google-meridian 1.2.0__py3-none-any.whl → 1.2.1__py3-none-any.whl

{google_meridian-1.2.0.dist-info → google_meridian-1.2.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: google-meridian
-Version: 1.2.0
+Version: 1.2.1
 Summary: Google's open source mixed marketing model library, helps you understand your return on investment and direct your ad spend with confidence. 
 Author-email: The Meridian Authors <no-reply@google.com>
 License: 
@@ -403,7 +403,7 @@ To cite this repository:
   author = {Google Meridian Marketing Mix Modeling Team},
   title = {Meridian: Marketing Mix Modeling},
   url = {https://github.com/google/meridian},
-  version = {1.2.0},
+  version = {1.2.1},
   year = {2025},
 }
 ```

{google_meridian-1.2.0.dist-info → google_meridian-1.2.1.dist-info}/RECORD

@@ -1,15 +1,15 @@
-google_meridian-1.2.0.dist-info/licenses/LICENSE,sha256=WNHhf_5RCaeuKWyq_K39vmp9F28LxKsB4SpomwSZ2L0,11357
+google_meridian-1.2.1.dist-info/licenses/LICENSE,sha256=WNHhf_5RCaeuKWyq_K39vmp9F28LxKsB4SpomwSZ2L0,11357
 meridian/__init__.py,sha256=0fOT5oNZF7-pbiWWGUefV-ysafttieG079m1ijMFQO8,861
-meridian/constants.py,sha256=PZLPEDmqzTER3nzt84qV83WPulb-ScwYfq9nNfBBVkk,18312
-meridian/version.py,sha256=eV51cCZSYYHp8DRnwq4HDZVPlzL9bcnUV6t9V0FIaf4,644
+meridian/constants.py,sha256=19A4Hzhfdrdj6CzjoqKxqTg3d3wbTGHgvz9TBwdIRZg,18485
+meridian/version.py,sha256=2wFL4gzqzx21aqU1XHRxIuP5xZOZFXVxiDQUG5v38do,644
 meridian/analysis/__init__.py,sha256=nGBYz7k9FVdadO_WVGMKJcfq7Yy_TuuP8zgee4i9pSA,836
-meridian/analysis/analyzer.py,sha256=92so-WVfuoaEuouJwY_MdQz75lvOOF9RhSk-3rhmQ_Y,214705
+meridian/analysis/analyzer.py,sha256=ftcjavIPKy1y0uL_uEKfFaSYnWdQYMc8YBnw8p7mf6g,217876
 meridian/analysis/formatter.py,sha256=ENIdR1CRiaVqIGEXx1HcnsA4ewgDD_nhsYCweJAThaw,7270
-meridian/analysis/optimizer.py,sha256=rGUGqpORlHQyyPN0ceR0rngpaQhDzLMzxfMcwIr4ksE,118267
-meridian/analysis/summarizer.py,sha256=IthOUTMufGvAvbxiDhaKwe7uYCyiTyiQ8vgdmUtdevs,18855
+meridian/analysis/optimizer.py,sha256=4LhEbPBz8NtWWzwLuYiAhkuTiLfIJbhhdBPn973EVeQ,120492
+meridian/analysis/summarizer.py,sha256=VF4uuZ5xavrfZdLk1Cwf1ZPrkiQ2-kVnLkjvpWtcZ98,19367
 meridian/analysis/summary_text.py,sha256=I_smDkZJYp2j77ea-9AIbgeraDa7-qUYyb-IthP2qO4,12438
 meridian/analysis/test_utils.py,sha256=z5NBjcOzvM7xwwTFI_26sfLyyGLYCd21j52eygQHBRs,77911
-meridian/analysis/visualizer.py,sha256=z3j2_BRlv7980FGpsDGxVQJFlVfkTvA8dhx1Qtv5apo,94025
+meridian/analysis/visualizer.py,sha256=RgrqIBRFG_HJBlz_IcOVaB3jSeXpD5PHLSkkGy2rWJs,94537
 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
@@ -19,34 +19,34 @@ meridian/analysis/templates/style.css,sha256=RODTWc2pXcG9zW3q9SEJpVXgeD-WwQgzLpm
 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/backend/__init__.py,sha256=rInUMct5eggmYlHifRXMGi1iLdPFGtsnNVoqF-HKS5E,14556
