scikit-survival 0.23.1__cp310-cp310-macosx_11_0_arm64.whl → 0.24.1__cp310-cp310-macosx_11_0_arm64.whl

{scikit_survival-0.23.1.dist-info → scikit_survival-0.24.1.dist-info}/METADATA

@@ -1,9 +1,9 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: scikit-survival
-Version: 0.23.1
+Version: 0.24.1
 Summary: Survival analysis built on top of scikit-learn
 Author-email: Sebastian Pölsterl <sebp@k-d-w.org>
-License: GNU GENERAL PUBLIC LICENSE
+License:                     GNU GENERAL PUBLIC LICENSE
                                Version 3, 29 June 2007
         
          Copyright (C) 2007 Free Software Foundation, Inc. <http://fsf.org/>
@@ -694,52 +694,53 @@ Classifier: Programming Language :: C++
 Classifier: Programming Language :: Cython
 Classifier: Programming Language :: Python
 Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
 Classifier: Topic :: Software Development
 Classifier: Topic :: Scientific/Engineering
-Requires-Python: >=3.9
+Requires-Python: >=3.10
 Description-Content-Type: text/x-rst
 License-File: COPYING
 Requires-Dist: ecos
 Requires-Dist: joblib
 Requires-Dist: numexpr
 Requires-Dist: numpy
-Requires-Dist: osqp !=0.6.0,!=0.6.1
-Requires-Dist: pandas >=1.4.0
-Requires-Dist: scipy >=1.3.2
-Requires-Dist: scikit-learn <1.6,>=1.4.0
+Requires-Dist: osqp<1.0.0,>=0.6.3
+Requires-Dist: pandas>=1.4.0
+Requires-Dist: scipy>=1.3.2
+Requires-Dist: scikit-learn<1.7,>=1.6.1
 Provides-Extra: dev
-Requires-Dist: black[jupyter] ; extra == 'dev'
-Requires-Dist: build ; extra == 'dev'
-Requires-Dist: coverage ; extra == 'dev'
-Requires-Dist: Cython >=3.0.10 ; extra == 'dev'
-Requires-Dist: packaging ; extra == 'dev'
-Requires-Dist: pre-commit ; extra == 'dev'
-Requires-Dist: pytest ; extra == 'dev'
-Requires-Dist: ruff ; extra == 'dev'
-Requires-Dist: setuptools-scm >=8 ; extra == 'dev'
-Requires-Dist: tomli ; extra == 'dev'
-Requires-Dist: tox ; extra == 'dev'
+Requires-Dist: black[jupyter]; extra == "dev"
+Requires-Dist: build; extra == "dev"
+Requires-Dist: coverage; extra == "dev"
+Requires-Dist: Cython>=3.0.10; extra == "dev"
+Requires-Dist: packaging; extra == "dev"
+Requires-Dist: pre-commit; extra == "dev"
+Requires-Dist: pytest; extra == "dev"
+Requires-Dist: ruff; extra == "dev"
+Requires-Dist: setuptools-scm>=8; extra == "dev"
+Requires-Dist: tomli; extra == "dev"
+Requires-Dist: tox; extra == "dev"
 Provides-Extra: docs
-Requires-Dist: ipython !=8.7.0 ; extra == 'docs'
-Requires-Dist: nbsphinx >=0.9.2 ; extra == 'docs'
-Requires-Dist: docutils ; extra == 'docs'
-Requires-Dist: setuptools-scm ; extra == 'docs'
-Requires-Dist: sphinx ~=7.3.7 ; extra == 'docs'
-Requires-Dist: pydata-sphinx-theme ~=0.15.2 ; extra == 'docs'
-Requires-Dist: sphinxcontrib-spelling ; extra == 'docs'
-Requires-Dist: sphinx-design ~=0.5.0 ; extra == 'docs'
-Requires-Dist: sphinx-copybutton ~=0.5.2 ; extra == 'docs'
+Requires-Dist: ipython!=8.7.0; extra == "docs"
+Requires-Dist: nbsphinx>=0.9.2; extra == "docs"
+Requires-Dist: docutils; extra == "docs"
+Requires-Dist: setuptools-scm; extra == "docs"
+Requires-Dist: sphinx~=8.1.3; extra == "docs"
+Requires-Dist: pydata-sphinx-theme~=0.16.1; extra == "docs"
+Requires-Dist: sphinxcontrib-spelling; extra == "docs"
+Requires-Dist: sphinx-design~=0.6.1; extra == "docs"
+Requires-Dist: sphinx-copybutton~=0.5.2; extra == "docs"
 Provides-Extra: nbval
-Requires-Dist: ipykernel ; extra == 'nbval'
-Requires-Dist: ipython !=8.7.0 ; extra == 'nbval'
-Requires-Dist: matplotlib ~=3.8.0 ; extra == 'nbval'
-Requires-Dist: nbformat ; extra == 'nbval'
-Requires-Dist: nbval >=0.10.0 ; extra == 'nbval'
-Requires-Dist: seaborn ~=0.11.2 ; extra == 'nbval'
+Requires-Dist: ipykernel; extra == "nbval"
+Requires-Dist: ipython!=8.7.0; extra == "nbval"
+Requires-Dist: matplotlib~=3.9.0; extra == "nbval"
+Requires-Dist: nbformat; extra == "nbval"
+Requires-Dist: nbval>=0.10.0; extra == "nbval"
+Requires-Dist: seaborn~=0.13.2; extra == "nbval"
+Dynamic: license-file
 
 |License| |Docs| |DOI|
 
@@ -775,14 +776,14 @@ this unique characteristic of such a dataset into account.
 Requirements
 ============
 
