ahead.VAR.VAR

  1import numpy as np
  2
  3from ..Base import Base
  4from ..utils import multivariate as mv
  5from ..utils import unimultivariate as umv
  6from .. import config
  7
  8
  9class VAR(Base):
 10    """Vector AutoRegressive model
 11
 12    Parameters:
 13
 14        h: an integer;
 15            forecasting horizon
 16
 17        level: an integer;
 18            Confidence level for prediction intervals
 19
 20        lags: an integer;
 21            the lag order
 22
 23        type_VAR: a string;
 24            Type of deterministic regressors to include
 25            ("const", "trend", "both", "none")
 26
 27        date_formatting: a string;
 28            Currently:
 29            - "original": yyyy-mm-dd
 30            - "ms": milliseconds
 31
 32    Attributes:
 33
 34        fcast_: an object;
 35            raw result from fitting R's `ahead::varf` through `rpy2`
 36
 37        averages_: a list of lists;
 38            mean forecast in a list for each series
 39
 40        ranges_: a list of lists;
 41            lower and upper prediction intervals in a list for each series
 42
 43        output_dates_: a list;
 44            a list of output dates (associated to forecast)
 45
 46        mean_: a numpy array
 47            contains series mean forecast as a numpy array
 48
 49        lower_: a numpy array
 50            contains series lower bound forecast as a numpy array
 51
 52        upper_: a numpy array
 53            contains series upper bound forecast as a numpy array
 54
 55        result_dfs_: a tuple of data frames;
 56            each element of the tuple contains 3 columns,
 57            mean forecast, lower + upper prediction intervals,
 58            and a date index
 59
 60    Examples:
 61
 62    ```python
 63    import pandas as pd
 64    from ahead import VAR
 65
 66    # Data frame containing the time series
 67    dataset = {
 68    'date' : ['2001-01-01', '2002-01-01', '2003-01-01', '2004-01-01', '2005-01-01'],
 69    'series1' : [34, 30, 35.6, 33.3, 38.1],
 70    'series2' : [4, 5.5, 5.6, 6.3, 5.1],
 71    'series3' : [100, 100.5, 100.6, 100.2, 100.1]}
 72    df = pd.DataFrame(dataset).set_index('date')
 73    print(df)
 74
 75    # multivariate time series forecasting
 76    v1 = VAR(h = 5, date_formatting = "original", type_VAR="none")
 77    v1.forecast(df)
 78    print(v1.result_dfs_)
 79    ```
 80
 81    """
 82
 83    def __init__(
 84        self, h=5, level=95, lags=1, type_VAR="none", date_formatting="original"
 85    ):  # type_VAR = "const", "trend", "both", "none"
 86
 87        assert type_VAR in (
 88            "const",
 89            "trend",
 90            "both",
 91            "none",
 92        ), "must have: type_VAR in ('const', 'trend', 'both', 'none')"
 93
 94        super().__init__(
 95            h=h,
 96            level=level,
 97        )
 98
 99        self.lags = lags
100        self.type_VAR = type_VAR
101        self.date_formatting = date_formatting
102        self.input_df = None
103
104        self.fcast_ = None
105        self.averages_ = None
106        self.ranges_ = None
107        self.output_dates_ = []
108        self.mean_ = None
109        self.lower_ = None
110        self.upper_ = None
111        self.result_dfs_ = None
112
113    def forecast(self, df):
114        """Forecasting method from `VAR` class
115
116        Parameters:
117
118            df: a data frame;
119                a data frame containing the input time series (see example)
120
121        """
122
123        # get input dates, output dates, number of series, series names, etc.
124        self.init_forecasting_params(df)
125
126        # obtain time series object -----
127        self.format_input()
128
129        self.get_forecast("var")
130
131        # result -----
132        (
133            self.averages_,
134            self.ranges_,
135            _,
136        ) = mv.format_multivariate_forecast(
137            n_series=self.n_series,
138            date_formatting=self.date_formatting,
139            output_dates=self.output_dates_,
140            horizon=self.h,
141            fcast=self.fcast_,
142        )
143
144        self.mean_ = np.asarray(self.fcast_.rx2["mean"])
145        self.lower_ = np.asarray(self.fcast_.rx2["lower"])
146        self.upper_ = np.asarray(self.fcast_.rx2["upper"])
147
148        self.result_dfs_ = tuple(
149            umv.compute_result_df(self.averages_[i], self.ranges_[i])
150            for i in range(self.n_series)
151        )
152
153        return self