Merge pull request #59 from CSchoel/dev

Merge 0.6.1 into main

.github/workflows/ci.yaml

@@ -1,6 +1,7 @@
 on:
   push:
     branches: ["main", "dev", "v*"]
+  pull_request:
 
 name: build
 
@@ -9,14 +10,17 @@ jobs:
     strategy:
       matrix:
         python: ["3.7", "3.10"]
+        extras: ["", "[RANSAC, qrandom, plots]"]
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
       - uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python }}
-      - run: pip install .
+      - run: pip install ".${{ matrix.extras }}"
       - run: pip install codecov .
       - run: coverage run -m unittest nolds.test_measures
       - run: codecov
-        if: ${{ matrix.python == '3.10' }}
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
+        if: ${{ matrix.python == '3.10' && matrix.extras != '' }}

.gitignore

@@ -20,3 +20,4 @@ _build
 
 # virtual environment
 .venv
+.venv*

CHANGELOG.md

@@ -10,6 +10,18 @@ and this project adheres to [Semantic Versioning](http://semver.org/).
 ### Changed
 ### Fixed
 
+## [0.6.1]
+
+### Added
+
+* Regression tests for all major algorithms that check for small changes in the main output value.
+
+### Changed
+
+* Nolds now supports numpy 2.x as well as 1.x.
+
+### Fixed
+
 ## [0.6.0]
 
 ### Added
@@ -221,7 +233,8 @@ and this project adheres to [Semantic Versioning](http://semver.org/).
   - Hurst exponent (`hurst_rs`)
   - detrended fluctuation analysis (DFA) (`dfa`)
 
-[Unreleased]: https://github.com/CSchoel/nolds/compare/0.6.0..HEAD
+[Unreleased]: https://github.com/CSchoel/nolds/compare/0.6.1..HEAD
+[0.6.1]: https://github.com/CSchoel/nolds/compare/0.6.0..0.6.1
 [0.6.0]: https://github.com/CSchoel/nolds/compare/0.5.2..0.6.0
 [0.5.2]: https://github.com/CSchoel/nolds/compare/0.5.1..0.5.2
 [0.5.1]: https://github.com/CSchoel/nolds/compare/0.5.0..0.5.1

doc/source/conf.py

@@ -64,7 +64,7 @@
 # The short X.Y version.
 version = '0.6'
 # The full version, including alpha/beta/rc tags.
-release = '0.6.0'
+release = '0.6.1'
 
 # The language for content autogenerated by Sphinx. Refer to documentation
 # for a list of supported languages.

nolds/datasets.py

@@ -23,15 +23,19 @@ def lorenz_euler(length, sigma, rho, beta, dt=0.01, start=[1,1,1]):
   """
   def lorenz(state, sigma, rho, beta):
     x, y, z = state
+    # NOTE: Numpy 1.x stores intermediate results as float64
+    # => to achieve consistency between numpy versions, we have to use
+    #    float32 for all values that enter the formula to simulate numpy 1.x
+    #    behavior with numpy 2.x.
     return np.array([
-      sigma * (y - x),
-      rho * x - y - x * z,
-      x * y - beta * z
+      np.float32(sigma) * (y - x),
+      np.float32(rho) * x - y - x * z,
+      x * y - np.float32(beta) * z
     ], dtype="float32")
   trajectory = np.zeros((length, 3), dtype="float32")
   trajectory[0] = start
   for i in range(1, length):
-    t = i * dt
+    # t = i * dt
     trajectory[i] = trajectory[i-1] + lorenz(trajectory[i-1], sigma, rho, beta) * dt
   return trajectory
 

nolds/measures.py

@@ -1442,7 +1442,7 @@ def mfhurst_b(data, qvals=None, dists=None, fit='poly',
 
     Essentially, we can calculate c_q(d) of a discrete evenly sampled time
     series Y = [y_0, y_1, y_2, ... y_(N-1)] by taking the absolute differences
-    [|y_0 - y_d|, |y_1 - y_(d+1)|, ... , |y_(N-d-1) - y_(N-1)|] raising them to
+    [\|y_0 - y_d\|, \|y_1 - y_(d+1)\|, ... , \|y_(N-d-1) - y_(N-1)\|] raising them to
     the qth power and taking the mean.
 
