[Summarizer] Add channel contribution area chart

PiperOrigin-RevId: 739326212

Author: andyl7an

CHANGELOG.md

@@ -23,6 +23,12 @@ To release a new version (e.g. from `1.0.0` -> `2.0.0`):
 
 ## [Unreleased]
 
+* Add `plot_channel_contribution_area_chart` method to `MediaSummary` in the
+  visualizer.
+
+* Update contribution calculation methods in `MediaSummary` with
+  `aggregate_times` parameter to support granular time.
+
 * Add a `new_data` argument to `analyzer.optimal_freq()`.
 * Refactor args in `create_optimization_grid` to be consistent with
  `optimize(...)`.

meridian/analysis/summarizer.py

@@ -270,6 +270,13 @@ def _create_outcome_contrib_card_html(
   ) -> str:
     """Creates the HTML snippet for the Outcome Contrib card."""
     outcome = self._kpi_or_revenue()
+    channel_contribution_by_time_chart = formatter.ChartSpec(
+        id=summary_text.CHANNEL_CONTRIB_BY_TIME_CHART_ID,
+        description=summary_text.CHANNEL_CONTRIB_BY_TIME_CHART_DESCRIPTION.format(
+            outcome=outcome
+        ),
+        chart_json=media_summary.plot_channel_contribution_area_chart().to_json(),
+    )
     channel_drivers_chart = formatter.ChartSpec(
         id=summary_text.CHANNEL_DRIVERS_CHART_ID,
         description=summary_text.CHANNEL_DRIVERS_CHART_DESCRIPTION.format(
@@ -305,6 +312,7 @@ def _create_outcome_contrib_card_html(
         CHANNEL_CONTRIB_CARD_SPEC,
         insights,
         [
+            channel_contribution_by_time_chart,
             channel_drivers_chart,
             spend_outcome_chart,
             outcome_contribution_chart,
@@ -318,7 +326,7 @@ def _get_sorted_posterior_mean_metrics_df(
       ascending: bool = False,
   ) -> pd.DataFrame:
     return (
-        media_summary.paid_summary_metrics[metrics]
+        media_summary.get_paid_summary_metrics()[metrics]
         .sel(distribution=c.POSTERIOR, metric=c.MEAN)
         .drop_sel(channel=c.ALL_CHANNELS)
         .to_dataframe()
@@ -334,7 +342,7 @@ def _get_sorted_posterior_median_metrics_df(
       ascending: bool = False,
   ) -> pd.DataFrame:
     return (
-        media_summary.paid_summary_metrics[metrics]
+        media_summary.get_paid_summary_metrics()[metrics]
         .sel(distribution=c.POSTERIOR, metric=c.MEDIAN)
         .drop_sel(channel=c.ALL_CHANNELS)
         .to_dataframe()
@@ -479,7 +487,7 @@ def _select_optimal_rf_data(
     rf_channels = reach_frequency.optimal_frequency_data.rf_channel
     assert rf_channels.size > 0
     # This will raise KeyError if not all `rf_channels` can be found in here:
-    rf_channel_spends = media_summary.paid_summary_metrics[c.SPEND].sel(
+    rf_channel_spends = media_summary.get_paid_summary_metrics()[c.SPEND].sel(
         channel=rf_channels
     )
     most_spend_rf_channel = rf_channel_spends.idxmax()

meridian/analysis/summarizer_test.py

@@ -140,6 +140,9 @@ def _stub_plotters(self):
     self.reach_frequency.plot_optimal_frequency().to_json.return_value = '{}'
 
   def _stub_media_summary_plotters(self, media_summary):
+    media_summary.plot_channel_contribution_area_chart().to_json.return_value = (
+        '{}'
+    )
     media_summary.plot_contribution_waterfall_chart().to_json.return_value = (
         '{}'
     )
@@ -152,7 +155,9 @@ def _stub_media_summary_plotters(self, media_summary):
 
   def _stub_for_insights(self):
     self.media_metrics = test_utils.generate_paid_summary_metrics()
-    self.media_summary.paid_summary_metrics = self.media_metrics
+    self.media_summary.get_paid_summary_metrics = mock.MagicMock(
+        return_value=self.media_metrics
+    )
 
     frequency_data = test_utils.generate_optimal_frequency_data(
         channel_prefix='rf_ch', num_channels=2
@@ -365,6 +370,12 @@ def test_output_card_static_chart_spec(self, card_spec):
       (
           summary_text.CHANNEL_CONTRIB_CARD_ID,
           [
+              (
+                  summary_text.CHANNEL_CONTRIB_BY_TIME_CHART_ID,
+                  summary_text.CHANNEL_CONTRIB_BY_TIME_CHART_DESCRIPTION.format(
+                      outcome=c.REVENUE
+                  ),
+              ),
               (
                   summary_text.CHANNEL_DRIVERS_CHART_ID,
                   summary_text.CHANNEL_DRIVERS_CHART_DESCRIPTION.format(
@@ -781,6 +792,10 @@ def test_channel_contrib_card_plotters_called(self):
     media_summary.plot_contribution_pie_chart().to_json.return_value = (
         f'["{mock_spec_3}"]'
     )
+    mock_spec_4 = 'revenue_area_chart'
+    media_summary.plot_channel_contribution_area_chart().to_json.return_value = (
+        f'["{mock_spec_4}"]'
+    )
 
     summary_html_dom = self._get_output_model_results_summary_html_dom(
         self.summarizer_revenue,
@@ -789,6 +804,7 @@ def test_channel_contrib_card_plotters_called(self):
         media_summary.plot_contribution_waterfall_chart(),
         media_summary.plot_spend_vs_contribution(),
         media_summary.plot_contribution_pie_chart(),
+        media_summary.plot_channel_contribution_area_chart(),
     ]:
       mock_plot.to_json.assert_called_once()
 
