OutputDecay

Bases: ModelOutputItem

Source code in wt_ml/output/output_decay.py
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
class OutputDecay(ModelOutputItem):
    def __init__(
        self,
        intermediaries: EconomicIntermediaries | list[EconomicIntermediaries] = None,
        encodings: Encodings | None = None,
        max_time: int = 20,
        desired_num_points: int = 256,
        combine_granularities_flag: bool = False,
        use_vehicles: Sequence[str] | None = None,
        final_df: pd.DataFrame | list[pd.DataFrame] = None,
        is_animation_call: bool = False,
    ):
        super().__init__(final_df, [encodings, intermediaries])
        self.final_df = final_df
        self.is_animation_call = is_animation_call
        if self.final_df is None:
            self.encodings = encodings
            self.intermediaries = [
                RecursiveNamespace.parse(inter) if isinstance(inter, Mapping) else inter
                for inter in (intermediaries if isinstance(intermediaries, list) else [intermediaries])
            ]
            self.max_time = max_time
            self.desired_num_points = desired_num_points
            self.combine_granularities_flag = combine_granularities_flag

    def get_decay_df(self, intermediaries: EconomicIntermediaries, cumulative_decay_flag=False):
        if intermediaries.impacts.roicurve is None:
            return pd.DataFrame()
        step = to_numpy(intermediaries.step)
        vehicle_names = to_signal_names(intermediaries.impacts.roicurve.signal_names)

        decayed_amount, time_points = get_decay_impact_matrix(
            to_numpy(intermediaries.impacts.roicurve.betagamma.beta),
            to_numpy(intermediaries.impacts.roicurve.betagamma.gamma),
            self.max_time,
            self.desired_num_points,
            cumulative_decay_flag,
        )
        granularity_names, level_names = get_granularity_names(self.encodings, intermediaries.inputs)
        decay_df = pd.DataFrame(
            decayed_amount,
            columns=pd.MultiIndex.from_tuples(
                [(*granularity, "impact", label) for granularity in granularity_names for label in vehicle_names],
                names=(*level_names, "value", "vehicle"),
            ),
            index=pd.Index(time_points.reshape(-1), name="week"),
        )
        step_cols = pd.MultiIndex.from_tuples(
            [(*names, "step", vehicle) for names in granularity_names for vehicle in vehicle_names],
            names=(*level_names, "value", "vehicle"),
        )
        return pd.concat(
            [
                decay_df,
                pd.DataFrame(
                    np.full((len(decay_df.index), len(step_cols)), step, dtype=np.int32),
                    index=decay_df.index,
                    columns=step_cols,
                ),
            ],
            axis=1,
        )

    @cached_property
    def df(
        self,
    ) -> pd.DataFrame:
        """Get decay dataframe"""

        if self.final_df is not None:
            return self.final_df

        decay_dfs = []
        for step_intermediary in self.intermediaries:
            step_decay_df = self.get_decay_df(step_intermediary)
            decay_dfs.append(combine_granularities(step_decay_df) if self.combine_granularities_flag else step_decay_df)

        decay_dfs = decay_dfs[0] if len(self.intermediaries) == 1 else decay_dfs

        return decay_dfs

    @property
    def cumulative_df(
        self,
    ) -> pd.DataFrame:
        if self.final_df:
            return self.final_df

        cumulative_decay_dfs = []
        for step_intermediary in self.intermediaries:
            step_cumulative_decay_df = self.get_decay_df(step_intermediary, True)
            cumulative_decay_dfs.append(
                combine_granularities(step_cumulative_decay_df)
                if self.combine_granularities_flag
                else step_cumulative_decay_df
            )

        return cumulative_decay_dfs

    def visualize(
        self,
        height: int,
        wibbles: list[str] = None,
        vehicle_names: Sequence[str] | None = None,
        wibble_encodings: dict[str, int] | None = None,
        vehicle_encodings: dict[str, int] | None = None,
        get_range: Callable[[pd.DataFrame, list[str]], tuple[int, int]] = lambda df, cols: (0, 1),
    ) -> dict[str, go.Figure]:
        """Visualize decay dataframe

        Args:
            height (int): The height of the line or the scatter plot.
            wibbles (list[str]): Wibble names
            vehicle_names (Sequence[str] | None, optional): Vehicle names. Defaults to None.
            wibble_encodings (dict[str, int] | None, optional): Granularity encodings. Defaults to None.
            vehicle_encodings (dict[str, int] | None, optional): Vehcile encodings. Defaults to None.
            get_range (Callable[[pd.DataFrame, list[str]], tuple[int, int]], optional): Function to get the range of
            values for y axis. Defaults to lambda df, cols: (0, 1).
            show_plots (bool, optional): Flag to indicate whether to show the plots. Defaults to True.

