Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,11 +1,8 @@
 import streamlit as st
 import io
 import csv
-import concurrent.futures
-from segments import SegmentsClient
 from datetime import datetime
-import sys
-import os
+from segments import SegmentsClient
 from get_labels_from_samples import (
     get_samples as get_samples_objects,
     export_frames_and_annotations,
@@ -47,95 +44,6 @@ def parse_classes(input_str: str) -> list:
     return sorted(set(classes))
 
 
-def _count_from_frames(frames, target_set):
-    """Helper to count frames, total annotations, and matching annotations directly."""
-    if not frames:
-        return 0, 0, 0
-    num_frames = len(frames)
-    total_annotations = 0
-    matching_annotations = 0
-    for f in frames:
-        anns = getattr(f, 'annotations', [])
-        total_annotations += len(anns)
-        if target_set:
-            for ann in anns:
-                if getattr(ann, 'category_id', None) in target_set:
-                    matching_annotations += 1
-    return num_frames, total_annotations, matching_annotations
-
-
-def compute_metrics_for_sample(sample, api_key, target_set, is_multisensor, sensor_select):
-    """
-    Fetch label for a single sample and compute metrics.
-    Returns a list of metric dicts (one per sensor if 'All sensors', otherwise one).
-    """
-    try:
-        client = init_client(api_key)
-        label = client.get_label(sample.uuid)
-        labelset = getattr(label, 'labelset', '') or ''
-        labeled_by = getattr(label, 'created_by', '') or ''
-        reviewed_by = getattr(label, 'reviewed_by', '') or ''
-
-        metrics_rows = []
-
-        if is_multisensor:
-            sensors = getattr(getattr(label, 'attributes', None), 'sensors', None) or []
-            if sensor_select and sensor_select != 'All sensors':
-                # single sensor
-                for sensor in sensors:
-                    if getattr(sensor, 'name', None) == sensor_select:
-                        frames = getattr(getattr(sensor, 'attributes', None), 'frames', [])
-                        num_frames, total_annotations, matching_annotations = _count_from_frames(frames, target_set)
-                        metrics_rows.append({
-                            'name': getattr(sample, 'name', sample.uuid),
-                            'uuid': sample.uuid,
-                            'labelset': labelset,
-                            'sensor': sensor_select,
-                            'num_frames': num_frames,
-                            'total_annotations': total_annotations,
-                            'matching_annotations': matching_annotations,
-                            'labeled_by': labeled_by,
-                            'reviewed_by': reviewed_by
-                        })
-                        break
-            else:
-                # all sensors
-                for sensor in sensors:
-                    sensor_name = getattr(sensor, 'name', 'Unknown')
-                    frames = getattr(getattr(sensor, 'attributes', None), 'frames', [])
-                    num_frames, total_annotations, matching_annotations = _count_from_frames(frames, target_set)
-                    metrics_rows.append({
-                        'name': getattr(sample, 'name', sample.uuid),
-                        'uuid': sample.uuid,
-                        'labelset': labelset,
-                        'sensor': sensor_name,
-                        'num_frames': num_frames,
-                        'total_annotations': total_annotations,
-                        'matching_annotations': matching_annotations,
-                        'labeled_by': labeled_by,
-                        'reviewed_by': reviewed_by
-                    })
-        else:
-            # single-sensor dataset
-            frames = getattr(getattr(label, 'attributes', None), 'frames', [])
-            num_frames, total_annotations, matching_annotations = _count_from_frames(frames, target_set)
-            metrics_rows.append({
-                'name': getattr(sample, 'name', sample.uuid),
-                'uuid': sample.uuid,
-                'labelset': labelset,
-                'sensor': '',
-                'num_frames': num_frames,
-                'total_annotations': total_annotations,
-                'matching_annotations': matching_annotations,
-                'labeled_by': labeled_by,
-                'reviewed_by': reviewed_by
-            })
-
-        return metrics_rows
-    except Exception:
-        return []
-
-
 def generate_csv(metrics: list, dataset_identifier: str) -> str:
     """
     Generate CSV content from list of per-sample metrics.
@@ -194,9 +102,6 @@ if api_key and dataset_identifier:
 if is_multisensor:
     sensor_select = st.selectbox("Choose sensor (optional)", options=['All sensors'] + sensor_names)
 
-# Concurrency control
-parallel_workers = st.slider("Parallel requests", min_value=1, max_value=32, value=8, help="Increase to speed up processing; lower if you hit API limits.")
