google-meridian 1.1.0__py3-none-any.whl → 1.1.2__py3-none-any.whl

meridian/model/posterior_sampler.py

@@ -1,4 +1,4 @@
-# Copyright 2024 The Meridian Authors.
+# Copyright 2025 The Meridian Authors.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -120,8 +120,6 @@ class PosteriorMCMCSampler:
     def joint_dist_unpinned():
       # Sample directly from prior.
       knot_values = yield prior_broadcast.knot_values
-      gamma_c = yield prior_broadcast.gamma_c
-      xi_c = yield prior_broadcast.xi_c
       sigma = yield prior_broadcast.sigma
 
       tau_g_excl_baseline = yield tfp.distributions.Sample(
@@ -377,19 +375,25 @@ class PosteriorMCMCSampler:
         combined_beta = tf.concat([combined_beta, beta_gorf], axis=-1)
 
       sigma_gt = tf.transpose(tf.broadcast_to(sigma, [n_times, n_geos]))
-      gamma_gc_dev = yield tfp.distributions.Sample(
-          tfp.distributions.Normal(0, 1),
-          [n_geos, n_controls],
-          name=constants.GAMMA_GC_DEV,
-      )
-      gamma_gc = yield tfp.distributions.Deterministic(
-          gamma_c + xi_c * gamma_gc_dev, name=constants.GAMMA_GC
-      )
-      y_pred_combined_media = (
-          tau_gt
-          + tf.einsum("gtm,gm->gt", combined_media_transformed, combined_beta)
-          + tf.einsum("gtc,gc->gt", controls_scaled, gamma_gc)
+      y_pred_combined_media = tau_gt + tf.einsum(
+          "gtm,gm->gt", combined_media_transformed, combined_beta
       )
+      # Omit gamma_c, xi_c, and gamma_gc from joint distribution output if
+      # there are no control variables in the model.
+      if n_controls:
+        gamma_c = yield prior_broadcast.gamma_c
+        xi_c = yield prior_broadcast.xi_c
+        gamma_gc_dev = yield tfp.distributions.Sample(
+            tfp.distributions.Normal(0, 1),
+            [n_geos, n_controls],
+            name=constants.GAMMA_GC_DEV,
+        )
+        gamma_gc = yield tfp.distributions.Deterministic(
+            gamma_c + xi_c * gamma_gc_dev, name=constants.GAMMA_GC
+        )
+        y_pred_combined_media += tf.einsum(
+            "gtc,gc->gt", controls_scaled, gamma_gc
+        )
 
       if mmm.non_media_treatments is not None:
         xi_n = yield prior_broadcast.xi_n

meridian/model/prior_distribution.py

@@ -1,4 +1,4 @@
-# Copyright 2024 The Meridian Authors.
+# Copyright 2025 The Meridian Authors.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

meridian/model/prior_sampler.py

@@ -1,4 +1,4 @@
-# Copyright 2024 The Meridian Authors.
+# Copyright 2025 The Meridian Authors.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -175,8 +175,9 @@ class PriorDistributionSampler:
         (https://github.com/tensorflow/probability/blob/main/PRNGS.md).
 
     Returns:
-      A mapping of RF parameter names to a tensor of shape `[n_draws, n_geos,
-      n_rf_channels]` or `[n_draws, n_rf_channels]` containing the samples.
+      A mapping of RF parameter names to a tensor of shape
+      `[n_draws, n_geos, n_rf_channels]` or `[n_draws, n_rf_channels]`
+      containing the samples.
     """
     mmm = self._meridian
 
@@ -269,9 +270,9 @@ class PriorDistributionSampler:
         (https://github.com/tensorflow/probability/blob/main/PRNGS.md).
 
     Returns:
-      A mapping of organic media parameter names to a tensor of shape [n_draws,
-      n_geos, n_organic_media_channels] or [n_draws, n_organic_media_channels]
-      containing the samples.
+      A mapping of organic media parameter names to a tensor of shape
+      `[n_draws, n_geos, n_organic_media_channels]` or
+      `[n_draws, n_organic_media_channels]` containing the samples.
     """
     mmm = self._meridian
 
@@ -352,9 +353,9 @@ class PriorDistributionSampler:
         (https://github.com/tensorflow/probability/blob/main/PRNGS.md).
 
