halib 0.1.58__py3-none-any.whl → 0.1.60__py3-none-any.whl

halib/research/perfcalc.py

@@ -124,6 +124,7 @@ class PerfCalc(ABC): # Abstract base class for performance calculation
         all_metric_data = self.prepare_exp_data_for_metrics(
             metric_names, *args, **kwargs
         )
+        metric_col_names = []
         for metric in metric_names:
             if metric not in all_metric_data:
                 raise ValueError(f"Metric '{metric}' not found in provided data.")
@@ -140,8 +141,12 @@ class PerfCalc(ABC): # Abstract base class for performance calculation
                 args = metric_data
             else:
                 raise TypeError(f"Unsupported data format for metric '{metric}'")
+
             # Call update and compute
-            tmetric.update(*args)
+            if len(expected_args) == 1:
+                tmetric.update(args)  # pass as single argument
+            else:
+                tmetric.update(*args)    # unpack multiple arguments
             computed_value = tmetric.compute()
             # ensure the computed value converted to a scala value or list array
             if isinstance(computed_value, torch.Tensor):
@@ -149,16 +154,16 @@ class PerfCalc(ABC): # Abstract base class for performance calculation
                     computed_value = computed_value.item()
                 else:
                     computed_value = computed_value.tolist()
-            out_dict[metric] = computed_value
+            col_name = f"metric_{metric}" if 'metric_' not in metric else metric
+            metric_col_names.append(col_name)
+            out_dict[col_name] = computed_value
 
         # check if any kwargs named "outfile"
         csv_outfile = kwargs.get("outfile", None)
         if csv_outfile is not None:
-            # get the file path without the extension
             filePathNoExt, _ = os.path.splitext(csv_outfile)
-            # add the postfix to the file path
-            csvfilename = f"{now_str()}_{filePathNoExt}{CSV_FILE_POSTFIX}.csv"
-            csv_outfile = os.path.join(os.path.dirname(csv_outfile), csvfilename)
+            # pprint(f"CSV Outfile Path (No Ext): {filePathNoExt}")
+            csv_outfile = f'{filePathNoExt}{CSV_FILE_POSTFIX}.csv'
         elif "outdir" in kwargs:
             csvoutdir = kwargs["outdir"]
             csvfilename = f"{now_str()}_{self.get_dataset_name()}_{self.get_experiment_name()}_{CSV_FILE_POSTFIX}.csv"
@@ -166,7 +171,7 @@ class PerfCalc(ABC): # Abstract base class for performance calculation
 
         # convert out_dict to a DataFrame
         df = pd.DataFrame([out_dict])
-        ordered_cols = REQUIRED_COLS + custom_fields + metric_names
+        ordered_cols = REQUIRED_COLS + custom_fields + metric_col_names
         df = df[ordered_cols]  # reorder columns
 
         if csv_outfile:
@@ -208,7 +213,7 @@ class PerfCalc(ABC): # Abstract base class for performance calculation
                         temp_df[col] = None  # fill missing columns with None
                 df = pd.concat([df, temp_df], ignore_index=True)
             # assert that REQUIRED_COLS are present in the DataFrame
-            pprint(df.columns.tolist())
+            # pprint(df.columns.tolist())
             for col in REQUIRED_COLS:
                 if col not in df.columns:
                     raise ValueError(f"Required column '{col}' is missing from the DataFrame. REQUIRED_COLS = {REQUIRED_COLS}")
@@ -275,21 +280,36 @@ class PerfCalc(ABC): # Abstract base class for performance calculation
 
         assert os.path.exists(indir), f"Input directory {indir} does not exist."
 
+        csv_perf_files = []
         # Find experiment subdirectories
         exp_dirs = [
             os.path.join(indir, d)
             for d in os.listdir(indir)
             if os.path.isdir(os.path.join(indir, d))
         ]
-        assert exp_dirs, f"No experiment directories found in {indir}."
+        if len(exp_dirs) == 0:
+            csv_perf_files = glob.glob(
+                os.path.join(indir, f"*{exp_perf_csv_pattern}*.csv")
+            )
+            csv_perf_files = [
+                file_item
+                for file_item in csv_perf_files
+                if exp_perf_csv_pattern in file_item
+            ]
+        else:
+            # multiple experiment directories found
+            # Collect all matching CSV files in those subdirs
+            for exp_dir in exp_dirs:
+                # pprint(f"Searching in experiment directory: {exp_dir}")
+                matched = glob.glob(
+                    os.path.join(exp_dir, f"*{exp_perf_csv_pattern}*.csv")
+                )
+                csv_perf_files.extend(matched)
 
-        # Collect all matching CSV files in those subdirs
-        csv_perf_files = []
-        for exp_dir in exp_dirs:
-            pprint(f"Searching in experiment directory: {exp_dir}")
-            matched = glob.glob(os.path.join(exp_dir, f"*{exp_perf_csv_pattern}*.csv"))
+        assert (
+            len(csv_perf_files) > 0
+        ), f"No CSV files matching pattern '{exp_perf_csv_pattern}' found in the experiment directories."
 