-- Python 3.9 or later
+- Python 3.10 or later
 - ecos
 - joblib
 - numexpr
 - numpy
 - osqp
 - pandas 1.4.0 or later
-- scikit-learn 1.4 or 1.5
+- scikit-learn 1.6
 - scipy
 - C/C++ compiler
 

scikit_survival-0.24.1.dist-info/RECORD

@@ -0,0 +1,57 @@
+scikit_survival-0.24.1.dist-info/RECORD,,
+scikit_survival-0.24.1.dist-info/WHEEL,sha256=TmyW8D9OPImQItPFLlTWg3ThBsUQjFY1sQx0hG5nmd4,136
+scikit_survival-0.24.1.dist-info/top_level.txt,sha256=fPkcFA-XQGbwnD_ZXOvaOWmSd34Qezr26Mn99nYPvAg,7
+scikit_survival-0.24.1.dist-info/METADATA,sha256=dg43_aZQq6kxDldl8S3mgqRvOZYxMP5UXswJqipPI14,48948
+scikit_survival-0.24.1.dist-info/licenses/COPYING,sha256=jOtLnuWt7d5Hsx6XXB2QxzrSe2sWWh3NgMfFRetluQM,35147
+sksurv/functions.py,sha256=Y0hmtcF1llMkS-ZZOBLDhYUnThko8PGYvYKPtFDReSg,3677
+sksurv/metrics.py,sha256=l6WbcKkb-Ry3tYiLkLs4jMGPbDQOcNW-xG2l_Msg9gs,37358
+sksurv/nonparametric.py,sha256=KVWiASlfNpUGvmaT4RzdQsiBrkAIB6WTjFU4slUyzqo,29020
+sksurv/util.py,sha256=0iTd7gKP8toxQSePYqRa376P9ZVpYF7sv2bFwTNtVAo,13208
+sksurv/__init__.py,sha256=IfdVMjYlvlXe5-Et9-1b2LyujeidQZPuLJltgbTM6ag,3591
+sksurv/preprocessing.py,sha256=gJiMD-b_ybnb-jTpEsmQwr-4dMFeS2T2Dkw69p1Y7IQ,5204
+sksurv/exceptions.py,sha256=CRun7zrKzcZ9zinni5b2cMaV-pU-pw1UnXpRV2h3z_4,801
+sksurv/testing.py,sha256=2oeCsTzEiVRKDRb3iSJLKn03hBO2IrUq-2U5TfvOYK4,4295
+sksurv/compare.py,sha256=zcWPl0rjRvMRS02r1681Q5Xbz-6WLV5fjAgPzRdquUg,4089
+sksurv/base.py,sha256=VfCS3AcFnoVxc-h_6KYQONSelUnI0611lmMmUOb4c-Q,3771
+sksurv/column.py,sha256=dlh1HvsXqMnIRGgm60Expp2FpinqcHbHWDNn2lxM5k0,6469
+sksurv/tree/tree.py,sha256=_z8BtU00Xles-T8kSQV1IB74DhrI94A_AaQC6CFaLOk,26569
+sksurv/tree/__init__.py,sha256=7RUjPZtGrVYiHY4roDXdEDM7RVBSsbY_CXWmyqZk2ts,64
+sksurv/tree/_criterion.cpython-310-darwin.so,sha256=1oCglqO0YSRHimcz-Qgl6mki73tkZwUmlcnGvfF0Uvc,225488
+sksurv/ensemble/boosting.py,sha256=luPw2qEOYTZaVZCC6_Sfz_tbnR0pZy6HKx457HNi-sY,62091
+sksurv/ensemble/_coxph_loss.cpython-310-darwin.so,sha256=gAPfVfZ_8YAaihMBAwVu3eP72ekspX17Jaf14Y3bvjY,204784
+sksurv/ensemble/__init__.py,sha256=7kZAzxFpJGtgLQfhoOqZUyGUubIs_Kw3RgyUsAd1Fq0,191
+sksurv/ensemble/survival_loss.py,sha256=mhIbuOqz7t-nuygswZD0d0are2R0EQ3d3yHMRdxOKIk,5942
+sksurv/ensemble/forest.py,sha256=0NgC1yUOznWCMnc5rTgVMemtfXoX3GULJoWX_xNQv3E,35981
+sksurv/kernels/clinical.py,sha256=27U1fDAlhrZeQEANelDFPWw3aXrTIwWqxUEKo8u_t9I,10763
+sksurv/kernels/__init__.py,sha256=_aZIFutv7kUTlkHJlP52zBDkpUXnKIlPPf3cikuAmCA,77
+sksurv/kernels/_clinical_kernel.cpython-310-darwin.so,sha256=wPWhtEaHDohQ0L8umJldv9NtYjmhD5-WYmXkazL4hCQ,205336
+sksurv/bintrees/__init__.py,sha256=l6Fe4PAMByrABpGzZ5W8KHieEYG-rh-DADo2QiEMLrU,727
