From e776bcbbc8fb7573b092863f358c5de7a44b5887 Mon Sep 17 00:00:00 2001
From: Kay Robbins <1189050+VisLab@users.noreply.github.com>
Date: Wed, 30 Apr 2025 16:17:12 -0500
Subject: [PATCH 01/10] Wrote a tag_summary

---
 hed/tools/analysis/tag_summary_util.py | 94 ++++++++++++++++++++++++++
 1 file changed, 94 insertions(+)
 create mode 100644 hed/tools/analysis/tag_summary_util.py

diff --git a/hed/tools/analysis/tag_summary_util.py b/hed/tools/analysis/tag_summary_util.py
new file mode 100644
index 000000000..161f41c0b
--- /dev/null
+++ b/hed/tools/analysis/tag_summary_util.py
@@ -0,0 +1,94 @@
+
+from hed.tools.analysis.event_manager import EventManager
+from hed.models.tabular_input import TabularInput
+from hed.tools.analysis.hed_tag_manager import HedTagManager
+
+# Excluding tags for condition-variables and task -- these can be done separately if we want to.
+REMOVE_TYPES = ['Condition-variable', 'Task']
+
+# Tags organized by whether they are found with either of these
+# MATCH_TYPES = ['Sensory-event', 'Agent-action']
+MATCH_TYPES = ['Experimental-stimulus', 'Participant-response', 'Incidental', 'Instructional', 'Mishap',
+               'Task-activity', 'Warning']
+# If a tag has any of these as a parent, it is excluded
+EXCLUDED_PARENTS = {'data-marker', 'data-resolution', 'quantitative-value', 'spatiotemporal-value',
+                    'statistical-value', 'informational-property', 'organizational-property',
+                    'grayscale', 'hsv-color', 'rgb-color', 'luminance', 'luminance-contrast', 'opacity',
+                    'task-effect-evidence', 'task-relationship', 'relation'}
+
+# If a tag has any of these as a parent, it is replaced by this parent only
+CUTOFF_TAGS = {'blue-color', 'brown-color', 'cyan-color', 'gray-color', 'green-color', 'orange-color',
+               'pink-color', 'purple-color', 'red-color', 'white-color', 'yellow-color',
+               'visual-presentation'}
+
+# These tags are removed at the end as non-informational
+FILTERED_TAGS = {'event', 'agent', 'action', 'move-body-part', 'item', 'biological-item', 'anatomical-item', 'body-part',
+                 'lower-extremity-part', 'upper-extremity-part', 'head-part', 'torso-part', 'face-part',
+                 'language-item', 'object', 'geometric-object',
+                 'man-made-object', 'device', 'computing-device', 'io-device', 'input-device', 'output-device',
+                 'auditory-device', 'display-device',
+                 'recording-device', 'natural-object', 'document', 'media', 'media-clip', 'visualization',
+                 'property', 'agent-property', 'agent-state',
+                 'agent-cognitive-state', 'agent-emotional-state', 'agent-physiological-state', 'agent-postural-state',
+                 'agent-task-role', 'agent-trait',
+                 'data-property', 'biological-artifact', 'nonbiological-artifact',
+                 'spatial-property', 'temporal-property', 'spectral-property', 'dara-source-type', 'data-value',
+                 'categorical-value', 'categorical-class-value', 'categorical-judgment-value',
+                 'categorical-level-value', 'categorical-location-value', 'categorical-orientation-value',
+                 'physical-value', 'data-variability-attribute', 'environmental-property', 'sensory-property',
+                 'sensory-attribute', 'auditory-attribute', 'gustatory-attribute', 'olfactory-attribute',
+                 'tactile-attribute', 'visual-attribute', 'sensory-presentation', 'task-property', 'task-action-type',
+                 'task-attentional-demand', 'task-event-role', 'task-stimulus-role'}
+
+def extract_tag_summary(hed_schema, df, sidecar=None, name=None):
+    """ Extract a summary of the tags in a given tabular input file.
+    Parameters:
+        hed_schema (HedSchema): The HedSchema object to use for the summary.
+        df (pd.DataFrame): The DataFrame to summarize.
+        sidecar (str): The sidecar file to use for the summary.
+        name (str): The name of the summary.
+
+    Returns:
+        dict: A dictionary with the summary information.
+    """
+
+    group_dict = {key: set() for key in MATCH_TYPES}
+    other = set()
+    input_data = TabularInput(df, sidecar=sidecar, name=name)
+    event_manager = EventManager(input_data, hed_schema)
+    tag_man = HedTagManager(event_manager, remove_types=REMOVE_TYPES)
+    hed_objs = tag_man.get_hed_objs(include_context=False, replace_defs=True)
+    for hed in hed_objs:
+        if not hed:
+            continue
+        all_tags = hed.get_all_tags()
+        found = False
+        for key, tags in group_dict.items():
+            if match_tags(all_tags, key):
+                group_dict[key] = update_tags(group_dict[key], all_tags)
+                found = True
+                break
+        if not found:
+           other = update_tags(other, all_tags)
+
+    for key, tags in group_dict.items():
+        group_dict[key] = tags - FILTERED_TAGS
+    other = other - FILTERED_TAGS
+    return group_dict, other
+
+
+def match_tags(all_tags, key):
+    return any(tag.short_base_tag == key for tag in all_tags)
+
+
+def update_tags(tag_set, all_tags):
+    for tag in all_tags:
+        terms = tag.tag_terms
+        if any(item in EXCLUDED_PARENTS for item in terms):
+            continue
+        match = next((item for item in terms if item in CUTOFF_TAGS), None)
+        if match:
+            tag_set.add(match)
+        else:
+            tag_set.update(tag.tag_terms)
+    return tag_set
\ No newline at end of file

From 845b03cb54114fab67701c0ca0d1b512bd372a7a Mon Sep 17 00:00:00 2001
From: Kay Robbins <1189050+VisLab@users.noreply.github.com>
Date: Wed, 30 Apr 2025 17:18:48 -0500
Subject: [PATCH 02/10] Updated the match types

---
 .github/workflows/ci.yaml              |  2 +-
 hed/tools/analysis/tag_summary_util.py | 37 ++++++++++++++++++++------
 2 files changed, 30 insertions(+), 9 deletions(-)

diff --git a/.github/workflows/ci.yaml b/.github/workflows/ci.yaml
index b169b8f0b..e1bcf5aa8 100644
--- a/.github/workflows/ci.yaml
+++ b/.github/workflows/ci.yaml
@@ -51,7 +51,7 @@ jobs:
       # Install dependencies
       - name: Install dependencies
         run: |
-          python -m pip install --upgrade --upgrade-strategy eager pip
+          python -m pip install --upgrade pip
           pip install -r requirements.txt
           pip install -r docs/requirements.txt
 
diff --git a/hed/tools/analysis/tag_summary_util.py b/hed/tools/analysis/tag_summary_util.py
index 161f41c0b..a3c856889 100644
--- a/hed/tools/analysis/tag_summary_util.py
+++ b/hed/tools/analysis/tag_summary_util.py
@@ -1,4 +1,5 @@
-
+import os
+from hed import load_schema_version
 from hed.tools.analysis.event_manager import EventManager
 from hed.models.tabular_input import TabularInput
 from hed.tools.analysis.hed_tag_manager import HedTagManager
@@ -7,9 +8,9 @@
 REMOVE_TYPES = ['Condition-variable', 'Task']
 
 # Tags organized by whether they are found with either of these
-# MATCH_TYPES = ['Sensory-event', 'Agent-action']
 MATCH_TYPES = ['Experimental-stimulus', 'Participant-response', 'Incidental', 'Instructional', 'Mishap',
-               'Task-activity', 'Warning']
+               'Task-activity', 'Warning', 'Sensory-event', 'Agent-action']
+
 # If a tag has any of these as a parent, it is excluded
 EXCLUDED_PARENTS = {'data-marker', 'data-resolution', 'quantitative-value', 'spatiotemporal-value',
                     'statistical-value', 'informational-property', 'organizational-property',
@@ -40,12 +41,12 @@
                  'tactile-attribute', 'visual-attribute', 'sensory-presentation', 'task-property', 'task-action-type',
                  'task-attentional-demand', 'task-event-role', 'task-stimulus-role'}
 
-def extract_tag_summary(hed_schema, df, sidecar=None, name=None):
+def extract_tag_summary(hed_schema, tsv_file, sidecar_file=None, name=None):
     """ Extract a summary of the tags in a given tabular input file.
     Parameters:
         hed_schema (HedSchema): The HedSchema object to use for the summary.
-        df (pd.DataFrame): The DataFrame to summarize.
-        sidecar (str): The sidecar file to use for the summary.
+        tsv_file(str): The path of the tsv file
+        sidecar_file (str): The sidecar file to use for the summary.
         name (str): The name of the summary.
 
