excluded _prior suffix from CLV models

docs/source/notebooks/clv/bg_nbd.ipynb

@@ -280,7 +280,7 @@
    "id": "0a5fc96b-eedd-43ae-bd70-5ae388f1f636",
    "metadata": {},
    "source": [
-    "Notice the additional `phi_dropout` and `kappa_dropout` priors. These were added to the default configuration to improve performance, but can be omitted when specifying a custom `model_config` with `a_prior` and `b_prior`.\n",
+    "Notice the additional `phi_dropout` and `kappa_dropout` priors. These were added to the default configuration to improve performance, but can be omitted when specifying a custom `model_config` with `a` and `b`.\n",
     "\n",
     "The specified model structure can also be visualized:"
    ]

docs/source/notebooks/clv/clv_quickstart.ipynb

@@ -576,10 +576,10 @@
    "outputs": [],
    "source": [
     "model_config = {\n",
-    "    \"a_prior\": Prior(\"HalfNormal\", sigma=10),\n",
-    "    \"b_prior\": Prior(\"HalfNormal\", sigma=10),\n",
-    "    \"alpha_prior\": Prior(\"HalfNormal\", sigma=10),\n",
-    "    \"r_prior\": Prior(\"HalfNormal\", sigma=10),\n",
+    "    \"a\": Prior(\"HalfNormal\", sigma=10),\n",
+    "    \"b\": Prior(\"HalfNormal\", sigma=10),\n",
+    "    \"alpha\": Prior(\"HalfNormal\", sigma=10),\n",
+    "    \"r\": Prior(\"HalfNormal\", sigma=10),\n",
     "}"
    ]
   },

docs/source/notebooks/clv/dev/beta_geo_beta_binom.ipynb

@@ -52,10 +52,10 @@
    ],
    "source": [
     "model_config = {\n",
-    "    \"alpha_prior\": Prior(\"HalfFlat\"),\n",
-    "    \"beta_prior\": Prior(\"HalfFlat\"),\n",
-    "    \"gamma_prior\": Prior(\"HalfFlat\"),\n",
-    "    \"delta_prior\": Prior(\"HalfFlat\"),\n",
+    "    \"alpha\": Prior(\"HalfFlat\"),\n",
+    "    \"beta\": Prior(\"HalfFlat\"),\n",
+    "    \"gamma\": Prior(\"HalfFlat\"),\n",
+    "    \"delta\": Prior(\"HalfFlat\"),\n",
     "}\n",
     "\n",
     "model = BetaGeoBetaBinomModel(data=data,model_config=model_config)\n",

docs/source/notebooks/clv/mbg_nbd.ipynb

@@ -269,7 +269,7 @@
    "id": "0a5fc96b-eedd-43ae-bd70-5ae388f1f636",
    "metadata": {},
    "source": [
-    "Notice the additional `phi_dropout` and `kappa_dropout` priors. These were added to the default configuration to improve performance, but can be omitted when specifying a custom `model_config` with `a_prior` and `b_prior`.\n",
+    "Notice the additional `phi_dropout` and `kappa_dropout` priors. These were added to the default configuration to improve performance, but can be omitted when specifying a custom `model_config` with `a` and `b`.\n",
     "\n",
     "The specified model structure can also be visualized:"
    ]

docs/source/notebooks/clv/pareto_nbd.ipynb

@@ -588,10 +588,10 @@
    "outputs": [],
    "source": [
     "flat_config = {\n",
-    "    \"r_prior\": Prior(\"HalfFlat\"),\n",
-    "    \"alpha_prior\": Prior(\"HalfFlat\"),\n",
-    "    \"s_prior\": Prior(\"HalfFlat\"),\n",
-    "    \"beta_prior\": Prior(\"HalfFlat\"),\n",
+    "    \"r\": Prior(\"HalfFlat\"),\n",
+    "    \"alpha\": Prior(\"HalfFlat\"),\n",
+    "    \"s\": Prior(\"HalfFlat\"),\n",
+    "    \"beta\": Prior(\"HalfFlat\"),\n",
     "}\n",
     "\n",
     "pnbd_pymc = clv.ParetoNBDModel(data=rfm_data, model_config=flat_config)"

pymc_marketing/clv/models/basic.py

@@ -47,6 +47,19 @@
         non_distributions: list[str] | None = None,
     ):
         model_config = model_config or {}
+
+        deprecated_keys = [key for key in model_config if key.endswith("_prior")]
+        for key in deprecated_keys:
+            new_key = key.replace("_prior", "")
+            warnings.warn(
+                f"The key '{key}' in model_config is deprecated and will be removed in future versions."
+                f"Use '{new_key}' instead.",
+                DeprecationWarning,
+                stacklevel=2,
+            )
+
+            model_config[new_key] = model_config.pop(key)
+
         model_config = parse_model_config(
             model_config,
             non_distributions=non_distributions,
@@ -279,12 +292,28 @@
                 model_config=json.loads(idata.attrs["model_config"]),  # type: ignore
                 sampler_config=json.loads(idata.attrs["sampler_config"]),
             )
+
         model.idata = idata
+        model._rename_posterior_variables()
+
         model.build_model()  # type: ignore
         if model.id != idata.attrs["id"]:
             raise ValueError(f"Inference data not compatible with {cls._model_type}")
         return model
 
