fprcal 0.1.0__py3-none-any.whl

fprcal/__init__.py

@@ -0,0 +1,28 @@
+# Copyright 2026 Cisco Systems, Inc. and its affiliates
+#
+# 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.
+#
+# SPDX-License-Identifier: Apache-2.0
+
+"""FPR-based model calibration using sklearn IsotonicRegression."""
+
+from importlib.metadata import version as _distribution_version
+
+from fprcal.calibration import (
+    fit_calibration_pipeline,
+    fpr_to_calibrated,
+)
+
+__all__ = ["__version__", "fit_calibration_pipeline", "fpr_to_calibrated"]
+
+__version__ = _distribution_version("fprcal")

fprcal/calibration.py

@@ -0,0 +1,269 @@
+# Copyright 2026 Cisco Systems, Inc. and its affiliates
+#
+# 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.
+#
+# SPDX-License-Identifier: Apache-2.0
+
+"""FPR-based calibration using sklearn Pipeline.
+
+Two-step fitting, single-step inference:
+1. Fit temporary IsotonicRegression: FPR -> score (discarded after fitting).
+2. Fit final IsotonicRegression: score -> calibrated (kept in pipeline).
+
+The final pipeline stores about ``n_knots`` (score, calibrated) knots regardless
+of training set size.
+"""
+
+from __future__ import annotations
+
+from typing import Literal
+
+import numpy as np
+from numpy.typing import NDArray
+from sklearn.isotonic import IsotonicRegression
+from sklearn.pipeline import Pipeline
+from sklearn.preprocessing import MinMaxScaler
+
+SCORE_MAX: float = 0.99
+PlottingPosition = Literal["filliben", "mean"]
+
+# FPR-to-calibrated mapping knots (piecewise linear in log10(FPR) space).
+_FPR_CAL_KNOTS: list[tuple[int, float]] = [
+    (0, 0.0),  # 100% FPR    -> cal=0.0
+    (-1, 0.1),  # 10% FPR     -> cal=0.1
+    (-2, 0.3),  # 1% FPR      -> cal=0.3
+    (-3, 0.5),  # 0.1% FPR    -> cal=0.5
+    (-4, 0.7),  # 0.01% FPR   -> cal=0.7
+    (-5, 0.85),  # 0.001% FPR  -> cal=0.85
+    (-6, 0.95),  # 0.0001% FPR -> cal=0.95
+    (-10, 0.99),  # ~0% FPR     -> cal=0.99
+]
+
+_sorted_idx = np.argsort([k[0] for k in _FPR_CAL_KNOTS])
+_LOG_FPR_KNOTS: NDArray[np.float64] = np.array(
+    [_FPR_CAL_KNOTS[i][0] for i in _sorted_idx], dtype=np.float64
+)
+_CAL_KNOTS: NDArray[np.float64] = np.array(
+    [_FPR_CAL_KNOTS[i][1] for i in _sorted_idx], dtype=np.float64
+)
+_FPR_KNOTS: NDArray[np.float64] = 10.0**_LOG_FPR_KNOTS
+
+
+def fpr_to_calibrated(fpr: NDArray[np.float64] | float) -> NDArray[np.float64]:
+    """Map FPR values to calibrated [0, 1] scores via the fixed log-scale anchors.
+
+    Parameters
+    ----------
+    fpr : array-like or float
+        False positive rate in ``[0, 1]``. Values outside this range are clipped
+        to ``[1e-10, 1.0]`` before interpolation.
+
+    Returns
+    -------
+    ndarray
+        Calibrated scores in ``[0, 0.99]``. The anchors are: FPR=1 -> 0.0,
+        FPR=0.1 -> 0.1, FPR=0.01 -> 0.3, FPR=0.001 -> 0.5, FPR=0.0001 -> 0.7,
+        FPR=1e-5 -> 0.85, FPR=1e-6 -> 0.95, FPR=1e-10 -> 0.99.
+    """
+    fpr_arr = np.asarray(fpr, dtype=np.float64)
+    log_fpr = np.log10(np.clip(fpr_arr, 1e-10, 1.0))
+    return np.interp(log_fpr, _LOG_FPR_KNOTS, _CAL_KNOTS)
+
+
+def _sample_fpr_values(n_total: int = 1000) -> NDArray[np.float64]:
+    """Sample FPR values including all explicit knots, with log-spaced fill between.
+
+    Returns FPR values (not log) sorted in increasing order. Covers the full
+    log-anchor contract range from 1e-10 to 1.0 so the second isotonic has
+    knots across every decade the contract defines.
+    """
+    # Explicit knot FPRs covering every decade the contract defines.
+    explicit_fprs = [1e-10, 1e-9, 1e-8, 1e-7, 1e-6, 1e-5, 1e-4, 1e-3, 1e-2, 1e-1, 1.0]
+
+    n_explicit = len(explicit_fprs)
+    n_fill = n_total - n_explicit
+    n_gaps = n_explicit - 1