+sksurv/bintrees/_binarytrees.cpython-310-darwin.so,sha256=G1oCoSgjcM92VSPoYulnI88ZzBOjyrOeJ0ayLkJAv1c,111232
+sksurv/datasets/__init__.py,sha256=EPzJ50wd-cZ6mWuHFPRRRMqgt14WzM32HGxDrlOp9Q4,361
+sksurv/datasets/base.py,sha256=ZTJuH0SLnCQJUVB2Bw61DkhNjIoqRoc6op7rVDVXvKI,24265
+sksurv/datasets/data/cgvhd.arff,sha256=0lxUqY74JaMpC_vWJC4RWJy6vTmQwCg1yrUxjX65VX8,5214
+sksurv/datasets/data/GBSG2.arff,sha256=jBuh302AIWtYaV1rvJ9RKEZkqzcSThAdVt8ImFFkWwQ,26204
+sksurv/datasets/data/actg320.arff,sha256=8GE2kIU8Nvx7m5Ns-uTJW6Rgtk3xmJzBzMEmtynq5FU,45446
+sksurv/datasets/data/bmt.arff,sha256=yRCh87tAlsBQAocliDquyP28lsnQhCTNU0vJatgH6ns,509
+sksurv/datasets/data/breast_cancer_GSE7390-metastasis.arff,sha256=Iz9MHAay7imf_8ug-YgfbtZqNWbMvsMLUATw0pi1JXA,264743
+sksurv/datasets/data/flchain.arff,sha256=vyYA7EN90ZBx9zva2C3mgXgEV9EUHsNu1VGwAm5uV3M,343058
+sksurv/datasets/data/whas500.arff,sha256=9kBAyROYh1E3gi7KMGqScgjfaJaAjNl2SvcGVyL6U9Y,27772
+sksurv/datasets/data/veteran.arff,sha256=cdvJ4jXzzC7RCzolTjn5hcCSNG0chFc27SGxP74mNFY,5260
+sksurv/io/arffwrite.py,sha256=68FZRU4KKJ5dIaOZwhK-L7R47gPK9oHorQVBdD0my18,4464
+sksurv/io/__init__.py,sha256=LacpKG9UKO_RefPXc6umPaGFGPOGzA-FZra_MCRWCxk,92
+sksurv/io/arffread.py,sha256=cQqdKoCgCcd8FHJVGnsmpRWeaGqnYiauRJ4oANOkri8,1839
+sksurv/meta/__init__.py,sha256=VLA0VhLxZhF3z35md5Z4-nhw6BSSCfR6L7YOBGk1w1A,216
+sksurv/meta/stacking.py,sha256=PO8Cgc1SKFCUwpIEcCuFvA3PLp-qBgkRYbNyz-7DJp0,12280
+sksurv/meta/ensemble_selection.py,sha256=VFWGiHRXK3lfndF3etU9BJnaEK_MBSVMdVcdAyrEdiA,24031
+sksurv/meta/base.py,sha256=mV6653v4txKKHJqcJXVT-J-ARNN9rDfzIq02xoEy93I,1437
+sksurv/linear_model/coxph.py,sha256=gEi0otT6Vmt9Fxi_PhUWChrCJ2CtGMJhb3vA7jtWFSg,20871
+sksurv/linear_model/__init__.py,sha256=58Lt5Tj3xGqRS4uZfVR5avKQNZubHD6RSknVDyzLTso,152
+sksurv/linear_model/coxnet.py,sha256=v5lfcldVViB5QDGIM6bMVS1SK60CjtmTYoQXqdG0AIA,20016
+sksurv/linear_model/_coxnet.cpython-310-darwin.so,sha256=8H3r6MftcTFLYd_A44tgv14a0aAfXo1mJAs290hvFeI,130528
+sksurv/linear_model/aft.py,sha256=TSiYEsPwYIyHpRu-11F0-i985D2Lwi_HLJ1aztiPaoU,7411
+sksurv/svm/naive_survival_svm.py,sha256=FaAS1_pzTSa1ivOzObJ3IFMILc7inKNUkefr7rEPNe0,7978
+sksurv/svm/__init__.py,sha256=7BRFkatw9wbtsY-aes9cnz31VPpIjZ-383LuDmucDsw,328
+sksurv/svm/_minlip.cpython-310-darwin.so,sha256=w1ylI4tZvYRhI3YXmMFBMRczSpYTfjHXxxgKvcon3rU,204976
+sksurv/svm/_prsvm.cpython-310-darwin.so,sha256=Hm8kMZDnRIcwKvL9zRZvhTJAT7ix7TPOMIb0KSZQURI,204832
+sksurv/svm/survival_svm.py,sha256=Qbpdzm3mhBI-ajGW4TonFTDxYdt8sKoDFiV5X5buqbA,43595
+sksurv/svm/minlip.py,sha256=tDXyQaz5q4jdiiZYw_Gfc8rSyez0D8T2VbFmXv7zZdQ,21935