     Returns:
@@ -54,7 +55,7 @@ def extract_tag_summary(hed_schema, df, sidecar=None, name=None):
 
     group_dict = {key: set() for key in MATCH_TYPES}
     other = set()
-    input_data = TabularInput(df, sidecar=sidecar, name=name)
+    input_data = TabularInput(tsv_file, sidecar=sidecar_file, name=name)
     event_manager = EventManager(input_data, hed_schema)
     tag_man = HedTagManager(event_manager, remove_types=REMOVE_TYPES)
     hed_objs = tag_man.get_hed_objs(include_context=False, replace_defs=True)
@@ -91,4 +92,24 @@ def update_tags(tag_set, all_tags):
             tag_set.add(match)
         else:
             tag_set.update(tag.tag_terms)
-    return tag_set
\ No newline at end of file
+    return tag_set
+
+
+if __name__ == '__main__':
+    schema = load_schema_version('8.4.0')
+    root_dir = 'g:/HEDExamples/hed-examples/datasets/eeg_ds003645s_hed'
+    sidecar_path = os.path.join(root_dir, 'task-FacePerception_events.json')
+    tsv_path = os.path.join(root_dir, 'sub-002/eeg/sub-002_task-FacePerception_run-1_events.tsv')
+
+    tag_dict, others = extract_tag_summary(schema, tsv_path, sidecar_file=sidecar_path, name='eeg_ds003645s_hed')
+
+    for the_key, the_item in tag_dict.items():
+        if not the_item:
+            continue
+        print(f"{the_key}:")
+        for tag in the_item:
+            print(f"  {tag}")
+
+    print("Other:")
+    for tag in others:
+        print(f"  {tag}")
\ No newline at end of file

From aa47ea69fcc0ffa3dbc8f0f19bbd6394674d0028 Mon Sep 17 00:00:00 2001
From: Kay Robbins <1189050+VisLab@users.noreply.github.com>
Date: Wed, 30 Apr 2025 17:24:20 -0500
Subject: [PATCH 03/10] Updated the actions to try to fix pip error

---
 .github/workflows/ci.yaml         | 2 +-
 .github/workflows/ci_cov.yaml     | 2 +-
 .github/workflows/ci_windows.yaml | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/.github/workflows/ci.yaml b/.github/workflows/ci.yaml
index e1bcf5aa8..d79f7178c 100644
--- a/.github/workflows/ci.yaml
+++ b/.github/workflows/ci.yaml
@@ -51,7 +51,7 @@ jobs:
       # Install dependencies
       - name: Install dependencies
         run: |
-          python -m pip install --upgrade pip
+          pip install --upgrade pip
           pip install -r requirements.txt
           pip install -r docs/requirements.txt
 
diff --git a/.github/workflows/ci_cov.yaml b/.github/workflows/ci_cov.yaml
index b63ca7a70..a5ebae942 100644
--- a/.github/workflows/ci_cov.yaml
+++ b/.github/workflows/ci_cov.yaml
@@ -46,7 +46,7 @@ jobs:
       # Install dependencies
       - name: Install dependencies
         run: |
-          python -m pip install --upgrade --upgrade-strategy eager pip
+          pip install --upgrade pip
           pip install flake8 coverage -r requirements.txt -r docs/requirements.txt
 
       # Run flake8
diff --git a/.github/workflows/ci_windows.yaml b/.github/workflows/ci_windows.yaml
index d02dfb2e0..d93001394 100644
--- a/.github/workflows/ci_windows.yaml
+++ b/.github/workflows/ci_windows.yaml
@@ -32,7 +32,7 @@ jobs:
 
       - name: Install dependencies
         run: |
-          python -m pip install --upgrade --upgrade-strategy eager pip
+          pip install --upgrade pip
           pip install -r requirements.txt
 
       - name: Test with unittest

From 343dfa78081e117b1c0bf761faaf2df9984efa97 Mon Sep 17 00:00:00 2001
From: Kay Robbins <1189050+VisLab@users.noreply.github.com>
Date: Wed, 30 Apr 2025 17:29:19 -0500
Subject: [PATCH 04/10] Trying again to upgrade

---
 .github/workflows/ci.yaml         | 1 +
 .github/workflows/ci_cov.yaml     | 1 +
 .github/workflows/ci_windows.yaml | 1 +
 3 files changed, 3 insertions(+)

diff --git a/.github/workflows/ci.yaml b/.github/workflows/ci.yaml
index d79f7178c..6985cf2bf 100644
--- a/.github/workflows/ci.yaml
+++ b/.github/workflows/ci.yaml
@@ -51,6 +51,7 @@ jobs:
       # Install dependencies
       - name: Install dependencies
         run: |
+          python -m pip uninstall pip setuptools
           pip install --upgrade pip
           pip install -r requirements.txt
           pip install -r docs/requirements.txt
diff --git a/.github/workflows/ci_cov.yaml b/.github/workflows/ci_cov.yaml
index a5ebae942..1dd05e50f 100644
--- a/.github/workflows/ci_cov.yaml
+++ b/.github/workflows/ci_cov.yaml
@@ -46,6 +46,7 @@ jobs:
       # Install dependencies
       - name: Install dependencies
         run: |
+          python -m pip uninstall pip setuptools
           pip install --upgrade pip
           pip install flake8 coverage -r requirements.txt -r docs/requirements.txt
 
diff --git a/.github/workflows/ci_windows.yaml b/.github/workflows/ci_windows.yaml
index d93001394..460123daf 100644
--- a/.github/workflows/ci_windows.yaml
+++ b/.github/workflows/ci_windows.yaml
@@ -32,6 +32,7 @@ jobs:
 
       - name: Install dependencies
         run: |
+          python -m pip uninstall pip setuptools
           pip install --upgrade pip
           pip install -r requirements.txt
 

From fc3035d7b0e49c5fac8a1c28fb2da8b4e457493e Mon Sep 17 00:00:00 2001
From: Kay Robbins <1189050+VisLab@users.noreply.github.com>
Date: Wed, 30 Apr 2025 17:32:06 -0500
Subject: [PATCH 05/10] Trying not upgrading pip

---
 .github/workflows/ci.yaml         | 2 --
 .github/workflows/ci_cov.yaml     | 2 --
 .github/workflows/ci_windows.yaml | 2 --
 3 files changed, 6 deletions(-)

diff --git a/.github/workflows/ci.yaml b/.github/workflows/ci.yaml
index 6985cf2bf..1f380cae7 100644
--- a/.github/workflows/ci.yaml
+++ b/.github/workflows/ci.yaml
@@ -51,8 +51,6 @@ jobs:
       # Install dependencies
       - name: Install dependencies
         run: |
-          python -m pip uninstall pip setuptools
-          pip install --upgrade pip
           pip install -r requirements.txt
           pip install -r docs/requirements.txt
 
diff --git a/.github/workflows/ci_cov.yaml b/.github/workflows/ci_cov.yaml
index 1dd05e50f..d99d1acf4 100644
--- a/.github/workflows/ci_cov.yaml
+++ b/.github/workflows/ci_cov.yaml
@@ -46,8 +46,6 @@ jobs:
       # Install dependencies
       - name: Install dependencies
         run: |
-          python -m pip uninstall pip setuptools
-          pip install --upgrade pip
           pip install flake8 coverage -r requirements.txt -r docs/requirements.txt
 
       # Run flake8
diff --git a/.github/workflows/ci_windows.yaml b/.github/workflows/ci_windows.yaml
index 460123daf..0ead772cc 100644
--- a/.github/workflows/ci_windows.yaml
+++ b/.github/workflows/ci_windows.yaml
@@ -32,8 +32,6 @@ jobs:
 
       - name: Install dependencies
         run: |
-          python -m pip uninstall pip setuptools
-          pip install --upgrade pip
           pip install -r requirements.txt
 
       - name: Test with unittest

From f73c2b0a06ddf1e3ea402c9588b94d50a166adfb Mon Sep 17 00:00:00 2001
From: Kay Robbins <1189050+VisLab@users.noreply.github.com>
Date: Wed, 30 Apr 2025 18:03:41 -0500
Subject: [PATCH 06/10] Trying a specific version of pip

---
 .github/workflows/ci.yaml         | 1 +
 .github/workflows/ci_cov.yaml     | 1 +
 .github/workflows/ci_windows.yaml | 1 +
 3 files changed, 3 insertions(+)

diff --git a/.github/workflows/ci.yaml b/.github/workflows/ci.yaml
index 1f380cae7..095bbff6b 100644
--- a/.github/workflows/ci.yaml
+++ b/.github/workflows/ci.yaml
@@ -51,6 +51,7 @@ jobs:
       # Install dependencies
       - name: Install dependencies
         run: |
+          python -m pip install --upgrade pip==23.3.1
           pip install -r requirements.txt
           pip install -r docs/requirements.txt
 
diff --git a/.github/workflows/ci_cov.yaml b/.github/workflows/ci_cov.yaml
index d99d1acf4..768217d9f 100644
--- a/.github/workflows/ci_cov.yaml
+++ b/.github/workflows/ci_cov.yaml
@@ -46,6 +46,7 @@ jobs:
       # Install dependencies
       - name: Install dependencies
         run: |
+          python -m pip install --upgrade pip==23.3.1
           pip install flake8 coverage -r requirements.txt -r docs/requirements.txt
 
       # Run flake8
diff --git a/.github/workflows/ci_windows.yaml b/.github/workflows/ci_windows.yaml
index 0ead772cc..037a1d329 100644
--- a/.github/workflows/ci_windows.yaml
+++ b/.github/workflows/ci_windows.yaml
@@ -32,6 +32,7 @@ jobs:
 