-
 if run_button:
     st.session_state.csv_content = None
     st.session_state.error = None
@@ -217,33 +122,75 @@ if run_button:
             st.info("Checking dataset type...")
         try:
             target_classes = parse_classes(classes_input)
-            target_set = set(target_classes)
+            client = init_client(api_key)
             metrics = []
             # Update loader after dataset type check
             if status_ctx is not None:
                 status_ctx.update(label="Dataset type checked. Processing samples...", state="running")
-            progress = st.progress(0)
-            total = len(samples_objects)
-            done = 0
-            with concurrent.futures.ThreadPoolExecutor(max_workers=parallel_workers) as executor:
-                futures = [
-                    executor.submit(
-                        compute_metrics_for_sample,
-                        sample,
-                        api_key,
-                        target_set,
-                        is_multisensor,
-                        sensor_select,
-                    )
-                    for sample in samples_objects
-                ]
-                for future in concurrent.futures.as_completed(futures):
-                    rows = future.result()
-                    if rows:
-                        metrics.extend(rows)
-                    done += 1
-                    if total:
-                        progress.progress(min(done / total, 1.0))
+            for sample in samples_objects:
+                try:
+                    label = client.get_label(sample.uuid)
+                    labelset = getattr(label, 'labelset', '') or ''
+                    labeled_by = getattr(label, 'created_by', '') or ''
+                    reviewed_by = getattr(label, 'reviewed_by', '') or ''
+                    if is_multisensor and sensor_select and sensor_select != 'All sensors':
+                        frames_list = export_sensor_frames_and_annotations(label, sensor_select)
+                        sensor_val = sensor_select
+                        num_frames = len(frames_list)
+                        total_annotations = sum(len(f['annotations']) for f in frames_list)
+                        matching_annotations = sum(
+                            1
+                            for f in frames_list
+                            for ann in f['annotations']
+                            if getattr(ann, 'category_id', None) in target_classes
+                        )
+                    elif is_multisensor and (not sensor_select or sensor_select == 'All sensors'):
+                        all_sensor_frames = export_all_sensor_frames_and_annotations(label)
+                        for sensor_name, frames_list in all_sensor_frames.items():
+                            num_frames = len(frames_list)
+                            total_annotations = sum(len(f['annotations']) for f in frames_list)
+                            matching_annotations = sum(
+                                1
+                                for f in frames_list
+                                for ann in f['annotations']
+                                if getattr(ann, 'category_id', None) in target_classes
+                            )
+                            metrics.append({
+                                'name': getattr(sample, 'name', sample.uuid),
+                                'uuid': sample.uuid,
+                                'labelset': labelset,
+                                'sensor': sensor_name,
+                                'num_frames': num_frames,
+                                'total_annotations': total_annotations,
+                                'matching_annotations': matching_annotations,
+                                'labeled_by': labeled_by,
+                                'reviewed_by': reviewed_by
+                            })
+                        continue
+                    else:
+                        frames_list = export_frames_and_annotations(label)
+                        sensor_val = ''
+                        num_frames = len(frames_list)
+                        total_annotations = sum(len(f['annotations']) for f in frames_list)
+                        matching_annotations = sum(
+                            1
+                            for f in frames_list
+                            for ann in f['annotations']
+                            if getattr(ann, 'category_id', None) in target_classes
+                        )
+                    metrics.append({
+                        'name': getattr(sample, 'name', sample.uuid),
+                        'uuid': sample.uuid,
+                        'labelset': labelset,
+                        'sensor': sensor_val if is_multisensor else '',
+                        'num_frames': num_frames,
+                        'total_annotations': total_annotations,
+                        'matching_annotations': matching_annotations,
+                        'labeled_by': labeled_by,
+                        'reviewed_by': reviewed_by
+                    })
+                except Exception as e:
+                    continue
             if not metrics:
                 st.session_state.error = "No metrics could be generated for the dataset."
             else:
@@ -266,4 +213,4 @@ if st.session_state.csv_content:
         data=st.session_state.csv_content,
         file_name=filename,
         mime="text/csv"
-    )
+    )