     Returns:
-      A mapping of organic RF parameter names to a tensor of shape [n_draws,
-      n_geos, n_organic_rf_channels] or [n_draws, n_organic_rf_channels]
-      containing the samples.
+      A mapping of organic RF parameter names to a tensor of shape
+      `[n_draws, n_geos, n_organic_rf_channels]` or
+      `[n_draws, n_organic_rf_channels]` containing the samples.
     """
     mmm = self._meridian
 
@@ -436,9 +437,8 @@ class PriorDistributionSampler:
 
     Returns:
       A mapping of non-media treatment parameter names to a tensor of shape
-      [n_draws,
-      n_geos, n_non_media_channels] or [n_draws, n_non_media_channels]
-      containing the samples.
+      `[n_draws, n_geos, n_non_media_channels]` or
+      `[n_draws, n_non_media_channels]` containing the samples.
     """
     mmm = self._meridian
 
@@ -470,8 +470,7 @@ class PriorDistributionSampler:
           mmm.compute_non_media_treatments_baseline()
       )
       linear_predictor_counterfactual_difference = (
-          mmm.non_media_treatments_normalized
-          - baseline_scaled
+          mmm.non_media_treatments_normalized - baseline_scaled
       )
       gamma_n_value = mmm.calculate_beta_x(
           is_non_media=True,
@@ -517,8 +516,6 @@ class PriorDistributionSampler:
     tau_g_excl_baseline = prior.tau_g_excl_baseline.sample(**sample_kwargs)
     base_vars = {
         constants.KNOT_VALUES: prior.knot_values.sample(**sample_kwargs),
-        constants.GAMMA_C: prior.gamma_c.sample(**sample_kwargs),
-        constants.XI_C: prior.xi_c.sample(**sample_kwargs),
         constants.SIGMA: prior.sigma.sample(**sample_kwargs),
         constants.TAU_G: (
             _get_tau_g(
@@ -527,6 +524,7 @@ class PriorDistributionSampler:
             ).sample()
         ),
     }
+
     base_vars[constants.MU_T] = tfp.distributions.Deterministic(
         tf.einsum(
             "...k,kt->...t",
@@ -536,16 +534,24 @@ class PriorDistributionSampler:
         name=constants.MU_T,
     ).sample()
 
-    gamma_gc_dev = tfp.distributions.Sample(
-        tfp.distributions.Normal(0, 1),
-        [mmm.n_geos, mmm.n_controls],
-        name=constants.GAMMA_GC_DEV,
-    ).sample(**sample_kwargs)
-    base_vars[constants.GAMMA_GC] = tfp.distributions.Deterministic(
-        base_vars[constants.GAMMA_C][..., tf.newaxis, :]
-        + base_vars[constants.XI_C][..., tf.newaxis, :] * gamma_gc_dev,
-        name=constants.GAMMA_GC,
-    ).sample()
+    # Omit gamma_c, xi_c, and gamma_gc parameters from sampled distributions if
+    # there are no control variables in the model.
+    if mmm.n_controls:
+      base_vars |= {
+          constants.GAMMA_C: prior.gamma_c.sample(**sample_kwargs),
+          constants.XI_C: prior.xi_c.sample(**sample_kwargs),
+      }
+
+      gamma_gc_dev = tfp.distributions.Sample(
+          tfp.distributions.Normal(0, 1),
+          [mmm.n_geos, mmm.n_controls],
+          name=constants.GAMMA_GC_DEV,
+      ).sample(**sample_kwargs)
+      base_vars[constants.GAMMA_GC] = tfp.distributions.Deterministic(
+          base_vars[constants.GAMMA_C][..., tf.newaxis, :]
+          + base_vars[constants.XI_C][..., tf.newaxis, :] * gamma_gc_dev,
+          name=constants.GAMMA_GC,
+      ).sample()
 
     media_vars = (
         self._sample_media_priors(n_draws, seed)