       - name: Install dependencies
         run: |
+          python -m pip install --upgrade pip==23.3.1
           pip install -r requirements.txt
 
       - name: Test with unittest

From 1d70c67ef26c9e4e5562e3d1877af660674feb3e Mon Sep 17 00:00:00 2001
From: Kay Robbins <1189050+VisLab@users.noreply.github.com>
Date: Wed, 30 Apr 2025 18:13:04 -0500
Subject: [PATCH 07/10] Tried not using cache

---
 .github/workflows/ci.yaml               |   3 ++-
 .github/workflows/ci_cov.yaml           |   3 ++-
 .github/workflows/ci_windows.yaml       |   3 ++-
 hed/tools/analysis/tag_summary_util.zip | Bin 0 -> 2181 bytes
 4 files changed, 6 insertions(+), 3 deletions(-)
 create mode 100644 hed/tools/analysis/tag_summary_util.zip

diff --git a/.github/workflows/ci.yaml b/.github/workflows/ci.yaml
index 095bbff6b..e348824c6 100644
--- a/.github/workflows/ci.yaml
+++ b/.github/workflows/ci.yaml
@@ -42,6 +42,7 @@ jobs:
         uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
+          cache: false
 
       - uses: actions/cache@v4
         with:
@@ -51,7 +52,7 @@ jobs:
       # Install dependencies
       - name: Install dependencies
         run: |
-          python -m pip install --upgrade pip==23.3.1
+          python -m pip install --upgrade pip
           pip install -r requirements.txt
           pip install -r docs/requirements.txt
 
diff --git a/.github/workflows/ci_cov.yaml b/.github/workflows/ci_cov.yaml
index 768217d9f..c29ab3a47 100644
--- a/.github/workflows/ci_cov.yaml
+++ b/.github/workflows/ci_cov.yaml
@@ -42,11 +42,12 @@ jobs:
         uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
+          cache: false
 
       # Install dependencies
       - name: Install dependencies
         run: |
-          python -m pip install --upgrade pip==23.3.1
+          python -m pip install --upgrade pip
           pip install flake8 coverage -r requirements.txt -r docs/requirements.txt
 
       # Run flake8
diff --git a/.github/workflows/ci_windows.yaml b/.github/workflows/ci_windows.yaml
index 037a1d329..4ba32579f 100644
--- a/.github/workflows/ci_windows.yaml
+++ b/.github/workflows/ci_windows.yaml
@@ -24,6 +24,7 @@ jobs:
         uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
+          cache: false
 
       - uses: actions/cache@v4
         with:
@@ -32,7 +33,7 @@ jobs:
 
       - name: Install dependencies
         run: |
-          python -m pip install --upgrade pip==23.3.1
+          python -m pip install --upgrade pip
           pip install -r requirements.txt
 
       - name: Test with unittest
diff --git a/hed/tools/analysis/tag_summary_util.zip b/hed/tools/analysis/tag_summary_util.zip
new file mode 100644
index 0000000000000000000000000000000000000000..ced22a82d07edacb349ea6013d68d99849664300
GIT binary patch
literal 2181
zcma);XE+-Q7snF>HEV0dZi!NRl<38^x1efVgi@knB?ygFuMTR*s;VGX)vg_B?bXs!
zyNF$@s1Y@a+rA&(_kMiO|9Q@M&i{NmUw&4mv~=76#$Q^FAvgm56<h!j0NTyV6%~v`
zx&?)~2BQ(avH@Yi7-j&F?zith>6R@kfMF|_)4Mm1(>qL)!#msFDRHWi2PX_aqg9AV
zVyH?*G+*bX|0!>zX&yNsVMLzcjeV?bTH7C|_xj3mjKEUMkC(b8L~N#mGJ7?~2)BZp
z?=2ebRzOx()*Gn#N}5RAEFUBHBdfVsKmBO8FB!!^P>$oOi_gXxq>&N_e>RaH246Kx
zton1|zGZBMDv3K_e8>DYD#dg(q@v}`L1(B@b3dz5)8eQ?O9Sz*Js&tGf+|^m>^R~q
zb*pQR?CFHG&$}fh=$*3Fl#I1u{?K@BJ~F}s@qXIEzKyA3!l24px~<H+Y2IRlL89TC
zag}5R7^Ttt?zlGmd_JcXd%B%i`pLHsXX=uZD~U=k1455xVrva_YD*gN=b(H3Y~K))
zktI4G8M@;E3ebzI#w0;5eEt5|hu{e68SeBL*%?5s<1tW$BV3Bd`ie@Sv6@;ziyop*
zNh&Js^^Oks<?L%7#yzL+HHLX0)sp0lke(?ITtrvVxlv4N$Ix3egXXcc8k1RUPR`>u
zU%=MSXs=A){;pG8x32P_!4rJi8Ui-Q@z=UH-i3QKDtU1d+Z1&OT+7tab=S%V$IAoj
z=4U%+!|N+5uTQT_H7z1K2J+>56Vh`FE1(OE1?TA8CNy}7XD*H;zKLX}+oUsK;g=b-
zOr>6SBD1Pq?@p0PW+J|tr??~TDNoE!iQk~2H)yb)hix>fZCl^|xQ;G27PLWj>(8iI
z2i}VAqd7=Zn#R`!e_%dhk&N54^=%*q%!#2}48=(tDlxvHZ?1lI%f_B-P2bgX+H3Er
zn*z4^E0wQzP)9dh$ApE1cB!XYWIi?cFl;D($kOL8UIwA^LHiw(Xm2iT$!p-6GTNy`
zsAm}I^+jXho}RiaA>_0EeFoV0@tWeU%a;T!>w%S@dxOek^g5eF9Y;JR%B@j%Ljib+
z?ZC!LN`m9pPrh#zQ`fmVPvAwOrI^tN+!4>ky-7pMq9D^@q2Adf^{b4|u<r*~An_Jz
zT-Io++4n2CWciZAb!}{P)kEX)dapHT+XuJ#+Ujt7q^K-mkxurTcAJjk+asDC6ACYh
z<72PbCSnDUE1<0p(bsU15uJ!A;3GXury0E_h_LQq_EjHp43(95d8aq8=0;igV!5?r
z^m#|kcpRiws+bt*s!?W`yh>VqF}G=uif0!_z)tk2)qG4J!(0Nxh;zo4QufQT2qOk2
zXDMS(W$>n&2vN5j`o%kRu=wdJlrl0VeIj<pm4Fs>eu9^jJIo2!E^|o*OfZX{^}a|7
z@(TUvX5D<_+Me!SbWA;{MUcysU%<K)O8an|t(;$Dbh$o-8=hj4h4>T`qd!o7vxQnH
zEghGs^~_b*t*Nze48(q?Khybet#k%OhOkIHquUHr#H)<4Zi!T?Whb)d9enoYd6F3u
z)`8vewG^~4*M2IKZB@#azx}A}Ufg5xU3EJ)X?f-3zRf`viCWn1E8YF_P)@s33`mvQ
z7DSLE1hM5}zoyCOlm-EE?G%<+l8^HSZA#SB+&@%>&_XX4Ajex}f}hXBHx19!Q6V}0
zI$i2D^77pBC5t{sN@ks?BFv(eKcCC{tSkZk`U@O)|BmF70L{`C{vFTsI@;ZB-wU^I
zIMJWq+RxO=<{}UaJAy$}qd3l$A}F#|EpOZgu*;81UIyC@<|e+35}Ax1D^-bVQj641
z*rtbV66h|=b$+Q?waXn|%a|m#Elkz2Y4!}C{geb!VO<gs&w1W&1l-Uj+%a5GufaiC
z-y_O0y!ZWT#lVgR8+YPDRpjmXtQmY~mEN|VT<rE)dQn5qXJP7<Acq75%l=`VDl{g;
z)3@oO;-Rbdi$5-9q>L~4dMG9S6!v>kEIge_KD^7-8OGlj)PJ=(PS^)XA1LZ0Ge_51
z#wokqCqnyHI|y7W>X6P(u6L(cHmWZrIaipEZ$zaRtkhgi5@&DkfFYhjV-b$xBwJ_h
z0CEND{qw7DBVa{@k^60X9fk||WP627u!b<+4;}F&g$E8c1`u^7xS^l&yi^QR7xRa$
zj#({!vT>rX-!M7cFl^q_$(ph$aG_ORSljAmJj1wala$h4Cw{hPA(}r=v^ZWIQ@@o~
zQRu5kv_y5C6K=XgD#b^dwBp;3Ui`!h)6i(P->u4+%vP114KQ`AS;kvuKD#JWJ=cAF
zpSL>g)jl)dBtqfE8l#vZ^T>*XhxwC>wFC?kNDn2}+P5dzc4AHn2YVJv>4X3in05oc
zCR<u1`CCR)G8<3^5k6wV^MZk_-MtuxkKS4&F_A7=@Q;I+=DvZ@9lINA&Vc?sa4DRS
z-+~9PC)kD&=ne;0(^t-Zs+!{ZalKo3A(wlQWX>qr65dKm1*PoWF1<_r0nZ34ChIZC
z4mRiSdI7dv__q0EWA?#eR+mNw9U;%cM)(n9{Uw~IYprb!!C1>oQ+w?M0?$QO4=vdS
zArHFRt%h%Vt<uVgO!}ozW==t%aGrO2sMR8ywVeAxky$KZajNl(jQKm$np~e0A$>zK
zT+%|9ZG(IYjCTNjO>!dN6*^s$zM5UQ;9075>R!-ba7}HBf@O|-C+Fu^+;wwl8Ps|9
z$DP@^xgS|Nn3ljj;D8F;07FTLwK1kII0sspGB65H3Y^w4001()0DzS#kcOM~e_ZhI
n9T$NAzm!n_@OS(FPyz@5{7nf~rXc#?C%|8F_*Hose^37aqwEK7

literal 0
HcmV?d00001


From c2c771c745ff474ab822c12442e261252ce4f39b Mon Sep 17 00:00:00 2001
From: Kay Robbins <1189050+VisLab@users.noreply.github.com>
Date: Mon, 5 May 2025 09:35:47 -0500
Subject: [PATCH 08/10] Updated requirements, first implementation of event
 checker