{scikit_survival-0.23.1.dist-info → scikit_survival-0.24.1.dist-info}/WHEEL

@@ -1,5 +1,6 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.3.0)
+Generator: setuptools (78.0.2)
 Root-Is-Purelib: false
 Tag: cp310-cp310-macosx_11_0_arm64
+Generator: delocate 0.13.0
 

sksurv/__init__.py

@@ -19,7 +19,7 @@ def _get_version(name):
 def show_versions():
     sys_info = {
         "Platform": platform.platform(),
-        "Python version": f"{platform.python_implementation()} {platform}",
+        "Python version": f"{platform.python_implementation()} {platform.python_version()}",
         "Python interpreter": sys.executable,
     }
 
@@ -44,7 +44,7 @@ def show_versions():
         max(map(len, deps)),
         max(map(len, sys_info.keys())),
     )
-    fmt = "{0:<%ds}: {1}" % minwidth
+    fmt = f"{{0:<{minwidth}s}}: {{1}}"
 
     print("SYSTEM")
     print("------")

sksurv/base.py

@@ -99,5 +99,7 @@ class SurvivalAnalysisMixin:
         result = concordance_index_censored(y[name_event], y[name_time], risk_score)
         return result[0]
 
-    def _more_tags(self):
-        return {"requires_y": True}
+    def __sklearn_tags__(self):
+        tags = super().__sklearn_tags__()
+        tags.target_tags.required = True
+        return tags

sksurv/datasets/__init__.py

@@ -2,7 +2,9 @@ from .base import (
     get_x_y,  # noqa: F401
     load_aids,  # noqa: F401
     load_arff_files_standardized,  # noqa: F401
+    load_bmt,  # noqa: F401
     load_breast_cancer,  # noqa: F401
+    load_cgvhd,  # noqa: F401
     load_flchain,  # noqa: F401
     load_gbsg2,  # noqa: F401
     load_veterans_lung_cancer,  # noqa: F401

sksurv/datasets/base.py

@@ -12,6 +12,8 @@ __all__ = [
     "get_x_y",
     "load_arff_files_standardized",
     "load_aids",
+    "load_bmt",
+    "load_cgvhd",
     "load_breast_cancer",
     "load_flchain",
     "load_gbsg2",
@@ -26,13 +28,17 @@ def _get_data_path(name):
     return files(__package__) / "data" / name
 
 
-def _get_x_y_survival(dataset, col_event, col_time, val_outcome):
+def _get_x_y_survival(dataset, col_event, col_time, val_outcome, competing_risks=False):
     if col_event is None or col_time is None:
         y = None
         x_frame = dataset
     else:
-        y = np.empty(dtype=[(col_event, bool), (col_time, np.float64)], shape=dataset.shape[0])
-        y[col_event] = (dataset[col_event] == val_outcome).values
+        event_type = np.int64 if competing_risks else bool
+        y = np.empty(dtype=[(col_event, event_type), (col_time, np.float64)], shape=dataset.shape[0])
+        if competing_risks:
+            y[col_event] = dataset[col_event].values
+        else:
+            y[col_event] = (dataset[col_event] == val_outcome).values
         y[col_time] = dataset[col_time].values
 
         x_frame = dataset.drop([col_event, col_time], axis=1)
@@ -51,7 +57,7 @@ def _get_x_y_other(dataset, col_label):
     return x_frame, y
 
 
-def get_x_y(data_frame, attr_labels, pos_label=None, survival=True):
+def get_x_y(data_frame, attr_labels, pos_label=None, survival=True, competing_risks=False):
     """Split data frame into features and labels.
 
     Parameters
@@ -75,6 +81,9 @@ def get_x_y(data_frame, attr_labels, pos_label=None, survival=True):
     survival : bool, optional, default: True
         Whether to return `y` that can be used for survival analysis.
 