     Now we take the logarithm on both sides of our relation c_q(d) ~ d^(q H_q)

nolds/test_measures.py

@@ -36,7 +36,7 @@ def assert_array_equals(self, expected, actual, print_arrays=False):
       print("==")
       print(expected)
       print()
-    self.assertTrue(np.alltrue(actual == expected))
+    self.assertTrue(np.all(actual == expected))
 
   def test_delay_embed_lag2(self):
     data = np.arange(10, dtype="float32")
@@ -459,7 +459,7 @@ def test_lorenz(self):
     x = data[discard:,1]
     rvals = nolds.logarithmic_r(1, np.e, 1.1)  # determined experimentally
     cd = nolds.corr_dim(x, emb_dim, fit="poly", rvals=rvals, lag=lag)
-    self.assertAlmostEqual(cd, 2.05, delta=0.1)
+    self.assertAlmostEqual(cd, 2.05, delta=0.2)
 
   def test_logistic(self):
     # TODO replicate tests with logistic map from grassberger-procaccia
@@ -544,5 +544,132 @@ def test_sampen_lorenz(self):
     self.assertAlmostEqual(0.25, sz, delta=0.05)
 
 
+class RegressionTests(unittest.TestCase):
+  """Regression tests for main algorithms.
+
+  These tests are here to safeguard against accidental algorithmic changes such
+  as updates to core dependencies such as numpy or the Python standard library.
+  """
+
+  def test_sampen(self):
+    """Test hypothesis: The exact output of sampen() on random data hasn't changed since the last version."""
+    data = datasets.load_qrandom()[:1000]
+    se = nolds.sampen(data, emb_dim=2, tolerance=None, lag=1, dist=nolds.rowwise_chebyshev, closed=False)
+    self.assertAlmostEqual(2.1876999522832743, se, places=15)
+
+  def test_corr_dim(self):
+    """Test hypothesis: The exact output of corr_dim() with `fit=poly` on random data hasn't changed since the last version."""
+    data = datasets.load_qrandom()[:1000]
+    cd = nolds.corr_dim(data, emb_dim=5, lag=1, rvals=None, dist=nolds.rowwise_euclidean, fit="poly")
+    self.assertAlmostEqual(1.303252839255068, cd, places=15)
+
+  @unittest.skipUnless(SCIPY_AVAILABLE, "Tests with RANSAC require scipy.")
+  def test_corr_dim_RANSAC(self):
+    """Test hypothesis: The exact output of corr_dim() with `fit=RANSAC` on random data hasn't changed since the last version."""
+    data = datasets.load_qrandom()[:1000]
+    sd = np.std(data, ddof=1)
+    # fix seed
+    np.random.seed(42)
+    # usa a too wide range for rvals to give RANSAC something to do ;)
+    rvals = nolds.logarithmic_r(0.01 * sd, 2 * sd, 1.03)
+    cd = nolds.corr_dim(data, emb_dim=5, lag=1, rvals=rvals, dist=nolds.rowwise_euclidean, fit="RANSAC")
+    self.assertAlmostEqual(0.44745494643404665, cd, places=15)
+
+  def test_lyap_e(self):
+    """Test hypothesis: The exact output of lyap_e() on random data hasn't changed since the last version."""
+    data = datasets.load_qrandom()[:1000]
+    le = nolds.lyap_e(data, emb_dim=10, matrix_dim=4, min_nb=10, min_tsep=1, tau=1)
+    expected = np.array([ 0.03779942603329712,  -0.014314012551504982, -0.08436867977030214, -0.22316730257003717])
+    for i in range(le.shape[0]):
+      self.assertAlmostEqual(expected[i], le[i], places=15, msg=f"{i+1}th Lyapunov exponent doesn't match")
+
+  def test_lyap_r(self):
+    """Test hypothesis: The exact output of lyap_r() with `fit=poly` on random data hasn't changed since the last version."""
+    data = datasets.load_qrandom()[:1000]
+    le = nolds.lyap_r(data, emb_dim=10, lag=1, min_tsep=1, tau=1, min_neighbors=10, trajectory_len=10, fit="poly")
+    expected = 0.094715945307378
+    self.assertAlmostEqual(expected, le, places=15)
+
+  @unittest.skipUnless(SCIPY_AVAILABLE, "Tests with RANSAC require scipy.")
+  def test_lyap_r_RANSAC(self):
+    """Test hypothesis: The exact output of lyap_r() with `fit=RANSAC` on random data hasn't changed since the last version."""
+    data = datasets.load_qrandom()[:1000]
+    np.random.seed(42)
+    # set lag to 2 for weird duplicate lines
+    # set trajectory_len to 100 to get many datapoints for RANSAC to choose from
+    le = nolds.lyap_r(data, emb_dim=10, lag=2, min_tsep=1, tau=1, min_neighbors=10, trajectory_len=100, fit="RANSAC")
+    expected = 0.0003401212353253564
+    self.assertAlmostEqual(expected, le, places=15)
+
+  def test_hurst_rs(self):
+    """Test hypothesis: The exact output of hurst_rs() with `fit=poly` on random data hasn't changed since the last version."""
+    data = datasets.load_qrandom()[:1000]
