pypricing 0.0.1__tar.gz

pypricing-0.0.1/LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

pypricing-0.0.1/PKG-INFO

@@ -0,0 +1,371 @@
+Metadata-Version: 2.4
+Name: pypricing
+Version: 0.0.1
+Summary: Bayesian price analytics with PyMC
+Author-email: Arthur Mello <arthur.bmello@gmail.com>
+Maintainer-email: Arthur Mello <arthur.bmello@gmail.com>
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://github.com/arthurmello/pypricing
+Project-URL: Documentation, https://pypricing.readthedocs.io
+Project-URL: Repository, https://github.com/arthurmello/pypricing
+Project-URL: Issues, https://github.com/arthurmello/pypricing/issues
+Keywords: bayesian,demand,elasticity,pricing,pymc
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Scientific/Engineering
+Classifier: Topic :: Scientific/Engineering :: Mathematics
+Classifier: Typing :: Typed
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: arviz>=0.17
+Requires-Dist: matplotlib>=3.7
+Requires-Dist: numpy>=1.24
+Requires-Dist: pandas>=2.0
+Requires-Dist: pymc>=5.0
+Requires-Dist: pymc-marketing>=0.19.0
+Requires-Dist: scipy>=1.10
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0; extra == "dev"
+Requires-Dist: ruff>=0.15.7; extra == "dev"
+Provides-Extra: docs
+Requires-Dist: sphinx>=7.0; extra == "docs"
+Requires-Dist: myst-nb>=1.0; extra == "docs"
+Requires-Dist: furo>=2024.1.29; extra == "docs"
+Requires-Dist: sphinx-copybutton>=0.5; extra == "docs"
+Provides-Extra: graphviz
+Requires-Dist: graphviz>=0.21; extra == "graphviz"
+Dynamic: license-file
+
+# pypricing
+
+Bayesian own-price elasticity estimation with PyMC for long-format panels (one row per SKU–time observation).
+
+This is currently an MVP for log-demand panels (per-SKU intercept + per-SKU elasticity) with:
+
+- optional **shared control** regressors (`control_`* columns)
+- optional **hierarchical / partial pooling** across group columns
+- optional **cross-price elasticities** (`CrossElasticitySpec`)
+- simple diagnostics + plotting helpers
+- posterior predictive simulation for counterfactual price scenarios
+- per-SKU **revenue price optimization** (`optimize_prices`)
+
+## Install
+
+```bash
+pip install pypricing
+```
+
+Optional model-graph rendering (also needs the [system Graphviz](https://graphviz.org/download/) binaries):
+
+```bash
+pip install 'pypricing[graphviz]'
+```
+
+Docs: [pypricing.readthedocs.io](https://pypricing.readthedocs.io)
+
+### Development
+
+From a clone of this repository:
+
+```bash
+uv sync --extra dev
+uv run pytest
+```
+
+For local docs builds: `uv sync --extra docs`.
+
+## Quickstart
+
+```python
+import numpy as np
+
+from pypricing import LogLogDemandModel, generate_mock_data
+
+# 1) Example data (replace with your own panel)
+df = generate_mock_data(
+    n_periods=20,
+    n_skus=5,
+    n_controls=2,     # creates control_1, control_2
+    random_state=0,
+)
+
+# 2) Fit
+model = LogLogDemandModel()
+idata = model.fit(
+    df,
+    draws=1000,
+    tune=1000,
+    chains=4,
+    random_seed=42,
+)
+
+print(model.run_diagnostics())
+print(model.fit_summary().head())
+
+# 3) Counterfactual prediction (quantity column not required)
+df_scenario = df.drop(columns=["quantity"]).copy()
+df_scenario["price"] = df_scenario["price"] * 1.05  # +5% price scenario
+
+pred = model.predict(df_scenario, hdi_prob=0.9, random_seed=123)
+print(pred[["sku", "period", "price", "quantity_mean", "quantity_hdi_lower", "quantity_hdi_upper"]].head())
+
+# 4) Plots
+_ = model.plot_elasticity_posterior(hdi_prob=0.9)
+
+sku0 = model.sku_levels_[0]
+price_grid = np.linspace(df["price"].min(), df["price"].max(), 25)
+controls = {c: float(df.loc[df["sku"] == sku0, c].iloc[0]) for c in model.control_names_}
+_ = model.plot_response_curve(sku=sku0, price_grid=price_grid, controls=controls, hdi_prob=0.9)
+```
+
+## Data format
+
+`LogLogDemandModel.fit(df)` expects a pandas DataFrame with **level-scale** columns:
+
+- **Required**
+  - `sku` (configurable via `sku_col`)
+  - `price` (configurable via `price_col`) — must be **strictly positive**
+  - `quantity` (configurable via `quantity_col`) — must be **non-negative**
+- **Optional**
+  - `control_`* columns (or pass an explicit `control_columns=(...)` via `PanelColumns`) — must be numeric, no NaNs
+  - hierarchy columns (e.g. `category_1`, `category_2`) via `PanelColumns(group_columns=...)`
+  - `period` (and often `region`) for `fit_train_test()` / cross-elasticity market cells
+
+Internally the model works on logs:
+
+- `log_price = log(price)`
+- `log_quantity = log(max(quantity, quantity_floor))`
+
+The default `quantity_floor=1.0` allows zero quantities without \log(0).