---
 .github/workflows/ci_windows.yaml          |   1 -
 docs/requirements.txt                      |  20 +-
 hed/errors/error_messages.py               |  21 +-
 hed/errors/error_types.py                  |   5 +
 hed/tools/analysis/event_checker.py        | 293 +++++++++++++++++++++
 hed/tools/analysis/tag_summary_util.py     | 115 --------
 hed/tools/analysis/tag_summary_util.zip    | Bin 2181 -> 0 bytes
 requirements.txt                           |  22 +-
 tests/tools/analysis/test_event_checker.py |  80 ++++++
 9 files changed, 419 insertions(+), 138 deletions(-)
 create mode 100644 hed/tools/analysis/event_checker.py
 delete mode 100644 hed/tools/analysis/tag_summary_util.py
 delete mode 100644 hed/tools/analysis/tag_summary_util.zip
 create mode 100644 tests/tools/analysis/test_event_checker.py

diff --git a/.github/workflows/ci_windows.yaml b/.github/workflows/ci_windows.yaml
index 4ba32579f..750f754c3 100644
--- a/.github/workflows/ci_windows.yaml
+++ b/.github/workflows/ci_windows.yaml
@@ -24,7 +24,6 @@ jobs:
         uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
-          cache: false
 
       - uses: actions/cache@v4
         with:
diff --git a/docs/requirements.txt b/docs/requirements.txt
index 30ba57d1e..1cf074a59 100644
--- a/docs/requirements.txt
+++ b/docs/requirements.txt
@@ -1,12 +1,12 @@
 defusedxml>=0.7.1
-inflect>=6.0.5
-jsonschema>=4.17.3
-numpy>=1.21.6
-openpyxl>=3.1.0
-pandas>=1.3.5
-portalocker>=2.7.0
+inflect>=7.5.0
+jsonschema>=4.23.0
+numpy==2.0.2
+openpyxl>=3.1.5
+pandas>=2.2.3
+portalocker>=3.1.1
 semantic-version>=2.10.0
-myst-parser>=1.0.0
-Sphinx>=5.2.2
-sphinx_rtd_theme>=1.0.0
-wordcloud==1.9.4
+myst-parser==3.0.1
+Sphinx==7.4.7
+sphinx_rtd_theme>=3.0.2
+wordcloud>=1.9.4
diff --git a/hed/errors/error_messages.py b/hed/errors/error_messages.py
index b520d6eb8..8b7d69554 100644
--- a/hed/errors/error_messages.py
+++ b/hed/errors/error_messages.py
@@ -5,7 +5,7 @@
 
 from hed.errors.error_reporter import hed_error, hed_tag_error
 from hed.errors.error_types import (ValidationErrors, SidecarErrors, ErrorSeverity, DefinitionErrors,
-                                    TemporalErrors, ColumnErrors)
+                                    TemporalErrors, ColumnErrors, TagQualityErrors)
 