+    def _rename_posterior_variables(self):
+        """Rename variables in the posterior group to remove the _prior suffix.
+
+        This is used to support the old model configuration format, which used
+        to include a _prior suffix for each parameter.
+        """
+        prior_vars = [
+            var for var in self.idata.posterior.data_vars if var.endswith("_prior")
+        ]
+        rename_dict = {var: var.replace("_prior", "") for var in prior_vars}
+        self.idata.posterior = self.idata.posterior.rename(rename_dict)
+        return self.idata.posterior
+
     def thin_fit_result(self, keep_every: int):
         """Return a copy of the model with a thinned fit result.
 

pymc_marketing/clv/models/beta_geo.py

@@ -57,14 +57,14 @@
             * `T`: Time between the first purchase and the end of the observation period
     model_config : dict, optional
         Dictionary of model prior parameters:
-            * `alpha_prior`: Scale parameter for time between purchases; defaults to `Prior("Weibull", alpha=2, beta=10)`
-            * `r_prior`: Shape parameter for time between purchases; defaults to `Prior("Weibull", alpha=2, beta=1)`
-            * `a_prior`: Shape parameter of dropout process; defaults to `phi_purchase_prior` * `kappa_purchase_prior`
-            * `b_prior`: Shape parameter of dropout process; defaults to `1-phi_dropout_prior` * `kappa_dropout_prior`
-            * `phi_dropout_prior`: Nested prior for a and b priors; defaults to `Prior("Uniform", lower=0, upper=1)`
-            * `kappa_dropout_prior`: Nested prior for a and b priors; defaults to `Prior("Pareto", alpha=1, m=1)`
-            * `purchase_covariates_prior`: Coefficients for purchase rate covariates; defaults to `Normal(0, 3)`
-            * `dropout_covariates_prior`: Coefficients for dropout covariates; defaults to `Normal.dist(0, 3)`
+            * `alpha`: Scale parameter for time between purchases; defaults to `Prior("Weibull", alpha=2, beta=10)`
+            * `r`: Shape parameter for time between purchases; defaults to `Prior("Weibull", alpha=2, beta=1)`
+            * `a`: Shape parameter of dropout process; defaults to `phi_purchase` * `kappa_purchase`
+            * `b`: Shape parameter of dropout process; defaults to `1-phi_dropout` * `kappa_dropout`
+            * `phi_dropout`: Nested prior for a and b priors; defaults to `Prior("Uniform", lower=0, upper=1)`
+            * `kappa_dropout`: Nested prior for a and b priors; defaults to `Prior("Pareto", alpha=1, m=1)`
+            * `purchase_covariates`: Coefficients for purchase rate covariates; defaults to `Normal(0, 3)`
+            * `dropout_covariates`: Coefficients for dropout covariates; defaults to `Normal.dist(0, 3)`
             * `purchase_covariate_cols`: List containing column names of covariates for customer purchase rates.
             * `dropout_covariate_cols`: List containing column names of covariates for customer dropouts.
     sampler_config : dict, optional
@@ -100,10 +100,10 @@
         model = BetaGeoModel(
             data=data,
             model_config={
-                "r_prior": Prior("Weibull", alpha=2, beta=1),
-                "alpha_prior": Prior("HalfFlat"),
-                "a_prior": Prior("Beta", alpha=2, beta=3),
-                "b_prior": Prior("Beta", alpha=3, beta=2),
+                "r": Prior("Weibull", alpha=2, beta=1),
+                "alpha": Prior("HalfFlat"),
+                "a": Prior("Beta", alpha=2, beta=3),
+                "b": Prior("Beta", alpha=3, beta=2),
             },
             sampler_config={
                 "draws": 1000,
@@ -185,12 +185,12 @@
     def default_model_config(self) -> ModelConfig:
         """Default model configuration."""
         return {
-            "alpha_prior": Prior("Weibull", alpha=2, beta=10),
-            "r_prior": Prior("Weibull", alpha=2, beta=1),
-            "phi_dropout_prior": Prior("Uniform", lower=0, upper=1),
-            "kappa_dropout_prior": Prior("Pareto", alpha=1, m=1),
-            "purchase_coefficient_prior": Prior("Normal", mu=0, sigma=1),
-            "dropout_coefficient_prior": Prior("Normal", mu=0, sigma=1),
+            "alpha": Prior("Weibull", alpha=2, beta=10),
+            "r": Prior("Weibull", alpha=2, beta=1),
+            "phi_dropout": Prior("Uniform", lower=0, upper=1),
+            "kappa_dropout": Prior("Pareto", alpha=1, m=1),
+            "purchase_coefficient": Prior("Normal", mu=0, sigma=1),
+            "dropout_coefficient": Prior("Normal", mu=0, sigma=1),
             "purchase_covariate_cols": [],
             "dropout_covariate_cols": [],
         }
@@ -211,16 +211,12 @@
                     self.data[self.purchase_covariate_cols],
                     dims=["customer_id", "purchase_covariate"],
                 )
-                self.model_config[
-                    "purchase_coefficient_prior"
-                ].dims = "purchase_covariate"
+                self.model_config["purchase_coefficient"].dims = "purchase_covariate"
                 purchase_coefficient_alpha = self.model_config[
-                    "purchase_coefficient_prior"
+                    "purchase_coefficient"
                 ].create_variable("purchase_coefficient_alpha")
 