+    rs = nolds.hurst_rs(data, nvals=None, fit="poly", corrected=True, unbiased=True)
+    expected = 0.5123887964986258
+    self.assertAlmostEqual(expected, rs, places=15)
+
+  @unittest.skipUnless(SCIPY_AVAILABLE, "Tests with RANSAC require scipy.")
+  def test_hurst_rs_RANSAC(self):
+    """Test hypothesis: The exact output of hurst_rs() with `fit=RANSAC` on random data hasn't changed since the last version."""
+    data = datasets.load_qrandom()[:1000]
+    np.random.seed(42)
+    # increase nsteps in nvals to have more data points for RANSAC to choose from
+    nvals = nolds.logmid_n(data.shape[0], ratio=1/4.0, nsteps=100)
+    rs = nolds.hurst_rs(data, nvals=nvals, fit="RANSAC", corrected=True, unbiased=True)
+    expected = 0.4805431939943321
+    self.assertAlmostEqual(expected, rs, places=15)
+
+  def test_dfa(self):
+    """Test hypothesis: The exact output of dfa() with `fit_exp=poly` on random data hasn't changed since the last version."""
+    data = datasets.load_qrandom()[:1000]
+    h = nolds.dfa(data, nvals=None, overlap=True, order=1, fit_trend="poly", fit_exp="poly")
+    expected = 0.5450874638765073
+    self.assertAlmostEqual(expected, h, places=15)
+
+  @unittest.skipUnless(SCIPY_AVAILABLE, "Tests with RANSAC require scipy.")
+  def test_dfa_RANSAC(self):
+    """Test hypothesis: The exact output of dfa() with `fit_exp=RANSAC` on random data hasn't changed since the last version."""
+    # adds trend to data to introduce a less clear line for fitting
+    data = datasets.load_qrandom()[:1000] + np.arange(1000) * 100
+    np.random.seed(42)
+    # adds more steps and higher values to nvals to introduce some scattering for RANSAC to have an effect on
+    nvals = nolds.logarithmic_n(10, 0.9 * data.shape[0], 1.1)
+    h = nolds.dfa(data, nvals=nvals, overlap=True, order=1, fit_trend="poly", fit_exp="RANSAC")
+    expected = 1.1372303125405405
+    self.assertAlmostEqual(expected, h, places=15)
+
+  def test_mfhurst_b(self):
+    """Test hypothesis: The exact output of mfhurst_b() with `fit=poly` on random data hasn't changed since the last version."""
+    data = datasets.load_qrandom()[:1000]
+    h = nolds.mfhurst_b(data, qvals=[1], dists=None, fit="poly")
+    expected = [-0.00559398934417339]
+    self.assertAlmostEqual(expected[0], h[0], places=15)
+
+  @unittest.skipUnless(SCIPY_AVAILABLE, "Tests with RANSAC require scipy.")
+  def test_mfhurst_b_RANSAC(self):
+    """Test hypothesis: The exact output of mfhurst_b() with `fit=RANSAC` on random data hasn't changed since the last version."""
+    data = datasets.load_qrandom()[:1000]
+    np.random.seed(42)
+    h = nolds.mfhurst_b(data, qvals=[1], dists=None, fit="RANSAC")
+    expected = [-0.009056463064211057]
+    self.assertAlmostEqual(expected[0], h[0], places=15)
+
+  def test_mfhurst_dm(self):
+    """Test hypothesis: The exact output of mfhurst_dm() with `fit=poly` on random data hasn't changed since the last version."""
+    data = datasets.load_qrandom()[:1000]
+    h, _ = nolds.mfhurst_dm(data, qvals=[1], max_dists=range(5, 20), detrend=True, fit="poly")
+    expected = [0.008762803881203145]
+    self.assertAlmostEqual(expected[0], h[0], places=15)
+
+  @unittest.skipUnless(SCIPY_AVAILABLE, "Tests with RANSAC require scipy.")
+  def test_mfhurst_dm_RANSAC(self):
+    """Test hypothesis: The exact output of mfhurst_dm() with `fit=RANSAC` on random data hasn't changed since the last version."""
+    data = datasets.load_qrandom()[:1000]
+    np.random.seed(42)
+    h, _ = nolds.mfhurst_dm(data, qvals=[1], max_dists=range(5, 20), detrend=True, fit="RANSAC")
+    expected = [0.005324834328837356]
+    self.assertAlmostEqual(expected[0], h[0], places=15)
+
+
 if __name__ == "__main__":
   unittest.main()

setup.py

@@ -22,7 +22,7 @@ def run(self):
 
 with io.open("README.rst", "r", encoding="utf-8") as f:
     readme = f.read()
-version = '0.6.0'
+version = '0.6.1'
 setup(
     name='nolds',
     packages=['nolds'],
@@ -57,12 +57,12 @@ def run(self):
     ],
     test_suite='nolds.test_measures',
     install_requires=[
-        'numpy<2.0',
+        'numpy>1.0,<3.0',
         'future',
         'setuptools'
     ],
     extras_require={
-        'RANSAC': ['sklearn>=0.19'],
+        'RANSAC': ['scikit-learn>=0.19'],
         'qrandom': ['quantumrandom'],
         'plots': ['matplotlib']
     },