Skip to content

Contrasting Results

ForecastOfT module-attribute 

ForecastOfT = Literal['mu', 'sigma', 'closed', 'adj_price']

Contrast

Bases: dict

Source code in passengersim/contrast.py 
17
18
19
20
21
22
23
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
class Contrast(dict):
    def apply(
        self,
        func: Callable,
        axis: int | Literal["index", "columns", "rows"] = 0,
        warn_if_missing: bool = False,
    ) -> pd.DataFrame | pd.Series:
        data = {}
        for k, v in self.items():
            if v is not None:
                data[k] = func(v)
            else:
                if warn_if_missing:
                    warnings.warn(f"no data found for {k!r}", stacklevel=2)
        try:
            return pd.concat(data, axis=axis, names=["source"])
        except TypeError:
            return pd.Series(data).rename_axis(index="source")

    def __getattr__(self, attr):
        if attr.startswith("fig_"):
            g = globals()
            if attr in g:
                return partial(g[attr], self)
                # return lambda *a, **k: g[attr](self, *a, **k)
        raise AttributeError(attr)

    def __dir__(self):
        x = set(super().__dir__())
        x |= {g for g in globals() if g.startswith("fig_")}
        return sorted(x)

    def write_report(self, filename: PathLike, **kwargs) -> pathlib.Path:
        from passengersim.reporting.contrast import to_html

        return to_html(self, filename, **kwargs)

    def subset(self, keys=None, *, regex: str = None) -> Self:
        """Subset the contrast to only include the specified keys.

        Parameters
        ----------
        keys : str or list of str, optional
            The keys to include in the subset. If None, use the `regex` filter.
        regex : str, optional
            A regular expression to filter the keys. If None, use the `keys` filter.

        Returns
        -------
        Contrast
        """
        if keys is not None and regex is not None:
            raise ValueError("cannot use both keys and regex")
        if keys is not None:
            if isinstance(keys, str):
                keys = [keys]
            if not isinstance(keys, list | tuple):
                raise TypeError("keys must be a string or a list of strings")
            result = type(self)({key: self[key] for key in keys if key in self})
        else:
            import re

            matches = []
            for k in self.keys():
                if re.match(regex, k):
                    matches.append(k)
            result = type(self)({k: self[k] for k in matches})
        if len(result) == 0:
            raise ValueError("no matches found")
        return result

__dir__ 

__dir__()
Source code in passengersim/contrast.py 
44
45
46
47
def __dir__(self):
    x = set(super().__dir__())
    x |= {g for g in globals() if g.startswith("fig_")}
    return sorted(x)

__getattr__ 

__getattr__(attr)
Source code in passengersim/contrast.py 
36
37
38
39
40
41
42
def __getattr__(self, attr):
    if attr.startswith("fig_"):
        g = globals()
        if attr in g:
            return partial(g[attr], self)
            # return lambda *a, **k: g[attr](self, *a, **k)
    raise AttributeError(attr)

apply 

apply(
    func: Callable,
    axis: int | Literal["index", "columns", "rows"] = 0,
    warn_if_missing: bool = False,
) -> DataFrame | Series
Source code in passengersim/contrast.py 
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
def apply(
    self,
    func: Callable,
    axis: int | Literal["index", "columns", "rows"] = 0,
    warn_if_missing: bool = False,
) -> pd.DataFrame | pd.Series:
    data = {}
    for k, v in self.items():
        if v is not None:
            data[k] = func(v)
        else:
            if warn_if_missing:
                warnings.warn(f"no data found for {k!r}", stacklevel=2)
    try:
        return pd.concat(data, axis=axis, names=["source"])
    except TypeError:
        return pd.Series(data).rename_axis(index="source")

subset 

subset(keys=None, *, regex: str = None) -> Self

Subset the contrast to only include the specified keys.

Parameters:

  • keys (str or list of str, default: None ) –

    The keys to include in the subset. If None, use the regex filter.

  • regex (str, default: None ) –

    A regular expression to filter the keys. If None, use the keys filter.

Returns:

Source code in passengersim/contrast.py 
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
def subset(self, keys=None, *, regex: str = None) -> Self:
    """Subset the contrast to only include the specified keys.

    Parameters
    ----------
    keys : str or list of str, optional
        The keys to include in the subset. If None, use the `regex` filter.
    regex : str, optional
        A regular expression to filter the keys. If None, use the `keys` filter.

    Returns
    -------
    Contrast
    """
    if keys is not None and regex is not None:
        raise ValueError("cannot use both keys and regex")
    if keys is not None:
        if isinstance(keys, str):
            keys = [keys]
        if not isinstance(keys, list | tuple):
            raise TypeError("keys must be a string or a list of strings")
        result = type(self)({key: self[key] for key in keys if key in self})
    else:
        import re

        matches = []
        for k in self.keys():
            if re.match(regex, k):
                matches.append(k)
        result = type(self)({k: self[k] for k in matches})
    if len(result) == 0:
        raise ValueError("no matches found")
    return result

write_report 

write_report(filename: PathLike, **kwargs) -> Path
Source code in passengersim/contrast.py 
49
50
51
52
def write_report(self, filename: PathLike, **kwargs) -> pathlib.Path:
    from passengersim.reporting.contrast import to_html

    return to_html(self, filename, **kwargs)

MultiContrast

Bases: dict

Source code in passengersim/contrast.py 
 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
class MultiContrast(dict):
    def __getattr__(self, attr):
        if attr.startswith("fig_"):
            g = globals()
            if attr in g:
                alter_defaults = {}
                if attr in [
                    "fig_carrier_revenues",
                    "fig_carrier_yields",
                    "fig_carrier_total_bookings",
                    "fig_carrier_load_factors",
                ]:
                    alter_defaults["width"] = 300

                def fig_func(*args, **kwargs):
                    figs = {}
                    kwargs.update(alter_defaults)
                    report = kwargs.pop("report", None)
                    trace = kwargs.pop("trace", None)
                    if trace:
                        raise NotImplementedError("trace not implemented")
                    for k, v in self.items():
                        if v is not None:
                            figs[k] = partial(g[attr], v)(*args, **kwargs)
                    fig, title = self._hconcat(figs)
                    if report:
                        report.add_figure(title=title, fig=fig)
                    return fig

                return fig_func
        raise AttributeError(attr)

    def __dir__(self):
        x = set(super().__dir__())
        x |= {g for g in globals() if g.startswith("fig_")}
        return sorted(x)

    @staticmethod
    def _hconcat(charts: dict[str, alt.Chart]) -> tuple[alt.HConcatChart, str]:
        if not charts:
            raise ValueError("no charts to concatenate")
        queue = []
        title = ""
        for k, c in charts.items():
            if c is None:
                warnings.warn(f"no data found for {k!r}", stacklevel=2)
                continue
            config = c._kwds.get("config", alt.Undefined)
            c._kwds["config"] = alt.Undefined
            title = c._kwds.get("title", "")
            c._kwds["title"] = f"{k} {title}"
            queue.append(c)
        if not queue:
            raise ValueError("no charts to concatenate")
        result = alt.hconcat(*queue)
        result._kwds["config"] = config
        return result, title

__dir__ 

__dir__()
Source code in passengersim/contrast.py 
121
122
123
124
def __dir__(self):
    x = set(super().__dir__())
    x |= {g for g in globals() if g.startswith("fig_")}
    return sorted(x)

