bump for 2024.2.0 major release (LLNL#212)

Update README.md (LLNL#211)

confidence interval init

base impl

README.md

@@ -7,8 +7,13 @@
 
 # Thicket
 
-A Python-based toolkit for analyzing ensemble performance data. You can find
-detailed documentation, along with tutorials of Thicket in the
+A Python-based toolkit for Exploratory Data Analysis (EDA) of parallel performance data
+that enables performance optimization and understanding of applications’ performance on
+supercomputers. It bridges the performance tool gap between being able to consider only
+a single instance of a simulation run (e.g., single platform, single measurement tool,
+or single scale) and finding actionable insights in multi-dimensional, multi-scale,
+multi-architecture, and multi-tool performance datasets. You can find detailed
+documentation, along with tutorials of Thicket in the
 [ReadtheDocs](https://thicket.readthedocs.io/en/latest/).
 
 ### Installation

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [tool.poetry]
 name = "llnl-thicket"
-version = "2024.1.0"
+version = "2024.2.0"
 description = "A Python-based toolkit for analyzing ensemble performance data."
 license = "MIT"
 

thicket/stats/__init__.py

@@ -23,6 +23,7 @@
 from .preference import preference
 from .distance import bhattacharyya_distance
 from .distance import hellinger_distance
+from .confidence_interval import confidence_interval
 
 
 try:

thicket/stats/confidence_interval.py

@@ -0,0 +1,50 @@
+# Copyright 2022 Lawrence Livermore National Security, LLC and other
+# Thicket Project Developers. See the top-level LICENSE file for details.
+#
+# SPDX-License-Identifier: MIT
+
+import numpy as np
+import pandas as pd
+import scipy.stats as stats
+
+import thicket as th
+from ..utils import verify_thicket_structures
+from .stats_utils import cache_stats_op
+from thicket.stats import mean
+
+
+@cache_stats_op
+def confidence_interval(thicket, columns=None, confidence_value=0.95):
+    output_column_names = []
+
+    mean_cols = th.stats.mean(thicket, columns=columns)
+    std_cols = th.stats.std(thicket, columns=columns)
+    sample_sizes = []
+    z = stats.norm.ppf((1 + confidence_value) / 2)
+
+    idx = pd.IndexSlice
+    for node in thicket.graph.traverse():
+        node_df = thicket.dataframe.loc[idx[node, :]]
+        sample_sizes.append(len(node_df))
+
+    for i in range(0, len(columns)):
+        x = thicket.statsframe.dataframe[mean_cols[i]]
+        s = thicket.statsframe.dataframe[std_cols[i]]
+        n = sample_sizes
+
+        c_p = x + (z * (s / np.sqrt(n)))
+        c_m = x - (z * (s / np.sqrt(n)))
+
+        out = list(zip(c_m, c_p))
+        out = pd.Series(out, index=thicket.statsframe.dataframe.index)
+
+        # If multi index, place below first level
+        out_col = f"confidence_interval_{confidence_value}_{columns[i]}"
+        output_column_names.append(out_col)
+        thicket.statsframe.dataframe[out_col] = out
+        break
+
+    thicket.statsframe.dataframe = thicket.statsframe.dataframe.sort_index(axis=1)
+    return output_column_names
+
+

thicket/version.py

@@ -3,5 +3,5 @@
 #
 # SPDX-License-Identifier: MIT
 
-__version_info__ = ("2024", "1", "0")
+__version_info__ = ("2024", "2", "0")
 __version__ = ".".join(__version_info__)