Timeseries and calc_temporal_pattern (#88)

* timeseries and temporal pattern functionality

initial tests

added test files

fixed the from_timeseries function

memory pattern mapping works, still needs cleanup

adding memory pattern visual to tree

refactor to temporal pattern

* switched to concat_thickets from unify_ensemble

thicket/stats/__init__.py

@@ -21,6 +21,7 @@
 from .scoring import score_bhattacharyya
 from .scoring import score_hellinger
 from .preference import preference
+from .calc_temporal_pattern import calc_temporal_pattern
 from .distance import bhattacharyya_distance
 from .distance import hellinger_distance
 from .confidence_interval import confidence_interval

thicket/stats/calc_temporal_pattern.py

@@ -0,0 +1,77 @@
+# 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 pandas as pd
+import numpy as np
+
+from ..utils import verify_thicket_structures
+
+
+def calc_temporal_pattern(thicket, columns=None):
+    """Calculate the associated temporal pattern with the passed in columns.
+
+    Designed to take in a timeseries thicket, and append two columns to the
+    aggregated statistics (statsframe) table for the temporal pattern calculated on each node over time.
+
+    The two additional columns include the _temporal_score, and the _pattern associated with that score.
+    The score assigns a value between 0 and 1 based on how drastically the values change over time
+
+    Arguments:
+        thicket (thicket): timeseries Thicket object
+        columns (list): List of numeric columns to calculate temporal pattern.
+            Note, if using a columnar joined thicket a list of tuples must be passed in
+            with the format (column index, column name).
+
+    Returns:
+        (list): returns a list of output statsframe column names
+    """
+    if columns is None:
+        raise ValueError(
+            "To see a list of valid columns, run 'Thicket.performance_cols'."
+        )
+
+    if "iteration" not in thicket.dataframe.index.names:
+        raise ValueError(
+            "Must have a timeseries thicket with iteration as an index level"
+        )
+
+    verify_thicket_structures(thicket.dataframe, index=["node"], columns=columns)
+
+    output_column_names = []
+
+    for column in columns:
+        if not pd.api.types.is_numeric_dtype(thicket.dataframe[column]):
+            raise ValueError("Column data type must be numeric")
+        pattern_col = []
+        score_col = []
+        # for any node that has temporal values we can calculate the pattern per node
+        for node, node_df in thicket.dataframe.groupby(level=0):
+            # if the node has any nans, pattern is none
+            if node_df[column].isna().values.any():
+                pattern = "none"
+                score = np.nan
+            else:
+                values = node_df[column]
+                score = 1 - (sum(values) / (max(values) * len(values)))
+                if score < 0.2:
+                    pattern = "constant"
+                elif score >= 0.2 and score < 0.4:
+                    pattern = "phased"
+                elif score >= 0.4 and score < 0.6:
+                    pattern = "dynamic"
+                else:
+                    pattern = "sporadic"
+            pattern_col.append(pattern)
+            score_col.append(score)
+
+        # add the new columns to the statsframe and output list
+        pattern_column_name = column + "_pattern"
+        score_column_name = column + "_temporal_score"
+        thicket.statsframe.dataframe[pattern_column_name] = pattern_col
+        thicket.statsframe.dataframe[score_column_name] = score_col
+        output_column_names.append(pattern_column_name)
+        output_column_names.append(score_column_name)
+
+    return output_column_names

thicket/tests/conftest.py

@@ -290,3 +290,39 @@ def literal_thickets():
     thickets = [tk, tk2, tk3]
 