__getattr__ 

__getattr__(attr)
Source code in passengersim/contrast.py 
 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
def __getattr__(self, attr):
    if attr.startswith("fig_"):
        g = globals()
        if attr in g:
            alter_defaults = {}
            if attr in [
                "fig_carrier_revenues",
                "fig_carrier_yields",
                "fig_carrier_total_bookings",
                "fig_carrier_load_factors",
            ]:
                alter_defaults["width"] = 300

            def fig_func(*args, **kwargs):
                figs = {}
                kwargs.update(alter_defaults)
                report = kwargs.pop("report", None)
                trace = kwargs.pop("trace", None)
                if trace:
                    raise NotImplementedError("trace not implemented")
                for k, v in self.items():
                    if v is not None:
                        figs[k] = partial(g[attr], v)(*args, **kwargs)
                fig, title = self._hconcat(figs)
                if report:
                    report.add_figure(title=title, fig=fig)
                return fig

            return fig_func
    raise AttributeError(attr)

fig_bid_price_history 

fig_bid_price_history(
    summaries,
    *,
    by_carrier: bool | str = True,
    show_stdev: float | bool | None = None,
    cap: Literal["some", "zero", None] = None,
    raw_df: bool = False,
    title: str | None = "Bid Price History",
    also_df: bool = False,
)
Source code in passengersim/contrast.py 
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
@report_figure
def fig_bid_price_history(
    summaries,
    *,
    by_carrier: bool | str = True,
    show_stdev: float | bool | None = None,
    cap: Literal["some", "zero", None] = None,
    raw_df: bool = False,
    title: str | None = "Bid Price History",
    also_df: bool = False,
):
    if cap is None:
        bp_mean = "bid_price_mean"
    elif cap == "some":
        bp_mean = "some_cap_bid_price_mean"
    elif cap == "zero":
        bp_mean = "zero_cap_bid_price_mean"
    else:
        raise ValueError(f"cap={cap!r} not in ['some', 'zero', None]")

    if not isinstance(by_carrier, str) and show_stdev:
        raise NotImplementedError(
            "contrast.fig_bid_price_history with show_stdev requires looking at a single carrier (set `by_carrier`)"
        )
    df = _assemble(
        summaries,
        "bid_price_history",
        by_carrier=by_carrier,
        show_stdev=show_stdev,
        cap=cap,
    )
    if raw_df:
        return df

    line_encoding = dict(
        x=alt.X("days_prior:Q").scale(reverse=True).title("Days Prior to Departure"),
        y=alt.Y(bp_mean, title="Bid Price"),
        color="source:N",
    )
    chart = alt.Chart(df)
    fig = chart.mark_line(interpolate="step-before").encode(**line_encoding)
    if show_stdev:
        area_encoding = dict(
            x=alt.X("days_prior:Q").scale(reverse=True).title("Days Prior to Departure"),
            y=alt.Y("bid_price_lower:Q", title="Bid Price"),
            y2=alt.Y2("bid_price_upper:Q", title="Bid Price"),
            color="source:N",
        )
        bound = chart.mark_area(
            opacity=0.1,
            interpolate="step-before",
        ).encode(**area_encoding)
        bound_line = chart.mark_line(opacity=0.4, strokeDash=[5, 5], interpolate="step-before").encode(
            x=alt.X("days_prior:Q").scale(reverse=True).title("Days Prior to Departure"),
            color="source:N",
        )
        top_line = bound_line.encode(y=alt.Y("bid_price_lower:Q", title="Bid Price"))
        bottom_line = bound_line.encode(y=alt.Y("bid_price_upper:Q", title="Bid Price"))
        fig = fig + bound + top_line + bottom_line
    if not isinstance(by_carrier, str):
        fig = fig.properties(height=125, width=225).facet(facet="carrier:N", columns=2)
        if title:
            fig = fig.properties(title=title)
    else:
        if title:
            title = f"{title} ({by_carrier})"
            fig = fig.properties(title=title)
    if also_df:
        return fig, df
    return fig

fig_bookings_by_timeframe 

fig_bookings_by_timeframe(
    summaries: dict[str, SummaryTables],
    by_carrier: bool | str = True,
    by_class: bool | str = False,
    *,
    by_segment: str | None = None,
    raw_df=False,
    source_labels: bool = False,
    ratio: str | bool = False,
    also_df: bool = False,
) -> Chart | DataFrame

Generate a figure contrasting bookings by timeframe for one or more runs.

Parameters:

  • summaries (dict[str, SummaryTables]) –

    One or more SummaryTables to compare. The keys of this dictionary are the text names used to label the "source" for each set of data in the figure.

  • by_carrier (bool or str, default: True ) –

    Whether to differentiate carriers by colors (the default) or give the name of a particular carrier as a string to filter the results shown in the figure to only that one carrier.

  • by_class (bool or str, default: False ) –

    Whether to differentiate booking class by colors (the default) or give the name of a particular booking class as a string to filter the results shown in the figure to only that one booking class.

  • raw_df (bool, default: False ) –

    Set to true to return the raw dataframe used to generate the figure, instead of the figure itself.

  • source_labels (bool, default: False ) –

    Write source labels above the columns of the figure. Source labels are also available as tool tips, but if the figure is being shared as an image without tooltips, the source labels may make it easier to interpret.

  • ratio (str or bool, default: False ) –

    Compute ratios against a reference point and display them in tooltips.

Other Parameters:

  • report (Reporter) –

    Giving a reporter for this keyword only argument allow you to automatically append this figure to the report (in addition to returning it for display or other processing).

  • trace (ExcelWriter or (ExcelWriter, str)) –

    Write the raw dataframe backing this figure to the Excel workbook.

Source code in passengersim/contrast.py 
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
@report_figure
def fig_bookings_by_timeframe(
    summaries: dict[str, SummaryTables],
    by_carrier: bool | str = True,
    by_class: bool | str = False,
    *,
    by_segment: str | None = None,
    raw_df=False,
    source_labels: bool = False,
    ratio: str | bool = False,
    also_df: bool = False,
) -> alt.Chart | pd.DataFrame:
    """
    Generate a figure contrasting bookings by timeframe for one or more runs.

    Parameters
    ----------
    summaries : dict[str, SummaryTables]
        One or more SummaryTables to compare. The keys of this dictionary are the
        text names used to label the "source" for each set of data in the figure.
    by_carrier : bool or str, default True
        Whether to differentiate carriers by colors (the default) or give the name
        of a particular carrier as a string to filter the results shown in the
        figure to only that one carrier.
    by_class : bool or str, default False
        Whether to differentiate booking class by colors (the default) or give the
        name of a particular booking class as a string to filter the results shown
        in the figure to only that one booking class.
    raw_df : bool, default False
        Set to true to return the raw dataframe used to generate the figure, instead
        of the figure itself.
    source_labels : bool, default False
        Write source labels above the columns of the figure. Source labels are also
        available as tool tips, but if the figure is being shared as an image without
        tooltips, the source labels may make it easier to interpret.
    ratio : str or bool, default False
        Compute ratios against a reference point and display them in tooltips.

    Other Parameters
    ----------------
    report : xmle.Reporter, optional
        Giving a reporter for this keyword only argument allow you to automatically
        append this figure to the report (in addition to returning it for display
        or other processing).
    trace : pd.ExcelWriter or (pd.ExcelWriter, str), optional
        Write the raw dataframe backing this figure to the Excel workbook.
    """
    if by_carrier is True and by_class is True:
        raise NotImplementedError("comparing by both class and carrier is messy")
    df = _assemble(summaries, "bookings_by_timeframe", by_carrier=by_carrier, by_class=by_class)
    source_order = list(summaries.keys())

    title = "Bookings by Timeframe"
    if by_class is True:
        title = "Bookings by Timeframe and Booking Class"
    title_annot = []
    if isinstance(by_carrier, str):
        title_annot.append(by_carrier)
    if isinstance(by_class, str):
        title_annot.append(f"Class {by_class}")
    if by_segment:
        title_annot.append(by_segment)
    if title_annot:
        title = f"{title} ({', '.join(title_annot)})"

    against = source_order[0]
    ratio_tooltips = ()
    if ratio:
        if isinstance(ratio, str):
            against = ratio
        idx = list({"source", "carrier", "segment", "days_prior", "booking_class"} & set(df.columns))
        df_ = df.set_index(idx)
        ratios = df_.div(df_.query(f"source == '{against}'").droplevel("source")) - 1.0
        ratios.columns = ["ratio"]
        df = df.join(ratios, on=idx)
        ratio_tooltips = (alt.Tooltip("ratio:Q", title=f"vs {against}", format=".3%"),)