meridian/model/spec.py

@@ -1,4 +1,4 @@
-# Copyright 2024 The Meridian Authors.
+# Copyright 2025 The Meridian Authors.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -109,17 +109,27 @@ class ModelSpec:
     roi_calibration_period: An optional boolean array of shape `(n_media_times,
       n_media_channels)` indicating the subset of `time` that the ROI value of
       the `roi_m` prior applies to. The ROI numerator is the incremental outcome
-      generated during this time period, and the denominator is the spend during
-      this time period. (Spend data by time period is required). If `None`, all
-      times are used. Only used if `media_prior_type` is `'roi'`.
+      generated by media executed during the calibration period. More precisely,
+      it is the difference in expected outcome between the counterfactual where
+      media is set to historical values versus the counterfactual where media is
+      set to zero during the calibration period and set to historical values for
+      all other time periods. The denominator is the channel spend during
+      calibration period (excluding any calibration time periods prior to the
+      first KPI time period). Spend data by time period is required. If `None`,
+      all times are used. Only used if `media_prior_type` is `'roi'`.
       Default: `None`.
     rf_roi_calibration_period: An optional boolean array of shape
       `(n_media_times, n_rf_channels)` indicating the subset of `time` that the
       ROI value of the `roi_rf` prior applies to. The ROI numerator is the
-      incremental outcome generated during this time period, and the denominator
-      is the spend during this time period. (Spend data by time period is
-      required). If `None`, all times are used. Only used if `rf_prior_type` is
-      `'roi'`. Default: `None`.
+      incremental outcome generated by media executed during the calibration
+      period. More precisely, it is the difference in expected outcome between
+      the counterfactual where reach and frequency is set to historical values
+      versus the counterfactual where reach is set to zero during the
+      calibration period and set to historical values for all other time
+      periods. The denominator is the channel spend during calibration period
+      (excluding any calibration time periods prior to the first KPI time
+      period). Spend data by time period is required. If `None`, all times are
+      used. Only used if `rf_prior_type` is `'roi'`. Default: `None`.
     organic_media_prior_type: A string to specify the prior type for the organic
       media coefficients. Allowed values: `'contribution'`, `'coefficient'`.
       `PriorDistribution` contains `contribution_om` and `beta_om`, but only one

meridian/model/transformers.py

@@ -1,4 +1,4 @@
-# Copyright 2024 The Meridian Authors.
+# Copyright 2025 The Meridian Authors.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