     return thickets
+
+
+@pytest.fixture
+def example_timeseries(data_dir, tmpdir):
+    """Timeseries Caliper file"""
+    cali_timeseries_dir = os.path.join(data_dir, "example-timeseries")
+    cali_file = os.path.join(cali_timeseries_dir, "timeseries.cali")
+
+    shutil.copy(cali_file, str(tmpdir))
+    tmpfile = os.path.join(str(tmpdir), "timeseries.cali")
+
+    return tmpfile
+
+
+@pytest.fixture
+def example_timeseries_cxx(data_dir, tmpdir):
+    """Timeseries Caliper file"""
+    cali_timeseries_dir = os.path.join(data_dir, "example-timeseries")
+    cali_file = os.path.join(cali_timeseries_dir, "cxx.cali")
+
+    shutil.copy(cali_file, str(tmpdir))
+    tmpfile = os.path.join(str(tmpdir), "cxx.cali")
+
+    return tmpfile
+
+
+@pytest.fixture
+def mem_power_timeseries(data_dir, tmpdir):
+    """Timeseries Caliper file"""
+    cali_timeseries_dir = os.path.join(data_dir, "example-timeseries")
+    cali_file = os.path.join(cali_timeseries_dir, "mem_power_timeseries.cali")
+
+    shutil.copy(cali_file, str(tmpdir))
+    tmpfile = os.path.join(str(tmpdir), "mem_power_timeseries.cali")
+
+    return tmpfile

