google-meridian 1.1.6__py3-none-any.whl → 1.2.1__py3-none-any.whl

meridian/analysis/summarizer.py

@@ -77,6 +77,7 @@ class Summarizer:
       filepath: str,
       start_date: tc.Date = None,
       end_date: tc.Date = None,
+      use_kpi: bool = False,
   ):
     """Generates and saves the HTML results summary output.
 
@@ -86,15 +87,18 @@ class Summarizer:
       start_date: Optional start date selector, *inclusive*, in _yyyy-mm-dd_
         format.
       end_date: Optional end date selector, *inclusive* in _yyyy-mm-dd_ format.
+      use_kpi: If `True`, calculate the incremental KPI. Otherwise, calculate
+        the incremental revenue using the revenue per KPI (if available).
     """
     os.makedirs(filepath, exist_ok=True)
     with open(os.path.join(filepath, filename), 'w') as f:
-      f.write(self._gen_model_results_summary(start_date, end_date))
+      f.write(self._gen_model_results_summary(start_date, end_date, use_kpi))
 
   def _gen_model_results_summary(
       self,
       start_date: tc.Date = None,
       end_date: tc.Date = None,
+      use_kpi: bool = False,
   ) -> str:
     """Generate HTML results summary output (as sanitized content str)."""
     all_dates = self._meridian.input_data.time_coordinates.all_dates
@@ -140,6 +144,7 @@ class Summarizer:
     cards_htmls = self._create_cards_htmls(
         template_env,
         selected_times=selected_times,
+        use_kpi=use_kpi,
     )
 
     return html_template.render(
@@ -150,6 +155,7 @@ class Summarizer:
       self,
       template_env: jinja2.Environment,
       selected_times: Sequence[str] | None,
+      use_kpi: bool,
   ) -> Sequence[str]:
     """Creates the HTML snippets for cards in the summary page."""
     media_summary = visualizer.MediaSummary(
@@ -165,10 +171,13 @@ class Summarizer:
     )
     cards = [
         self._create_model_fit_card_html(
-            template_env, selected_times=selected_times
+            template_env, selected_times=selected_times, use_kpi=use_kpi
         ),
         self._create_outcome_contrib_card_html(
-            template_env, media_summary, selected_times=selected_times
+            template_env,
+            media_summary,
+            selected_times=selected_times,
+            use_kpi=use_kpi,
         ),
         self._create_performance_breakdown_card_html(
             template_env, media_summary
@@ -179,16 +188,17 @@ class Summarizer:
             media_summary=media_summary,
             media_effects=media_effects,
             reach_frequency=reach_frequency,
+            use_kpi=use_kpi,
         ),
     ]
     return cards
 
   def _create_model_fit_card_html(
-      self, template_env: jinja2.Environment, **kwargs
+      self, template_env: jinja2.Environment, use_kpi: bool, **kwargs
   ) -> str:
     """Creates the HTML snippet for the Model Fit card."""
     model_fit = self._model_fit
-    outcome = self._kpi_or_revenue()
+    outcome = self._kpi_or_revenue(use_kpi)
     expected_actual_outcome_chart = formatter.ChartSpec(
         id=summary_text.EXPECTED_ACTUAL_OUTCOME_CHART_ID,
         description=summary_text.EXPECTED_ACTUAL_OUTCOME_CHART_DESCRIPTION_FORMAT.format(
@@ -197,7 +207,9 @@ class Summarizer:
         chart_json=model_fit.plot_model_fit(**kwargs).to_json(),
     )
 
-    predictive_accuracy_table = self._predictive_accuracy_table_spec(**kwargs)
+    predictive_accuracy_table = self._predictive_accuracy_table_spec(
+        use_kpi=use_kpi, **kwargs
+    )
     insights = summary_text.MODEL_FIT_INSIGHTS_FORMAT
 
     return formatter.create_card_html(
@@ -207,9 +219,11 @@ class Summarizer:
         [expected_actual_outcome_chart, predictive_accuracy_table],
     )
 
-  def _predictive_accuracy_table_spec(self, **kwargs) -> formatter.TableSpec:
+  def _predictive_accuracy_table_spec(
+      self, use_kpi: bool, **kwargs
+  ) -> formatter.TableSpec:
     """Creates the HTML snippet for the predictive accuracy table."""
-    outcome = self._kpi_or_revenue()
+    outcome = self._kpi_or_revenue(use_kpi)
     model_diag = self._model_diagnostics
     table = model_diag.predictive_accuracy_table(column_var=c.METRIC, **kwargs)
 