-meridian/backend/config.py,sha256=eEBqYm31BVYUmmio-EyQ2A0zHxvHBkX8atWyPeCRakw,1661
-meridian/backend/test_utils.py,sha256=CovPYZpX9_Me3eRU2iUSY22vKXKNkz3gWtrVAAIpB0U,3202
+meridian/backend/__init__.py,sha256=9DCcwp-9hIr66vciMhdkROndO40AAlJXjtrAbFihero,28454
+meridian/backend/config.py,sha256=B9VQnhBfg9RW04GNbt7F5uCugByenoJzt-keFLLYEp8,3561
+meridian/backend/test_utils.py,sha256=jmlFdo3mQrDG-gmxd8GqYAhi_GdAXRUjRkHxRY0z_1A,6410
 meridian/data/__init__.py,sha256=StIe-wfYnnbfUbKtZHwnAQcRQUS8XCZk_PCaEzw90Ww,929
 meridian/data/arg_builder.py,sha256=Kqlt88bOqFj6D3xNwvWo4MBwNwcDFHzd-wMfEOmLoPU,3741
 meridian/data/data_frame_input_data_builder.py,sha256=_hexZMFAuAowgo6FaOGElHSFHqhGnHQwEEBcwnT3zUE,27295
-meridian/data/input_data.py,sha256=QYxm8Ri1Pk6CbGRbYWnSFFHncbei6bOu4w-nVfo27l0,43078
+meridian/data/input_data.py,sha256=Qlxm4El6h1SRPsWDqZoKkOcMtrjiRWr3z8sU2mtghRA,43151
 meridian/data/input_data_builder.py,sha256=tbZjVXPDfmtndVyJA0fmzGzZwZb0RCEjXOTXb-ga8Nc,25648
 meridian/data/load.py,sha256=X2nmYCC-7A0RUgmdolTqCt0TD3NEZabQ5oGv-TugE00,40129
 meridian/data/nd_array_input_data_builder.py,sha256=lfpmnENGuSGKyUd7bDGAwoLqHqteOKmHdKl0VI2wCQA,16341
-meridian/data/test_utils.py,sha256=-Z6OUkDYjamtNVja-7SqHIrjJ7miBDXYQT8wZK_0txk,59763
+meridian/data/test_utils.py,sha256=mw-QPTP15oXf32I7cxMe8iSFBLB3seqEiITZMTz_Eg8,59838
 meridian/data/time_coordinates.py,sha256=C5A5fscSLjPH6G9YT8OspgIlCrkMY7y8dMFEt3tNSnE,9874
 meridian/mlflow/__init__.py,sha256=elwXUqPQYi7VF9PYjelU1tydfcUrmtuoq6eJCOnV9bk,693
-meridian/mlflow/autolog.py,sha256=s240eLGAurzaNsulwRlyM1ZdBLvUzyr2eOMYgOyWAzk,6393
+meridian/mlflow/autolog.py,sha256=SZsrynLjozcyrAFCNWiqchSa2yOszVnwFBGz23BmWUU,6379
 meridian/model/__init__.py,sha256=9NFfqUE5WgFc-9lQMkbfkwwV-bQIz0tsQ_3Jyq0A4SU,982
-meridian/model/adstock_hill.py,sha256=v07yiFNF1O8G79qUKtTdR5TbQVsaocg8Dwm6xEP_PVE,17631
-meridian/model/knots.py,sha256=OZ1zDNhzZmt-hh5hri-CuifEum0oRVZdHUqdkkNpstE,25979
+meridian/model/adstock_hill.py,sha256=HoRKjyL03pCTBz6Utof9wEvlQCFM43BvrEW_oupj7NU,17688
+meridian/model/knots.py,sha256=1geYCcWHjXy1Uzwi5bxIuHaIY2rfSYVfneEdPetcMA8,25978
 meridian/model/media.py,sha256=ZWYLN2iHLYWYrSRyR03L8DgFdVtgRs37JfTVjbzynBU,14364
 meridian/model/model.py,sha256=D6pQOD0A7ZE7MhDd2tLMSB7sVmDwyzJ82DuKaF_auVs,66516
-meridian/model/model_test_data.py,sha256=VKYyA9y1OFviVpVO_SALi1N7BJBjlVrVvl0P2xUiJvs,21733
-meridian/model/posterior_sampler.py,sha256=7i46E8oBR6zH756i-UylQ2FBxt4flN3h-PcrF4xycVY,28168
-meridian/model/prior_distribution.py,sha256=y0Dzcg4m-_ah7Vcs3GWSVfLsNYLxftDXFWtuCmxieU4,54526
+meridian/model/model_test_data.py,sha256=cG_8vBMRJJ3O63uVDz4x1tdJRaVQXsYQtQvfScBoXV4,21878
+meridian/model/posterior_sampler.py,sha256=xFnvRw-Arz8j6a2oj5ywOCN1r5JcbZRADBWOrdVPFE8,26910