+    competing_risks : bool, optional, default: False
+        Whether `y` refers to competing risks situation. Only used if `survival` is True
+
     Returns
     -------
     X : pandas.DataFrame, shape = (n_samples, n_columns - len(attr_labels))
@@ -89,9 +98,9 @@ def get_x_y(data_frame, attr_labels, pos_label=None, survival=True):
     if survival:
         if len(attr_labels) != 2:
             raise ValueError(f"expected sequence of length two for attr_labels, but got {len(attr_labels)}")
-        if pos_label is None:
+        if pos_label is None and not competing_risks:
             raise ValueError("pos_label needs to be specified if survival=True")
-        return _get_x_y_survival(data_frame, attr_labels[0], attr_labels[1], pos_label)
+        return _get_x_y_survival(data_frame, attr_labels[0], attr_labels[1], pos_label, competing_risks)
 
     return _get_x_y_other(data_frame, attr_labels)
 
@@ -434,3 +443,147 @@ def load_flchain():
     """
     fn = _get_data_path("flchain.arff")
     return get_x_y(loadarff(fn), attr_labels=["death", "futime"], pos_label="dead")
+
+
+def load_bmt():
+    """Load and return response to hematopoietic stem cell transplantation (HSCT) for acute leukemia patients.
+
+    The dataset has 35 samples and 1 feature "dis" indicating the type of leukemia::
+
+        0=ALL (Acute Lymphoblastic Leukemia)
+        1=AML (Acute Myeloid Leukemia)
+
+    The endpoint (status) is defined as
+
+    +-------+------------------------------------+---------------------+
+    | Value | Description                        | Count (%)           |
+    +=======+====================================+=====================+
+    | 0     | Survival (Right-censored data)     | 11 patients (31.4%) |
+    +-------+------------------------------------+---------------------+
+    | 1     | Transplant related mortality (TRM) | 9 events (25.7%)    |
+    +-------+------------------------------------+---------------------+
+    | 2     | Relapse                            | 15 events (42.8%)   |
+    +-------+------------------------------------+---------------------+
+
+    See [1]_ for further description and [2]_ for the dataset.
+
+    Returns
+    -------
+    x : pandas.DataFrame
+        The measurements for each patient.
+
+    y : structured array with 2 fields
+        *status*: Integer indicating the endpoint: 0-(survival i.e. right censored data), 1-(TRM), 2-(relapse)
+
+        *ftime*: total length of follow-up or time of event.
+
+    References
+    ----------
+    .. [1] https://doi.org/10.1038/sj.bmt.1705727
+           Scrucca, L., Santucci, A. & Aversa, F.:
+           "Competing risk analysis using R: an easy guide for clinicians. Bone Marrow Transplant 40, 381–387 (2007)"
+
+    .. [2] https://luca-scr.github.io/R/bmt.csv
+    """
+    full_path = _get_data_path("bmt.arff")
+    data = loadarff(full_path)
+    data["ftime"] = data["ftime"].astype(int)
+    return get_x_y(data, attr_labels=["status", "ftime"], competing_risks=True)
+
+
+def load_cgvhd():
+    r"""Load and return data from multicentre randomized clinical trial
+    initiated for patients with a myeloid malignancy who were to
+    undergo an allogeneic bone marrow transplant.
+
+    The dataset is a 100 patient subsample of the full data set. See [2]_ for further details.
+
+    +-------+------------+----------------------------------------------+-------------------------------------------+
+    | Index | Name       | Description                                  | Encoding                                  |
+    +=======+============+==============================================+===========================================+
+    | 1     | dx         | Diagnosis                                    | | AML=acute myeloid leukaemia             |
+    |       |            |                                              | | CML=chronic myeloid leukaemia           |
+    +-------+------------+----------------------------------------------+-------------------------------------------+
+    | 2     | tx         | Randomized treatment                         | | BM=cell harvested from the bone marrow  |
+    |       |            |                                              | | PB=cell harvested from peripheral blood |
+    +-------+------------+----------------------------------------------+-------------------------------------------+
+    | 3     | extent     | Extent of disease                            | L=limited, E=extensive                    |
+    +-------+------------+----------------------------------------------+-------------------------------------------+
+    | 4     | agvhdgd    | Grade of acute GVHD                          |                                           |
+    +-------+------------+----------------------------------------------+-------------------------------------------+
+    | 5     | age        | Age                                          | Years                                     |
+    +-------+------------+----------------------------------------------+-------------------------------------------+
+    | 6     | survtime   | Time from date of transplant to death        | Years                                     |