 
 @hed_tag_error(ValidationErrors.UNITS_INVALID)
@@ -462,3 +462,22 @@ def nested_column_ref(column_name, ref_column):
 @hed_error(ColumnErrors.MALFORMED_COLUMN_REF, actual_code=SidecarErrors.SIDECAR_BRACES_INVALID)
 def malformed_column_ref(column_name, index, symbol):
     return f"Column {column_name} has a malformed column reference.  Improper symbol {symbol} found at index {index}."
+
+
+@hed_error(TagQualityErrors.MISSING_EVENT_TYPE, default_severity=ErrorSeverity.WARNING,
+           actual_code=TagQualityErrors.MISSING_EVENT_TYPE)
+def missing_event_type(string, line):
+    return f"The HED string '{string}' at line {line} has no Event type."
+
+
+@hed_error(TagQualityErrors.MISSING_TASK_ROLE, default_severity=ErrorSeverity.WARNING,
+           actual_code=TagQualityErrors.MISSING_TASK_ROLE)
+def missing_task_role(event_type, string, line):
+    return f"The HED string '{string}' at line {line} with event {event_type} has no Task-event-role type tag."
+
+
+@hed_error(TagQualityErrors.IMPROPER_TAG_GROUPING, default_severity=ErrorSeverity.WARNING,
+           actual_code=TagQualityErrors.IMPROPER_TAG_GROUPING)
+def improper_tag_grouping(event_types, string, line):
+    return f"The HED string '{string}' at line {line} has multiple events [{event_types}] but is improperly " + \
+    f"parenthesized so the other tags cannot be uniquely associated with an event."
\ No newline at end of file
diff --git a/hed/errors/error_types.py b/hed/errors/error_types.py
index d743606b6..6157c5978 100644
--- a/hed/errors/error_types.py
+++ b/hed/errors/error_types.py
@@ -190,3 +190,8 @@ class ColumnErrors:
     SELF_COLUMN_REF = "SELF_COLUMN_REF"
     NESTED_COLUMN_REF = "NESTED_COLUMN_REF"
     MALFORMED_COLUMN_REF = "MALFORMED_COLUMN_REF"
+
+class TagQualityErrors:
+    MISSING_EVENT_TYPE = "MISSING_EVENT_TYPE"
+    MISSING_TASK_ROLE = "MISSING_TASK_ROLE"
+    IMPROPER_TAG_GROUPING = "IMPROPER_TAG_GROUPING"
\ No newline at end of file
diff --git a/hed/tools/analysis/event_checker.py b/hed/tools/analysis/event_checker.py
new file mode 100644
index 000000000..3bc2d79b9
--- /dev/null
+++ b/hed/tools/analysis/event_checker.py
@@ -0,0 +1,293 @@
+import os
+from hed import load_schema_version, get_printable_issue_string
+from hed.tools.analysis.event_manager import EventManager
+from hed.errors.error_reporter import ErrorHandler, ErrorContext
+from hed.errors.error_types import TagQualityErrors
+from hed.models.tabular_input import TabularInput
+from hed.tools.analysis.hed_tag_manager import HedTagManager
+
+class EventChecker:
+    EVENT_TAGS = {'Event', 'Sensory-event', 'Agent-action', 'Data-feature', 'Experiment-control',
+                  'Experiment-structure', 'Measurement-event'}
+    NON_TASK_EVENTS = {'Data-feature', 'Experiment-control', 'Experiment-structure', 'Measurement-event'}
+    TASK_ROLES = {'Experimental-stimulus', 'Participant-response', 'Incidental', 'Instructional', 'Mishap',
+                  'Task-activity', 'Warning'}
+    ACTION_ROLES = {'Appropriate-action', 'Correct-action', 'Correction', 'Done-indication',
+                   'Imagined-action', 'Inappropriate-action', 'Incorrect-action', 'Indeterminate-action', 'Miss',
+                   'Near-miss', 'Omitted-action', 'Ready-indication'}
+    STIMULUS_ROLES = {'Cue', 'Distractor', 'Expected', 'Extraneous', 'Feedback', 'Go-signal', 'Meaningful',
+                      'Newly-learned', 'Non-informative', 'Non-target', 'Not-meaningful', 'Novel', 'Oddball',
+                      'Penalty', 'Planned', 'Priming', 'Query', 'Reward', 'Stop-signal', 'Target', 'Threat',
+                      'Timed', 'Unexpected', 'Unplanned'}
+
+    ALL_ROLES = TASK_ROLES.union(ACTION_ROLES).union(STIMULUS_ROLES)
+
+    def __init__(self, hed_obj, line_number, error_handler=None):
+        """ Constructor for the EventChecker class.
+
+        Parameters:
+            hed_obj (HedString): The HED string to check.
+            line_number (int or None): The index of the HED string in the file.
+            error_handler (ErrorHandler): The ErrorHandler object to use for error handling.
+
+        """
+        self.hed_obj = hed_obj
+        self.line_number = line_number
+        if error_handler is None:
+            self.error_handler = ErrorHandler()
+        else:
+            self.error_handler = error_handler
+        self.issues = self._verify_events(self.hed_obj)
+        self.group_error = any(issue['code'] == TagQualityErrors.IMPROPER_TAG_GROUPING for issue in self.issues)
+
+    def _verify_events(self, hed_obj):
+        """ Verify that the events in the HED string are properly grouped.
+
+        Parameters:
+            hed_obj (HedString): The HED string to verify.
+
+        Returns:
+            list: list of issues
+        """
+        if not hed_obj:
+            return []
+        hed_groups = [hed_obj]  # Initialize with the top-level HedGroup
+        while len(hed_groups) > 0:
+            issues = self._check_grouping(hed_groups)
+            if issues:
+                return issues
+        return []
+
+    def _check_grouping(self, hed_groups):
+        """ Check for event tagging errors in a group.
+
+        Parameters:
+            hed_groups (list): A list of the HED Groups to check.
+
+        Returns:
+            list: list of issues
+
+        """
+        group = hed_groups.pop()
+        all_tags = group.get_all_tags()
+        event_tags = [tag.short_base_tag for tag in all_tags if tag.short_base_tag in self.EVENT_TAGS]
+        if not event_tags:
+            return ErrorHandler.format_error_with_context(self.error_handler, TagQualityErrors.MISSING_EVENT_TYPE,
+                                                           string=str(group), line=self.line_number)
+        if len(event_tags) == 1:
+            return self._check_task_role(group, event_tags[0], all_tags)
+
+        # At this point, we know we have multiple event tags in the group.
+        if any(tag.short_base_tag in event_tags for tag in group.tags()):
+            return ErrorHandler.format_error_with_context(self.error_handler, TagQualityErrors.IMPROPER_TAG_GROUPING,
+                                                          string=str(group), line=self.line_number,
+                                                          event_types =', '.join(event_tags))
+        hed_groups.extend(group.groups())
+        return []
+
+    def _check_task_role(self, hed_group, event_tag, all_tags):
+        """ Check that a group with a single event tag has at least one task role tag.
+
+        Parameters:
+            hed_group (HedGroup): The HED group to check (should have a single event tag).
+            event_tag (str): The single event tag associated with the group.
+            all_tags (list): A list of all the HedTag objects in the group.
+
+        Returns:
+            list: list of issues
+
+        ."""
+
+        if event_tag in self.NON_TASK_EVENTS:
+            return []
+        has_task_role = any(tag.short_base_tag in self.TASK_ROLES for tag in all_tags)
+        if has_task_role:
+            return []
+        if event_tag == 'Agent-action' and any(tag.short_base_tag in self.ACTION_ROLES for tag in all_tags):
+            return []
+
+        if event_tag == 'Sensory-event' and any(tag.short_base_tag in self.STIMULUS_ROLES for tag in all_tags):
+            return []
+
+        return ErrorHandler.format_error_with_context(self.error_handler, TagQualityErrors.MISSING_TASK_ROLE,
+                                                      event_type=event_tag, string=str(hed_group),
+                                                      line=self.line_number)
+
+class EventsSummary:
+    # Excluding tags for condition-variables and task -- these can be done separately if we want to.
+    REMOVE_TYPES = ['Condition-variable', 'Task']
+    # Tags organized by whether they are found with either of these
+    MATCH_TYPES = ['Experimental-stimulus', 'Participant-response', 'Cue', 'Feedback', 'Instructional', 'Sensory-event', 'Agent-action']
+
+    # If a tag has any of these as a parent, it is excluded
+    EXCLUDED_PARENTS = {'data-marker', 'data-resolution', 'quantitative-value', 'spatiotemporal-value',
+                        'statistical-value', 'informational-property', 'organizational-property',
+                        'grayscale', 'hsv-color', 'rgb-color', 'luminance', 'luminance-contrast', 'opacity',
+                        'task-effect-evidence', 'task-relationship', 'relation'}
+
+    # If a tag has any of these as a parent, it is replaced by this parent only
+    CUTOFF_TAGS = {'blue-color', 'brown-color', 'cyan-color', 'gray-color', 'green-color', 'orange-color',
+                   'pink-color', 'purple-color', 'red-color', 'white-color', 'yellow-color',
+                   'visual-presentation'}
+
+    # These tags are removed at the end as non-informational
+    FILTERED_TAGS = {'event', 'agent', 'action', 'move-body-part', 'item', 'biological-item', 'anatomical-item',
+                     'body-part',
+                     'lower-extremity-part', 'upper-extremity-part', 'head-part', 'torso-part', 'face-part',
+                     'language-item', 'object', 'geometric-object',
+                     'man-made-object', 'device', 'computing-device', 'io-device', 'input-device', 'output-device',
+                     'auditory-device', 'display-device',
+                     'recording-device', 'natural-object', 'document', 'media', 'media-clip', 'visualization',
+                     'property', 'agent-property', 'agent-state',
+                     'agent-cognitive-state', 'agent-emotional-state', 'agent-physiological-state',
+                     'agent-postural-state',
+                     'agent-task-role', 'agent-trait',
+                     'data-property', 'biological-artifact', 'nonbiological-artifact',
+                     'spatial-property', 'temporal-property', 'spectral-property', 'dara-source-type', 'data-value',
+                     'categorical-value', 'categorical-class-value', 'categorical-judgment-value',
+                     'categorical-level-value', 'categorical-location-value', 'categorical-orientation-value',
+                     'physical-value', 'data-variability-attribute', 'environmental-property', 'sensory-property',
+                     'sensory-attribute', 'auditory-attribute', 'gustatory-attribute', 'olfactory-attribute',
+                     'tactile-attribute', 'visual-attribute', 'sensory-presentation', 'task-property',
+                     'task-action-type',
+                     'task-attentional-demand', 'task-event-role', 'task-stimulus-role'}
+
+    def __init__(self, hed_schema, file, sidecar=None, name=None):
+        """ Constructor for the HedString class.
+
+        Parameters:
+            hed_schema (HedSchema): The HedSchema object to use for the summary.
+            file (str or FileLike or pd.Dataframe): A tsv file to open.
+            sidecar (str or Sidecar or FileLike): A Sidecar or source file/filename.
+            name (str): The name to display for this file for error purposes.
+
+
+        """
+        self._schema = hed_schema
+        self.name = name
+        if name is None and isinstance(file, str):
+            self.name = file
+        self.hed_objs = self._initialize_hed(file, sidecar, name)
+        self.group_error_lines = []
+        self.missing_error_lines = []
+
+    def _initialize_hed(self, file, sidecar, name):
+        input_data = TabularInput(file, sidecar, name=name)
+        event_manager = EventManager(input_data, self._schema)
+        tag_man = HedTagManager(event_manager, remove_types=self.REMOVE_TYPES)
+        return tag_man.get_hed_objs(include_context=False, replace_defs=True)
+
+    def validate_event_tags(self):
+        """ Verify that the events in the HED strings validly represent events.
+
+        Returns:
+            dict: A dictionary with the summary information.
+            set: A set of tags that do not match any of the specified types but are not excluded.
+        """
+        all_issues = []
+        error_handler = ErrorHandler()
+        error_handler.push_error_context(ErrorContext.FILE_NAME, self.name)
+        for index, hed_obj in enumerate(self.hed_objs):
+            if not hed_obj:
+                continue
+            event_check = EventChecker(hed_obj, index, error_handler)
+            if event_check.group_error:
+                self.group_error_lines.append(index)
+            if event_check.issues:
+                self.missing_error_lines.append(index)
+                all_issues += event_check.issues
+        return all_issues
+
+    def extract_tag_summary(self):
+        """ Extract a summary of the tags in a given tabular input file.
+
+        Returns:
+            dict: A dictionary with the summary information - (str, list)
+            list: A set of tags that do not match any of the specified types but are not excluded.
+        """
+
+        group_dict = {key: set() for key in self.MATCH_TYPES}
+        other = set()
+
+        for index, hed_obj in enumerate(self.hed_objs):
+            if not hed_obj or index in self.group_error_lines:
+                continue
+            all_tags = hed_obj.get_all_tags()
+            if index in self.missing_error_lines:
+                other = self.update_tags(other, all_tags)
+                continue
+            found = False
+            for key, tags in group_dict.items():
+                if self.match_tags(all_tags, key):
+                    group_dict[key] = self.update_tags(group_dict[key], all_tags)
+                    found = True
+                    break
+            if not found:
+                other = self.update_tags(other, all_tags)
+
+        for key, tags in group_dict.items():
+            group_dict[key] = sorted(tags - self.FILTERED_TAGS)
+        other = sorted(other - self.FILTERED_TAGS)
+        return group_dict, other
+
+    @staticmethod
+    def match_tags(all_tags, key):
+        return any(tag.short_base_tag == key for tag in all_tags)
+
+    def update_tags(self, tag_set, all_tags):
+        for tag in all_tags:
+            terms = tag.tag_terms
+            if any(item in self.EXCLUDED_PARENTS for item in terms):
+                continue
+            match = next((item for item in terms if item in self.CUTOFF_TAGS), None)
+            if match:
+                tag_set.add(match)
+            else:
+                tag_set.update(tag.tag_terms)
+        return tag_set
+
+
+if __name__ == '__main__':
+    schema = load_schema_version('8.4.0')
+
+    # # Wakeman Henson example
+    # root_dir = 'g:/HEDExamples/hed-examples/datasets/eeg_ds003645s_hed'
+    # sidecar_path = os.path.join(root_dir, 'task-FacePerception_events.json')
+    # tsv_path = os.path.join(root_dir, 'sub-002/eeg/sub-002_task-FacePerception_run-1_events.tsv')
+    # data_name = 'eeg_ds003645s_hed'
+
+    # # Attention shift example
+    # root_dir = 'g:/HEDExamples/hed-examples/datasets/eeg_ds002893s_hed_attention_shift'
+    # sidecar_path = os.path.join(root_dir, 'task-AuditoryVisualShift_events.json')
+    # tsv_path = os.path.join(root_dir, 'sub-002/eeg/sub-002_task-AuditoryVisualShift_run-01_events.tsv')
+    # data_name = 'eeg_ds002893s_hed_attention_shift'
+
+    # Sternberg example
+    root_dir = 'g:/HEDExamples/hed-examples/datasets/eeg_ds004117s_hed_sternberg'
+    sidecar_path = os.path.join(root_dir, 'task-WorkingMemory_events.json')
+    tsv_path = os.path.join(root_dir, 'sub-001/ses-01/eeg/sub-001_ses-01_task-WorkingMemory_run-1_events.tsv')
+    data_name = 'eeg_ds004117s_hed_sternberg'
+
+    # Create the event summary
+    events_summary = EventsSummary(schema, tsv_path, sidecar_path, data_name)
+
+    # Check the validity of the event tags
+    issues = events_summary.validate_event_tags()
+    if issues:
+        print(f"Errors found in {get_printable_issue_string(issues, '')}")
+    else:
+        print(f"No errors found in {data_name}.")
+
+    # Extract the tag summary
+    tag_dict, others = events_summary.extract_tag_summary()
+
+    for the_key, the_item in tag_dict.items():
+        if not the_item:
+            continue
+        print(f"{the_key}:")
+        for tag in the_item:
+            print(f"  {tag}")
+
+    print("Other:")
+    for tag in others:
+        print(f"  {tag}")
\ No newline at end of file
diff --git a/hed/tools/analysis/tag_summary_util.py b/hed/tools/analysis/tag_summary_util.py
deleted file mode 100644
index a3c856889..000000000
--- a/hed/tools/analysis/tag_summary_util.py
+++ /dev/null
@@ -1,115 +0,0 @@
-import os
-from hed import load_schema_version
-from hed.tools.analysis.event_manager import EventManager
-from hed.models.tabular_input import TabularInput
-from hed.tools.analysis.hed_tag_manager import HedTagManager
-
-# Excluding tags for condition-variables and task -- these can be done separately if we want to.
-REMOVE_TYPES = ['Condition-variable', 'Task']
-
-# Tags organized by whether they are found with either of these
-MATCH_TYPES = ['Experimental-stimulus', 'Participant-response', 'Incidental', 'Instructional', 'Mishap',
-               'Task-activity', 'Warning', 'Sensory-event', 'Agent-action']
-
-# If a tag has any of these as a parent, it is excluded
-EXCLUDED_PARENTS = {'data-marker', 'data-resolution', 'quantitative-value', 'spatiotemporal-value',
-                    'statistical-value', 'informational-property', 'organizational-property',
-                    'grayscale', 'hsv-color', 'rgb-color', 'luminance', 'luminance-contrast', 'opacity',
-                    'task-effect-evidence', 'task-relationship', 'relation'}
-
-# If a tag has any of these as a parent, it is replaced by this parent only
-CUTOFF_TAGS = {'blue-color', 'brown-color', 'cyan-color', 'gray-color', 'green-color', 'orange-color',
-               'pink-color', 'purple-color', 'red-color', 'white-color', 'yellow-color',
-               'visual-presentation'}
-
-# These tags are removed at the end as non-informational
-FILTERED_TAGS = {'event', 'agent', 'action', 'move-body-part', 'item', 'biological-item', 'anatomical-item', 'body-part',
-                 'lower-extremity-part', 'upper-extremity-part', 'head-part', 'torso-part', 'face-part',
-                 'language-item', 'object', 'geometric-object',
-                 'man-made-object', 'device', 'computing-device', 'io-device', 'input-device', 'output-device',
-                 'auditory-device', 'display-device',
-                 'recording-device', 'natural-object', 'document', 'media', 'media-clip', 'visualization',
-                 'property', 'agent-property', 'agent-state',
-                 'agent-cognitive-state', 'agent-emotional-state', 'agent-physiological-state', 'agent-postural-state',
-                 'agent-task-role', 'agent-trait',
-                 'data-property', 'biological-artifact', 'nonbiological-artifact',
-                 'spatial-property', 'temporal-property', 'spectral-property', 'dara-source-type', 'data-value',
-                 'categorical-value', 'categorical-class-value', 'categorical-judgment-value',
-                 'categorical-level-value', 'categorical-location-value', 'categorical-orientation-value',
-                 'physical-value', 'data-variability-attribute', 'environmental-property', 'sensory-property',
-                 'sensory-attribute', 'auditory-attribute', 'gustatory-attribute', 'olfactory-attribute',
-                 'tactile-attribute', 'visual-attribute', 'sensory-presentation', 'task-property', 'task-action-type',
-                 'task-attentional-demand', 'task-event-role', 'task-stimulus-role'}
-
-def extract_tag_summary(hed_schema, tsv_file, sidecar_file=None, name=None):
-    """ Extract a summary of the tags in a given tabular input file.
-    Parameters:
-        hed_schema (HedSchema): The HedSchema object to use for the summary.
-        tsv_file(str): The path of the tsv file
-        sidecar_file (str): The sidecar file to use for the summary.
-        name (str): The name of the summary.
-
-    Returns:
-        dict: A dictionary with the summary information.
-    """
-
-    group_dict = {key: set() for key in MATCH_TYPES}
-    other = set()
-    input_data = TabularInput(tsv_file, sidecar=sidecar_file, name=name)
-    event_manager = EventManager(input_data, hed_schema)
-    tag_man = HedTagManager(event_manager, remove_types=REMOVE_TYPES)
-    hed_objs = tag_man.get_hed_objs(include_context=False, replace_defs=True)
-    for hed in hed_objs:
-        if not hed:
-            continue
-        all_tags = hed.get_all_tags()
-        found = False
-        for key, tags in group_dict.items():
-            if match_tags(all_tags, key):
-                group_dict[key] = update_tags(group_dict[key], all_tags)
-                found = True
-                break
-        if not found:
-           other = update_tags(other, all_tags)
-
-    for key, tags in group_dict.items():
-        group_dict[key] = tags - FILTERED_TAGS
-    other = other - FILTERED_TAGS
-    return group_dict, other
-
-
-def match_tags(all_tags, key):
-    return any(tag.short_base_tag == key for tag in all_tags)
-
-
-def update_tags(tag_set, all_tags):
-    for tag in all_tags:
-        terms = tag.tag_terms
-        if any(item in EXCLUDED_PARENTS for item in terms):
-            continue
-        match = next((item for item in terms if item in CUTOFF_TAGS), None)
-        if match:
-            tag_set.add(match)
-        else:
-            tag_set.update(tag.tag_terms)
-    return tag_set
-
-
-if __name__ == '__main__':
-    schema = load_schema_version('8.4.0')
-    root_dir = 'g:/HEDExamples/hed-examples/datasets/eeg_ds003645s_hed'
-    sidecar_path = os.path.join(root_dir, 'task-FacePerception_events.json')
-    tsv_path = os.path.join(root_dir, 'sub-002/eeg/sub-002_task-FacePerception_run-1_events.tsv')
-
-    tag_dict, others = extract_tag_summary(schema, tsv_path, sidecar_file=sidecar_path, name='eeg_ds003645s_hed')
-
-    for the_key, the_item in tag_dict.items():
-        if not the_item:
-            continue
-        print(f"{the_key}:")
-        for tag in the_item:
-            print(f"  {tag}")
-
-    print("Other:")
-    for tag in others:
-        print(f"  {tag}")
\ No newline at end of file
diff --git a/hed/tools/analysis/tag_summary_util.zip b/hed/tools/analysis/tag_summary_util.zip
deleted file mode 100644
index ced22a82d07edacb349ea6013d68d99849664300..0000000000000000000000000000000000000000
GIT binary patch
literal 0
HcmV?d00001

