guidepost 0.3.1__tar.gz → 0.3.2__tar.gz

guidepost-0.3.2/MANIFEST.in

@@ -0,0 +1,4 @@
+# `python -m build` builds the wheel from the sdist, so the compiled frontend
+# bundles must be in the sdist for them to reach the installed wheel. They are
+# gitignored (built by esbuild.config.js), so include them explicitly here.
+recursive-include guidepost/static *.js *.js.map

{guidepost-0.3.1 → guidepost-0.3.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: guidepost
-Version: 0.3.1
+Version: 0.3.2
 Summary: Guidepost. An overview visualization for understanding supercomputer queue data.
 Home-page: https://github.com/cscully-allison/guidepost
 Author: Connor Scully-Allison
@@ -50,22 +50,13 @@ import pandas as pd
 gp = Guidepost()
 gp.load_data(pd.read_parquet("data/jobs_data.parquet"))
 
-gp.vis_configs = {
-    'x':           'start_time',       # x-axis (numeric or datetime)
-    'y':           'queue_wait',       # y-axis (numeric)
-    'color':       'nodes_requested',  # cell color (numeric)
-    'color_agg':   'avg',              # aggregation for color
-    'categorical': 'user',             # bar chart / filter
-    'facet_by':    'partition'         # splits the data into groups
-}
-
 gp   # display in a notebook cell
 ```
 
 Brush the heatmap or its histograms, then pull the selected rows back into Python:
 
 ```python
-df = gp.retrieve_selected_data()   # or: gp.selection.dataframe
+df = gp.selection.dataframe
 ```
 
 Input is a `pandas` DataFrame with at least three numeric and two categorical columns (datetime columns are supported on the x-axis).

{guidepost-0.3.1 → guidepost-0.3.2}/README.md

@@ -19,22 +19,13 @@ import pandas as pd
 gp = Guidepost()
 gp.load_data(pd.read_parquet("data/jobs_data.parquet"))
 
-gp.vis_configs = {
-    'x':           'start_time',       # x-axis (numeric or datetime)
-    'y':           'queue_wait',       # y-axis (numeric)
-    'color':       'nodes_requested',  # cell color (numeric)
-    'color_agg':   'avg',              # aggregation for color
-    'categorical': 'user',             # bar chart / filter
-    'facet_by':    'partition'         # splits the data into groups
-}
-
 gp   # display in a notebook cell
 ```
 
 Brush the heatmap or its histograms, then pull the selected rows back into Python:
 
 ```python
-df = gp.retrieve_selected_data()   # or: gp.selection.dataframe
+df = gp.selection.dataframe
 ```
 
 Input is a `pandas` DataFrame with at least three numeric and two categorical columns (datetime columns are supported on the x-axis).

{guidepost-0.3.1 → guidepost-0.3.2}/guidepost/seriation.py

@@ -167,11 +167,49 @@ def _seriate_component(members, A, node_list, SpectralEmbedding):
         return sorted(members, key=lambda i: node_list[i])
 
     sub = A[members][:, members].toarray()
+
+    # On symmetric structures (e.g. a clique) the smallest non-zero Laplacian
+    # eigenvalue is degenerate, so the 1-D spectral coordinate is not unique:
+    # the eigensolver returns an arbitrary basis vector from that eigenspace,
+    # which varies across runs, platforms, and BLAS threading. There is no
+    # canonical order in that case, so fall back to deterministic name order.
+    # (EigenVALUES are stable even when the corresponding eigenVECTORS are not,
+    # so this test is itself reproducible.)
+    if _spectral_order_is_degenerate(sub):
+        return sorted(members, key=lambda i: node_list[i])
+
     emb = SpectralEmbedding(n_components=1, affinity="precomputed", random_state=0)
     coords = emb.fit_transform(sub)[:, 0]
-    local = sorted(range(len(members)), key=lambda t: (coords[t], node_list[members[t]]))
+    # Round so any residual floating-point noise on near-tied nodes collapses and
+    # the name-based secondary key decides their order deterministically.
+    local = sorted(
+        range(len(members)),
+        key=lambda t: (round(float(coords[t]), 9), node_list[members[t]]),
+    )
     seq = [members[t] for t in local]
     # Eigenvectors carry a sign ambiguity; canonicalize orientation by name.
     if node_list[seq[0]] > node_list[seq[-1]]:
         seq.reverse()
     return seq
+
+
+def _spectral_order_is_degenerate(sub, tol=1e-9):
+    """True when the 1-D spectral embedding of ``sub`` is ill-defined.
+
+    The seriation uses the eigenvector of the smallest non-zero eigenvalue of
+    the symmetric normalized Laplacian. When that eigenvalue is (near-)repeated,
+    the eigenvector — and hence the node order — is not unique. We detect that
+    from the eigenvalue *spectrum*, which ``eigvalsh`` returns deterministically
+    regardless of solver/threading, unlike the eigenvectors themselves.
+    """
+    deg = sub.sum(axis=1)
+    if np.any(deg <= 0):
+        return True  # an isolated node has no meaningful spectral position
+    d_inv_sqrt = 1.0 / np.sqrt(deg)
+    laplacian = np.eye(sub.shape[0]) - (d_inv_sqrt[:, None] * sub * d_inv_sqrt[None, :])
+    evals = np.linalg.eigvalsh(laplacian)  # ascending; evals[0] ~ 0 (connected)
+    if len(evals) < 3:
+        return False
+    # Degenerate iff the 2nd and 3rd smallest eigenvalues coincide, i.e. the
+    # smallest non-zero eigenvalue has multiplicity > 1.
+    return bool((evals[2] - evals[1]) < tol)