+    points_per_gap = n_fill // n_gaps
+
+    all_fprs: list[float] = []
+    for i in range(n_gaps):
+        fpr_lo = explicit_fprs[i]
+        fpr_hi = explicit_fprs[i + 1]
+        fill = np.logspace(np.log10(fpr_lo), np.log10(fpr_hi), points_per_gap + 2)[1:-1]
+        all_fprs.append(fpr_lo)
+        all_fprs.extend(fill)
+    all_fprs.append(explicit_fprs[-1])
+
+    return np.array(sorted(set(all_fprs)), dtype=np.float64)
+
+
+def _extrapolate_score(fpr: float, fpr1: float, score1: float, fpr2: float, score2: float) -> float:
+    """Linear extrapolation from two (FPR, score) points."""
+    slope = (score2 - score1) / (fpr2 - fpr1)
+    return score1 + slope * (fpr - fpr1)
+
+
+def _plotting_positions(n: int, method: PlottingPosition) -> NDArray[np.float64]:
+    """Return upper-tail FPR plotting positions for sorted scores.
+
+    The returned array aligns with scores sorted in ascending order. Entry ``i``
+    is the plotting-position FPR for ``sorted_scores[i]`` under the inclusive
+    threshold convention ``score >= threshold``.
+    """
+    if n < 2:
+        raise ValueError("At least two benign scores are required for calibration")
+
+    rank_from_top = n - np.arange(n, dtype=np.float64)
+
+    if method == "mean":
+        return rank_from_top / (n + 1)
+
+    if method == "filliben":
+        positions = (rank_from_top - 0.3175) / (n + 0.365)
+        endpoint = 0.5 ** (1.0 / n)
+        positions[0] = endpoint
+        positions[-1] = 1.0 - endpoint
+        return positions
+
+    raise ValueError("plotting_position must be 'filliben' or 'mean'")
+
+
+def fit_calibration_pipeline(
+    benign_scores: NDArray[np.float64],
+    n_knots: int = 10000,
+    *,
+    keep_debug: bool = False,
+    plotting_position: PlottingPosition = "filliben",
+) -> Pipeline:
+    """Fit a whole-curve FPR calibration pipeline from benign scores.
+
+    The pipeline maps raw detector scores in ``[0, 1]`` to calibrated values in
+    ``[0, 0.99]``, where every calibrated value has a stable FPR meaning
+    (``0.5 = 0.1% FPR``, ``0.7 = 0.01%``, and so on).
+
+    Two-step fitting:
+
+    1. Fit a temporary ``IsotonicRegression`` on the benign empirical CDF to get
+       ``FPR -> score``.
+    2. Sample ~``n_knots`` FPR values on a log-spaced base grid, add the first
+       spline's fitted edge FPRs, and compute ``(score, calibrated)`` pairs.
+    3. Fit the final ``IsotonicRegression`` on those pairs as ``score -> calibrated``.
+
+    Parameters
+    ----------
+    benign_scores : ndarray
+        Scores from benign/negative samples, in ``[0, 1]``.
+    n_knots : int, optional
+        Approximate number of knots to store in the final pipeline. Default 10000.
+    keep_debug : bool, optional
+        When True, attach the first-pass ``fpr_to_score_`` isotonic and the
+        sampled FPR/score arrays to the returned Pipeline for plotting. These
+        attributes serialize under ``joblib.dump`` and inflate artifact size
+        with ``len(benign_scores)``, so the default is False for production use.
+    plotting_position : {"filliben", "mean"}, optional
+        FPR coordinate assigned to each sorted benign threshold in the temporary
+        FPR-to-score spline. ``"filliben"`` uses median-centered order-statistic
+        plotting positions and is the default. ``"mean"`` uses the mean-centered
+        ``k/(n+1)`` positions.
+
+    Returns
+    -------
+    sklearn.pipeline.Pipeline
+        Fitted sklearn Pipeline with ``MinMaxScaler`` and ``IsotonicRegression``
+        stages. Call ``pipeline.predict(scores.reshape(-1, 1))`` to calibrate.
+
+    Raises
+    ------
+    ValueError
+        If any benign score falls outside ``[0, 1]``.
+    """