    if by_segment:
        df = df[df["segment"] == by_segment]

    if raw_df:
        df.attrs["title"] = title
        return df

    if by_class:
        if isinstance(by_class, str):
            color = alt.Color("source:N", title="Source", sort=source_order).title("Source")
            tooltips = ()
        else:
            color = alt.Color("booking_class:N").title("Booking Class")
            tooltips = (alt.Tooltip("booking_class", title="Booking Class"),)
        chart = alt.Chart(df.sort_values("source", ascending=False))
        chart_1 = chart.mark_bar().encode(
            color=color,
            x=alt.X("days_prior:O").scale(reverse=True).title("Days Prior to Departure"),
            xOffset=alt.XOffset("source:N", title="Source", sort=source_order),
            y=alt.Y("bookings", stack=True),
            tooltip=[
                alt.Tooltip("source:N", title="Source"),
                alt.Tooltip("segment", title="Passenger Segment"),
                *tooltips,
                alt.Tooltip("days_prior", title="DfD"),
                alt.Tooltip("bookings", format=".2f"),
                *ratio_tooltips,
            ],
        )
        chart_2 = chart.mark_text(
            color="#616161",
            yOffset=-2,
            angle=270,
            fontSize=8,
            baseline="middle",
            align="left",
        ).encode(
            text=alt.Text("source:N", title="Source"),
            x=alt.X("days_prior:O").scale(reverse=True).title("Days Prior to Departure"),
            xOffset=alt.XOffset("source:N", title="Source", sort=source_order),
            # shape=alt.Shape("source:N", title="Source", sort=source_order),
            y=alt.Y("sum(bookings)", title=None),
        )
        fig = (
            ((chart_1 + chart_2) if source_labels else chart_1)
            .properties(
                width=500,
                height=200,
            )
            .facet(
                row=alt.Row("segment:N", title="Passenger Segment"),
                title=title,
            )
        )
    elif by_carrier is True:
        fig = (
            alt.Chart(df.sort_values("source", ascending=False))
            .mark_bar()
            .encode(
                color=alt.Color("carrier:N").title("Carrier"),
                x=alt.X("days_prior:O").scale(reverse=True).title("Days Prior to Departure"),
                xOffset=alt.XOffset("source:N", title="Source", sort=source_order),
                y=alt.Y("bookings", stack=True),
                tooltip=[
                    alt.Tooltip("source:N", title="Source"),
                    alt.Tooltip("segment", title="Passenger Segment"),
                    alt.Tooltip("carrier", title="Carrier"),
                    alt.Tooltip("days_prior", title="DfD"),
                    alt.Tooltip("bookings", format=".2f"),
                    *ratio_tooltips,
                ],
            )
            .properties(
                width=500,
                height=200,
            )
            .facet(
                row=alt.Row("segment:N", title="Passenger Segment"),
                title=title,
            )
        )
    else:
        fig = (
            alt.Chart(df.sort_values("source", ascending=False), title=title)
            .mark_line()
            .encode(
                color=alt.Color("source:N", title="Source", sort=source_order),
                x=alt.X("days_prior:O").scale(reverse=True).title("Days Prior to Departure"),
                y="bookings",
                strokeDash=alt.StrokeDash("segment").title("Passenger Segment"),
                strokeWidth=alt.StrokeWidth("source:N", title="Source", sort=source_order),
                tooltip=[
                    alt.Tooltip("source:N", title="Source"),
                    alt.Tooltip("segment", title="Passenger Segment"),
                    alt.Tooltip("days_prior", title="DfD"),
                    alt.Tooltip("bookings", format=".2f"),
                    *ratio_tooltips,
                ],
            )
            .properties(
                width=500,
                height=300,
            )
            .configure_axis(
                labelFontSize=12,
                titleFontSize=12,
            )
            .configure_legend(
                titleFontSize=12,
                labelFontSize=15,
            )
        )
    if also_df:
        return fig, df
    return fig

fig_carrier_load_factors 

fig_carrier_load_factors(
    summaries: dict[str, SummaryTables],
    raw_df: bool = False,
    load_measure: Literal[
        "sys_lf", "avg_leg_lf"
    ] = "sys_lf",
    orient: Literal["h", "v"] = "h",
    ratio: str | bool = "all",
    *,
    width: int = 500,
    also_df: bool = False,
    title: str | None = "_default_",
)

Generate a figure contrasting carrier load factors for one or more runs.

Parameters:

  • summaries (dict[str, SummaryTables]) –
  • raw_df (bool, default: False ) –
  • load_measure ((sys_lf, avg_leg_lf), default: 'sys_lf' ) –
  • orient ((h, v), default: 'h' ) –
  • ratio (bool or str, default: "all" ) –

    Add tooltip(s) giving the percentage change of each carrier's load factor to the load factor of the same carrier in the other summaries. Can be the key giving a specific summary to compare against, or 'all' to compare against all other summaries.

  • title (str, default: '_default_' ) –

    Title of the figure. Set to None for no title, otherwise a default title is used.

Returns:

  • Chart or DataFrame –
Source code in passengersim/contrast.py 
 958
 959
 960
 961
 962
 963
 964
 965
 966
 967
 968
 969
 970
 971
 972
 973
 974
 975
 976
 977
 978
 979
 980
 981
 982
 983
 984
 985
 986
 987
 988
 989
 990
 991
 992
 993
 994
 995
 996
 997
 998
 999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
@report_figure
def fig_carrier_load_factors(
    summaries: dict[str, SummaryTables],
    raw_df: bool = False,
    load_measure: Literal["sys_lf", "avg_leg_lf"] = "sys_lf",
    orient: Literal["h", "v"] = "h",
    ratio: str | bool = "all",
    *,
    width: int = 500,
    also_df: bool = False,
    title: str | None = "_default_",
):
    """
    Generate a figure contrasting carrier load factors for one or more runs.

    Parameters
    ----------
    summaries : dict[str, SummaryTables]
    raw_df : bool, default False
    load_measure : {'sys_lf', 'avg_leg_lf'}, default 'sys_lf'
    orient : {'h', 'v'}, default 'h'
    ratio : bool or str, default "all"
        Add tooltip(s) giving the percentage change of each carrier's load factor
        to the load factor of the same carrier in the other summaries.  Can be
        the key giving a specific summary to compare against, or 'all' to
        compare against all other summaries.
    title : str, optional
        Title of the figure. Set to `None` for no title, otherwise a default
        title is used.

    Returns
    -------
    alt.Chart or pd.DataFrame
    """
    measure_name = {
        "sys_lf": "System Load Factor",
        "avg_leg_lf": "Leg Load factor",
    }.get(load_measure, "Load Factor")
    if title == "_default_":
        title = f"Carrier {measure_name}s"
    df = _assemble(summaries, "carrier_load_factors", load_measure=load_measure)
    source_order = list(summaries.keys())
    if raw_df:
        if title:
            df.attrs["title"] = title
        return df
    fig = _fig_carrier_measure(
        df,
        source_order,
        load_measure=load_measure,
        measure_name=measure_name,
        measure_format=".2f",
        orient=orient,
        title=title,
        ratio=ratio,
        ratio_all=(ratio == "all"),
        width=width,
    )
    if also_df:
        if title:
            df.attrs["title"] = title
        return fig, df
    return fig

fig_carrier_local_share 

fig_carrier_local_share(
    summaries,
    load_measure: Literal[
        "bookings", "leg_pax"
    ] = "bookings",
    raw_df=False,
    orient: Literal["h", "v"] = "h",
    ratio: str | bool = "all",
    *,
    width: int = 500,
    also_df: bool = False,
)

Generate a figure contrasting carrier local shares for one or more runs.

