Operators

Operator Python 
ts_sum(df, window)







def ts_sum(df, window=10):
    """
    Wrapper function to estimate rolling sum.
    :param df: a pandas DataFrame.
    :param window: the rolling window.
    :return: a pandas DataFrame with the time-series min over the past 'window' days.
    """
    return df.rolling(window).sum()

sma(df, window)







def sma(df, window=10):
    """
    Wrapper function to estimate SMA.
    :param df: a pandas DataFrame.
    :param window: the rolling window.
    :return: a pandas DataFrame with the time-series min over the past 'window' days.
    """
    return df.rolling(window).mean()
stddev(df, window)







def stddev(df, window=10):
    """
    Wrapper function to estimate rolling standard deviation.
    :param df: a pandas DataFrame.
    :param window: the rolling window.
    :return: a pandas DataFrame with the time-series min over the past 'window' days.
    """
    return df.rolling(window).std()

correlation(x, y, window)







def correlation(x, y, window=10):
    """
    Wrapper function to estimate rolling corelations.
    :param df: a pandas DataFrame.
    :param window: the rolling window.
    :return: a pandas DataFrame with the time-series min over the past 'window' days.
    """
    return x.rolling(window).corr(y)

covariance(x, y, window)







def covariance(x, y, window=10):
    """
    Wrapper function to estimate rolling covariance.
    :param df: a pandas DataFrame.
    :param window: the rolling window.
    :return: a pandas DataFrame with the time-series min over the past 'window' days.
    """
    return x.rolling(window).cov(y)

rolling_rank(na)







def rolling_rank(na):
    """
    Auxiliary function to be used in pd.rolling_apply
    :param na: numpy array.
    :return: The rank of the last value in the array.
    """
    return rankdata(na)[-1]

rolling_rank(na)







def rolling_rank(na):
    """
    Auxiliary function to be used in pd.rolling_apply
    :param na: numpy array.
    :return: The rank of the last value in the array.
    """
    return rankdata(na)[-1]

ts_rank(df, window)







def ts_rank(df, window=10):
    """
    Wrapper function to estimate rolling rank.
    :param df: a pandas DataFrame.
    :param window: the rolling window.
    :return: a pandas DataFrame with the time-series rank over the past window days.
    """
    return df.rolling(window).apply(rolling_rank)

rolling_prod(na)







def rolling_prod(na):
    """
    Auxiliary function to be used in pd.rolling_apply
    :param na: numpy array.
    :return: The product of the values in the array.
    """
    return np.prod(na)

product(df, window)







def product(df, window=10):
    """
    Wrapper function to estimate rolling product.
    :param df: a pandas DataFrame.
    :param window: the rolling window.
    :return: a pandas DataFrame with the time-series product over the past 'window' days.
    """
    return df.rolling(window).apply(rolling_prod)

ts_min(df, window)







def ts_min(df, window=10):
    """
    Wrapper function to estimate rolling min.
    :param df: a pandas DataFrame.
    :param window: the rolling window.
    :return: a pandas DataFrame with the time-series min over the past 'window' days.
    """
    return df.rolling(window).min()

ts_max(df, window)







def ts_max(df, window=10):
    """
    Wrapper function to estimate rolling min.
    :param df: a pandas DataFrame.
    :param window: the rolling window.
    :return: a pandas DataFrame with the time-series max over the past 'window' days.
    """
    return df.rolling(window).max()

delta(df, period)







def delta(df, period=1):
    """
    Wrapper function to estimate difference.
    :param df: a pandas DataFrame.
    :param period: the difference grade.
    :return: a pandas DataFrame with today’s value minus the value 'period' days ago.
    """
    return df.diff(period)

delay(df, period)







def delay(df, period=1):
    """
    Wrapper function to estimate lag.
    :param df: a pandas DataFrame.
    :param period: the lag grade.
    :return: a pandas DataFrame with lagged time series
    """
    return df.shift(period)

rank(df)







def rank(df):
    """
    Cross sectional rank
    :param df: a pandas DataFrame.
    :return: a pandas DataFrame with rank along columns.
    """
    return df.rank(axis=1, pct=True)

scale(df, k)







def scale(df, k=1):
    """
    Scaling time serie.
    :param df: a pandas DataFrame.
    :param k: scaling factor.
    :return: a pandas DataFrame rescaled df such that sum(abs(df)) = k
    """
    return df.mul(k).div(np.abs(df).sum())

ts_argmax(df, window)







def ts_argmax(df, window=10):
    """
    Wrapper function to estimate which day ts_max(df, window) occurred on
    :param df: a pandas DataFrame.
    :param window: the rolling window.
    :return: well.. that :)
    """
    return df.rolling(window).apply(np.argmax) + 1

ts_argmin(df, window)







def ts_argmin(df, window=10):
    """
    Wrapper function to estimate which day ts_min(df, window) occurred on
    :param df: a pandas DataFrame.
    :param window: the rolling window.
    :return: well.. that :)
    """
    return df.rolling(window).apply(np.argmin) + 1

decay_linear(df, period)

























def decay_linear(df, period=10):
    """
    Linear weighted moving average implementation.
    :param df: a pandas DataFrame.
    :param period: the LWMA period
    :return: a pandas DataFrame with the LWMA.
    """
    # Clean data
    if df.isnull().values.any():
        df.fillna(method='ffill', inplace=True)
        df.fillna(method='bfill', inplace=True)
        df.fillna(value=0, inplace=True)
na_lwma = np.zeros_like(df)
na_lwma[:period, :] = df.ix[:period, :]
na_series = df.as_matrix()

divisor = period * (period + 1) / 2
y = (np.arange(period) + 1) * 1.0 / divisor
# Estimate the actual lwma with the actual close.
# The backtest engine should assure to be snooping bias free.
for row in range(period - 1, df.shape[0]):
    x = na_series[row - period + 1: row + 1, :]
    na_lwma[row, :] = (np.dot(x.T, y))
return pd.DataFrame(na_lwma, index=df.index, columns=df.columns)