@@ -812,8 +828,16 @@ def test_channel_contrib_card_plotters_called(self):
     mock_spec_3_exists = any(
         [mock_spec_3 in script_text for script_text in script_texts]
     )
+    mock_spec_4_exists = any(
+        [mock_spec_4 in script_text for script_text in script_texts]
+    )
     self.assertTrue(
-        all([mock_spec_1_exists, mock_spec_2_exists, mock_spec_3_exists])
+        all([
+            mock_spec_1_exists,
+            mock_spec_2_exists,
+            mock_spec_3_exists,
+            mock_spec_4_exists,
+        ])
     )
 
   def test_channel_contrib_card_insights(self):
@@ -998,7 +1022,7 @@ def test_response_curves_card_insights_multiple_channels(self):
     media_summary = self.media_summary
     reach_frequency = self.reach_frequency
 
-    media_summary.paid_summary_metrics.spend.data = [
+    media_summary.get_paid_summary_metrics().spend.data = [
         100,  # 'ch_0'
         200,  # 'ch_1'
         300,  # 'ch_2'

meridian/analysis/summary_text.py

@@ -42,6 +42,14 @@
 understand what drove your {outcome}. {lead_channels} drove the most overall
 {outcome}."""
 
+CHANNEL_CONTRIB_BY_TIME_CHART_ID = 'channel-contrib-by-time-chart'
+CHANNEL_CONTRIB_BY_TIME_CHART_TITLE = (
+    'Contribution over time by baseline and marketing channels'
+)
+CHANNEL_CONTRIB_BY_TIME_CHART_DESCRIPTION = """Note: This graphic encompasses all of
+your {outcome} drivers, but breaks down your marketing {outcome} by the baseline
+and all channels over time."""
+
 CHANNEL_DRIVERS_CHART_ID = 'channel-drivers-chart'
 CHANNEL_DRIVERS_CHART_TITLE = 'Contribution by baseline and marketing channels'
 CHANNEL_DRIVERS_CHART_DESCRIPTION = """Note: This graphic encompasses all of

meridian/analysis/test_utils.py

@@ -2914,7 +2914,7 @@ def generate_paid_summary_metrics() -> xr.Dataset:
   )
 
 
-def generate_all_summary_metrics() -> xr.Dataset:
+def generate_all_summary_metrics(aggregate_times: bool = True) -> xr.Dataset:
   """Helper method to generate simulated summary metrics data."""
   channel = (
       [f"ch_{i}" for i in range(3)]
@@ -2926,33 +2926,36 @@ def generate_all_summary_metrics() -> xr.Dataset:
   channel.append(c.ALL_CHANNELS)
   metric = [c.MEAN, c.MEDIAN, c.CI_LO, c.CI_HI]
   distribution = [c.PRIOR, c.POSTERIOR]
+  time = [f"time_{i}" for i in range(5)]
 
   np.random.seed(0)
-  shape = (len(channel), len(metric), len(distribution))
+
+  if aggregate_times:
+    shape = (len(channel), len(metric), len(distribution))
+    dims = [c.CHANNEL, c.METRIC, c.DISTRIBUTION]
+  else:
+    shape = (len(time), len(channel), len(metric), len(distribution))
+    dims = [c.TIME, c.CHANNEL, c.METRIC, c.DISTRIBUTION]
+
   incremental_outcome = np.random.lognormal(10, 1, size=shape)
   effectiveness = np.random.lognormal(1, 1, size=shape)
   pct_of_contribution = np.random.randint(low=0, high=50, size=shape)
 
+  coords = {
+      c.CHANNEL: channel,
+      c.METRIC: metric,
+      c.DISTRIBUTION: distribution,
+  }
+  if not aggregate_times:
+    coords[c.TIME] = time
+
   return xr.Dataset(
       data_vars={
-          c.INCREMENTAL_OUTCOME: (
-              [c.CHANNEL, c.METRIC, c.DISTRIBUTION],
-              incremental_outcome,
-          ),
-          c.PCT_OF_CONTRIBUTION: (
-              [c.CHANNEL, c.METRIC, c.DISTRIBUTION],
-              pct_of_contribution,
-          ),
-          c.EFFECTIVENESS: (
-              [c.CHANNEL, c.METRIC, c.DISTRIBUTION],
-              effectiveness,
-          ),
-      },
-      coords={
-          c.CHANNEL: channel,
-          c.METRIC: metric,
-          c.DISTRIBUTION: distribution,
+          c.INCREMENTAL_OUTCOME: (dims, incremental_outcome),
+          c.PCT_OF_CONTRIBUTION: (dims, pct_of_contribution),
+          c.EFFECTIVENESS: (dims, effectiveness),
       },
+      coords=coords,
       attrs={c.CONFIDENCE_LEVEL: c.DEFAULT_CONFIDENCE_LEVEL},
   )