Function sequence_frame

alphapy/frame.py:318–364

r"""Create sequences of lagging and leading values. Parameters ---------- df : pandas.DataFrame The original dataframe. target : str The target variable for prediction. forecast_period : int The period for forecasting the target of the analysis. leade

(df, target, forecast_period=1, leaders=[], lag_period=1)

#

def sequence_frame(df, target, forecast_period=1, leaders=[], lag_period=1):
    r"""Create sequences of lagging and leading values.

    Parameters
    ----------
    df : pandas.DataFrame
        The original dataframe.
    target : str
        The target variable for prediction.
    forecast_period : int
        The period for forecasting the target of the analysis.
    leaders : list
        The features that are contemporaneous with the target.
    lag_period : int
        The number of lagged rows for prediction.

    Returns
    -------
    new_frame : pandas.DataFrame
        The transformed dataframe with variable sequences.

    """

    # Set Leaders and Laggards
    le_cols = sorted(leaders)
    le_len = len(le_cols)
    df_cols = sorted(list(set(df.columns) - set(le_cols)))
    df_len = len(df_cols)

    # Add lagged columns
    new_cols, new_names = list(), list()
    for i in range(lag_period, 0, -1):
        new_cols.append(df[df_cols].shift(i))
        new_names += ['%s[%d]' % (df_cols[j], i) for j in range(df_len)]

    # Preserve leader columns
    new_cols.append(df[le_cols])
    new_names += [le_cols[j] for j in range(le_len)]

    # Forecast Target(s)
    new_cols.append(pd.DataFrame(df[target].shift(1-forecast_period)))
    new_names.append(target)

    # Collect all columns into new frame
    new_frame = pd.concat(new_cols, axis=1)
    new_frame.columns = new_names
    return new_frame