@@ -270,9 +284,10 @@ class Summarizer:
       template_env: jinja2.Environment,
       media_summary: visualizer.MediaSummary,
       selected_times: Sequence[str] | None,
+      use_kpi: bool,
   ) -> str:
     """Creates the HTML snippet for the Outcome Contrib card."""
-    outcome = self._kpi_or_revenue()
+    outcome = self._kpi_or_revenue(use_kpi)
 
     num_selected_times = (
         self._meridian.n_times
@@ -442,9 +457,10 @@ class Summarizer:
       media_summary: visualizer.MediaSummary,
       media_effects: visualizer.MediaEffects,
       reach_frequency: visualizer.ReachAndFrequency | None,
+      use_kpi: bool,
   ) -> str:
     """Creates the HTML snippet for the Optimal Analyst card."""
-    outcome = self._kpi_or_revenue()
+    outcome = self._kpi_or_revenue(use_kpi)
     charts = []
     charts.append(
         formatter.ChartSpec(
@@ -457,6 +473,7 @@ class Summarizer:
                 selected_times=(
                     frozenset(selected_times) if selected_times else None
                 ),
+                use_kpi=use_kpi,
                 plot_separately=False,
                 include_ci=False,
                 num_channels_displayed=7,
@@ -524,9 +541,7 @@ class Summarizer:
         rf_channel=most_spend_rf_channel
     ).optimal_frequency
 
-  def _kpi_or_revenue(self) -> str:
-    if self._meridian.input_data.revenue_per_kpi is not None:
-      outcome_str = c.REVENUE
-    else:
-      outcome_str = c.KPI.upper()
-    return outcome_str
+  def _kpi_or_revenue(self, use_kpi: bool) -> str:
+    if use_kpi or self._meridian.input_data.revenue_per_kpi is None:
+      return c.KPI.upper()
+    return c.REVENUE

