ahead.VAR

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