Parameters:

  • summaries (dict[str, SummaryTables]) –
  • raw_df (bool, default: False ) –
  • orient ((h, v), default: 'h' ) –
  • ratio (bool or str, default: True ) –

    Add tooltip(s) giving the percentage change of each carrier's local share to the local share of the same carrier in the other summaries. Can be the key giving a specific summary to compare against, or 'all' to compare against all other summaries.

Returns:

  • Chart or DataFrame –
Source code in passengersim/contrast.py 
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
@report_figure
def fig_carrier_local_share(
    summaries,
    load_measure: "Literal['bookings', 'leg_pax']" = "bookings",
    raw_df=False,
    orient: Literal["h", "v"] = "h",
    ratio: str | bool = "all",
    *,
    width: int = 500,
    also_df: bool = False,
):
    """
    Generate a figure contrasting carrier local shares for one or more runs.

    Parameters
    ----------
    summaries : dict[str, SummaryTables]
    raw_df : bool, default False
    orient : {'h', 'v'}, default 'h'
    ratio : bool or str, default True
        Add tooltip(s) giving the percentage change of each carrier's local share
        to the local share of the same carrier in the other summaries.  Can be
        the key giving a specific summary to compare against, or 'all' to
        compare against all other summaries.

    Returns
    -------
    alt.Chart or pd.DataFrame
    """
    measure_name = "Local Percent of Bookings" if load_measure == "bookings" else "Local Percent of Leg Passengers"
    m = "local_pct_bookings" if load_measure == "bookings" else "local_pct_leg_pax"
    df = _assemble(summaries, "carrier_local_share", load_measure=load_measure)
    source_order = list(summaries.keys())
    if raw_df:
        df.attrs["title"] = "Carrier Local Share"
        return df
    fig = _fig_carrier_measure(
        df,
        source_order,
        load_measure=m,
        measure_name=measure_name,
        measure_format=".2f",
        orient=orient,
        title=f"Carrier {measure_name}",
        ratio=ratio,
        ratio_all=(ratio == "all"),
        width=width,
    )
    if also_df:
        df.attrs["title"] = "Carrier Local Share"
        return fig, df
    return fig

fig_carrier_rasm 

fig_carrier_rasm(
    summaries,
    raw_df=False,
    orient: Literal["h", "v"] = "h",
    ratio: str | bool = "all",
    *,
    width: int = 500,
    also_df: bool = False,
)

Generate a figure contrasting carrier RASM for one or more runs.

Parameters:

  • summaries (dict[str, SummaryTables]) –
  • raw_df (bool, default: False ) –
  • orient ((h, v), default: 'h' ) –
  • ratio (bool or str, default: True ) –

    Add tooltip(s) giving the percentage change of each carrier's yield to the yield of the same carrier in the other summaries. Can be the key giving a specific summary to compare against, or 'all' to compare against all other summaries.

Returns:

  • Chart or DataFrame –
Source code in passengersim/contrast.py 
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
@report_figure
def fig_carrier_rasm(
    summaries,
    raw_df=False,
    orient: Literal["h", "v"] = "h",
    ratio: str | bool = "all",
    *,
    width: int = 500,
    also_df: bool = False,
):
    """
    Generate a figure contrasting carrier RASM for one or more runs.

    Parameters
    ----------
    summaries : dict[str, SummaryTables]
    raw_df : bool, default False
    orient : {'h', 'v'}, default 'h'
    ratio : bool or str, default True
        Add tooltip(s) giving the percentage change of each carrier's yield
        to the yield of the same carrier in the other summaries.  Can be
        the key giving a specific summary to compare against, or 'all' to
        compare against all other summaries.

    Returns
    -------
    alt.Chart or pd.DataFrame
    """
    df = _assemble(summaries, "carrier_rasm")
    source_order = list(summaries.keys())
    if raw_df:
        df.attrs["title"] = "Carrier RASM"
        return df
    fig = _fig_carrier_measure(
        df,
        source_order,
        load_measure="rasm",
        measure_name="Revenue per Available Seat Mile",
        measure_format="$.4f",
        orient=orient,
        title="Carrier Revenue per Available Seat Mile (RASM)",
        ratio=ratio,
        ratio_all=(ratio == "all"),
        width=width,
    )
    if also_df:
        df.attrs["title"] = "Carrier RASM"
        return fig, df
    return fig

fig_carrier_revenues 

fig_carrier_revenues(
    summaries,
    raw_df=False,
    orient: Literal["h", "v"] = "h",
    ratio: str | bool = "all",
    *,
    width: int = 500,
    also_df: bool = False,
)

Generate a figure contrasting carrier revenues for one or more runs.

Parameters:

  • summaries (dict[str, SummaryTables]) –
  • raw_df (bool, default: False ) –

    Return only the raw data used to generate the figure.

  • orient ((h, v), default: 'h' ) –
  • ratio (bool or str, default: True ) –

    Add tooltip(s) giving the percentage change of each carrier's revenue to the revenue of the same carrier in the other summaries. Can be the key giving a specific summary to compare against, or 'all' to compare against all other summaries.

  • also_df (bool, default: False ) –

    Return the raw data used to generate the figure in addition to the figure itself.

Returns:

  • Chart or DataFrame or tuple[Chart, DataFrame] –
Source code in passengersim/contrast.py 
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
@report_figure
def fig_carrier_revenues(
    summaries,
    raw_df=False,
    orient: Literal["h", "v"] = "h",
    ratio: str | bool = "all",
    *,
    width: int = 500,
    also_df: bool = False,
):
    """
    Generate a figure contrasting carrier revenues for one or more runs.

    Parameters
    ----------
    summaries : dict[str, SummaryTables]
    raw_df : bool, default False
        Return only the raw data used to generate the figure.
    orient : {'h', 'v'}, default 'h'
    ratio : bool or str, default True
        Add tooltip(s) giving the percentage change of each carrier's revenue
        to the revenue of the same carrier in the other summaries.  Can be
        the key giving a specific summary to compare against, or 'all' to
        compare against all other summaries.
    also_df : bool, default False
        Return the raw data used to generate the figure in addition to the
        figure itself.

    Returns
    -------
    alt.Chart or pd.DataFrame or tuple[alt.Chart, pd.DataFrame]
    """
    df = _assemble(summaries, "carrier_revenues")
    source_order = list(summaries.keys())
    if raw_df:
        df.attrs["title"] = "Carrier Revenues"
        return df
    fig = _fig_carrier_measure(
        df,
        source_order,
        load_measure="avg_rev",
        measure_name="Revenue ($)",
        measure_format="$.4s",
        orient=orient,
        title="Carrier Revenues",
        ratio=ratio,
        ratio_all=(ratio == "all"),
        width=width,
    )
    if also_df:
        df.attrs["title"] = "Carrier Revenues"
        return fig, df
    return fig

fig_carrier_total_bookings 

fig_carrier_total_bookings(
    summaries,
    raw_df=False,
    orient: Literal["h", "v"] = "h",
    ratio: str | bool = "all",
    *,
    width: int = 500,
    also_df: bool = False,
)

Generate a figure contrasting carrier total bookings for one or more runs.

Parameters:

  • summaries (dict[str, SummaryTables]) –
  • raw_df (bool, default: False ) –
  • orient ((h, v), default: 'h' ) –
  • ratio (bool or str, default: "all" ) –

    Add tooltip(s) giving the percentage change of each carrier's bookings to the bookings of the same carrier in the other summaries. Can be the key giving a specific summary to compare against, or 'all' to compare against all other summaries.

Returns:

  • Chart or DataFrame –
Source code in passengersim/contrast.py 
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
@report_figure
def fig_carrier_total_bookings(
    summaries,
    raw_df=False,
    orient: Literal["h", "v"] = "h",
    ratio: str | bool = "all",
    *,
    width: int = 500,
    also_df: bool = False,
):
    """
    Generate a figure contrasting carrier total bookings for one or more runs.

    Parameters
    ----------
    summaries : dict[str, SummaryTables]
    raw_df : bool, default False
    orient : {'h', 'v'}, default 'h'
    ratio : bool or str, default "all"
        Add tooltip(s) giving the percentage change of each carrier's bookings
        to the bookings of the same carrier in the other summaries.  Can be
        the key giving a specific summary to compare against, or 'all' to
        compare against all other summaries.