meridian/analysis/test_utils.py

@@ -2571,6 +2571,9 @@ ADSTOCK_DECAY_MEAN = np.array([1.0, 1.0, 0.8493, 0.8630, 0.7215])
 ORGANIC_ADSTOCK_DECAY_CI_HI = np.array([1.0, 0.9636, 0.9291, 0.8962, 0.8650])
 ORGANIC_ADSTOCK_DECAY_CI_LO = np.array([1.0, 0.6623, 0.4394, 0.2920, 0.1944])
 ORGANIC_ADSTOCK_DECAY_MEAN = np.array([1.0, 0.8076, 0.6633, 0.5537, 0.4693])
+ORGANIC_RF_ADSTOCK_DECAY_CI_HI = np.array([1.0, 0.9208, 0.8482, 0.781, 0.7202])
+ORGANIC_RF_ADSTOCK_DECAY_CI_LO = np.array([1.0, 0.6674, 0.4460, 0.2985, 0.2001])
+ORGANIC_RF_ADSTOCK_DECAY_MEAN = np.array([1.0, 0.8344, 0.7042, 0.6001, 0.5155])
 HILL_CURVES_CI_HI = np.array([0.0, 0.0, 0.00098, 0.00895, 0.00195])
 HILL_CURVES_CI_LO = np.array([0.0, 0.0, 0.00085, 0.00322, 0.00169])
 HILL_CURVES_MEAN = np.array([0.0, 0.0, 0.00091, 0.00606, 0.00183])
@@ -2600,110 +2603,106 @@ PREDICTIVE_ACCURACY_NO_HOLDOUT_ID_TIMES_AND_GEOS = np.array(
     [-13.597, -7.360, 1.634, 0.887, 0.990, 0.757]
 )
 PREDICTIVE_ACCURACY_HOLDOUT_ID_NO_GEOS_OR_TIMES = np.array([
-    -2.907,
-    -2.356,
-    -2.784,
-    -3.267,
-    -1.431,
-    -5.836,
-    2.481,
-    46.381,
-    10.724,
-    0.729,
-    63.022,
-    0.696,
-    0.994,
-    1.038,
-    1.001,
-    0.633,
-    0.906,
-    0.596,
+    -2.690704,
+    -3.231603,
+    -2.784759,
+    -2.866354,
+    -1.595214,
+    -5.836171,
+    12.76909,
+    1.634914,
+    10.724035,
+    0.720384,
+    1.306767,
+    0.696319,
+    0.993516,
+    1.036484,
+    1.00181,
+    0.595755,
+    0.945436,
+    0.596676,
 ])
-
 PREDICTIVE_ACCURACY_HOLDOUT_ID_GEOS_NO_TIMES = np.array([
-    -4.6241765,
-    -3.13614225,
-    -4.29795837,
-    -4.48636341,
-    -1.84796333,
-    -4.71139717,
-    2.49890709,
-    8.42507458,
-    3.6478579,
-    1.22353196,
-    4.74503851,
-    1.15957963,
-    1.09398592,
-    1.03744256,
-    1.08360898,
-    0.91437268,
-    1.00845361,
-    0.82047617,
+    -5.167992,
+    -2.34246,
+    -4.297958,
+    -3.945161,
+    -2.930509,
+    -4.711397,
+    4.080629,
+    1.58583,
+    3.647858,
+    1.457559,
+    1.268536,
+    1.15958,
+    1.123409,
+    0.932309,
+    1.083609,
+    0.8971,
+    0.932309,
+    0.820476,
 ])
-
 PREDICTIVE_ACCURACY_HOLDOUT_ID_TIMES_NO_GEOS = np.array([
-    -1.23524213,
-    -9.06220913,
-    -1.39263272,
-    0.3634333,
-    -8.32915783,
-    -0.81341398,
-    1.35193038,
-    4.68957043,
-    2.24196768,
-    0.75223929,
-    3.71988177,
-    0.99283481,
-    1.01492858,
-    2.17278171,
-    1.17750895,
-    0.45635709,
-    2.17278171,
-    0.60861236,
+    -1.398977,
+    0.791522,
+    -1.392633,
+    -0.294972,
+    0.791522,
+    -0.813414,
+    2.577664,
+    0.059942,
+    2.241968,
+    1.445928,
+    0.059942,
+    0.992835,
+    1.349253,
+    0.051477,
+    1.177509,
+    0.693587,
+    0.051477,
+    0.608612,
 ])
 PREDICTIVE_ACCURACY_HOLDOUT_ID_TIMES_AND_GEO = np.array([
-    -38.25726318,
-    float("-inf"),
-    -13.59724903,
-    -1.61034203,
-    float("-inf"),
-    -7.37024498,
-    0.80568475,
-    5.78146744,
-    1.63498175,
-    0.43890095,
-    5.78146744,
-    0.88831377,
-    0.7162329,
-    5.78146744,
-    0.99158531,
-    0.46946037,
-    5.78146744,
-    0.75822759,
+    -20.432268,
+    0.791522,
+    -13.597249,
+    -4.614312,
+    0.791522,
+    -7.370245,
+    2.422502,
+    0.059942,
+    1.634982,
+    2.440133,
+    0.059942,
+    0.888314,
+    1.646492,
+    0.051477,
+    0.991585,
+    1.25399,
+    0.051477,
+    0.758228,
 ])
-
 PREDICTIVE_ACCURACY_HOLDOUT_ID_NATIONAL_NO_TIMES = np.array([
-    0.42883771657943726,
-    0.4715208411216736,
-    0.45594334602355957,
-    0.8378637433052063,
-    13.80582332611084,
-    2.9550814628601074,
-    0.34947845339775085,
-    0.4262354075908661,
-    0.3586611747741699,
+    -15.619549,
+    -28.130356,
+    -17.316074,
+    16.30377,
+    10.817584,
+    15.296103,
+    2.40538,
+    2.640707,
+    2.449049,
 ])
-
 PREDICTIVE_ACCURACY_HOLDOUT_ID_NATIONAL_TIMES = np.array([
-    -0.30289185,
-    float("-inf"),
-    0.15624052,
-    0.86708003,
-    107.46259308,
-    36.39891815,
-    0.61977416,
-    107.46259308,
-    0.88497865,
+    -22.270792,
+    np.nan,
+    -22.270792,
+    161.652573,
+    np.nan,
+    161.652573,
+    4.597788,
+    np.nan,
+    4.597788,
 ])
 