+    |       |            | or last follow-up                            |                                           |
+    +-------+------------+----------------------------------------------+-------------------------------------------+
+    | 7     | reltime    | Time from date of transplant to relapse      | Years                                     |
+    |       |            | or last follow-up                            |                                           |
+    +-------+------------+----------------------------------------------+-------------------------------------------+
+    | 8     | agvhtime   | Time from date of transplant to acute GVHD   | Years                                     |
+    |       |            | or last follow-up                            |                                           |
+    +-------+------------+----------------------------------------------+-------------------------------------------+
+    | 9     | cgvhtime   | Time from date of transplant to chronic GVHD | Years                                     |
+    |       |            | or last follow-up                            |                                           |
+    +-------+------------+----------------------------------------------+-------------------------------------------+
+    | 10    | stat       | Status                                       | 1=Dead, 0=Alive                           |
+    +-------+------------+----------------------------------------------+-------------------------------------------+
+    | 11    | rcens      | Relapse                                      | 1=Yes, 0=No                               |
+    +-------+------------+----------------------------------------------+-------------------------------------------+
+    | 12    | agvh       | Acute GVHD                                   | 1=Yes, 0=No                               |
+    +-------+------------+----------------------------------------------+-------------------------------------------+
+    | 13    | cgvh       | Chronic GVHD                                 | 1=Yes, 0=No                               |
+    +-------+------------+----------------------------------------------+-------------------------------------------+
+    | 14    | stnum      | patient ID                                   |                                           |
+    +-------+------------+----------------------------------------------+-------------------------------------------+
+
+    Columns 6,7 and 9 contain the time to death, relapse and CGVHD
+    calculated in years (survtime, reltime, cgvhtime) and the
+    respective indicator variables are in columns 10,11 and 13 (stat,
+    rcens, cgvh). The earliest time that any of these events happened
+    is calculated by taking the minimum of the observed times. The
+    censoring variable cens is coded as 0 when no events were
+    observed, 1 if CGVHD was observed as first event, 2 if a relapse
+    was observed as the first event and 3 if death occurred before
+    either of the events: The endpoint (status) is therefore defined as
+
+    +-------+-------------------------------------------+-----------------+
+    | Value | Description                               | Count (%)       |
+    +=======+===========================================+=================+
+    | 0     | Survival (Right-censored data)            | 4 patients (4%) |
+    +-------+-------------------------------------------+-----------------+
+    | 1     | Chronic graft versus host disease (CGVHD) | 86 events (86%) |
+    +-------+-------------------------------------------+-----------------+
+    | 2     | Relapse (TRM)                             | 5 events (5%)   |
+    +-------+-------------------------------------------+-----------------+
+    | 3     | Death                                     | 5 events (5%)   |
+    +-------+-------------------------------------------+-----------------+
+
+    The dataset has been obtained from [1]_.
+
+    Returns
+    -------
+    x : pandas.DataFrame
+        The measurements for each patient.
+
+    y : structured array with 2 fields
+        *status*: Integer indicating the endpoint: 0: right censored data; 1: CGVHD; 2: relapse; 3: death.
+
+        *ftime*: total length of follow-up or time of event.
+
+    References
+    ----------
+    .. [1] https://sites.google.com/view/melaniapintiliemscstatistics/home/statistics
+
+    .. [2] Melania Pintilie: "Competing Risks: A Practical Perspective". John Wiley & Sons, 2006
+    """
+    full_path = _get_data_path("cgvhd.arff")
+    data = loadarff(full_path)
+    data["ftime"] = data[["survtime", "reltime", "cgvhtime"]].min(axis=1)
+    data["status"] = (
+        ((data["ftime"] == data["cgvhtime"]) & (data["cgvh"] == "1")).astype(int)
+        + 2 * ((data["ftime"] == data["reltime"]) & (data["rcens"] == "1")).astype(int)
+        + 3 * ((data["ftime"] == data["survtime"]) & (data["stat"] == "1")).astype(int)
+    )
+    data = data[["ftime", "status", "dx", "tx", "extent", "age"]]
+
+    return get_x_y(data, attr_labels=["status", "ftime"], competing_risks=True)