-            csv_perf_files.extend(matched)
         assert len(csv_perf_files) > 0, f"No CSV files matching pattern '{exp_perf_csv_pattern}' found in the experiment directories."
 
         all_exp_perf_df = get_df_for_all_exp_perf(csv_perf_files, csv_sep=csv_sep)

halib/utils/dataclass_util.py

@@ -26,6 +26,7 @@ def yaml_to_dataclass(name: str, yaml_str: str):
     data = yaml.safe_load(yaml_str)
     return dict_to_dataclass(name, data)
 
+
 def yamlfile_to_dataclass(name: str, file_path: str):
     data_dict = yamlfile.load_yaml(file_path, to_dict=True)
     if "__base__" in data_dict:

halib/utils/dict_op.py

@@ -0,0 +1,9 @@
+def flatten_dict(d, parent_key="", sep="."):
+    items = {}
+    for k, v in d.items():
+        key = f"{parent_key}{sep}{k}" if parent_key else k
+        if isinstance(v, dict):
+            items.update(flatten_dict(v, key, sep=sep))
+        else:
+            items[key] = v
+    return items

halib/utils/video.py

@@ -0,0 +1,62 @@
+import os
+import cv2
+from ..filetype import csvfile
+from ..system import filesys as fs
+
+
+class VideoUtils:
+    @staticmethod
+    def get_video_meta_dict(video_path):
+        # Open the video file
+        cap = cv2.VideoCapture(video_path)
+
+        # Check if the video was opened successfully
+        if not cap.isOpened():
+            print(f"Error: Could not open video file {video_path}")
+            return None, None
+
+        # Get the frame count
+        frame_count = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
+
+        # Get the FPS
+        fps = cap.get(cv2.CAP_PROP_FPS)
+
+        # Release the video capture object
+        cap.release()
+        meta_dict = {
+            "video_path": video_path,
+            "frame_count": frame_count,
+            "fps": fps
+        }
+        return meta_dict
+
+    @staticmethod
+    def get_video_dir_meta_df(video_dir, video_exts=['.mp4', '.avi', '.mov', '.mkv'], search_recursive=False, csv_outfile=None):
+        assert os.path.exists(video_dir), f"Video directory {video_dir} does not exist"
+        video_files = fs.filter_files_by_extension(video_dir, video_exts, recursive=search_recursive)
+        assert len(video_files) > 0, f"No video files found in {video_dir} with extensions {video_exts}"
+        video_meta_list = []
+        for vfile in video_files:
+            meta_dict = VideoUtils.get_video_meta_dict(vfile)
+            if meta_dict:
+                video_meta_list.append(meta_dict)
+        dfmk = csvfile.DFCreator()
+        columns = list(video_meta_list[0].keys())
+        assert len(columns) > 0, "No video metadata found"
+        assert 'video_path' in columns, "video_path column not found in video metadata"
+        # move video_path to the first column
+        columns.remove('video_path')
+        columns.insert(0, 'video_path')
+        dfmk.create_table("video_meta", columns)
+        rows = [[meta[col] for col in columns] for meta in video_meta_list]
+        dfmk.insert_rows("video_meta", rows)
+        dfmk.fill_table_from_row_pool("video_meta")
+
+        if csv_outfile:
+            dfmk["video_meta"].to_csv(csv_outfile, index=False, sep=";")
+        return dfmk["video_meta"].copy()
+
+
+
+
+

{halib-0.1.58.dist-info → halib-0.1.60.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: halib
-Version: 0.1.58
+Version: 0.1.60
 Summary: Small library for common tasks
 Author: Hoang Van Ha
 Author-email: hoangvanhauit@gmail.com
@@ -45,7 +45,11 @@ Requires-Dist: dataclass-wizard
 
 Helper package for coding and automation
 
-**Version 0.1.58**
+**Version 0.1.60**
+
++ add `util/video`: add `VideoUtils` class to handle common video-related tasks
+
+**Version 0.1.59**
 
 + add `util/perfcalc`: abstract class for performance calculation. This class need to be inherited and implemented with specific performance calculation logic.
 

