MNT add rng seed for profile-narx

fastcan/narx/_base.py

@@ -13,7 +13,6 @@
 from sklearn.base import BaseEstimator, MultiOutputMixin, RegressorMixin
 from sklearn.linear_model import LinearRegression
 from sklearn.utils import check_array, check_consistent_length, column_or_1d
-from sklearn.utils._openmp_helpers import _openmp_effective_n_threads
 from sklearn.utils._param_validation import Interval, StrOptions, validate_params
 from sklearn.utils.validation import (
     _check_sample_weight,
@@ -493,9 +492,9 @@ def _grad(
         else:
             n_x = n_coefs
             y_ids = output_ids
+
         dydx = np.zeros((n_samples, n_outputs, n_x), dtype=float)
         dcf = np.zeros((max_delay, n_outputs, n_outputs), dtype=float)
-        n_threads = _openmp_effective_n_threads()
 
         _update_dydx(
             X,
@@ -510,7 +509,6 @@ def _grad(
             grad_feat_ids,
             dydx,
             dcf,
-            n_threads,
         )
 
         mask_valid = mask_missing_values(y, y_hat, sample_weight_sqrt, return_mask=True)

fastcan/narx/_narx_fast.pyx

@@ -20,7 +20,6 @@ cdef inline void _update_terms(
     const int[:, ::1] feat_ids,     # IN
     const int[:, ::1] delay_ids,    # IN
     const int k,                    # IN
-    const int num_threads,          # IN
 ) noexcept nogil:
     """
     Evaluate all terms for the given features and delays at timestep k.
@@ -195,7 +194,6 @@ cpdef void _update_dydx(
     const int[:, ::1] grad_feat_ids,
     double[:, :, ::1] dydx,       # OUT
     double[:, :, ::1] dcf,        # OUT
-    const int num_threads,          # IN
 ) noexcept nogil:
     """
     Computation of the Jacobian matrix dydx.
@@ -245,7 +243,6 @@ cpdef void _update_dydx(
             feat_ids,
             delay_ids,
             k,
-            num_threads,
         )
 
         # Update constant terms of Jacobian

pyproject.toml

@@ -116,7 +116,7 @@ time-h = "python -m timeit -n 5 -s 'import numpy as np; from fastcan import Fast
 time-eta = "python -m timeit -n 5 -s 'import numpy as np; from fastcan import FastCan; X = np.random.rand(3000, 100); y = np.random.rand(3000, 20)' 's = FastCan(100, eta=True, verbose=0).fit(X, y)'"
 profile-minibatch = { cmd = '''python -c "import cProfile; import numpy as np; from fastcan import minibatch; X = np.random.rand(100, 3000); y = np.random.rand(100, 20); cProfile.run('minibatch(X, y, 1000, 10, verbose=0)', sort='$SORT')"''', env = { SORT = "cumtime" } }
 time-narx = '''python -m timeit -n 1 -s "import numpy as np; from fastcan.narx import make_narx; rng = np.random.default_rng(5); X = rng.random((1000, 10)); y = rng.random((1000, 2)); m = make_narx(X, y, 10, max_delay=2, poly_degree=2, verbose=0)" "m.fit(X, y, coef_init='one_step_ahead', verbose=1)"'''
-profile-narx = { cmd = '''python -c "import cProfile; import numpy as np; from fastcan.narx import make_narx; X = np.random.rand(3000, 3); y = np.random.rand(3000, 3); m = make_narx(X, y, 10, max_delay=10, poly_degree=2, verbose=0); cProfile.run('m.fit(X, y, coef_init=[0]*33)', sort='$SORT')"''', env = { SORT = "tottime" } }
+profile-narx = { cmd = '''python -c "import cProfile; import numpy as np; from fastcan.narx import make_narx; rng = np.random.default_rng(8); X = rng.random((3000, 3)); y = rng.random((3000, 3)); m = make_narx(X, y, 10, max_delay=10, poly_degree=2, verbose=0); cProfile.run('m.fit(X, y, coef_init=[0]*33)', sort='$SORT')"''', env = { SORT = "tottime" } }
 
 [tool.pixi.feature.asv.tasks]
 asv-build = { cmd = "python -m asv machine --machine $MACHINE --yes && python -m asv run --show-stderr -v --machine $MACHINE $EXTRA_ARGS", cwd = "asv_benchmarks", env = { MACHINE = "MacOS-M1", EXTRA_ARGS = "" } }