literal 2181
zcma);XE+-Q7snF>HEV0dZi!NRl<38^x1efVgi@knB?ygFuMTR*s;VGX)vg_B?bXs!
zyNF$@s1Y@a+rA&(_kMiO|9Q@M&i{NmUw&4mv~=76#$Q^FAvgm56<h!j0NTyV6%~v`
zx&?)~2BQ(avH@Yi7-j&F?zith>6R@kfMF|_)4Mm1(>qL)!#msFDRHWi2PX_aqg9AV
zVyH?*G+*bX|0!>zX&yNsVMLzcjeV?bTH7C|_xj3mjKEUMkC(b8L~N#mGJ7?~2)BZp
z?=2ebRzOx()*Gn#N}5RAEFUBHBdfVsKmBO8FB!!^P>$oOi_gXxq>&N_e>RaH246Kx
zton1|zGZBMDv3K_e8>DYD#dg(q@v}`L1(B@b3dz5)8eQ?O9Sz*Js&tGf+|^m>^R~q
zb*pQR?CFHG&$}fh=$*3Fl#I1u{?K@BJ~F}s@qXIEzKyA3!l24px~<H+Y2IRlL89TC
zag}5R7^Ttt?zlGmd_JcXd%B%i`pLHsXX=uZD~U=k1455xVrva_YD*gN=b(H3Y~K))
zktI4G8M@;E3ebzI#w0;5eEt5|hu{e68SeBL*%?5s<1tW$BV3Bd`ie@Sv6@;ziyop*
zNh&Js^^Oks<?L%7#yzL+HHLX0)sp0lke(?ITtrvVxlv4N$Ix3egXXcc8k1RUPR`>u
zU%=MSXs=A){;pG8x32P_!4rJi8Ui-Q@z=UH-i3QKDtU1d+Z1&OT+7tab=S%V$IAoj
z=4U%+!|N+5uTQT_H7z1K2J+>56Vh`FE1(OE1?TA8CNy}7XD*H;zKLX}+oUsK;g=b-
zOr>6SBD1Pq?@p0PW+J|tr??~TDNoE!iQk~2H)yb)hix>fZCl^|xQ;G27PLWj>(8iI
z2i}VAqd7=Zn#R`!e_%dhk&N54^=%*q%!#2}48=(tDlxvHZ?1lI%f_B-P2bgX+H3Er
zn*z4^E0wQzP)9dh$ApE1cB!XYWIi?cFl;D($kOL8UIwA^LHiw(Xm2iT$!p-6GTNy`
zsAm}I^+jXho}RiaA>_0EeFoV0@tWeU%a;T!>w%S@dxOek^g5eF9Y;JR%B@j%Ljib+
z?ZC!LN`m9pPrh#zQ`fmVPvAwOrI^tN+!4>ky-7pMq9D^@q2Adf^{b4|u<r*~An_Jz
zT-Io++4n2CWciZAb!}{P)kEX)dapHT+XuJ#+Ujt7q^K-mkxurTcAJjk+asDC6ACYh
z<72PbCSnDUE1<0p(bsU15uJ!A;3GXury0E_h_LQq_EjHp43(95d8aq8=0;igV!5?r
z^m#|kcpRiws+bt*s!?W`yh>VqF}G=uif0!_z)tk2)qG4J!(0Nxh;zo4QufQT2qOk2
zXDMS(W$>n&2vN5j`o%kRu=wdJlrl0VeIj<pm4Fs>eu9^jJIo2!E^|o*OfZX{^}a|7
z@(TUvX5D<_+Me!SbWA;{MUcysU%<K)O8an|t(;$Dbh$o-8=hj4h4>T`qd!o7vxQnH
zEghGs^~_b*t*Nze48(q?Khybet#k%OhOkIHquUHr#H)<4Zi!T?Whb)d9enoYd6F3u
z)`8vewG^~4*M2IKZB@#azx}A}Ufg5xU3EJ)X?f-3zRf`viCWn1E8YF_P)@s33`mvQ
z7DSLE1hM5}zoyCOlm-EE?G%<+l8^HSZA#SB+&@%>&_XX4Ajex}f}hXBHx19!Q6V}0
zI$i2D^77pBC5t{sN@ks?BFv(eKcCC{tSkZk`U@O)|BmF70L{`C{vFTsI@;ZB-wU^I
zIMJWq+RxO=<{}UaJAy$}qd3l$A}F#|EpOZgu*;81UIyC@<|e+35}Ax1D^-bVQj641
z*rtbV66h|=b$+Q?waXn|%a|m#Elkz2Y4!}C{geb!VO<gs&w1W&1l-Uj+%a5GufaiC
z-y_O0y!ZWT#lVgR8+YPDRpjmXtQmY~mEN|VT<rE)dQn5qXJP7<Acq75%l=`VDl{g;
z)3@oO;-Rbdi$5-9q>L~4dMG9S6!v>kEIge_KD^7-8OGlj)PJ=(PS^)XA1LZ0Ge_51
z#wokqCqnyHI|y7W>X6P(u6L(cHmWZrIaipEZ$zaRtkhgi5@&DkfFYhjV-b$xBwJ_h
z0CEND{qw7DBVa{@k^60X9fk||WP627u!b<+4;}F&g$E8c1`u^7xS^l&yi^QR7xRa$
zj#({!vT>rX-!M7cFl^q_$(ph$aG_ORSljAmJj1wala$h4Cw{hPA(}r=v^ZWIQ@@o~
zQRu5kv_y5C6K=XgD#b^dwBp;3Ui`!h)6i(P->u4+%vP114KQ`AS;kvuKD#JWJ=cAF
zpSL>g)jl)dBtqfE8l#vZ^T>*XhxwC>wFC?kNDn2}+P5dzc4AHn2YVJv>4X3in05oc
zCR<u1`CCR)G8<3^5k6wV^MZk_-MtuxkKS4&F_A7=@Q;I+=DvZ@9lINA&Vc?sa4DRS
z-+~9PC)kD&=ne;0(^t-Zs+!{ZalKo3A(wlQWX>qr65dKm1*PoWF1<_r0nZ34ChIZC
z4mRiSdI7dv__q0EWA?#eR+mNw9U;%cM)(n9{Uw~IYprb!!C1>oQ+w?M0?$QO4=vdS
zArHFRt%h%Vt<uVgO!}ozW==t%aGrO2sMR8ywVeAxky$KZajNl(jQKm$np~e0A$>zK
zT+%|9ZG(IYjCTNjO>!dN6*^s$zM5UQ;9075>R!-ba7}HBf@O|-C+Fu^+;wwl8Ps|9
z$DP@^xgS|Nn3ljj;D8F;07FTLwK1kII0sspGB65H3Y^w4001()0DzS#kcOM~e_ZhI
n9T$NAzm!n_@OS(FPyz@5{7nf~rXc#?C%|8F_*Hose^37aqwEK7