sksurv/datasets/data/bmt.arff

@@ -0,0 +1,46 @@
+% Scrucca L., Santucci A., Aversa F. (2007)
+% Competing risks analysis using R: an easy guide for clinicians.
+% Bone Marrow Transplantation 40, 381-387.
+% https://luca-scr.github.io/R/bmt.csv
+@RELATION BMT
+
+@ATTRIBUTE dis {0,1}
+@ATTRIBUTE ftime NUMERIC
+@ATTRIBUTE status {0,1,2}
+
+@DATA
+0,13,2
+0,1,1
+0,72,0
+0,7,2
+0,8,2
+1,67,0
+0,9,2
+0,5,2
+1,70,0
+1,4,0
+1,7,0
+1,68,0
+0,1,2
+1,10,2
+1,7,2
+1,3,1
+1,4,1
+1,4,1
+1,3,1
+1,3,1
+0,22,2
+1,8,1
+1,2,2
+0,0,2
+0,0,1
+0,35,0
+1,35,0
+0,4,2
+0,14,2
+0,26,2
+0,3,2
+1,2,0
+1,8,0
+1,32,0
+0,12,1

sksurv/datasets/data/cgvhd.arff

@@ -0,0 +1,118 @@
+@RELATION CGVHD
+
+@ATTRIBUTE dx {CML, AML}
+@ATTRIBUTE tx {PB, BM}
+@ATTRIBUTE extent {L, E}
+@ATTRIBUTE agvhdgd NUMERIC
+@ATTRIBUTE age NUMERIC
+@ATTRIBUTE survtime NUMERIC
+@ATTRIBUTE reltime NUMERIC
+@ATTRIBUTE agvhtime NUMERIC
+@ATTRIBUTE cgvhtime NUMERIC
+@ATTRIBUTE stat {0, 1}
+@ATTRIBUTE rcens {0, 1}
+@ATTRIBUTE agvh {1, 0}
+@ATTRIBUTE cgvh {1, 0}
+@ATTRIBUTE stnum NUMERIC
+
+@DATA
+CML,PB,L,1,36,4.895,4.895,0.099,0.52,0,0,1,1,1
+AML,PB,L,3,57,3.474,0.753,0.101,0.408,1,1,1,1,2
+CML,PB,L,0,48,4.95,4.95,4.95,0.348,0,0,0,1,3
+AML,PB,L,2,52,4.643,4.643,0.057,0.482,0,0,1,1,4
+AML,PB,L,3,45,4.066,4.066,0.137,0.378,0,0,1,1,5
+AML,PB,L,3,47,1.558,0.416,0.055,1.558,1,1,1,0,6
+CML,PB,L,1,40,4.512,4.512,0.09,0.381,0,0,1,1,7
+AML,PB,L,3,38,4.041,4.041,0.082,0.914,0,0,1,1,8
+AML,PB,L,2,41,4.164,4.164,0.055,0.923,0,0,1,1,9
+CML,PB,L,0,50,4.011,4.011,4.011,0.397,0,0,0,1,10
+CML,PB,L,1,56,3.945,3.945,0.047,0.479,0,0,1,1,11
+CML,PB,L,2,56,4.361,4.361,0.079,0.991,0,0,1,1,12
+AML,PB,L,1,54,0.841,0.654,0.077,0.474,1,1,1,1,13
+CML,PB,L,3,25,2.951,2.951,0.164,0.339,0,0,1,1,14
+CML,PB,L,4,40,0.586,0.586,0.055,0.277,1,0,1,1,15
+CML,PB,L,0,41,3.559,3.559,3.559,0.367,0,0,0,1,16
+CML,PB,L,2,57,3.422,3.422,0.131,0.742,0,0,1,1,17
+CML,PB,L,3,62,0.408,0.408,0.408,0.408,0,0,1,1,18
+CML,PB,L,1,29,3.428,3.428,0.09,0.958,0,0,1,1,19
+AML,PB,L,1,44,0.063,0.063,0.014,0.063,1,0,1,0,20
+CML,PB,L,2,40,1.572,1.572,0.09,0.282,1,0,1,1,21
+CML,PB,L,1,54,1.013,1.013,0.093,0.413,1,0,1,1,22
+AML,PB,L,2,37,3.023,3.023,0.074,0.394,0,0,1,1,23
+AML,PB,L,1,58,2.979,2.979,0.079,0.342,0,0,1,1,24
+CML,PB,L,3,39,2.817,2.817,0.049,0.367,0,0,1,1,25
+CML,PB,L,2,31,2.804,2.804,0.137,0.277,0,0,1,1,26
+CML,PB,L,2,45,2.609,2.609,0.252,0.367,0,0,1,1,27
+AML,PB,L,0,48,2.508,2.508,2.508,0.331,0,0,0,1,28
+CML,PB,L,0,53,0.665,0.665,0.665,0.32,1,0,0,1,29
+CML,PB,L,0,29,2.497,2.497,2.497,0.329,0,0,0,1,30
+CML,PB,L,0,27,1.799,1.799,1.799,0.444,1,0,0,1,31
+AML,PB,L,3,45,0.471,0.438,0.071,0.471,1,1,1,0,32
+CML,PB,L,1,39,2.031,2.031,0.112,0.964,0,0,1,1,33
+CML,PB,L,3,49,2.073,2.073,0.063,0.564,0,0,1,1,34
+AML,PB,L,1,37,0.999,0.75,0.274,0.402,1,1,1,1,35
+AML,PB,L,3,53,0.427,0.427,0.055,0.277,1,0,1,1,36
+CML,PB,L,1,48,1.766,1.766,0.216,0.4,0,0,1,1,37
+AML,PB,L,1,59,1.555,1.555,0.178,0.446,0,0,1,1,38
+CML,PB,L,2,33,1.67,1.67,0.11,0.474,0,0,1,1,39