-                alpha_scale = self.model_config["alpha_prior"].create_variable(
-                    "alpha_scale"
-                )
+                alpha_scale = self.model_config["alpha"].create_variable("alpha_scale")
                 alpha = pm.Deterministic(
                     "alpha",
                     (
@@ -232,29 +228,27 @@
                     dims="customer_id",
                 )
             else:
-                alpha = self.model_config["alpha_prior"].create_variable("alpha")
+                alpha = self.model_config["alpha"].create_variable("alpha")
 
             # dropout priors
-            if "a_prior" in self.model_config and "b_prior" in self.model_config:
+            if "a" in self.model_config and "b" in self.model_config:
                 if self.dropout_covariate_cols:
                     dropout_data = pm.Data(
                         "dropout_data",
                         self.data[self.dropout_covariate_cols],
                         dims=["customer_id", "dropout_covariate"],
                     )
 
-                    self.model_config[
-                        "dropout_coefficient_prior"
-                    ].dims = "dropout_covariate"
+                    self.model_config["dropout_coefficient"].dims = "dropout_covariate"
                     dropout_coefficient_a = self.model_config[
-                        "dropout_coefficient_prior"
+                        "dropout_coefficient"
                     ].create_variable("dropout_coefficient_a")
                     dropout_coefficient_b = self.model_config[
-                        "dropout_coefficient_prior"
+                        "dropout_coefficient"
                     ].create_variable("dropout_coefficient_b")
 
-                    a_scale = self.model_config["a_prior"].create_variable("a_scale")
-                    b_scale = self.model_config["b_prior"].create_variable("b_scale")
+                    a_scale = self.model_config["a"].create_variable("a_scale")
+                    b_scale = self.model_config["b"].create_variable("b_scale")
                     a = pm.Deterministic(
                         "a",
                         a_scale
@@ -268,8 +262,8 @@
                         dims="customer_id",
                     )
                 else:
-                    a = self.model_config["a_prior"].create_variable("a")
-                    b = self.model_config["b_prior"].create_variable("b")
+                    a = self.model_config["a"].create_variable("a")
+                    b = self.model_config["b"].create_variable("b")
             else:
                 # hierarchical pooling of dropout rate priors
                 if self.dropout_covariate_cols:
@@ -279,22 +273,20 @@
                         dims=["customer_id", "dropout_covariate"],
                     )
 
-                    self.model_config[
-                        "dropout_coefficient_prior"
-                    ].dims = "dropout_covariate"
+                    self.model_config["dropout_coefficient"].dims = "dropout_covariate"
                     dropout_coefficient_a = self.model_config[
-                        "dropout_coefficient_prior"
+                        "dropout_coefficient"
                     ].create_variable("dropout_coefficient_a")
                     dropout_coefficient_b = self.model_config[
-                        "dropout_coefficient_prior"
+                        "dropout_coefficient"
                     ].create_variable("dropout_coefficient_b")
 
-                    phi_dropout = self.model_config[
-                        "phi_dropout_prior"
-                    ].create_variable("phi_dropout")
-                    kappa_dropout = self.model_config[
-                        "kappa_dropout_prior"
-                    ].create_variable("kappa_dropout")
+                    phi_dropout = self.model_config["phi_dropout"].create_variable(
+                        "phi_dropout"
+                    )
+                    kappa_dropout = self.model_config["kappa_dropout"].create_variable(
+                        "kappa_dropout"
+                    )
 
                     a_scale = pm.Deterministic(
                         "a_scale",
@@ -319,18 +311,18 @@
                     )
 
                 else:
-                    phi_dropout = self.model_config[
-                        "phi_dropout_prior"
-                    ].create_variable("phi_dropout")
-                    kappa_dropout = self.model_config[
-                        "kappa_dropout_prior"
-                    ].create_variable("kappa_dropout")
+                    phi_dropout = self.model_config["phi_dropout"].create_variable(
+                        "phi_dropout"
+                    )
+                    kappa_dropout = self.model_config["kappa_dropout"].create_variable(
+                        "kappa_dropout"
+                    )
 
                     a = pm.Deterministic("a", phi_dropout * kappa_dropout)
                     b = pm.Deterministic("b", (1.0 - phi_dropout) * kappa_dropout)
 
             # r remains unchanged with or without covariates
-            r = self.model_config["r_prior"].create_variable("r")
+            r = self.model_config["r"].create_variable("r")
 
             BetaGeoNBD(
                 name="recency_frequency",