diff --git a/requirements.txt b/requirements.txt
index 2a1c87a8c..52d16dac3 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,11 +1,11 @@
-defusedxml>=0.7.1
-inflect>=6.0.5
-jsonschema>=4.17.3
-matplotlib>=3
-numpy>=1.21.6
-openpyxl>=3.1.0
-pandas>=1.3.5
-pillow>=9.5.0
-portalocker>=2.7.0
-semantic-version>=2.10.0
-wordcloud>=1.9.3
+defusedxml>=0.7.1
+inflect>=7.5.0
+jsonschema>=4.23.0
+matplotlib==3.9.4
+numpy==2.0.2
+openpyxl>=3.1.5
+pandas>=2.2.3
+pillow>=11.2.1
+portalocker>=3.1.1
+semantic-version>=2.10.0
+wordcloud>=1.9.4
diff --git a/tests/tools/analysis/test_event_checker.py b/tests/tools/analysis/test_event_checker.py
new file mode 100644
index 000000000..636191966
--- /dev/null
+++ b/tests/tools/analysis/test_event_checker.py
@@ -0,0 +1,80 @@
+import unittest
+from hed.errors.error_types import TagQualityErrors
+from hed.schema import load_schema_version
+from hed.models.hed_string import HedString
+from hed.tools.analysis.event_checker import EventChecker
+
+
+class TestEventChecker(unittest.TestCase):
+
+    @classmethod
+    def setUpClass(cls):
+        cls.hed_schema = load_schema_version('8.3.0')
+
+    def test_no_event_tag(self):
+        hed_strings = ['Action, (Participant-response, Red)']
+        for hed_string in hed_strings:
+            hed_obj = HedString(hed_string, hed_schema=self.hed_schema)
+            checker = EventChecker(hed_obj, 0)
+            self.assertEqual(checker.issues[0]["code"], TagQualityErrors.MISSING_EVENT_TYPE)
+
+    def test_event_without_task_role(self):
+        hed_strings = ['Sensory-event, (Red, Blue)', '((Agent-action, Red))']
+        for hed_string in hed_strings:
+            hed_obj = HedString(hed_string, hed_schema=self.hed_schema)
+            checker = EventChecker(hed_obj, 2)
+            self.assertEqual(checker.issues[0]["code"], TagQualityErrors.MISSING_TASK_ROLE)
+
+    def test_event_with_task_role(self):
+        hed_strings = ['(Sensory-event, (Experimental-stimulus, Blue, Green))',
+                       '((Agent-action, Participant-response, Red))']
+        for hed_string in hed_strings:
+            hed_obj = HedString(hed_string, hed_schema=self.hed_schema)
+            checker = EventChecker(hed_obj, 2)
+            self.assertEqual(checker.issues, [])
+
+    def test_improperly_grouped_event_tags(self):
+        hed_strings = ['Sensory-event, (Red, Blue), Experiment-control',
+                       '((Sensory-event, (Red, Blue), Experiment-control))']
+        for hed_string in hed_strings:
+            hed_obj = HedString(hed_string, hed_schema=self.hed_schema)
+            checker = EventChecker(hed_obj, 2)
+            self.assertEqual(checker.issues[0]["code"], TagQualityErrors.IMPROPER_TAG_GROUPING)
+
+    def test_nested_group_with_event_and_task_role(self):
+        hed_strings = ['Sensory-event, ((Experimental-stimulus, Red))', '(Experiment-control, Incidental)']
+        for hed_string in hed_strings:
+            hed_obj = HedString(hed_string, hed_schema=self.hed_schema)
+            checker = EventChecker(hed_obj, 5)
+            self.assertEqual(checker.issues, [])
+
+    def test_empty_hed_string(self):
+        checker = EventChecker(None, 6)
+        self.assertEqual(checker.issues, [])
+
+    def test_flat_event_with_task_role(self):
+        hed_string = 'Agent-action, Participant-response, Red'
+        hed_obj = HedString(hed_string, hed_schema=self.hed_schema)
+        checker = EventChecker(hed_obj, 7)
+        self.assertEqual(checker.issues, [])
+
+    def test_task_role_without_event(self):
+        hed_string = '(Experimental-stimulus, Green)'
+        hed_obj = HedString(hed_string, hed_schema=self.hed_schema)
+        checker = EventChecker(hed_obj, 8)
+        self.assertEqual(checker.issues[0]["code"], TagQualityErrors.MISSING_EVENT_TYPE)
+
+    def test_multiple_event_tags_mixed_grouping(self):
+        hed_string = 'Sensory-event, (Agent-action, Instructional)'
+        hed_obj = HedString(hed_string, hed_schema=self.hed_schema)
+        checker = EventChecker(hed_obj, 9)
+        self.assertEqual(checker.issues[0]["code"], TagQualityErrors.IMPROPER_TAG_GROUPING)
+
+    def test_empty_nested_group(self):
+        hed_string = '(())'
+        hed_obj = HedString(hed_string, hed_schema=self.hed_schema)
+        checker = EventChecker(hed_obj, 10)
+        self.assertEqual(checker.issues[0]["code"], TagQualityErrors.MISSING_EVENT_TYPE)
+
+if __name__ == '__main__':
+    unittest.main()
\ No newline at end of file