    Returns
    -------
    alt.Chart or pd.DataFrame
    """

    df = _assemble(summaries, "carrier_total_bookings")
    # correct for variable name differences; the "avg_sold" column
    # is called "sold" in some older summaries
    if "sold" in df.columns:
        if "avg_sold" in df.columns:
            df["avg_sold"] = df["avg_sold"].fillna(df["sold"])
            df = df.drop(columns="sold")
        else:
            df = df.rename(columns={"sold": "avg_sold"})
    source_order = list(summaries.keys())
    if raw_df:
        df.attrs["title"] = "Carrier Total Bookings"
        return df
    fig = _fig_carrier_measure(
        df,
        source_order,
        load_measure="avg_sold",
        measure_name="Bookings",
        measure_format=".4s",
        orient=orient,
        title="Carrier Total Bookings",
        ratio=ratio,
        ratio_all=(ratio == "all"),
        width=width,
    )
    if also_df:
        df.attrs["title"] = "Carrier Total Bookings"
        return fig, df
    return fig

fig_carrier_yields 

fig_carrier_yields(
    summaries,
    raw_df=False,
    orient: Literal["h", "v"] = "h",
    ratio: str | bool = "all",
    *,
    width: int = 500,
    also_df: bool = False,
)

Generate a figure contrasting carrier yields for one or more runs.

Parameters:

  • summaries (dict[str, SummaryTables]) –
  • raw_df (bool, default: False ) –
  • orient ((h, v), default: 'h' ) –
  • ratio (bool or str, default: True ) –

    Add tooltip(s) giving the percentage change of each carrier's yield to the yield of the same carrier in the other summaries. Can be the key giving a specific summary to compare against, or 'all' to compare against all other summaries.

Returns:

  • Chart or DataFrame –
Source code in passengersim/contrast.py 
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
@report_figure
def fig_carrier_yields(
    summaries,
    raw_df=False,
    orient: Literal["h", "v"] = "h",
    ratio: str | bool = "all",
    *,
    width: int = 500,
    also_df: bool = False,
):
    """
    Generate a figure contrasting carrier yields for one or more runs.

    Parameters
    ----------
    summaries : dict[str, SummaryTables]
    raw_df : bool, default False
    orient : {'h', 'v'}, default 'h'
    ratio : bool or str, default True
        Add tooltip(s) giving the percentage change of each carrier's yield
        to the yield of the same carrier in the other summaries.  Can be
        the key giving a specific summary to compare against, or 'all' to
        compare against all other summaries.

    Returns
    -------
    alt.Chart or pd.DataFrame
    """

    df = _assemble(summaries, "carrier_yields")
    source_order = list(summaries.keys())
    if raw_df:
        df.attrs["title"] = "Carrier Yields"
        return df
    fig = _fig_carrier_measure(
        df,
        source_order,
        load_measure="yield",
        measure_name="Yield ($)",
        measure_format="$.4f",
        orient=orient,
        title="Carrier Yields",
        ratio=ratio,
        ratio_all=(ratio == "all"),
        width=width,
    )
    if also_df:
        df.attrs["title"] = "Carrier Yields"
        return fig, df
    return fig

fig_cp_segmentation 

fig_cp_segmentation(
    summaries: Contrast,
    *,
    raw_df: bool = False,
    title: str | None = "Continuous Price Segmentation",
    also_df: bool = False,
    height: int = 600,
    width: int = 300,
) -> Chart | tuple[Chart, DataFrame] | DataFrame

Generate a figure contrasting continuous price segmentation for one or more runs.

Parameters:

  • summaries (dict[str, SummaryTables]) –

    A dictionary of summary tables for different runs.

  • raw_df (bool, default: False ) –

    If True, return the raw data used to generate the figure.

  • title (str, default: "Continuous Price Segmentation" ) –

    The title of the figure.

  • also_df (bool, default: False ) –

    If True, return the raw data used to generate the figure in addition to the figure itself.

  • height (int, default: 600 ) –

    The height of each facet panel of the figure, in pixels.

  • width (int, default: 300 ) –

    The width of each facet panel of the figure, in pixels.

Returns:

  • Chart or tuple[Chart, DataFrame] or DataFrame –

    The generated Altair chart or the raw data used to generate the figure.

Source code in passengersim/contrast.py 
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
@report_figure
def fig_cp_segmentation(
    summaries: Contrast,
    *,
    raw_df: bool = False,
    title: str | None = "Continuous Price Segmentation",
    also_df: bool = False,
    height: int = 600,
    width: int = 300,
) -> alt.Chart | tuple[alt.Chart, pd.DataFrame] | pd.DataFrame:
    """
    Generate a figure contrasting continuous price segmentation for one or more runs.

    Parameters
    ----------
    summaries : dict[str, SummaryTables]
        A dictionary of summary tables for different runs.
    raw_df : bool, default False
        If True, return the raw data used to generate the figure.
    title : str, default "Continuous Price Segmentation"
        The title of the figure.
    also_df : bool, default False
        If True, return the raw data used to generate the figure in addition to the figure itself.
    height : int, default 600
        The height of each facet panel of the figure, in pixels.
    width : int, default 300
        The width of each facet panel of the figure, in pixels.

    Returns
    -------
    alt.Chart or tuple[alt.Chart, pd.DataFrame] or pd.DataFrame
        The generated Altair chart or the raw data used to generate the figure.
    """
    import altair as alt

    df = pd.concat(
        {k: s.cp_segmentation for k, s in summaries.items() if s.cp_segmentation is not None}, names=["source"]
    )
    source_order = list(summaries.keys())

    df = df.reset_index()[["source", "carrier", "booking_class", "sold", "cp_sold"]]
    if raw_df:
        return df
    df["Zero"] = 0

    base_chart = alt.Chart(df)

    # Add a solid border to the "Continuous Priced" bars using stroke/strokeWidth
    chart = (
        base_chart.mark_bar()
        .encode(
            y=alt.Y("booking_class:N", sort=None, title="Booking Class"),
            x=alt.X("sold:Q", title="Total Sold", stack=False, axis=alt.Axis()),
            color=alt.Color("source:N", title="Source"),
            yOffset=alt.YOffset("source:N", title="Source", sort=source_order),
            tooltip=[
                alt.Tooltip("source:N", title="Source"),
                alt.Tooltip("carrier:N", title="Carrier"),
                alt.Tooltip("booking_class:N", title="Booking Class"),
                alt.Tooltip("sold:Q", title="Total Sold", format=","),
                alt.Tooltip("cp_sold:Q", title="Continuous Priced Sold", format=","),
            ],
        )
        .properties(width=width, height=height)
    )

    chart_cp = (
        base_chart.transform_filter(
            alt.datum.cp_sold > 0  # Only show nonzero counts for cp_sold
        )
        .mark_errorbar(extent="ci", ticks=True)
        .encode(
            y=alt.Y("booking_class:N", sort=source_order, title="Booking Class"),
            x=alt.X("cp_sold:Q", title="Continuous Priced Sold"),
            x2=alt.X2("Zero:Q", title="Zero"),
            color=alt.value("black"),
            yOffset=alt.YOffset("source:N", title="Source", sort=source_order),
            tooltip=[
                alt.Tooltip("source:N", title="Source"),
                alt.Tooltip("carrier:N", title="Carrier"),
                alt.Tooltip("booking_class:N", title="Booking Class"),
                alt.Tooltip("sold:Q", title="Total Sold", format=","),
                alt.Tooltip("cp_sold:Q", title="Continuous Priced Sold", format=","),
            ],
            strokeWidth=alt.value(2),  # Set stroke width for the error bars
        )
        .properties(width=width, height=height)
    )

    fig = (chart + chart_cp).facet(
        facet=alt.Facet("carrier:N", title="Carrier"),
    )