google_meridian-1.1.0.dist-info/RECORD

@@ -1,41 +0,0 @@
-google_meridian-1.1.0.dist-info/licenses/LICENSE,sha256=WNHhf_5RCaeuKWyq_K39vmp9F28LxKsB4SpomwSZ2L0,11357
-meridian/__init__.py,sha256=Z2HBhx0G1hdGh8Q3k-4Bt6WrPHpHyAxUpeKaT0QXXQg,714
-meridian/constants.py,sha256=C0Af-w-q4fL-GW08Z9jrRRCet-dAdXpz7LsX1SA8uf0,17157
-meridian/analysis/__init__.py,sha256=-FooDZ5OzePpyTVkvRoWQx_xBaRR_hjVLny9H8-kkyQ,836
-meridian/analysis/analyzer.py,sha256=qVv8654KLyz8kFVn06oHfkKfwXQHwS4RwdckTRbFpgE,203995
-meridian/analysis/formatter.py,sha256=F8OYxD2bH13zV10JY63j2ugCOj-DpTXhyJr43n5ukr8,7270
-meridian/analysis/optimizer.py,sha256=tYOqgj-neqgOGdjs6F4GbQVAmMQ9JyEUXpqUScanhnk,106122
-meridian/analysis/summarizer.py,sha256=VVtMsNct5PrnWHdVnDzo_dyiTM9labUD55G1FXdxxOM,18855
-meridian/analysis/summary_text.py,sha256=n6a-DTZxtS3WvdI_pDEK7lvO3MRUX3h83GzuVnG6sQ4,12438
-meridian/analysis/test_utils.py,sha256=uNJuBsRaHz8Cnaqq5DhOc271mQKYk8h-fIG5du0kCBw,77699
-meridian/analysis/visualizer.py,sha256=6iyNOtjds4CwPaTmEoh_2XuYx4kFxUl8W7t2fmL4vSk,93736
-meridian/analysis/templates/card.html.jinja,sha256=pv4MVbQ25CcvtZY-LH7bFW0OSeHobkeEkAleB1sfQ14,1284
-meridian/analysis/templates/chart.html.jinja,sha256=87i0xnXHRBoLLxBpKv2i960TLToWq4r1aVQZqaXIeMQ,1086
-meridian/analysis/templates/chips.html.jinja,sha256=Az0tQwF_-b03JDLyOzpeH-8fb-6jgJgbNfnUUSm-q6E,645
-meridian/analysis/templates/insights.html.jinja,sha256=6hEWipbOMiMzs9QGZ6dcB_73tNkj0ZtNiC8E89a98zg,606
-meridian/analysis/templates/stats.html.jinja,sha256=9hQOG02FX1IHVIvdWS_-LI2bbSaqdyHEtCZkiArwAg0,772
-meridian/analysis/templates/style.css,sha256=RODTWc2pXcG9zW3q9SEJpVXgeD-WwQgzLpmFcbXPhLg,5492
-meridian/analysis/templates/style.scss,sha256=nSrZOpcIrVyiL4eC9jLUlxIZtAKZ0Rt8pwfk4H1nMrs,5076
-meridian/analysis/templates/summary.html.jinja,sha256=LuENVDHYIpNo4pzloYaCR2K9XN1Ow6_9oQOcOwD9nGg,1707
-meridian/analysis/templates/table.html.jinja,sha256=mvLMZx92RcD2JAS2w2eZtfYG-6WdfwYVo7pM8TbHp4g,1176
-meridian/data/__init__.py,sha256=ixOYHDQExjnPTLLnZ758pRQscZP7c8QJqtc8P4hK-mE,774
-meridian/data/arg_builder.py,sha256=f7LEysYmixAagwygZOEiJkRnWggRhTeXj5AXthBpkQ8,3741
-meridian/data/input_data.py,sha256=GJcf3wqMrF1jFZ3hBk1mlqUMV8_-gEo8ZagiB5siJ58,39610
-meridian/data/load.py,sha256=MKCnRoR8ZIfhEAcm5ZUQsjfoEzi1c9SDOgf6BR8Akr0,54642
-meridian/data/test_utils.py,sha256=4c2WIPfu-vYudyVM9WLUWrJ4Op14L-zk34N09_6Za8E,55015
-meridian/data/time_coordinates.py,sha256=wTr-JKWNkMOkiZQ8B16qy0bUUuMkdh9sI2-IP4HRUTw,9874
-meridian/model/__init__.py,sha256=bvx8vvXolktsCTDKViU9U1v85pgNWF3haDowTKy11d4,982
-meridian/model/adstock_hill.py,sha256=b_YYhqci6ndgi602FFXmx2f12ceC4N0tp338nMMtm54,9283
-meridian/model/knots.py,sha256=r7PPaJM96d5pkoOeV9crIOgkM0-rh24mWMvypMiV4aQ,8054
-meridian/model/media.py,sha256=Tb8tOK_ay1kGjq1a6xsjW8XdMOWAuYCgE7-YYSyJCho,13819
-meridian/model/model.py,sha256=Vg0HZg8X5BiKLRgrM65xO4P6uO7S46BfTaP3qmjtUCI,60398
-meridian/model/model_test_data.py,sha256=t6W-xRuQlrCuMOpdjy4zIzMdBCFuFbHB7_ELKqOI8L8,12917
-meridian/model/posterior_sampler.py,sha256=S0ZbWFghiUV51yKt2tr4_aBr2JrqR5Z6wEXn8P8VmbI,27527
-meridian/model/prior_distribution.py,sha256=vkvmZ0lIc150Fgejo7YVDzjWJxgs-tOPBlMneX5I1oo,42417
-meridian/model/prior_sampler.py,sha256=xJ-X_Q1gFp6amANre78Cq70T1qS6UKO_iXmePNokX8g,23001
-meridian/model/spec.py,sha256=lUGgSIAQdpBQIBNBPBTW5f9Dbk7PaxeLZVFuWQ1VZ00,17239
-meridian/model/transformers.py,sha256=j6yHvLpdDGOXcJHddDP7pZalxMs25eGUx1vu2ppfriQ,7763
-google_meridian-1.1.0.dist-info/METADATA,sha256=S4ADeuHKzmdSwL2GxVhwgeyr0DPpqJsM2m5xoi-R8XU,22055
-google_meridian-1.1.0.dist-info/WHEEL,sha256=zaaOINJESkSfm_4HQVc5ssNzHCPXhJm0kEUakpsEHaU,91
-google_meridian-1.1.0.dist-info/top_level.txt,sha256=nwaCebZvvU34EopTKZsjK0OMTFjVnkf4FfnBN_TAc0g,9
-google_meridian-1.1.0.dist-info/RECORD,,