From b5df3cf3340bd771f64255f481b0bf815dd774dd Mon Sep 17 00:00:00 2001
From: Kay Robbins <1189050+VisLab@users.noreply.github.com>
Date: Mon, 5 May 2025 09:45:29 -0500
Subject: [PATCH 09/10] Removed 3.8 from support

---
 .github/workflows/ci.yaml             |  5 +-
 .github/workflows/test_installer.yaml | 88 +++++++++++++--------------
 2 files changed, 46 insertions(+), 47 deletions(-)

diff --git a/.github/workflows/ci.yaml b/.github/workflows/ci.yaml
index e348824c6..70b48382f 100644
--- a/.github/workflows/ci.yaml
+++ b/.github/workflows/ci.yaml
@@ -16,10 +16,10 @@ jobs:
         run: |
           if [[ "${{ github.event_name }}" == 'push' && "${{ github.ref }}" == 'refs/heads/master' ]]; then
             # Push to master branch
-            echo 'matrix=["3.8", "3.9", "3.10", "3.11"]' >> $GITHUB_OUTPUT
+            echo 'matrix=["3.9", "3.10", "3.11"]' >> $GITHUB_OUTPUT
           elif [[ "${{ github.event_name }}" == 'pull_request' && "${{ github.event.pull_request.base.ref }}" == 'master' ]]; then
             # PR to master branch
-            echo 'matrix=["3.8", "3.9", "3.10", "3.11"]' >> $GITHUB_OUTPUT
+            echo 'matrix=["3.9", "3.10", "3.11"]' >> $GITHUB_OUTPUT
           else
             echo 'matrix=["3.9", "3.11"]' >> $GITHUB_OUTPUT
           fi
@@ -42,7 +42,6 @@ jobs:
         uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
-          cache: false
 
       - uses: actions/cache@v4
         with:
diff --git a/.github/workflows/test_installer.yaml b/.github/workflows/test_installer.yaml
index 31526b7ac..4be55c0cc 100644
--- a/.github/workflows/test_installer.yaml
+++ b/.github/workflows/test_installer.yaml
@@ -1,44 +1,44 @@
-on:
-  push:
-    branches: ["develop"]
-  pull_request:
-    branches: ["develop"]
-
-jobs:
-  build:
-    runs-on: ubuntu-latest
-
-    strategy:
-      matrix:
-        python-version: ["3.8", "3.11"]
-
-    steps:
-    - uses: actions/checkout@v4
-    - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v5
-      with:
-        python-version: ${{ matrix.python-version }}
-
-    - name: Create work directory
-      run: |
-        mkdir workdir
-        echo "WORKDIR=$(pwd)/workdir" >> $GITHUB_OUTPUT
-
-    - name: Create and activate virtual environment
-      run: |
-        cd $WORKDIR
-        python -m venv .venv
-        source .venv/bin/activate
-
-    - name: Install package
-      run: |
-        cd $WORKDIR
-        source .venv/bin/activate
-        python -m pip install --upgrade pip
-        pip install $GITHUB_WORKSPACE
-
-    - name: Run post-installation test
-      run: |
-        cd $WORKDIR
-        source .venv/bin/activate
-        python -c "from hed.models.hed_string import HedString; print('Import test passed.')"
+on:
+  push:
+    branches: ["develop"]
+  pull_request:
+    branches: ["develop"]
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+
+    strategy:
+      matrix:
+        python-version: ["3.9", "3.11"]
+
+    steps:
+    - uses: actions/checkout@v4
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v5
+      with:
+        python-version: ${{ matrix.python-version }}
+
+    - name: Create work directory
+      run: |
+        mkdir workdir
+        echo "WORKDIR=$(pwd)/workdir" >> $GITHUB_OUTPUT
+
+    - name: Create and activate virtual environment
+      run: |
+        cd $WORKDIR
+        python -m venv .venv
+        source .venv/bin/activate
+
+    - name: Install package
+      run: |
+        cd $WORKDIR
+        source .venv/bin/activate
+        python -m pip install --upgrade pip
+        pip install $GITHUB_WORKSPACE
+
+    - name: Run post-installation test
+      run: |
+        cd $WORKDIR
+        source .venv/bin/activate
+        python -c "from hed.models.hed_string import HedString; print('Import test passed.')"

From a22237cbac38c1822479886ae89cb410eb91fc53 Mon Sep 17 00:00:00 2001
From: Kay Robbins <1189050+VisLab@users.noreply.github.com>
Date: Mon, 5 May 2025 09:57:10 -0500
Subject: [PATCH 10/10] Updated the python versions

---
 .github/workflows/ci.yaml         | 6 +++---
 .github/workflows/ci_cov.yaml     | 3 +--
 .github/workflows/ci_windows.yaml | 2 +-
 pyproject.toml                    | 2 +-
 4 files changed, 6 insertions(+), 7 deletions(-)

diff --git a/.github/workflows/ci.yaml b/.github/workflows/ci.yaml
index 70b48382f..6a737758c 100644
--- a/.github/workflows/ci.yaml
+++ b/.github/workflows/ci.yaml
@@ -16,12 +16,12 @@ jobs:
         run: |
           if [[ "${{ github.event_name }}" == 'push' && "${{ github.ref }}" == 'refs/heads/master' ]]; then
             # Push to master branch
-            echo 'matrix=["3.9", "3.10", "3.11"]' >> $GITHUB_OUTPUT
+            echo 'matrix=["3.9", "3.10", "3.11", "3.12", "3.13"]' >> $GITHUB_OUTPUT
           elif [[ "${{ github.event_name }}" == 'pull_request' && "${{ github.event.pull_request.base.ref }}" == 'master' ]]; then
             # PR to master branch
-            echo 'matrix=["3.9", "3.10", "3.11"]' >> $GITHUB_OUTPUT
+            echo 'matrix=["3.9", "3.10", "3.11", "3.12", "3.13"]' >> $GITHUB_OUTPUT
           else
-            echo 'matrix=["3.9", "3.11"]' >> $GITHUB_OUTPUT
+            echo 'matrix=["3.9", "3.13"]' >> $GITHUB_OUTPUT
           fi
 
   build:
diff --git a/.github/workflows/ci_cov.yaml b/.github/workflows/ci_cov.yaml
index c29ab3a47..31f3c9946 100644
--- a/.github/workflows/ci_cov.yaml
+++ b/.github/workflows/ci_cov.yaml
@@ -29,7 +29,7 @@ jobs:
     strategy:
       matrix:
         platform: [ubuntu-latest]
-        python-version: [ "3.9" ]
+        python-version: [ "3.12" ]
 
     runs-on: ${{ matrix.platform }}
 
@@ -42,7 +42,6 @@ jobs:
         uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
-          cache: false
 
       # Install dependencies
       - name: Install dependencies
diff --git a/.github/workflows/ci_windows.yaml b/.github/workflows/ci_windows.yaml
index 750f754c3..df667792e 100644
--- a/.github/workflows/ci_windows.yaml
+++ b/.github/workflows/ci_windows.yaml
@@ -11,7 +11,7 @@ jobs:
     strategy:
       matrix:
         platform: [windows-latest]
-        python-version: ["3.10"]
+        python-version: ["3.9", "3.10", "3.11", "3.12", "3.13""]
 
     runs-on: ${{ matrix.platform }}
 
diff --git a/pyproject.toml b/pyproject.toml
index 9765045bd..dbc77e9c1 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -24,7 +24,7 @@ classifiers = [
     "Operating System :: OS Independent",
 ]
 
-requires-python = ">=3.8"
+requires-python = ">=3.9"
 
 dependencies = [
     "defusedxml",