+    benign_scores = np.asarray(benign_scores, dtype=np.float64).ravel()
+
+    if np.any(benign_scores < 0) or np.any(benign_scores > 1):
+        raise ValueError(
+            f"Scores must be in [0, 1], got [{benign_scores.min()}, {benign_scores.max()}]"
+        )
+
+    # Fit the rescaler on the input domain [0, 1] rather than on the
+    # observed calibration range. This makes the rescaler a pure
+    # ``raw * SCORE_MAX`` map, so inference scores above calib.max (but
+    # still in [0, 1]) land inside the isotonic's training range rather
+    # than clipping to calibrated 1.0. Isotonic is invariant to monotone
+    # rescale, so calibrated outputs for scores in [0, calib.max] are
+    # unchanged; scores in (calib.max, 1.0] now get honest calibrated
+    # values instead of the "flag nothing" terminal.
+    rescaler = MinMaxScaler(feature_range=(0, SCORE_MAX))
+    rescaler.fit(np.array([[0.0], [1.0]]))
+    scores_scaled = rescaler.transform(benign_scores.reshape(-1, 1)).ravel()
+
+    # Empirical CDF: (FPR, score) pairs.
+    # Evaluation counts still use the inclusive convention
+    # FPR(threshold) = P(score >= threshold). The first spline maps ordered
+    # thresholds to population FPR coordinates, so it uses a plotting position
+    # for each rank.
+    sorted_scores = np.sort(scores_scaled)
+    n = len(sorted_scores)
+    fprs = _plotting_positions(n, plotting_position)
+
+    # Step 1: temporary IsotonicRegression (FPR -> score).
+    fpr_to_score = IsotonicRegression(increasing=False, out_of_bounds="clip")
+    fpr_to_score.fit(fprs, sorted_scores)
+
+    min_fpr = float(fprs[-1])
+    fpr1, fpr2 = fprs[-2], fprs[-1]
+    score1, score2 = sorted_scores[-2], sorted_scores[-1]
+
+    # Step 2: sample FPR values, compute (score, calibrated) pairs.
+    sampled_fprs = _sample_fpr_values(n_knots)
+    first_spline_edge_fprs = np.array([fprs[0], fpr1, fpr2], dtype=np.float64)
+    sampled_fprs = np.unique(np.concatenate((sampled_fprs, first_spline_edge_fprs)))
+
+    knot_scores: list[float] = []
+    knot_calibrated: list[float] = []
+
+    for fpr in sampled_fprs:
+        if fpr >= min_fpr:
+            score = float(fpr_to_score.predict([[fpr]])[0])
+        else:
+            score = _extrapolate_score(fpr, fpr1, score1, fpr2, score2)
+            score = float(np.clip(score, 0, SCORE_MAX))
+
+        log_fpr = np.log10(max(fpr, 1e-10))
+        calibrated = float(np.interp(log_fpr, _LOG_FPR_KNOTS, _CAL_KNOTS))
+
+        knot_scores.append(score)
+        knot_calibrated.append(calibrated)
+
+    knot_scores_arr = np.array(knot_scores, dtype=np.float64)
+    knot_calibrated_arr = np.array(knot_calibrated, dtype=np.float64)
+
+    # Boundary pairs for the final rescaled-score-to-calibrated-score fit.
+    # Valid raw inputs are rescaled to at most SCORE_MAX and do not reach x=1.0.
+    knot_scores_arr = np.append(knot_scores_arr, [SCORE_MAX, 1.0])
+    knot_calibrated_arr = np.append(knot_calibrated_arr, [0.99, 1.0])
+
+    # Step 3: final IsotonicRegression (score -> calibrated).
+    score_to_cal = IsotonicRegression(increasing=True, out_of_bounds="clip")
+    score_to_cal.fit(knot_scores_arr, knot_calibrated_arr)
+
+    pipeline = Pipeline([("rescale", rescaler), ("isotonic", score_to_cal)])
+    setattr(pipeline, "plotting_position_", plotting_position)  # noqa: B010
+
+    if keep_debug:
+        # Debug artifacts for plotting; attached only when keep_debug=True so
+        # production pipelines serialize to a bounded size via joblib.dump.
+        setattr(pipeline, "fpr_to_score_", fpr_to_score)  # noqa: B010
+        setattr(pipeline, "sampled_fprs_", sampled_fprs)  # noqa: B010
+        setattr(pipeline, "sampled_scores_", knot_scores_arr[:-2])  # noqa: B010
+
+    return pipeline