 SAMPLE_IMPRESSIONS = np.array([
@@ -3142,6 +3141,7 @@ def generate_hill_curves_dataframe() -> pd.DataFrame:
       [f"ch_{i}" for i in range(3)]
       + [f"rf_ch_{i}" for i in range(2)]
       + [f"organic_ch_{i}" for i in range(2)]
+      + [f"organic_rf_ch_{i}" for i in range(1)]
   )
   channel_array = []
   channel_type_array = []
@@ -3154,6 +3154,8 @@ def generate_hill_curves_dataframe() -> pd.DataFrame:
         channel_type_array.append(c.RF)
       elif channel_name.startswith("organic_ch_"):
         channel_type_array.append(c.ORGANIC_MEDIA)
+      elif channel_name.startswith("organic_rf_ch_"):
+        channel_type_array.append(c.ORGANIC_RF)
 
   np.random.seed(0)
   media_units_array = [

meridian/analysis/visualizer.py

@@ -19,6 +19,7 @@ import functools
 from typing import Mapping
 import warnings
 import altair as alt
+from meridian import backend
 from meridian import constants as c
 from meridian.analysis import analyzer
 from meridian.analysis import formatter
@@ -26,8 +27,6 @@ from meridian.analysis import summary_text
 from meridian.model import model
 import numpy as np
 import pandas as pd
-import tensorflow as tf
-import tensorflow_probability as tfp
 import xarray as xr
 
 
@@ -312,10 +311,10 @@ class ModelDiagnostics:
         k: v.values
         for k, v in self._meridian.inference_data.posterior.data_vars.items()
     }
-    for k, v in tfp.mcmc.potential_scale_reduction(
-        {k: tf.einsum('ij...->ji...', v) for k, v in mcmc_states.items()}
+    for k, v in backend.mcmc.potential_scale_reduction(
+        {k: backend.einsum('ij...->ji...', v) for k, v in mcmc_states.items()}
     ).items():
-      rhat_temp = v.numpy().flatten()
+      rhat_temp = np.asarray(v).flatten()
       rhat = pd.concat([
           rhat,
           pd.DataFrame({
@@ -864,6 +863,7 @@ class MediaEffects:
       confidence_level: float = c.DEFAULT_CONFIDENCE_LEVEL,
       selected_times: frozenset[str] | None = None,
       by_reach: bool = True,
+      use_kpi: bool = False,
   ) -> xr.Dataset:
     """Dataset holding the calculated response curves data.
 
@@ -887,12 +887,14 @@ class MediaEffects:
       by_reach: For the channel w/ reach and frequency, return the response
         curves by reach given fixed frequency if true; return the response
         curves by frequency given fixed reach if false.
+      use_kpi: If `True`, calculate the incremental KPI. Otherwise, calculate
+        the incremental revenue using the revenue per KPI (if available).
 
     Returns:
       A Dataset displaying the response curves data.
     """
     selected_times_list = list(selected_times) if selected_times else None
-    use_kpi = self._meridian.input_data.revenue_per_kpi is None
+    use_kpi = use_kpi or self._meridian.input_data.revenue_per_kpi is None
     return self._analyzer.response_curves(
         spend_multipliers=list(np.arange(0, 2.2, c.RESPONSE_CURVE_STEP_SIZE)),
         confidence_level=confidence_level,
@@ -962,6 +964,7 @@ class MediaEffects:
       confidence_level: float = c.DEFAULT_CONFIDENCE_LEVEL,
       selected_times: frozenset[str] | None = None,
       by_reach: bool = True,
+      use_kpi: bool = False,
       plot_separately: bool = True,
       include_ci: bool = True,
       num_channels_displayed: int | None = None,
@@ -987,6 +990,8 @@ class MediaEffects:
       by_reach: For the channel w/ reach and frequency, return the response
         curves by reach given fixed frequency if true; return the response
         curves by frequency given fixed reach if false.
+      use_kpi: If `True`, calculate the incremental KPI. Otherwise, calculate
+        the incremental revenue using the revenue per KPI (if available).
       plot_separately: If `True`, the plots are faceted. If `False`, the plots
         are layered to create one plot with all of the channels.
       include_ci: If `True`, plots the credible interval. Defaults to `True`.
@@ -1022,11 +1027,13 @@ class MediaEffects:
         confidence_level=confidence_level,
         selected_times=selected_times,
         by_reach=by_reach,
+        use_kpi=use_kpi,
+    )
+    y_axis_label = (
+        summary_text.INC_KPI_LABEL
+        if use_kpi or self._meridian.input_data.revenue_per_kpi is None
+        else summary_text.INC_OUTCOME_LABEL
     )
-    if self._meridian.input_data.revenue_per_kpi is not None:
-      y_axis_label = summary_text.INC_OUTCOME_LABEL
-    else:
-      y_axis_label = summary_text.INC_KPI_LABEL
     base = (
         alt.Chart(response_curves_df, width=c.VEGALITE_FACET_DEFAULT_WIDTH)
         .transform_calculate(
@@ -1197,41 +1204,32 @@ class MediaEffects:
       include_ci: If `True`, plots the credible interval. Defaults to `True`.
 
