Add patch to remove benchmarksdebian/0.8.1+dfsg-2

This is just a temporary fix for #1002879, and should instead be
properly fixed upstream.

3 files changed, 238 insertions, 0 deletions

diff --git a/debian/changelog b/debian/changelog
index 03e245a..edab601 100644
--- a/debian/changelog
+++ b/debian/changelog
@@ -1,3 +1,9 @@
+python-pot (0.8.1+dfsg-2) unstable; urgency=medium
+
+  * Add patch to remove benchmarks. (Closes: #1002879)
+
+ -- Gard Spreemann <gspr@nonempty.org>  Fri, 31 Dec 2021 10:47:43 +0100
+
 python-pot (0.8.1+dfsg-1) unstable; urgency=medium
 
   * New upstream version.
diff --git a/debian/patches/0001-Remove-benchmarks-to-prevent-installation-in-wrong-p.patch b/debian/patches/0001-Remove-benchmarks-to-prevent-installation-in-wrong-p.patch
new file mode 100644
index 0000000..28ae7d5
--- /dev/null
+++ b/debian/patches/0001-Remove-benchmarks-to-prevent-installation-in-wrong-p.patch
@@ -0,0 +1,231 @@
+From: Gard Spreemann <gspr@nonempty.org>
+Date: Fri, 31 Dec 2021 10:46:27 +0100
+Subject: Remove benchmarks to prevent installation in wrong path
+
+---
+ benchmarks/__init__.py       |   5 ---
+ benchmarks/benchmark.py      | 105 -------------------------------------------
+ benchmarks/emd.py            |  40 -----------------
+ benchmarks/sinkhorn_knopp.py |  42 -----------------
+ 4 files changed, 192 deletions(-)
+ delete mode 100644 benchmarks/__init__.py
+ delete mode 100644 benchmarks/benchmark.py
+ delete mode 100644 benchmarks/emd.py
+ delete mode 100644 benchmarks/sinkhorn_knopp.py
+
+diff --git a/benchmarks/__init__.py b/benchmarks/__init__.py
+deleted file mode 100644
+index 37f5e56..0000000
+--- a/benchmarks/__init__.py
++++ /dev/null
+@@ -1,5 +0,0 @@
+-from . import benchmark
+-from . import sinkhorn_knopp
+-from . import emd
+-
+-__all__= ["benchmark", "sinkhorn_knopp", "emd"]
+diff --git a/benchmarks/benchmark.py b/benchmarks/benchmark.py
+deleted file mode 100644
+index 7973c6b..0000000
+--- a/benchmarks/benchmark.py
++++ /dev/null
+@@ -1,105 +0,0 @@
+-# /usr/bin/env python3
+-# -*- coding: utf-8 -*-
+-
+-from ot.backend import get_backend_list, jax, tf
+-import gc
+-
+-
+-def setup_backends():
+-    if jax:
+-        from jax.config import config
+-        config.update("jax_enable_x64", True)
+-
+-    if tf:
+-        from tensorflow.python.ops.numpy_ops import np_config
+-        np_config.enable_numpy_behavior()
+-
+-
+-def exec_bench(setup, tested_function, param_list, n_runs, warmup_runs):
+-    backend_list = get_backend_list()
+-    for i, nx in enumerate(backend_list):
+-        if nx.__name__ == "tf" and i < len(backend_list) - 1:
+-            # Tensorflow should be the last one to be benchmarked because
+-            # as far as I'm aware, there is no way to force it to release
+-            # GPU memory. Hence, if any other backend is benchmarked after
+-            # Tensorflow and requires the usage of a GPU, it will not have the
+-            # full memory available and you may have a GPU Out Of Memory error
+-            # even though your GPU can technically hold your tensors in memory.
+-            backend_list.pop(i)
+-            backend_list.append(nx)
+-            break
+-
+-    inputs = [setup(param) for param in param_list]
+-    results = dict()
+-    for nx in backend_list:
+-        for i in range(len(param_list)):
+-            print(nx, param_list[i])
+-            args = inputs[i]
+-            results_nx = nx._bench(
+-                tested_function,
+-                *args,
+-                n_runs=n_runs,
+-                warmup_runs=warmup_runs
+-            )
+-            gc.collect()
+-            results_nx_with_param_in_key = dict()
+-            for key in results_nx:
+-                new_key = (param_list[i], *key)
+-                results_nx_with_param_in_key[new_key] = results_nx[key]
+-            results.update(results_nx_with_param_in_key)
+-    return results
+-
+-
+-def convert_to_html_table(results, param_name, main_title=None, comments=None):
+-    string = "<table>\n"
+-    keys = list(results.keys())
+-    params, names, devices, bitsizes = zip(*keys)
+-
+-    devices_names = sorted(list(set(zip(devices, names))))
+-    params = sorted(list(set(params)))
+-    bitsizes = sorted(list(set(bitsizes)))
+-    length = len(devices_names) + 1