    if title:
        fig = fig.properties(title=title)

    if also_df:
        return fig, df
    else:
        return fig

fig_demand_to_come 

fig_demand_to_come(
    summaries: Contrast,
    func: Literal["mean", "std"]
    | list[Literal["mean", "std"]] = "mean",
    *,
    raw_df=False,
    title: str | None = "Demand to Come",
    also_df: bool = False,
)
Source code in passengersim/contrast.py 
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
@report_figure
def fig_demand_to_come(
    summaries: Contrast,
    func: Literal["mean", "std"] | list[Literal["mean", "std"]] = "mean",
    *,
    raw_df=False,
    title: str | None = "Demand to Come",
    also_df: bool = False,
):
    def dtc_seg(s):
        if s is None:
            return pd.DataFrame(columns=["segment"])
        sum_on = []
        if "orig" in s.index.names:
            sum_on.append("orig")
        if "dest" in s.index.names:
            sum_on.append("dest")
        if sum_on:
            s = s.groupby(s.index.names.difference(sum_on)).sum()
        return s

    def get_values(s, which="mean"):
        if isinstance(s, SummaryTables):
            result = getattr(s, "demand_to_come_summary", None)
            if result is None:
                result = dtc_seg(s.demand_to_come).groupby("segment", observed=False)
                result = result.mean() if which == "mean" else result.std()
                result = result.stack()
                return result
            else:
                if which == "mean":
                    return result["mean_future_demand"]
                elif which == "std":
                    return result["stdev_future_demand"]
                else:
                    raise ValueError(f"which must be in [mean, std] not {which}")
        elif isinstance(s, SimTabDemandToCome):
            result = s.demand_to_come_summary
            if which == "mean":
                return result["mean_future_demand"]
            elif which == "std":
                return result["stdev_future_demand"]
            else:
                raise ValueError(f"which must be in [mean, std] not {which}")

    if isinstance(func, list):
        if raw_df:
            raise NotImplementedError
        fig = fig_demand_to_come(summaries, func[0], raw_df=raw_df, title=None)
        for f in func[1:]:
            fig |= fig_demand_to_come(summaries, f, raw_df=raw_df, title=None)
        if title:
            fig = fig.properties(title=title)
        return fig

    if func == "mean":
        y_title = "Mean Demand to Come"
        demand_to_come_by_segment = summaries.apply(lambda s: get_values(s, "mean"), axis=1, warn_if_missing=True)
        demand_to_come_by_segment.index.names = ["segment", "days_prior"]
        df = demand_to_come_by_segment.stack().rename("dtc").reset_index()
    elif func == "std":
        y_title = "Std Dev Demand to Come"
        demand_to_come_by_segment = summaries.apply(lambda s: get_values(s, "std"), axis=1, warn_if_missing=True)
        demand_to_come_by_segment.index.names = ["segment", "days_prior"]
        df = demand_to_come_by_segment.stack().rename("dtc").reset_index()
    else:
        raise ValueError(f"func must be in [mean, std] not {func}")
    if raw_df:
        return df
    fig = (
        alt.Chart(df)
        .mark_line()
        .encode(
            x=alt.X("days_prior:O").scale(reverse=True).title("Days Prior to Departure"),
            y=alt.Y("dtc:Q").title(y_title),
            color="segment:N",
            strokeDash="source:N",
        )
    )
    if title:
        fig = fig.properties(title=title)
    if also_df:
        return fig, df
    return fig

fig_displacement_history 

fig_displacement_history(
    summaries,
    *,
    by_carrier: bool | str = True,
    show_stdev: float | bool | None = None,
    raw_df: bool = False,
    title: str | None = "Displacement Cost History",
    also_df: bool = False,
)
Source code in passengersim/contrast.py 
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
@report_figure
def fig_displacement_history(
    summaries,
    *,
    by_carrier: bool | str = True,
    show_stdev: float | bool | None = None,
    raw_df: bool = False,
    title: str | None = "Displacement Cost History",
    also_df: bool = False,
):
    if not isinstance(by_carrier, str) and show_stdev:
        raise NotImplementedError(
            "contrast.fig_displacement_history with show_stdev requires looking at a single carrier (set `by_carrier`)"
        )
    df = _assemble(
        summaries,
        "displacement_history",
        by_carrier=by_carrier,
        show_stdev=show_stdev,
    )
    if raw_df:
        return df

    line_encoding = dict(
        x=alt.X("days_prior:Q").scale(reverse=True).title("Days Prior to Departure"),
        y=alt.Y("displacement_mean", title="Displacement Cost"),
        color="source:N",
    )
    chart = alt.Chart(df)
    fig = chart.mark_line(interpolate="step-before").encode(**line_encoding)
    if show_stdev:
        area_encoding = dict(
            x=alt.X("days_prior:Q").scale(reverse=True).title("Days Prior to Departure"),
            y=alt.Y("displacement_lower:Q", title="Displacement Cost"),
            y2=alt.Y2("displacement_upper:Q", title="Displacement Cost"),
            color="source:N",
        )
        bound = chart.mark_area(
            opacity=0.1,
            interpolate="step-before",
        ).encode(**area_encoding)
        bound_line = chart.mark_line(opacity=0.4, strokeDash=[5, 5], interpolate="step-before").encode(
            x=alt.X("days_prior:Q").scale(reverse=True).title("Days Prior to Departure"),
            color="source:N",
        )
        top_line = bound_line.encode(y=alt.Y("displacement_lower:Q", title="Displacement Cost"))
        bottom_line = bound_line.encode(y=alt.Y("displacement_upper:Q", title="Displacement Cost"))
        fig = fig + bound + top_line + bottom_line
    if not isinstance(by_carrier, str):
        fig = fig.properties(height=125, width=225).facet(facet="carrier:N", columns=2)
        if title:
            fig = fig.properties(title=title)
    else:
        if title:
            title = f"{title} ({by_carrier})"
            fig = fig.properties(title=title)
    if also_df:
        return fig, df
    return fig

fig_fare_class_mix 

fig_fare_class_mix(
    summaries,
    *,
    raw_df=False,
    also_df: bool = False,
    label_threshold: float = 0.06,
)
Source code in passengersim/contrast.py 
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
@report_figure
def fig_fare_class_mix(summaries, *, raw_df=False, also_df: bool = False, label_threshold: float = 0.06):
    df = _assemble(summaries, "fare_class_mix")
    source_order = list(summaries.keys())
    if raw_df:
        df.attrs["title"] = "Carrier Fare Class Mix"
        return df
    import altair as alt

    label_threshold_value = df.groupby(["carrier", "source"]).avg_sold.sum().max() * label_threshold
    chart = alt.Chart(df).transform_calculate(
        halfsold="datum.avg_sold / 2.0",
    )
    bars = chart.mark_bar().encode(
        x=alt.X("source:N", title="Source", sort=source_order),
        y=alt.Y("avg_sold:Q", title="Seats").stack("zero"),
        color="booking_class",
        tooltip=[
            "source",
            "booking_class",
            alt.Tooltip("avg_sold", format=".2f"),
        ],
    )
    text = chart.mark_text(dx=0, dy=3, color="white", baseline="top").encode(
        x=alt.X("source:N", title="Source", sort=source_order),
        y=alt.Y("avg_sold:Q", title="Seats").stack("zero"),
        text=alt.Text("avg_sold:Q", format=".2f"),
        opacity=alt.condition(
            f"datum.avg_sold < {label_threshold_value:.3f}",
            alt.value(0),
            alt.value(1),
        ),
        order=alt.Order("booking_class:N", sort="descending"),
    )
    fig = (
        (bars + text)
        .properties(
            width=200,
            height=300,
        )
        .facet(
            column=alt.Column("carrier:N", title="Carrier"),
            title="Carrier Fare Class Mix",
        )
    )
    if also_df:
        df.attrs["title"] = "Carrier Fare Class Mix"
        return fig, df
    return fig