        Returns:
            dict[str, go.Figure]: Prepared line or scatter plots of decay dataframe of granularity names.
        """
        all_decay_df = self.df
        animation_frame = "step" if self.is_animation_call else None
        if isinstance(self.df, list):
            if self.is_animation_call:
                all_decay_df = pd.concat(all_decay_df, axis=0)
            else:
                all_decay_df = pd.concat(all_decay_df, axis=1)
        if wibbles is None:
            if wibble_encodings:
                wibbles = list(wibble_encodings.keys())
            else:
                wibbles = all_decay_df.columns.unique("granularity").tolist()
        if vehicle_names is None:
            if vehicle_encodings is None:
                vehicle_names = list(all_decay_df.columns.unique("vehicle"))
            else:
                vehicle_names = list(vehicle_encodings.keys())

        all_decay_df = filter_level_values(all_decay_df, "vehicle", vehicle_names)
        all_plots = {}
        for name in wibbles:
            decay_df = all_decay_df.xs(name, level="granularity", axis=1)
            line_names = [name for name in decay_df.columns if name != "step"]
            range_y = get_range(decay_df, line_names)
            # Scatter animates much more cleanly
            plt_fcn = px.line if animation_frame is None else px.scatter
            decay_plot = plt_fcn(
                decay_df,
                x=decay_df.index,
                y=line_names,
                animation_frame=animation_frame,
                animation_group=None if animation_frame is None else decay_df.index,
                range_y=range_y,
                height=height,
                title=name,
            )
            all_plots[name] = decay_plot

        return all_plots

df: pd.DataFrame cached property

Get decay dataframe

visualize(height, wibbles=None, vehicle_names=None, wibble_encodings=None, vehicle_encodings=None, get_range=lambda df, cols: (0, 1))

Visualize decay dataframe

Parameters:

Name Type Description Default
height int

The height of the line or the scatter plot.

required
wibbles list[str]

Wibble names

None
vehicle_names Sequence[str] | None

Vehicle names. Defaults to None.

None
wibble_encodings dict[str, int] | None

Granularity encodings. Defaults to None.

None
vehicle_encodings dict[str, int] | None

Vehcile encodings. Defaults to None.

None
get_range Callable[[DataFrame, list[str]], tuple[int, int]]

Function to get the range of

lambda df, cols: (0, 1)
values for y axis. Defaults to lambda df, cols

(0, 1).

required
show_plots bool

Flag to indicate whether to show the plots. Defaults to True.

required

Returns:

Type Description
dict[str, Figure]

dict[str, go.Figure]: Prepared line or scatter plots of decay dataframe of granularity names.

Source code in wt_ml/output/output_decay.py
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
def visualize(
    self,
    height: int,
    wibbles: list[str] = None,
    vehicle_names: Sequence[str] | None = None,
    wibble_encodings: dict[str, int] | None = None,
    vehicle_encodings: dict[str, int] | None = None,
    get_range: Callable[[pd.DataFrame, list[str]], tuple[int, int]] = lambda df, cols: (0, 1),
) -> dict[str, go.Figure]:
    """Visualize decay dataframe

    Args:
        height (int): The height of the line or the scatter plot.
        wibbles (list[str]): Wibble names
        vehicle_names (Sequence[str] | None, optional): Vehicle names. Defaults to None.
        wibble_encodings (dict[str, int] | None, optional): Granularity encodings. Defaults to None.
        vehicle_encodings (dict[str, int] | None, optional): Vehcile encodings. Defaults to None.
        get_range (Callable[[pd.DataFrame, list[str]], tuple[int, int]], optional): Function to get the range of
        values for y axis. Defaults to lambda df, cols: (0, 1).
        show_plots (bool, optional): Flag to indicate whether to show the plots. Defaults to True.

    Returns:
        dict[str, go.Figure]: Prepared line or scatter plots of decay dataframe of granularity names.
    """
    all_decay_df = self.df
    animation_frame = "step" if self.is_animation_call else None
    if isinstance(self.df, list):
        if self.is_animation_call:
            all_decay_df = pd.concat(all_decay_df, axis=0)
        else:
            all_decay_df = pd.concat(all_decay_df, axis=1)
    if wibbles is None:
        if wibble_encodings:
            wibbles = list(wibble_encodings.keys())
        else:
            wibbles = all_decay_df.columns.unique("granularity").tolist()
    if vehicle_names is None:
        if vehicle_encodings is None:
            vehicle_names = list(all_decay_df.columns.unique("vehicle"))
        else:
            vehicle_names = list(vehicle_encodings.keys())

    all_decay_df = filter_level_values(all_decay_df, "vehicle", vehicle_names)
    all_plots = {}
    for name in wibbles:
        decay_df = all_decay_df.xs(name, level="granularity", axis=1)
        line_names = [name for name in decay_df.columns if name != "step"]
        range_y = get_range(decay_df, line_names)
        # Scatter animates much more cleanly
        plt_fcn = px.line if animation_frame is None else px.scatter
        decay_plot = plt_fcn(
            decay_df,
            x=decay_df.index,
            y=line_names,
            animation_frame=animation_frame,
            animation_group=None if animation_frame is None else decay_df.index,
            range_y=range_y,
            height=height,
            title=name,
        )
        all_plots[name] = decay_plot

    return all_plots