+meridian/model/prior_distribution.py,sha256=xHNysn9sGjQL4xUOyoeMbTJwYyCmTbXykvEA9rNkkXY,57081
 meridian/model/prior_sampler.py,sha256=IKkVF-TUN3tFvnHKRrXI3A5slKq1vPcUn5e3u9UsfPU,23422
 meridian/model/spec.py,sha256=6ioI_wU6E2c-i7oltJUjBYHb3FxhRCyhWtuCx8GqkFA,19206
-meridian/model/transformers.py,sha256=jbGTib5Yj4qutXOHPLeHEromLeUkKeaRJh3PNr8vIhs,8258
+meridian/model/transformers.py,sha256=68pf6-6nG2eAgrE-ZM30S-cWCmNTftrRQZKjIoVHRO4,8230
 meridian/model/eda/__init__.py,sha256=MrGW1NER0JNsnWJRO5aeFEmMTDVYi4HgMmLXZaw_bbk,685
-meridian/model/eda/eda_engine.py,sha256=WJX3LW6DfV9z9i5wksrOSINj5zJh-nXhGLXZuVnZONM,10715
-google_meridian-1.2.0.dist-info/METADATA,sha256=MzZqcHOEVUJvfDapEsG1HewOUMBU_fAM1VEEP7RyoJY,22462
-google_meridian-1.2.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-google_meridian-1.2.0.dist-info/top_level.txt,sha256=nwaCebZvvU34EopTKZsjK0OMTFjVnkf4FfnBN_TAc0g,9
-google_meridian-1.2.0.dist-info/RECORD,,
+meridian/model/eda/eda_engine.py,sha256=QjOFril0NTonBg9mqx6nrBUfK5F_A53UcX-l6QSqgo8,25462
+google_meridian-1.2.1.dist-info/METADATA,sha256=zfGooQwkjN_mFUPDu7Y09SZ6euAEo_zaG4V_RAUt0T4,22462
+google_meridian-1.2.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+google_meridian-1.2.1.dist-info/top_level.txt,sha256=nwaCebZvvU34EopTKZsjK0OMTFjVnkf4FfnBN_TAc0g,9
+google_meridian-1.2.1.dist-info/RECORD,,

meridian/analysis/analyzer.py

@@ -675,43 +675,66 @@ def _validate_flexible_selected_times(
     selected_times: Sequence[str] | Sequence[bool] | None,
     media_selected_times: Sequence[str] | Sequence[bool] | None,
     new_n_media_times: int,
+    new_time: Sequence[str] | None = None,
 ):
   """Raises an error if selected times or media selected times is invalid.
 
-  This checks that the `selected_times` and `media_selected_times` arguments
-  are lists of booleans with the same number of elements as `new_n_media_times`.
-  This is only relevant if the time dimension of any of the variables in
-  `new_data` used in the analysis is modified.
+  This checks that (1) the `selected_times` and `media_selected_times` arguments
+  are lists of booleans with the same number of elements as `new_n_media_times`,
+  or (2) the `selected_times` and `media_selected_times` arguments are lists of
+  strings and the `new_time` list is provided and `selected_times` and
+  `media_selected_times` are subsets of `new_time`. This is only relevant if the
+  time dimension of any of the variables in `new_data` used in the analysis is
+  modified.
 
   Args:
     selected_times: Optional list of times to validate.
     media_selected_times: Optional list of media times to validate.
     new_n_media_times: The number of time periods in the new data.
+    new_time: The optional time dimension of the new data.