fig_leg_forecasts 

fig_leg_forecasts(
    summaries,
    raw_df=False,
    by_leg_id=None,
    by_class: bool | str = True,
    of: Literal["mu", "sigma"]
    | list[Literal["mu", "sigma"]] = "mu",
    agg_booking_classes: bool = False,
    also_df: bool = False,
)
Source code in passengersim/contrast.py 
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
@report_figure
def fig_leg_forecasts(
    summaries,
    raw_df=False,
    by_leg_id=None,
    by_class: bool | str = True,
    of: Literal["mu", "sigma"] | list[Literal["mu", "sigma"]] = "mu",
    agg_booking_classes: bool = False,
    also_df: bool = False,
):
    if isinstance(of, list):
        if raw_df:
            raise NotImplementedError
        fig = fig_leg_forecasts(
            summaries,
            by_leg_id=by_leg_id,
            by_class=by_class,
            of=of[0],
            agg_booking_classes=agg_booking_classes,
        )
        for of_ in of[1:]:
            fig |= fig_leg_forecasts(
                summaries,
                by_leg_id=by_leg_id,
                by_class=by_class,
                of=of_,
                agg_booking_classes=agg_booking_classes,
            )
        title = f"Leg Forecasts {by_leg_id}"
        try:
            if by_leg_id:
                first_summary = next(iter(summaries.values()))
                leg_def = first_summary.legs.loc[by_leg_id]
                title += f": {leg_def['carrier']} {leg_def['flt_no']}"
                title += f" ({leg_def['orig']}-{leg_def['dest']})"
        except Exception:
            raise
        return fig.properties(title=title)
    df = _assemble(summaries, "leg_forecasts", by_leg_id=by_leg_id, by_class=by_class, of=of)
    color = "booking_class:N"
    if isinstance(by_class, str):
        color = "source:N"
    if agg_booking_classes or not by_class:
        color = "source:N"
        if of == "mu":
            df = df.groupby(["source", "leg_id", "days_prior"]).forecast_mean.sum().reset_index()
        elif of == "sigma":

            def sum_sigma(x):
                return np.sqrt(sum(x**2))

            df = df.groupby(["source", "leg_id", "days_prior"]).forecast_stdev.apply(sum_sigma).reset_index()
    if raw_df:
        df.attrs["title"] = "Average Leg Forecasts"
        return df
    fig = _fig_forecasts(
        df,
        facet_on="flt_no" if not isinstance(by_leg_id, int) else None,
        y="forecast_mean" if of == "mu" else "forecast_stdev",
        y_title="Mean Demand Forecast" if of == "mu" else "Std Dev Demand Forecast",
        color=color,
    )
    if also_df:
        df.attrs["title"] = "Average Leg Forecasts"
        return fig, df
    return fig

fig_path_forecasts 

fig_path_forecasts(
    summaries,
    raw_df=False,
    by_path_id=None,
    path_names: dict | None = None,
    agg_booking_classes: bool = False,
    by_class: bool | str = True,
    of: ForecastOfT | list[ForecastOfT] = "mu",
    also_df: bool = False,
)
Source code in passengersim/contrast.py 
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
@report_figure
def fig_path_forecasts(
    summaries,
    raw_df=False,
    by_path_id=None,
    path_names: dict | None = None,
    agg_booking_classes: bool = False,
    by_class: bool | str = True,
    of: ForecastOfT | list[ForecastOfT] = "mu",
    also_df: bool = False,
):
    if isinstance(of, list):
        if raw_df:
            df = {
                _of: fig_path_forecasts(
                    summaries,
                    by_path_id=by_path_id,
                    path_names=path_names,
                    by_class=by_class,
                    of=of[0],
                    raw_df=raw_df,
                )
                for _of in of
            }
            return pd.concat(df, axis=0, names=["measurement"]).reset_index(0)
        fig = fig_path_forecasts(
            summaries,
            by_path_id=by_path_id,
            path_names=path_names,
            by_class=by_class,
            of=of[0],
        )
        for of_ in of[1:]:
            fig |= fig_path_forecasts(
                summaries,
                by_path_id=by_path_id,
                path_names=path_names,
                by_class=by_class,
                of=of_,
            )
        if by_path_id:
            title = f"Path {by_path_id} Forecasts"
        else:
            title = "Path Forecasts"
        try:
            if by_path_id:
                first_summary = next(iter(summaries.values()))
                path_def = first_summary.paths.loc[by_path_id]
                title += f" ({path_def['orig']}~{path_def['dest']})"
                for leg_id in first_summary.path_legs.query(f"path_id == {by_path_id}").leg_id:
                    leg_def = first_summary.legs.loc[leg_id]
                    title += f", {leg_def['carrier']} {leg_def['flt_no']} ({leg_def['orig']}-{leg_def['dest']})"
        except Exception:
            raise
        return fig.properties(title=title)
    df = _assemble(summaries, "path_forecasts", by_path_id=by_path_id, of=of, by_class=by_class)
    list(summaries.keys())
    if path_names is not None:
        df["path_id"] = df["path_id"].apply(lambda x: path_names.get(x, str(x)))
    color = "booking_class:N"
    if isinstance(by_class, str):
        color = "source:N"
    if agg_booking_classes:
        if of == "mu":
            df = df.groupby(["source", "path_id", "days_prior"]).forecast_mean.sum().reset_index()
        elif of == "sigma":

            def sum_sigma(x):
                return np.sqrt(sum(x**2))

            df = df.groupby(["source", "path_id", "days_prior"]).forecast_stdev.apply(sum_sigma).reset_index()
        elif of == "closed":
            df = df.groupby(["source", "path_id", "days_prior"]).forecast_closed_in_tf.mean().reset_index()
    if raw_df:
        if of == "mu":
            df.attrs["title"] = "Average Path Forecast Means"
        elif of == "sigma":
            df.attrs["title"] = "Average Path Forecast Standard Deviations"
        elif of == "closed":
            df.attrs["title"] = "Average Path Forecast Closed in Timeframe"
        return df
    if of == "mu":
        y = "forecast_mean"
        y_title = "Mean Demand Forecast"
    elif of == "sigma":
        y = "forecast_stdev"
        y_title = "Std Dev Demand Forecast"
    elif of == "closed":
        y = "forecast_closed_in_tf"
        y_title = "Mean Time Frame Closed of Demand Forecast"
    elif of == "adj_price":
        y = "adjusted_price"
        y_title = "Mean Adjusted Fare"
    else:
        raise NotImplementedError

    # use ordinal data type for DCP labels unless
    # the underlying data is daily, then use Q
    rrd_ntype: Literal["O", "Q"] = "O"
    if len(df["days_prior"].value_counts()) > 30:
        rrd_ntype = "Q"
    fig = _fig_forecasts(
        df,
        facet_on="path_id" if not isinstance(by_path_id, int) else None,
        y=y,
        y_title=y_title,
        color=color,
        rrd_ntype=rrd_ntype,
    )
    if also_df:
        if of == "mu":
            df.attrs["title"] = "Average Path Forecast Means"
        elif of == "sigma":
            df.attrs["title"] = "Average Path Forecast Standard Deviations"
        elif of == "closed":
            df.attrs["title"] = "Average Path Forecast Closed in Timeframe"
        return fig, df
    return fig

fig_segmentation_by_timeframe 

fig_segmentation_by_timeframe(
    summaries: dict[str, SummaryTables],
    metric: Literal["bookings", "revenue"],
    by_carrier: bool | str = True,
    by_class: bool | str = False,
    raw_df=False,
    source_labels: bool = False,
    ratio: str | bool = False,
    also_df: bool = False,
) -> Chart | DataFrame

Generate a figure contrasting segmentation by timeframe for one or more runs.

Parameters:

  • summaries (dict[str, SummaryTables]) –

    One or more SummaryTables to compare. The keys of this dictionary are the text names used to label the "source" for each set of data in the figure.

  • metric ((bookings, revenue), default: 'bookings' ) –

    The metric to display for the segmentation.