+
+## What model is being fit?
+
+At a high level this package fits **log-demand** with Gaussian noise:
+
+
+\log Q \sim \mathcal{N}(\mu, \sigma)
+
+
+Where \mu is a per-SKU demand curve plus optional global control effects.
+
+### Demand curve model classes
+
+Pick the model class directly:
+
+- `LogLogDemandModel` (default/simple)
+- `QuadraticLogDemandModel`
+- `SigmoidSaturationDemandModel`
+
+#### `log_log` (default)
+
+Constant elasticity log-log:
+
+
+$\mu = \alpha_{\text{sku}} + \epsilon_{\text{sku}} \log P + X\beta$
+
+
+- **Interpretation**: \epsilon_{\text{sku}} is own-price elasticity.
+  - Example: \epsilon=-1.5 implies a 1% price increase → ~1.5% quantity decrease (locally / in expectation).
+- **Best when**: you want a simple constant-elasticity approximation.
+
+#### `quadratic`
+
+Allows elasticity to vary with price (curvature in log-price):
+
+
+$\mu = \alpha_{\text{sku}} + \beta_{1,\text{sku}}\log P + c_{\text{sku}} (\log P)^2 + X\beta$
+
+
+This parameterization enforces that the elasticity at a **per-SKU midpoint price** equals `elasticity_sku`.
+The midpoint is computed from the training data as the **median** log-price per SKU.
+
+- **Best when**: elasticity changes with price level (e.g., premium vs discount regimes).
+
+#### `sigmoid`
+
+Saturating response curve in **level price** (softplus / log-sigmoid form):
+
+
+\mu = \alpha_{\text{sku}} - \mathrm{softplus}(b_{\text{sku}}(P - P_{\text{center,sku}})) + X\beta
+
+
+The per-SKU **center** `P_{\text{center,sku}} = \exp(\texttt{log\_price\_center\_sku})` is a **learned** parameter.
+Its prior is centered at the empirical per-SKU median log-price from training data (`log_price_midpoint_sku_`), with default `sigma=0.5`.
+The curve is parameterized so the elasticity at `P_{\text{center,sku}}` equals `elasticity_sku` (via `b_sku = -2 * elasticity_sku / price_center_sku`).
+
+- **Best when**: response “flattens out” at extreme prices (a simple saturation behavior).
+
+### Controls (`control_`*)
+
+If your frame contains `control_*` columns (or you pass `control_columns=(...)`), the model includes a **shared** linear term X\beta:
+
+- one global coefficient vector `beta_control` shared across all SKUs
+- controls must also be provided at prediction time
+
+### Priors and customization (`model_config`)
+
+You can override priors by passing `model_config` to each model class constructor.
+Each entry uses:
+
+```python
+{
+    "dist": <PyMC distribution constructor>,
+    "kwargs": { ... },
+}
+```
+
+Example:
+
+```python
+import pymc as pm
+from pypricing import QuadraticLogDemandModel
+
+model = QuadraticLogDemandModel(
+    model_config={
+        "alpha_sku": {"dist": pm.Normal, "kwargs": {"mu": 0.0, "sigma": 1.0}},
+        "elasticity_sku": {"dist": pm.Normal, "kwargs": {"mu": -1.0, "sigma": 0.7}},
+        "sigma": {"dist": pm.HalfNormal, "kwargs": {"sigma": 0.3}},
+        # "curvature_sku": ... (only used by QuadraticLogDemandModel)
+        # "beta_control": ...  (only used when you have controls)
+    }
+)
+```
+
+Defaults today:
+
+- `alpha_sku ~ Normal(mu=6, sigma=2)`
+- `elasticity_sku ~ Normal(mu=-1, sigma=2)`
+- `sigma ~ HalfNormal(sigma=0.5)`
+- `beta_control ~ Normal(mu=0, sigma=0.5)` (if controls exist)
+- `curvature_sku ~ Normal(mu=0, sigma=0.2)` (only for `quadratic`)
+- `log_price_center_sku ~ Normal(mu=log_price_midpoint_sku_, sigma=0.5)` (only for `sigmoid`)
+
+## Prediction
+
+- `sample_posterior_predictive(df)` returns an `xarray.Dataset` with posterior draws for `log_quantity` and `quantity`.
