff(prices)

    # m = interval length in terms of data points (6*~10sec = 1 minute)
    m = n * 6

    # each datapoint we're trying to cluster will be of the form:
    #     (xi,yi) = (time series of prices, price change after series)
    intervals = np.zeros((len(prices)-1,m+1))

    for i in range(0, len(prices)-m-1):
        intervals[i,0:m] = prices[i:i+m]
        intervals[i,m] = price_diffs[i+m]

    return intervals