     Returns:
-      A dictionary mapping channel type constants (`media`, `rf`, and
-      `organic_media`) to their respective Altair chart objects. Keys are only
-      present if charts for that type were generated (i.e., if the
-      corresponding channels exist in the data). Returns an empty dictionary if
-      no relevant channels are found.
+      A dictionary mapping channel type constants (`media`, `rf`,
+      `organic_media`, and `organic_rf`) to their respective Altair chart
+      objects. Keys are only present if charts for that type were generated
+      (i.e., if the corresponding channels exist in the data). Returns an empty
+      dictionary if no relevant channels are found.
     """
     hill_curves_dataframe = self.hill_curves_dataframe(
         confidence_level=confidence_level
     )
-    channel_types = list(set(hill_curves_dataframe[c.CHANNEL_TYPE]))
+    all_channel_types = set(hill_curves_dataframe[c.CHANNEL_TYPE])
     plots: dict[str, alt.Chart] = {}
 
-    if c.MEDIA in channel_types:
-      media_df = hill_curves_dataframe[
-          hill_curves_dataframe[c.CHANNEL_TYPE] == c.MEDIA
-      ]
-      plots[c.MEDIA] = self._plot_hill_curves_helper(
-          media_df, include_prior, include_ci
-      )
-
-    if c.RF in channel_types:
-      rf_df = hill_curves_dataframe[
-          hill_curves_dataframe[c.CHANNEL_TYPE] == c.RF
-      ]
-      plots[c.RF] = self._plot_hill_curves_helper(
-          rf_df, include_prior, include_ci
-      )
-
-    if c.ORGANIC_MEDIA in channel_types:
-      organic_media_df = hill_curves_dataframe[
-          hill_curves_dataframe[c.CHANNEL_TYPE] == c.ORGANIC_MEDIA
-      ]
-      plots[c.ORGANIC_MEDIA] = self._plot_hill_curves_helper(
-          organic_media_df, include_prior, include_ci
-      )
+    supported_channel_types = [
+        c.MEDIA,
+        c.RF,
+        c.ORGANIC_MEDIA,
+        c.ORGANIC_RF,
+    ]
+    for channel_type in supported_channel_types:
+      if channel_type in all_channel_types:
+        df_for_type = hill_curves_dataframe[
+            hill_curves_dataframe[c.CHANNEL_TYPE] == channel_type
+        ]
+        plots[channel_type] = self._plot_hill_curves_helper(
+            df_for_type, include_prior, include_ci
+        )
 
     return plots
 
@@ -1259,19 +1257,17 @@ class MediaEffects:
         column, or contains an unsupported channel type.
     """
     channel_type = df_channel_type[c.CHANNEL_TYPE].iloc[0]
-    if channel_type == c.MEDIA:
+    if channel_type in [c.MEDIA, c.ORGANIC_MEDIA]:
       x_axis_title = summary_text.HILL_X_AXIS_MEDIA_LABEL
       shaded_area_title = summary_text.HILL_SHADED_REGION_MEDIA_LABEL
-    elif channel_type == c.RF:
+    elif channel_type in [c.RF, c.ORGANIC_RF]:
       x_axis_title = summary_text.HILL_X_AXIS_RF_LABEL
       shaded_area_title = summary_text.HILL_SHADED_REGION_RF_LABEL
-    elif channel_type == c.ORGANIC_MEDIA:
-      x_axis_title = summary_text.HILL_X_AXIS_MEDIA_LABEL
-      shaded_area_title = summary_text.HILL_SHADED_REGION_MEDIA_LABEL
     else:
       raise ValueError(
           f"Unsupported channel type '{channel_type}' found in Hill curve data."
-          ' Expected one of: {c.MEDIA}, {c.RF}, {c.ORGANIC_MEDIA}.'
+          ' Expected one of: {c.MEDIA}, {c.RF}, {c.ORGANIC_MEDIA},'
+          ' {c.ORGANIC_RF}.'
       )
     domain_list = [
         c.POSTERIOR,
@@ -1345,6 +1341,7 @@ class MediaEffects:
       selected_times: frozenset[str] | None = None,
       confidence_level: float = c.DEFAULT_CONFIDENCE_LEVEL,
       by_reach: bool = True,
+      use_kpi: bool = False,
   ) -> pd.DataFrame:
     """Returns DataFrame with top channels by spend for the layered plot.
 