   """
   if selected_times and (
-      not _is_bool_list(selected_times)
-      or len(selected_times) != new_n_media_times
+      not (
+          _is_bool_list(selected_times)
+          and len(selected_times) == new_n_media_times
+      )
+      and not (
+          _is_str_list(selected_times)
+          and new_time is not None
+          and set(selected_times) <= set(new_time)
+      )
   ):
     raise ValueError(
         "If `media`, `reach`, `frequency`, `organic_media`,"
         " `organic_reach`, `organic_frequency`, `non_media_treatments`, or"
         " `revenue_per_kpi` is provided with a different number of time"
-        " periods than in `InputData`, then `selected_times` must be a list"
+        " periods than in `InputData`, then (1) `selected_times` must be a list"
         " of booleans with length equal to the number of time periods in"
-        " the new data."
+        " the new data, or (2) `selected_times` must be a list of strings and"
+        " `new_time` must be provided and `selected_times` must be a subset of"
+        " `new_time`."
     )
 
   if media_selected_times and (
-      not _is_bool_list(media_selected_times)
-      or len(media_selected_times) != new_n_media_times
+      not (
+          _is_bool_list(media_selected_times)
+          and len(media_selected_times) == new_n_media_times
+      )
+      and not (
+          _is_str_list(media_selected_times)
+          and new_time is not None
+          and set(media_selected_times) <= set(new_time)
+      )
   ):
     raise ValueError(
         "If `media`, `reach`, `frequency`, `organic_media`,"
         " `organic_reach`, `organic_frequency`, `non_media_treatments`, or"
         " `revenue_per_kpi` is provided with a different number of time"
-        " periods than in `InputData`, then `media_selected_times` must be"
+        " periods than in `InputData`, then (1) `media_selected_times` must be"
         " a list of booleans with length equal to the number of time"
-        " periods in the new data."
+        " periods in the new data, or (2) `media_selected_times` must be a list"
+        " of strings and `new_time` must be provided and"
+        " `media_selected_times` must be a subset of `new_time`."
     )
 
 
@@ -4056,6 +4079,7 @@ class Analyzer:
 
   def response_curves(
       self,
+      new_data: DataTensors | None = None,
       spend_multipliers: list[float] | None = None,
       use_posterior: bool = True,
       selected_geos: Sequence[str] | None = None,
@@ -4081,6 +4105,15 @@ class Analyzer:
     `selected_times` are also scaled by the multiplier.)
 
     Args:
+      new_data: Optional `DataTensors` object with optional new tensors:
+        `media`, `reach`, `frequency`, `media_spend`, `rf_spend`,
+        `revenue_per_kpi`, `times`. If provided, the response curves are
+        calculated using the values of the tensors passed in `new_data` and the
+        original values of all the remaining tensors. If `None`, the response
+        curves are calculated using the original values of all the tensors. If
+        any of the tensors in `new_data` is provided with a different number of
+        time periods than in `InputData`, then all tensors must be provided with
+        the same number of time periods and the `time` tensor must be provided.
       spend_multipliers: List of multipliers. Each channel's total spend is
         multiplied by these factors to obtain the values at which the curve is
         calculated for that channel.
@@ -4088,8 +4121,11 @@ class Analyzer:
         generated. If `False`, prior response curves are generated.
       selected_geos: Optional list containing a subset of geos to include. By
         default, all geos are included.
-      selected_times: Optional list containing a subset of dates to include. By
-        default, all time periods are included.
+      selected_times: Optional list containing a subset of dates to include. If
+        `new_data` is provided with modified time periods, then `selected_times`
+        must be a subset of `new_data.times`. Otherwise, `selected_times` must
+        be a subset of `self._meridian.input_data.time`. By default, all time
+        periods are included.
       by_reach: Boolean. For channels with reach and frequency. If `True`, plots
         the response curve by reach. If `False`, plots the response curve by
         frequency.
@@ -4118,11 +4154,49 @@ class Analyzer:
         "aggregate_geos": True,
         "aggregate_times": True,
     }
+    if new_data is None:
+      new_data = DataTensors()
+    # TODO: b/442920356 - Support flexible time without providing exact dates.