fprcal-0.1.0.dist-info/METADATA

@@ -0,0 +1,298 @@
+Metadata-Version: 2.4
+Name: fprcal
+Version: 0.1.0
+Summary: Stable low-FPR calibration for detection model scores across model releases.
+Project-URL: Homepage, https://github.com/cisco-ai-defense/fpr-model-calibration
+Project-URL: Repository, https://github.com/cisco-ai-defense/fpr-model-calibration
+Project-URL: Issues, https://github.com/cisco-ai-defense/fpr-model-calibration/issues
+Project-URL: Changelog, https://github.com/cisco-ai-defense/fpr-model-calibration/blob/main/CHANGELOG.md
+Author-email: Konstantin Berlin <berlink@cisco.com>
+License:                                  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 [2025] [CISCO - AI DEFENSE]
+        
+           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.
+License-File: LICENSE
+Keywords: calibration,detector,false-positive-rate,isotonic,ml,security
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Security
+Requires-Python: >=3.12
+Requires-Dist: joblib>=1.4
+Requires-Dist: numpy>=2.2
+Requires-Dist: scikit-learn>=1.5
+Provides-Extra: dev
+Requires-Dist: matplotlib>=3.9; extra == 'dev'
+Requires-Dist: pandas>=2.2; extra == 'dev'
+Requires-Dist: pip-audit>=2.9; extra == 'dev'
+Requires-Dist: pytest-cov>=6.0; extra == 'dev'
+Requires-Dist: pytest>=8.3; extra == 'dev'
+Requires-Dist: ruff>=0.6; extra == 'dev'
+Requires-Dist: scipy>=1.13; extra == 'dev'
+Requires-Dist: ty>=0.0.34; extra == 'dev'
+Provides-Extra: examples
+Requires-Dist: matplotlib>=3.9; extra == 'examples'
+Requires-Dist: pandas>=2.2; extra == 'examples'
+Requires-Dist: scipy>=1.13; extra == 'examples'
+Description-Content-Type: text/markdown
+
+# FPRCal
+
+[![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
+
+Stable low-FPR calibration for detection model scores across model releases, with a fixed log-scale interpretability contract (`0.5 = 0.1% FPR`, `0.7 = 0.01%`, `0.85 = 0.001%`).
+
+## Why
+
+Raw scores from ML detectors drift across model releases and are not comparable across detector categories. Downstream product rules break on every retrain. This package calibrates detector scores to FPR on benign traffic, then applies a fixed log-scale transform so every calibrated value has the same FPR meaning across model versions and detector categories.
+
+## Install
+
+```bash
+python -m pip install fprcal
+```
+
+Requires Python 3.12+, numpy, scikit-learn, joblib.
+
+For an editable development install, use `python -m pip install -e ".[dev]"`.
+
+## Usage
+
+```python
+from fprcal import fit_calibration_pipeline
+import joblib
+
+pipeline = fit_calibration_pipeline(benign_scores, n_knots=10000)
+joblib.dump(pipeline, "calibration.pkl")
+
+# In production:
+pipeline = joblib.load("calibration.pkl")
+calibrated = pipeline.predict(raw_scores.reshape(-1, 1))
+```
+
+The first-pass FPR-to-threshold spline uses Filliben median-centered plotting
+positions by default. Pass `plotting_position="mean"` to use the mean-centered
+`k/(n+1)` positions instead.
+
+## Demo
+
+Reproduce the evaluation figure on the Credit Card Fraud Detection dataset (OpenML, 284K rows, 0.172% positives):
+
+```bash
+# One-time: download the data, train both detectors, save holdout scores
+python examples/generate_credit_card_roc.py
+
+# Fit on the calibration subset and evaluate its held-out complement
+python examples/calibration_demo.py
+```
+
+Writes `examples/credit_card_validation.png`. See [examples/credit_card_readme.md](examples/credit_card_readme.md) for dataset provenance.
+
+## License
+
+Apache License 2.0. See [LICENSE](LICENSE).
+
+Maintainers can find the release procedure in [RELEASING.md](RELEASING.md).

fprcal-0.1.0.dist-info/RECORD

@@ -0,0 +1,6 @@
+fprcal/__init__.py,sha256=Ug1fy2Yiy4g-IVYz_aZoU7yDTBrS5zlyeKewR_LVBzY,988
+fprcal/calibration.py,sha256=u6FlFV-geweqFJRtNQGeOLqg5jXRVlqhh9g6qSRisJQ,10837
+fprcal-0.1.0.dist-info/METADATA,sha256=_E7L-UU0cBXvwEyepiaPsU6hAYMcx0-6E-czTzjDANY,16782
+fprcal-0.1.0.dist-info/WHEEL,sha256=lCkmxWfQsSc9CfIClYeavTdQeEX2toPqufh9gI35EQA,87
+fprcal-0.1.0.dist-info/licenses/LICENSE,sha256=2FwHuu9ECdXJ05xv5XL7D7fpbMLAefQDvRGWC7cojEM,11351
+fprcal-0.1.0.dist-info/RECORD,,

fprcal-0.1.0.dist-info/WHEEL

@@ -0,0 +1,4 @@
+Wheel-Version: 1.0
+Generator: hatchling 1.31.0
+Root-Is-Purelib: true
+Tag: py3-none-any

fprcal-0.1.0.dist-info/licenses/LICENSE

@@ -0,0 +1,201 @@
+                                 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 [2025] [CISCO - AI DEFENSE]
+
+   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.