thicket/tests/data/example-timeseries/cxx.cali

@@ -0,0 +1,65 @@
+__rec=node,id=21,attr=10,data=1612,parent=3
+__rec=node,id=92,attr=8,data=caliper.config,parent=21
+__rec=node,id=89,attr=10,data=1612,parent=1
+__rec=node,id=90,attr=8,data=iterations,parent=89
+__rec=node,id=22,attr=8,data=cali.caliper.version,parent=21
+__rec=node,id=23,attr=22,data=2.10.0-dev
+__rec=node,id=91,attr=90,data=100,parent=23
+__rec=node,id=93,attr=92,data=,parent=91
+__rec=node,id=30,attr=10,data=85,parent=5
+__rec=node,id=67,attr=8,data=min#time.duration.ns,parent=30
+__rec=node,id=68,attr=8,data=max#time.duration.ns,parent=30
+__rec=node,id=69,attr=8,data=sum#time.duration.ns,parent=30
+__rec=node,id=70,attr=8,data=avg#time.duration.ns,parent=30
+__rec=node,id=32,attr=10,data=85,parent=2
+__rec=node,id=85,attr=8,data=count,parent=32
+__rec=node,id=86,attr=8,data=aggregate.slot,parent=32
+__rec=node,id=26,attr=10,data=2133,parent=1
+__rec=node,id=27,attr=8,data=loop.iterations,parent=26
+__rec=node,id=31,attr=8,data=timeseries.starttime,parent=30
+__rec=node,id=33,attr=8,data=timeseries.snapshot,parent=32
+__rec=ctx,ref=93,attr=67=68=69=70=85=86=27=31=33,data=448713.000000=448713.000000=448713.000000=448713.000000=1=0=0=1689118709.135139=0
+__rec=node,id=18,attr=10,data=276,parent=3
+__rec=node,id=20,attr=8,data=region,parent=18
+__rec=node,id=94,attr=20,data=main
+__rec=ctx,ref=94=93,attr=67=68=69=70=85=86=27=31=33,data=59851.000000=59851.000000=59851.000000=59851.000000=1=1=0=1689118709.135139=0
+__rec=node,id=95,attr=20,data=init,parent=94
+__rec=node,id=42,attr=8,data=min#region.count,parent=30
+__rec=node,id=43,attr=8,data=max#region.count,parent=30
+__rec=node,id=44,attr=8,data=sum#region.count,parent=30
+__rec=node,id=45,attr=8,data=avg#region.count,parent=30
+__rec=ctx,ref=95=93,attr=42=43=44=45=67=68=69=70=85=86=27=31=33,data=1.000000=1.000000=1.000000=1.000000=12219.000000=12219.000000=12219.000000=12219.000000=1=2=0=1689118709.135139=0
+__rec=node,id=34,attr=10,data=2133,parent=5
+__rec=node,id=35,attr=8,data=timeseries.duration,parent=34
+__rec=ctx,ref=94=93,attr=27=31=33=35=31,data=0=1689118709.135139=0=0.001398=1689118709.136537
+__rec=node,id=28,attr=10,data=85,parent=1
+__rec=node,id=29,attr=8,data=loop.start_iteration,parent=28
+__rec=ctx,ref=94=93,attr=67=68=69=70=85=86=27=29=31=33,data=200739.000000=200739.000000=200739.000000=200739.000000=1=0=20=0=1689118709.136537=1
+__rec=node,id=19,attr=8,data=loop,parent=18
+__rec=node,id=103,attr=19,data=mainloop,parent=94
+__rec=ctx,ref=103=93,attr=42=43=44=45=67=68=69=70=85=86=27=29=31=33,data=1.000000=1.000000=19.000000=1.000000=3306.000000=13928.000000=282447.000000=4787.237288=59=1=20=0=1689118709.136537=1
+__rec=node,id=104,attr=20,data=foo,parent=103
+__rec=ctx,ref=104=93,attr=42=43=44=45=67=68=69=70=85=86=27=29=31=33,data=1.000000=1.000000=20.000000=1.000000=141457.000000=219005.000000=3281358.000000=164067.900000=20=2=20=0=1689118709.136537=1
+__rec=node,id=12,attr=10,data=84,parent=6
+__rec=node,id=16,attr=8,data=class.iteration,parent=12
+__rec=node,id=96,attr=16,data=true,parent=1
+__rec=node,id=97,attr=10,data=21,parent=96
+__rec=node,id=98,attr=8,data=iteration#mainloop,parent=97
+__rec=ctx,ref=103=93,attr=27=29=31=33=35=31=98,data=20=0=1689118709.136537=1=0.003734=1689118709.140271=19
+__rec=ctx,ref=103=93,attr=42=43=44=45=67=68=69=70=85=86=27=29=31=33,data=1.000000=1.000000=20.000000=1.000000=3238.000000=83328.000000=357604.000000=5960.066667=60=0=20=20=1689118709.140271=2
+__rec=ctx,ref=104=93,attr=42=43=44=45=67=68=69=70=85=86=27=29=31=33,data=1.000000=1.000000=20.000000=1.000000=159474.000000=209917.000000=3364016.000000=168200.800000=20=1=20=20=1689118709.140271=2
+__rec=ctx,ref=103=93,attr=27=29=31=33=35=31=98,data=20=20=1689118709.140271=2=0.003722=1689118709.143993=39
+__rec=ctx,ref=103=93,attr=42=43=44=45=67=68=69=70=85=86=27=29=31=33,data=1.000000=1.000000=20.000000=1.000000=3213.000000=84229.000000=402162.000000=6702.700000=60=0=20=40=1689118709.143993=3
+__rec=ctx,ref=104=93,attr=42=43=44=45=67=68=69=70=85=86=27=29=31=33,data=1.000000=1.000000=20.000000=1.000000=159545.000000=335990.000000=3522373.000000=176118.650000=20=1=20=40=1689118709.143993=3
+__rec=ctx,ref=103=93,attr=27=29=31=33=35=31=98,data=20=40=1689118709.143993=3=0.003928=1689118709.147921=59
+__rec=ctx,ref=103=93,attr=42=43=44=45=67=68=69=70=85=86=27=29=31=33,data=1.000000=1.000000=20.000000=1.000000=3342.000000=96083.000000=348946.000000=5815.766667=60=0=20=60=1689118709.147921=4
+__rec=ctx,ref=104=93,attr=42=43=44=45=67=68=69=70=85=86=27=29=31=33,data=1.000000=1.000000=20.000000=1.000000=136880.000000=173199.000000=3203448.000000=160172.400000=20=1=20=60=1689118709.147921=4
+__rec=ctx,ref=103=93,attr=27=29=31=33=35=31=98,data=20=60=1689118709.147921=4=0.003560=1689118709.151481=79
+__rec=ctx,ref=103=93,attr=42=43=44=45=67=68=69=70=85=86=27=29=31=33,data=1.000000=1.000000=20.000000=1.000000=3308.000000=112210.000000=407532.000000=6792.200000=60=0=20=80=1689118709.151481=5
+__rec=ctx,ref=104=93,attr=42=43=44=45=67=68=69=70=85=86=27=29=31=33,data=1.000000=1.000000=20.000000=1.000000=156252.000000=715191.000000=4120824.000000=206041.200000=20=1=20=80=1689118709.151481=5
+__rec=ctx,ref=103=93,attr=27=29=31=33=35=31=98,data=20=80=1689118709.151481=5=0.004522=1689118709.156003=99
+__rec=ctx,ref=103=93,attr=42=43=44=45=67=68=69=70=85=86=27=31=33,data=1.000000=1.000000=1.000000=1.000000=114486.000000=114486.000000=114486.000000=114486.000000=1=0=0=1689118709.156003=6
+__rec=ctx,ref=103=93,attr=27=31=33=35=31,data=0=1689118709.156003=6=0.000119=1689118709.156122
+__rec=node,id=24,attr=8,data=cali.channel,parent=21
+__rec=node,id=25,attr=24,data=default
+__rec=globals,ref=93=25