{halib-0.1.58.dist-info → halib-0.1.60.dist-info}/RECORD

@@ -30,7 +30,7 @@ halib/online/projectmake.py,sha256=Zrs96WgXvO4nIrwxnCOletL4aTBge-EoF0r7hpKO1w8,4
 halib/research/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 halib/research/benchquery.py,sha256=FuKnbWQtCEoRRtJAfN-zaN-jPiO_EzsakmTOMiqi7GQ,4626
 halib/research/dataset.py,sha256=QU0Hr5QFb8_XlvnOMgC9QJGIpwXAZ9lDd0RdQi_QRec,6743
-halib/research/perfcalc.py,sha256=AhcYqYO6aDIFQZ35pdVIfajwSAStIQSQ-ChiyhPML34,14392
+halib/research/perfcalc.py,sha256=qKgoDbXQtyOpRgOjSMUus7r4mgyiH8Gu9o59sd48SAE,15147
 halib/research/perftb.py,sha256=vazU-dYBJhfc4sK4zFgxOvzeXGi-5TyPHCt20ItiWhY,30463
 halib/research/plot.py,sha256=-pDUk4z3C_GnyJ5zWmf-mGMdT4gaipVJWzIgcpIPiRk,9448
 halib/research/torchloader.py,sha256=yqUjcSiME6H5W210363HyRUrOi3ISpUFAFkTr1w4DCw,6503
@@ -42,11 +42,13 @@ halib/system/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 halib/system/cmd.py,sha256=b2x7JPcNnFjLGheIESVYvqAb-w2UwBM1PAwYxMZ5YjA,228
 halib/system/filesys.py,sha256=ERpnELLDKJoTIIKf-AajgkY62nID4qmqmX5TkE95APU,2931
 halib/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-halib/utils/dataclass_util.py,sha256=aD5Ik9BRJzIEyfdlOCHmOddA7TM_TIAfapZfU0vMigE,1414
+halib/utils/dataclass_util.py,sha256=rj2IMLlUzbm2OlF5_B2dRTk9njZOaF7tTjYkOsq8uLY,1416
+halib/utils/dict_op.py,sha256=wYE6Iw-_CnCWdMg9tpJ2Y2-e2ESkW9FxmdBkZkbUh80,299
 halib/utils/listop.py,sha256=Vpa8_2fI0wySpB2-8sfTBkyi_A4FhoFVVvFiuvW8N64,339
 halib/utils/tele_noti.py,sha256=-4WXZelCA4W9BroapkRyIdUu9cUVrcJJhegnMs_WpGU,5928
-halib-0.1.58.dist-info/LICENSE.txt,sha256=qZssdna4aETiR8znYsShUjidu-U4jUT9Q-EWNlZ9yBQ,1100
-halib-0.1.58.dist-info/METADATA,sha256=8g1pRBqG07Nf_wyrglomhbe-qvzbzcMhX1TfmMUG3AQ,4856
-halib-0.1.58.dist-info/WHEEL,sha256=G16H4A3IeoQmnOrYV4ueZGKSjhipXx8zc8nu9FGlvMA,92
-halib-0.1.58.dist-info/top_level.txt,sha256=7AD6PLaQTreE0Fn44mdZsoHBe_Zdd7GUmjsWPyQ7I-k,6
-halib-0.1.58.dist-info/RECORD,,
+halib/utils/video.py,sha256=mJQFHFbijmu3lo0NZk4Ed64Tfa1u5KxNJpd_TuckpPU,2228
+halib-0.1.60.dist-info/LICENSE.txt,sha256=qZssdna4aETiR8znYsShUjidu-U4jUT9Q-EWNlZ9yBQ,1100
+halib-0.1.60.dist-info/METADATA,sha256=QMs6mroREHr6qCcrUJwOCwL86Rbu0_bQvf8sLiRsYFk,4957
+halib-0.1.60.dist-info/WHEEL,sha256=G16H4A3IeoQmnOrYV4ueZGKSjhipXx8zc8nu9FGlvMA,92
+halib-0.1.60.dist-info/top_level.txt,sha256=7AD6PLaQTreE0Fn44mdZsoHBe_Zdd7GUmjsWPyQ7I-k,6
+halib-0.1.60.dist-info/RECORD,,