+CML,PB,L,0,38,1.607,1.607,1.607,0.329,0,0,0,1,40
+CML,PB,L,4,37,1.511,1.511,0.055,0.323,0,0,1,1,41
+AML,PB,L,3,41,1.287,1.287,0.049,0.392,0,0,1,1,42
+AML,PB,E,1,64,1.227,1.227,0.23,0.496,0,0,1,1,43
+CML,PB,L,3,32,1.3,1.3,0.063,0.63,0,0,1,1,44
+CML,PB,L,0,41,1.27,1.27,1.27,0.383,0,0,0,1,45
+AML,PB,E,1,56,1.205,1.205,0.074,1.205,0,0,1,0,46
+CML,PB,L,1,50,1.147,1.147,0.131,0.361,0,0,1,1,47
+CML,PB,L,3,37,1.109,1.109,0.055,0.277,0,0,1,1,48
+CML,PB,L,0,27,0.994,0.994,0.994,0.287,0,0,0,1,49
+CML,BM,L,3,45,4.572,4.572,0.066,0.619,0,0,1,1,50
+AML,BM,L,3,45,4.616,4.616,0.101,0.452,0,0,1,1,51
+AML,BM,L,2,42,4.0,4.0,0.027,0.29,0,0,1,1,52
+CML,BM,L,0,22,4.238,4.238,4.238,0.479,0,0,0,1,53
+AML,BM,L,4,47,0.11,0.11,0.074,0.11,1,0,1,0,54
+AML,BM,L,2,48,4.03,4.03,0.101,0.857,0,0,1,1,55
+AML,BM,L,2,49,3.124,2.527,0.115,1.993,1,1,1,1,56
+CML,BM,L,2,38,0.515,0.515,0.079,0.463,1,0,1,1,57
+CML,BM,L,1,39,4.222,3.149,0.085,0.496,0,1,1,1,58
+CML,BM,L,3,41,4.027,4.027,0.104,0.422,0,0,1,1,59
+CML,BM,L,2,46,1.969,1.969,0.038,0.307,1,0,1,1,60
+AML,BM,L,0,24,3.792,3.792,3.792,0.701,0,0,0,1,61
+AML,BM,L,3,32,0.427,0.427,0.041,0.279,1,0,1,1,62
+CML,BM,L,0,36,3.34,3.34,3.34,0.419,0,0,0,1,63
+CML,BM,L,1,53,3.504,0.72,0.112,0.616,0,1,1,1,64
+CML,BM,L,0,52,3.685,3.685,3.685,0.331,0,0,0,1,65
+CML,BM,L,1,59,0.181,0.181,0.049,0.181,1,0,1,0,66
+CML,BM,L,3,42,0.736,0.736,0.09,0.567,1,0,1,1,67
+CML,BM,L,1,65,0.287,0.287,0.052,0.287,1,0,1,0,68
+CML,BM,E,0,60,0.057,0.057,0.057,0.057,0,0,0,0,69
+CML,BM,L,2,61,3.107,3.107,0.088,0.764,0,0,1,1,70
+CML,BM,L,1,55,3.088,3.088,0.11,0.381,0,0,1,1,71
+AML,BM,E,0,48,0.446,0.274,0.446,0.446,1,1,0,0,72
+AML,BM,E,0,49,2.776,2.776,2.776,2.776,0,0,0,0,73
+CML,BM,L,0,36,0.693,0.172,0.693,0.635,1,1,0,1,74
+AML,BM,L,1,48,2.01,2.01,0.077,0.553,0,0,1,1,75
+CML,BM,L,0,47,2.374,2.374,2.374,0.287,0,0,0,1,76
+AML,BM,L,3,43,1.079,1.079,0.088,0.345,1,0,1,1,77
+CML,BM,L,0,56,2.604,2.604,2.604,0.375,0,0,0,1,78
+CML,BM,L,1,56,2.478,2.478,0.17,0.517,0,0,1,1,79
+CML,BM,L,0,36,2.338,2.338,2.338,0.457,0,0,0,1,80
+CML,BM,L,2,52,2.3,2.3,0.049,0.345,0,0,1,1,81
+CML,BM,E,1,44,0.219,0.219,0.145,0.219,1,0,1,0,82
+AML,BM,L,3,32,2.127,2.127,0.118,0.422,0,0,1,1,83
+AML,BM,L,1,44,2.034,2.034,0.096,0.479,0,0,1,1,84
+CML,BM,L,0,45,2.034,2.034,2.034,0.29,0,0,0,1,85
+AML,BM,L,3,48,2.007,2.007,0.088,0.35,0,0,1,1,86
+CML,BM,L,0,48,1.183,1.183,1.183,0.372,0,0,0,1,87
+AML,BM,L,3,42,0.375,0.375,0.096,0.277,1,0,1,1,88
+AML,BM,E,2,24,0.353,0.301,0.096,0.353,1,1,1,0,89
+CML,BM,L,2,26,1.566,1.566,0.137,0.474,0,0,1,1,90
+CML,BM,L,2,34,1.588,1.588,0.129,0.465,0,0,1,1,91
+CML,BM,L,0,57,1.243,1.243,1.243,0.433,0,0,0,1,92
+CML,BM,L,3,51,1.555,1.555,0.09,0.359,0,0,1,1,93
+AML,BM,L,2,54,1.202,1.202,0.192,1.202,0,0,1,0,94
+AML,BM,E,0,20,1.251,1.251,1.251,0.408,0,0,0,1,95
+AML,BM,L,2,39,1.114,1.114,0.074,0.402,0,0,1,1,96
+AML,BM,L,0,49,1.15,1.15,1.15,0.35,0,0,0,1,97
+CML,BM,L,1,42,0.997,0.997,0.142,0.411,0,0,1,1,98
+CML,BM,L,0,44,1.057,1.057,1.057,0.301,0,0,0,1,99
+CML,BM,L,1,56,1.125,1.125,0.129,0.32,0,0,1,1,100