  • by_carrier (bool or str, default: True ) –

    Whether to differentiate carriers by colors (the default) or give the name of a particular carrier as a string to filter the results shown in the figure to only that one carrier.

  • by_class (bool or str, default: False ) –

    Whether to differentiate booking class by colors (the default) or give the name of a particular booking class as a string to filter the results shown in the figure to only that one booking class.

  • raw_df (bool, default: False ) –

    Set to true to return the raw dataframe used to generate the figure, instead of the figure itself.

  • source_labels (bool, default: False ) –

    Write source labels above the columns of the figure. Source labels are also available as tool tips, but if the figure is being shared as an image without tooltips, the source labels may make it easier to interpret.

  • ratio (str or bool, default: False ) –

    Compute ratios against a reference point and display them in tooltips.

Other Parameters:

  • report (Reporter) –

    Giving a reporter for this keyword only argument allow you to automatically append this figure to the report (in addition to returning it for display or other processing).

  • trace (ExcelWriter or (ExcelWriter, str)) –

    Write the raw dataframe backing this figure to the Excel workbook.

Source code in passengersim/contrast.py 
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
@report_figure
def fig_segmentation_by_timeframe(
    summaries: dict[str, SummaryTables],
    metric: Literal["bookings", "revenue"],
    by_carrier: bool | str = True,
    by_class: bool | str = False,
    raw_df=False,
    source_labels: bool = False,
    ratio: str | bool = False,
    also_df: bool = False,
) -> alt.Chart | pd.DataFrame:
    """
    Generate a figure contrasting segmentation by timeframe for one or more runs.

    Parameters
    ----------
    summaries : dict[str, SummaryTables]
        One or more SummaryTables to compare. The keys of this dictionary are the
        text names used to label the "source" for each set of data in the figure.
    metric : {'bookings', 'revenue'}
        The metric to display for the segmentation.
    by_carrier : bool or str, default True
        Whether to differentiate carriers by colors (the default) or give the name
        of a particular carrier as a string to filter the results shown in the
        figure to only that one carrier.
    by_class : bool or str, default False
        Whether to differentiate booking class by colors (the default) or give the
        name of a particular booking class as a string to filter the results shown
        in the figure to only that one booking class.
    raw_df : bool, default False
        Set to true to return the raw dataframe used to generate the figure, instead
        of the figure itself.
    source_labels : bool, default False
        Write source labels above the columns of the figure. Source labels are also
        available as tool tips, but if the figure is being shared as an image without
        tooltips, the source labels may make it easier to interpret.
    ratio : str or bool, default False
        Compute ratios against a reference point and display them in tooltips.

    Other Parameters
    ----------------
    report : xmle.Reporter, optional
        Giving a reporter for this keyword only argument allow you to automatically
        append this figure to the report (in addition to returning it for display
        or other processing).
    trace : pd.ExcelWriter or (pd.ExcelWriter, str), optional
        Write the raw dataframe backing this figure to the Excel workbook.
    """
    if by_carrier is True and by_class is True:
        raise NotImplementedError("comparing by both class and carrier is messy")
    df = _assemble(
        summaries,
        "segmentation_by_timeframe",
        metric=metric,
        by_carrier=by_carrier,
        by_class=by_class,
    )
    source_order = list(summaries.keys())

    title = f"{metric.title()} by Timeframe"
    if by_class is True:
        title = f"{metric.title()} by Timeframe and Booking Class"
    title_annot = []
    if isinstance(by_carrier, str):
        title_annot.append(by_carrier)
    if isinstance(by_class, str):
        title_annot.append(f"Class {by_class}")
    if title_annot:
        title = f"{title} ({', '.join(title_annot)})"

    against = source_order[0]
    ratio_tooltips = ()
    if ratio:
        if isinstance(ratio, str):
            against = ratio
        idx = list({"source", "carrier", "segment", "days_prior", "booking_class"} & set(df.columns))
        df_ = df.set_index(idx)
        ratios = df_.div(df_.query(f"source == '{against}'").droplevel("source")) - 1.0
        ratios.columns = ["ratio"]
        df = df.join(ratios, on=idx)
        ratio_tooltips = (alt.Tooltip("ratio:Q", title=f"vs {against}", format=".3%"),)

    if raw_df:
        df.attrs["title"] = title
        return df

    if by_class:
        if isinstance(by_class, str):
            color = alt.Color("source:N", title="Source", sort=source_order).title("Source")
            tooltips = ()
        else:
            color = alt.Color("booking_class:N").title("Booking Class")
            tooltips = (alt.Tooltip("booking_class", title="Booking Class"),)
        chart = alt.Chart(df.sort_values("source", ascending=False))
        chart_1 = chart.mark_bar().encode(
            color=color,
            x=alt.X("days_prior:O").scale(reverse=True).title("Days Prior to Departure"),
            xOffset=alt.XOffset("source:N", title="Source", sort=source_order),
            y=alt.Y(metric, stack=True),
            tooltip=[
                alt.Tooltip("source:N", title="Source"),
                alt.Tooltip("segment", title="Passenger Type"),
                *tooltips,
                alt.Tooltip("days_prior", title="Days Prior"),
                alt.Tooltip(metric, format=".2f"),
                *ratio_tooltips,
            ],
        )
        chart_2 = chart.mark_text(
            color="#616161",
            yOffset=-2,
            angle=270,
            fontSize=8,
            baseline="middle",
            align="left",
        ).encode(
            text=alt.Text("source:N", title="Source"),
            x=alt.X("days_prior:O").scale(reverse=True).title("Days Prior to Departure"),
            xOffset=alt.XOffset("source:N", title="Source", sort=source_order),
            # shape=alt.Shape("source:N", title="Source", sort=source_order),
            y=alt.Y(f"sum({metric})", title=None),
        )
        fig = (
            ((chart_1 + chart_2) if source_labels else chart_1)
            .properties(
                width=500,
                height=200,
            )
            .facet(
                row=alt.Row("segment:N", title="Passenger Type"),
                title=title,
            )
        )
    elif by_carrier is True:
        fig = (
            alt.Chart(df.sort_values("source", ascending=False))
            .mark_bar()
            .encode(
                color=alt.Color("carrier:N").title("Carrier"),
                x=alt.X("days_prior:O").scale(reverse=True).title("Days Prior to Departure"),
                xOffset=alt.XOffset("source:N", title="Source", sort=source_order),
                y=alt.Y(metric, stack=True, title=metric.title()),
                tooltip=[
                    alt.Tooltip("source:N", title="Source"),
                    alt.Tooltip("segment", title="Passenger Type"),
                    alt.Tooltip("carrier", title="Carrier"),
                    alt.Tooltip("days_prior", title="Days Prior"),
                    alt.Tooltip(metric, format=".2f"),
                    *ratio_tooltips,
                ],
            )
            .properties(
                width=500,
                height=200,
            )
            .facet(
                row=alt.Row("segment:N", title="Passenger Type"),
                title=title,
            )
        )
    else:
        fig = (
            alt.Chart(df.sort_values("source", ascending=False), title=title)
            .mark_line()
            .encode(
                color=alt.Color("source:N", title="Source", sort=source_order),
                x=alt.X("days_prior:O").scale(reverse=True).title("Days Prior to Departure"),
                y=metric,
                strokeDash=alt.StrokeDash("segment").title("Passenger Type"),
                strokeWidth=alt.StrokeWidth("source:N", title="Source", sort=source_order),
                tooltip=[
                    alt.Tooltip("source:N", title="Source"),
                    alt.Tooltip("segment", title="Passenger Type"),
                    alt.Tooltip("days_prior", title="Days Prior"),
                    alt.Tooltip(metric, format=".2f"),
                    *ratio_tooltips,
                ],
            )
            .properties(
                width=500,
                height=300,
            )
            .configure_axis(
                labelFontSize=12,
                titleFontSize=12,
            )
            .configure_legend(
                titleFontSize=12,
                labelFontSize=15,
            )
        )
    if also_df:
        return fig, df
    return fig