thicket/tests/data/example-timeseries/mem_power_timeseries.cali

@@ -0,0 +1,34 @@
+__rec=node,id=26,attr=10,data=2125,parent=1
+__rec=node,id=27,attr=8,data=loop.iterations,parent=26
+__rec=node,id=30,attr=10,data=2061,parent=2
+__rec=node,id=31,attr=8,data=memstat.vmsize,parent=30
+__rec=node,id=32,attr=8,data=memstat.vmrss,parent=30
+__rec=node,id=33,attr=8,data=memstat.data,parent=30
+__rec=node,id=36,attr=10,data=2133,parent=2
+__rec=node,id=37,attr=8,data=variorum.val.power_node_watts,parent=36
+__rec=node,id=38,attr=8,data=variorum.power_node_watts,parent=36
+__rec=node,id=18,attr=10,data=268,parent=3
+__rec=node,id=20,attr=8,data=region,parent=18
+__rec=node,id=41,attr=20,data=main
+__rec=node,id=21,attr=10,data=1612,parent=3
+__rec=node,id=22,attr=8,data=cali.caliper.version,parent=21
+__rec=node,id=23,attr=22,data=2.10.0
+__rec=ctx,ref=41=23,attr=27=31=32=33=37=38,data=0=923=679=537=389=194
+__rec=node,id=28,attr=10,data=77,parent=1
+__rec=node,id=29,attr=8,data=loop.start_iteration,parent=28
+__rec=node,id=19,attr=8,data=loop,parent=18
+__rec=node,id=45,attr=19,data=lulesh.cycle,parent=41
+__rec=node,id=12,attr=10,data=76,parent=6
+__rec=node,id=16,attr=8,data=class.iteration,parent=12
+__rec=node,id=42,attr=16,data=true,parent=1
+__rec=node,id=43,attr=10,data=13,parent=42
+__rec=node,id=44,attr=8,data=iteration#lulesh.cycle,parent=43
+__rec=ctx,ref=45=23,attr=27=29=31=32=33=37=38=44,data=20=0=1000=743=614=391=390=19
+__rec=ctx,ref=45=23,attr=27=29=31=32=33=37=38=44,data=20=20=1000=743=614=392=391=39
+__rec=ctx,ref=45=23,attr=27=29=31=32=33=37=38=44,data=20=40=1000=743=614=392=392=59
+__rec=ctx,ref=45=23,attr=27=29=31=32=33=37=38=44,data=20=60=1000=743=614=392=392=79
+__rec=ctx,ref=45=23,attr=27=29=31=32=33=37=38=44,data=20=80=1000=743=614=398=395=99
+__rec=ctx,ref=45=23,attr=27=31=32=33=37=38,data=0=1000=743=614=398=398
+__rec=node,id=24,attr=8,data=cali.channel,parent=21
+__rec=node,id=25,attr=24,data=default
+__rec=globals,ref=23=25