@@ -1359,6 +1356,7 @@ class MediaEffects:
       by_reach: For the channel w/ reach and frequency, return the response
         curves by reach given fixed frequency if true; return the response
         curves by frequency given fixed reach if false.
+      use_kpi: If `True`, use KPI instead of revenue.
 
     Returns:
       A DataFrame containing the top chosen channels
@@ -1369,6 +1367,7 @@ class MediaEffects:
         confidence_level=confidence_level,
         selected_times=selected_times,
         by_reach=by_reach,
+        use_kpi=use_kpi,
     )
     list_sorted_channels_cost = list(
         data.sel(spend_multiplier=1)
@@ -1433,8 +1432,8 @@ class MediaSummary:
       non_media_baseline_values: Optional list of shape
         `(n_non_media_channels,)`. Each element is a float denoting the fixed
         value which will be used as baseline for the given channel. If `None`,
-        the values defined with `ModelSpec.non_media_baseline_values`
-        will be used.
+        the values defined with `ModelSpec.non_media_baseline_values` will be
+        used.
     """
     self._meridian = meridian
     self._analyzer = analyzer.Analyzer(meridian)
@@ -1654,8 +1653,8 @@ class MediaSummary:
       non_media_baseline_values: Optional list of shape
         `(n_non_media_channels,)`. Each element is a float denoting the fixed
         value which will be used as baseline for the given channel. If `None`,
-        the values defined with `ModelSpec.non_media_baseline_values`
-        will be used.
+        the values defined with `ModelSpec.non_media_baseline_values` will be
+        used.
     """
     self._confidence_level = confidence_level or self._confidence_level
     self._selected_times = selected_times
@@ -1686,7 +1685,7 @@ class MediaSummary:
         c.DATE_FORMAT if time_granularity == c.WEEKLY else c.QUARTER_FORMAT
     )
 
-    outcome_df = self._transform_contribution_metrics(
+    outcome_df = self.contribution_metrics(
         include_non_paid=True, aggregate_times=False
     )
 
@@ -1800,7 +1799,7 @@ class MediaSummary:
           f'time_granularity must be one of {c.TIME_GRANULARITIES}'
       )
 
-    outcome_df = self._transform_contribution_metrics(
+    outcome_df = self.contribution_metrics(
         include_non_paid=True, aggregate_times=False
     )
     outcome_df[c.TIME] = pd.to_datetime(outcome_df[c.TIME])
@@ -1907,7 +1906,7 @@ class MediaSummary:
         if self._meridian.input_data.revenue_per_kpi is not None
         else c.KPI.upper()
     )
-    outcome_df = self._transform_contribution_metrics(include_non_paid=True)
+    outcome_df = self.contribution_metrics(include_non_paid=True)
     pct = c.PCT_OF_CONTRIBUTION
     value = c.INCREMENTAL_OUTCOME
     outcome_df['outcome_text'] = outcome_df.apply(
@@ -1991,7 +1990,7 @@ class MediaSummary:
     Returns:
       An Altair plot showing the contributions for all channels.
     """
-    outcome_df = self._transform_contribution_metrics(
+    outcome_df = self.contribution_metrics(
         [c.ALL_CHANNELS], include_non_paid=True
     )
 
@@ -2411,7 +2410,7 @@ class MediaSummary:
     spend_df = paid_summary_metrics[c.SPEND].to_dataframe().reset_index()
     return metrics_df.merge(spend_df, on=c.CHANNEL)
 
-  def _transform_contribution_metrics(
+  def contribution_metrics(
       self,
       selected_channels: Sequence[str] | None = None,
       include_non_paid: bool = False,