+- `predict(df)` returns a DataFrame with:
+  - `quantity_mean`
+  - `quantity_hdi_lower`
+  - `quantity_hdi_upper`
+
+Prediction requires:
+
+- `sku` and `price`
+- all control columns used during fit (if any)
+- `quantity` is **not** required
+
+Unknown SKUs at prediction time raise an error (no cold-start handling yet).
+
+## Train/test evaluation (time-aware)
+
+`fit_train_test(df, period_col="period", test_size=0.2, ...)`:
+
+- holds out the **last** fraction of unique periods (to avoid time leakage)
+- fits on train, predicts on test
+- returns:
+  - `rmse` on `quantity_mean`
+  - `hdi_coverage`: fraction of true quantities inside the predicted HDI
+  - `test_predictions`: the prediction frame
+
+## Save / load
+
+`<ModelClass>.save(path)` saves the model `InferenceData` to NetCDF (`.nc`) with model attrs.
+
+`<ModelClass>.load(path)` restores the model from that NetCDF artifact and rebuilds the PyMC model.
+
+## Interpretation helper
+
+`pypricing.posterior.summarize_quantity_multiplier_one_sku(...)` converts posterior elasticity draws into a posterior over relative quantity change for a price multiplier m via m^{\epsilon}.
+
+For all SKUs at once, use the model method:
+
+- `model.quantity_multiplier_summary(price_multiplier=..., hdi_prob=...)`
+- returns one row per SKU with mean and HDI bounds of the quantity multiplier
+- optionally, `model.quantity_multiplier_summary(..., return_draws=True)` returns
+  `(summary_df, draws_da)` where `draws_da` has dims `("chain", "draw", "sku")`
+
+This is only valid for `LogLogDemandModel` (constant elasticity).
+
+## Price optimization
+
+`optimize_prices` (also available as `model.optimize_prices(...)`) chooses one price per SKU that maximizes the posterior **mean** of revenue `price * exp(μ)`, where `μ` is the demand-curve mean log-quantity (same convention as prediction; residual `σ` is not folded into `exp(μ)`).
+
+```python
+from pypricing import LogLogDemandModel, generate_mock_data
+
+df = generate_mock_data(n_periods=20, n_skus=5, n_controls=1, random_state=0)
+model = LogLogDemandModel()
+model.fit(df, draws=500, tune=500, chains=2, random_seed=0)
+
+price_bounds = {
+    sku: (float(g["price"].min() * 0.8), float(g["price"].max() * 1.3))
+    for sku, g in df.groupby("sku")
+}
+controls_df = (
+    df.groupby("sku", as_index=False)[model.control_names_].median()
+)
+opt = model.optimize_prices(price_bounds=price_bounds, controls_df=controls_df)
+print(opt.head())
+```
+
+Caveats:
+
+- Optimization is **per-SKU and independent** (1D SciPy search on log-price within bounds).
+- **Not supported** when `cross_elasticity` is enabled (revenue then depends on the full market cell).
+- For `LogLogDemandModel`, expected revenue is proportional to `p^(1+ε)` draw-wise; if elasticity is roughly constant and `|ε| ≠ 1`, the optimum often sits on a **bound**.
+- If the model was fit with controls, pass `controls_df` with one row per SKU.
+
+See `docs/source/notebooks/quickstart.ipynb` for plots (`plot_revenue_vs_price`, `plot_optimization_summary`).
+
+## Hierarchy and cross-elasticity
+
+Pass column mapping via `PanelColumns`:
+
+```python
+from pypricing import CrossElasticitySpec, LogLogDemandModel, PanelColumns
+
+model = LogLogDemandModel(
+    panel_columns=PanelColumns(group_columns=("category_1", "category_2")),
+    cross_elasticity=CrossElasticitySpec(mode="within_group", group_level=0),
+)
+```
+
+Omit `cross_elasticity` for own-price only. Use `mode="all"` for every directed SKU pair (no `group_level`).
+
+## What is NOT implemented (yet)
+
+- Cold-start prediction for unseen SKUs
+- Joint / cross-aware price optimization (use counterfactual prediction on a full market cell instead)
+
+## Documentation
+
+Hosted docs (API + notebooks): [https://pypricing.readthedocs.io](https://pypricing.readthedocs.io)
+
+To build HTML locally (Sphinx + notebooks, no notebook re-execution):
+
+```bash
+uv sync --extra docs
+cd docs && uv run make html
+# open docs/build/html/index.html
+```
+
+## Development
+
+```bash
+uv sync --extra dev
+uv run pytest                 # unit + integration (default)
+uv run pytest -m unit         # fast only
+uv run pytest -m integration  # short MCMC smoke
+uv run pytest -m recovery     # parameter recovery (slower)
+uv run ruff check src tests
+```
+