+    required_tensors_names = constants.PERFORMANCE_DATA + (constants.TIME,)
+    filled_data = new_data.validate_and_fill_missing_data(
+        required_tensors_names=required_tensors_names,
+        meridian=self._meridian,
+        allow_modified_times=True,
+    )
+    new_n_media_times = filled_data.get_modified_times(self._meridian)
+
+    if new_n_media_times is None:
+      _validate_selected_times(
+          selected_times=selected_times,
+          input_times=self._meridian.input_data.time,
+          n_times=self._meridian.n_times,
+          arg_name="selected_times",
+          comparison_arg_name="the input data",
+      )
+    else:
+      new_time = np.asarray(filled_data.time).astype(str).tolist()
+      _validate_flexible_selected_times(
+          selected_times=selected_times,
+          media_selected_times=None,
+          new_n_media_times=new_n_media_times,
+          new_time=new_time,
+      )
+      # TODO: b/407847021 - Switch to Sequence[str] once it is supported.
+      if selected_times is not None:
+        selected_times = [x in selected_times for x in new_time]
+        dim_kwargs["selected_times"] = selected_times
+
     if self._meridian.n_rf_channels > 0 and use_optimal_frequency:
-      frequency = backend.ones_like(
-          self._meridian.rf_tensors.frequency
-      ) * backend.to_tensor(
+      opt_freq_data = DataTensors(
+          media=filled_data.media,
+          rf_impressions=filled_data.reach * filled_data.frequency,
+          media_spend=filled_data.media_spend,
+          rf_spend=filled_data.rf_spend,
+          revenue_per_kpi=filled_data.revenue_per_kpi,
+      )
+      frequency = backend.ones_like(filled_data.frequency) * backend.to_tensor(
           self.optimal_freq(
+              new_data=opt_freq_data,
               selected_geos=selected_geos,
               selected_times=selected_times,
               use_kpi=use_kpi,
@@ -4130,12 +4204,12 @@ class Analyzer:
           dtype=backend.float32,
       )
       reach = backend.divide_no_nan(
-          self._meridian.rf_tensors.reach * self._meridian.rf_tensors.frequency,
+          filled_data.reach * filled_data.frequency,
           frequency,
       )
     else:
-      frequency = self._meridian.rf_tensors.frequency
-      reach = self._meridian.rf_tensors.reach
+      frequency = filled_data.frequency
+      reach = filled_data.reach
     if spend_multipliers is None:
       spend_multipliers = list(np.arange(0, 2.2, 0.2))
     incremental_outcome = np.zeros((
@@ -4149,18 +4223,19 @@ class Analyzer:
             (len(self._meridian.input_data.get_all_paid_channels()), 3)
         )  # Last dimension = 3 for the mean, ci_lo and ci_hi.
         continue
-      new_data = _scale_tensors_by_multiplier(
+      scaled_data = _scale_tensors_by_multiplier(
           data=DataTensors(
-              media=self._meridian.media_tensors.media,
+              media=filled_data.media,
               reach=reach,
               frequency=frequency,
+              revenue_per_kpi=filled_data.revenue_per_kpi,
           ),
           multiplier=multiplier,
           by_reach=by_reach,
       )
       inc_outcome_temp = self.incremental_outcome(
           use_posterior=use_posterior,
-          new_data=new_data.filter_fields(constants.PAID_DATA),
+          new_data=scaled_data.filter_fields(constants.PAID_DATA),
           inverse_transform_outcome=True,
           batch_size=batch_size,
           use_kpi=use_kpi,
@@ -4171,22 +4246,11 @@ class Analyzer:
           inc_outcome_temp, confidence_level
       )
 
-    if self._meridian.n_media_channels > 0 and self._meridian.n_rf_channels > 0:
-      spend = backend.concatenate(
-          [
-              self._meridian.media_tensors.media_spend,
-              self._meridian.rf_tensors.rf_spend,
-          ],
-          axis=-1,
-      )
-    elif self._meridian.n_media_channels > 0:
-      spend = self._meridian.media_tensors.media_spend
-    else:
-      spend = self._meridian.rf_tensors.rf_spend
-
-    if backend.rank(spend) == 3:
+    spend = filled_data.total_spend()
+    if spend is not None and spend.ndim == 3:
       spend = self.filter_and_aggregate_geos_and_times(
           tensor=spend,
+          flexible_time_dim=True,
           **dim_kwargs,
       )
     spend_einsum = backend.einsum("k,m->km", np.array(spend_multipliers), spend)