+-    cpus_cols = list(devices).count("CPU") / len(bitsizes) / len(params)
+-    gpus_cols = list(devices).count("GPU") / len(bitsizes) / len(params)
+-    assert cpus_cols + gpus_cols == len(devices_names)
+-
+-    if main_title is not None:
+-        string += f'<tr><th align="center" colspan="{length}">{str(main_title)}</th></tr>\n'
+-
+-    for i, bitsize in enumerate(bitsizes):
+-
+-        if i != 0:
+-            string += f'<tr><td colspan="{length}">&nbsp;</td></tr>\n'
+-
+-        # make bitsize header
+-        text = f"{bitsize} bits"
+-        if comments is not None:
+-            text += " - "
+-            if isinstance(comments, (tuple, list)) and len(comments) == len(bitsizes):
+-                text += str(comments[i])
+-            else:
+-                text += str(comments)
+-        string += f'<tr><th align="center">Bitsize</th>'
+-        string += f'<th align="center" colspan="{length - 1}">{text}</th></tr>\n'
+-
+-        # make device header
+-        string += f'<tr><th align="center">Device</th>'
+-        string += f'<th align="center" colspan="{cpus_cols}">CPU</th>'
+-        string += f'<th align="center" colspan="{gpus_cols}">GPU</th></tr>\n'
+-
+-        # make param_name / backend header
+-        string += f'<tr><th align="center">{param_name}</th>'
+-        for device, name in devices_names:
+-            string += f'<th align="center">{name}</th>'
+-        string += "</tr>\n"
+-
+-        # make results rows
+-        for param in params:
+-            string += f'<tr><td align="center">{param}</td>'
+-            for device, name in devices_names:
+-                key = (param, name, device, bitsize)
+-                string += f'<td align="center">{results[key]:.4f}</td>'
+-            string += "</tr>\n"
+-
+-    string += "</table>"
+-    return string
+diff --git a/benchmarks/emd.py b/benchmarks/emd.py
+deleted file mode 100644
+index 9f64863..0000000
+--- a/benchmarks/emd.py
++++ /dev/null
+@@ -1,40 +0,0 @@
+-# /usr/bin/env python3
+-# -*- coding: utf-8 -*-
+-
+-import numpy as np
+-import ot
+-from .benchmark import (
+-    setup_backends,
+-    exec_bench,
+-    convert_to_html_table
+-)
+-
+-
+-def setup(n_samples):
+-    rng = np.random.RandomState(789465132)
+-    x = rng.randn(n_samples, 2)
+-    y = rng.randn(n_samples, 2)
+-
+-    a = ot.utils.unif(n_samples)
+-    M = ot.dist(x, y)
+-    return a, M
+-
+-
+-if __name__ == "__main__":
+-    n_runs = 100
+-    warmup_runs = 10
+-    param_list = [50, 100, 500, 1000, 2000, 5000]
+-
+-    setup_backends()
+-    results = exec_bench(
+-        setup=setup,
+-        tested_function=lambda a, M: ot.emd(a, a, M),
+-        param_list=param_list,
+-        n_runs=n_runs,
+-        warmup_runs=warmup_runs
+-    )
+-    print(convert_to_html_table(
+-        results, 
+-        param_name="Sample size",
+-        main_title=f"EMD - Averaged on {n_runs} runs"
+-    ))
+diff --git a/benchmarks/sinkhorn_knopp.py b/benchmarks/sinkhorn_knopp.py
+deleted file mode 100644
+index 3a1ef3f..0000000
+--- a/benchmarks/sinkhorn_knopp.py
++++ /dev/null
+@@ -1,42 +0,0 @@
+-# /usr/bin/env python3
+-# -*- coding: utf-8 -*-
+-
+-import numpy as np
+-import ot
+-from .benchmark import (
+-    setup_backends,
+-    exec_bench,
+-    convert_to_html_table
+-)
+-
+-
+-def setup(n_samples):
+-    rng = np.random.RandomState(123456789)
+-    a = rng.rand(n_samples // 4, 100)
+-    b = rng.rand(n_samples, 100)
+-
+-    wa = ot.unif(n_samples // 4)
+-    wb = ot.unif(n_samples)
+-
+-    M = ot.dist(a.copy(), b.copy())
+-    return wa, wb, M
+-
+-
+-if __name__ == "__main__":
+-    n_runs = 100
+-    warmup_runs = 10
+-    param_list = [50, 100, 500, 1000, 2000, 5000]
+-
+-    setup_backends()
+-    results = exec_bench(
+-        setup=setup,
+-        tested_function=lambda *args: ot.bregman.sinkhorn(*args, reg=1, stopThr=1e-7),
+-        param_list=param_list,
+-        n_runs=n_runs,
+-        warmup_runs=warmup_runs
+-    )
+-    print(convert_to_html_table(
+-        results, 
+-        param_name="Sample size",
+-        main_title=f"Sinkhorn Knopp - Averaged on {n_runs} runs"
+-    ))
diff --git a/debian/patches/series b/debian/patches/series
new file mode 100644
index 0000000..a82b8eb
--- /dev/null
+++ b/debian/patches/series
@@ -0,0 +1 @@
+0001-Remove-benchmarks-to-prevent-installation-in-wrong-p.patch