halib 0.1.67__tar.gz → 0.1.73__tar.gz

{halib-0.1.67 → halib-0.1.73}/PKG-INFO

@@ -1,57 +1,24 @@
-Metadata-Version: 2.4
+Metadata-Version: 2.1
 Name: halib
-Version: 0.1.67
+Version: 0.1.73
 Summary: Small library for common tasks
 Author: Hoang Van Ha
 Author-email: hoangvanhauit@gmail.com
+License: UNKNOWN
+Platform: UNKNOWN
 Classifier: Programming Language :: Python :: 3
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Operating System :: OS Independent
 Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 License-File: LICENSE.txt
-Requires-Dist: arrow
-Requires-Dist: click
-Requires-Dist: enlighten
-Requires-Dist: kaleido==0.1.*
-Requires-Dist: loguru
-Requires-Dist: more-itertools
-Requires-Dist: moviepy
-Requires-Dist: networkx
-Requires-Dist: numpy
-Requires-Dist: omegaconf
-Requires-Dist: opencv-python
-Requires-Dist: pandas
-Requires-Dist: Pillow
-Requires-Dist: Pyarrow
-Requires-Dist: pycurl
-Requires-Dist: python-telegram-bot
-Requires-Dist: requests
-Requires-Dist: rich
-Requires-Dist: scikit-learn
-Requires-Dist: matplotlib
-Requires-Dist: seaborn
-Requires-Dist: plotly
-Requires-Dist: pygwalker
-Requires-Dist: tabulate
-Requires-Dist: itables
-Requires-Dist: timebudget
-Requires-Dist: tqdm
-Requires-Dist: tube_dl
-Requires-Dist: wandb
-Requires-Dist: dataclass-wizard
-Dynamic: author
-Dynamic: author-email
-Dynamic: classifier
-Dynamic: description
-Dynamic: description-content-type
-Dynamic: license-file
-Dynamic: requires-dist
-Dynamic: requires-python
-Dynamic: summary
 
 Helper package for coding and automation
 
+**Version 0.1.73**
+
++ `research/base_exp`: add base experiment class to handle common experiment tasks, including performance calculation and saving results.
+
 **Version 0.1.67**
 
 + now use `uv` for venv management
@@ -188,3 +155,5 @@ New Features
 New Features
 
 + add support to upload local to google drive.
+
+

{halib-0.1.67 → halib-0.1.73}/README.md

@@ -1,5 +1,9 @@
 Helper package for coding and automation
 
+**Version 0.1.73**
+
++ `research/base_exp`: add base experiment class to handle common experiment tasks, including performance calculation and saving results.
+
 **Version 0.1.67**
 
 + now use `uv` for venv management

halib-0.1.73/halib/research/base_config.py

@@ -0,0 +1,100 @@
+import os
+from rich.pretty import pprint
+from abc import ABC, abstractmethod
+from dataclass_wizard import YAMLWizard
+
+
+class NamedConfig(ABC):
+    """
+    Base class for named configurations.
+    All configurations should have a name.
+    """
+
+    @abstractmethod
+    def get_name(self):
+        """
+        Get the name of the configuration.
+        This method should be implemented in subclasses.
+        """
+        pass
+
+
+class ExpBaseConfig(ABC, YAMLWizard):
+    """
+    Base class for configuration objects.
+    What a cfg class must have:
+    1 - a dataset cfg
+    2 - a metric cfg
+    3 - a method cfg
+    """
+
+    # Save to yaml fil
+    def save_to_outdir(
+        self, filename: str = "config.yaml", outdir=None, override: bool = False
+    ) -> None:
+        """
+        Save the configuration to the output directory.
+        """
+        if outdir is not None:
+            output_dir = outdir
+        else:
+            output_dir = self.get_outdir()
+        os.makedirs(output_dir, exist_ok=True)
+        assert (output_dir is not None) and (
+            os.path.isdir(output_dir)
+        ), f"Output directory '{output_dir}' does not exist or is not a directory."
+        file_path = os.path.join(output_dir, filename)
+        if os.path.exists(file_path) and not override:
+            pprint(
+                f"File '{file_path}' already exists. Use 'override=True' to overwrite."
+            )
+        else:
+            # method of YAMLWizard to_yaml_file
+            self.to_yaml_file(file_path)
+
+    @classmethod
+    @abstractmethod
+    # load from a custom YAML file
+    def from_custom_yaml_file(cls, yaml_file: str):
+        """Load a configuration from a custom YAML file."""
+        pass
+
+    @abstractmethod
+    def get_cfg_name(self):
+        """
+        Get the name of the configuration.
+        This method should be implemented in subclasses.
+        """
+        pass
+
+    @abstractmethod
+    def get_outdir(self):
+        """
+        Get the output directory for the configuration.
+        This method should be implemented in subclasses.
+        """
+        return None
+
+    @abstractmethod
+    def get_general_cfg(self):
+        """
+        Get the general configuration like output directory, log settings, SEED, etc.
+        This method should be implemented in subclasses.
+        """
+        pass
+
+    @abstractmethod
+    def get_dataset_cfg(self) -> NamedConfig:
+        """
+        Get the dataset configuration.
+        This method should be implemented in subclasses.
+        """
+        pass
+
+    @abstractmethod
+    def get_metric_cfg(self) -> NamedConfig:
+        """
+        Get the metric configuration.
+        This method should be implemented in subclasses.
+        """
+        pass

halib-0.1.73/halib/research/base_exp.py

@@ -0,0 +1,99 @@
+from abc import ABC, abstractmethod
+
+from ..research.base_config import ExpBaseConfig
+from ..research.perfcalc import PerfCalc
+from ..research.metrics import MetricsBackend
+
+# ! SEE https://github.com/hahv/base_exp for sample usage
+class BaseExperiment(PerfCalc, ABC):
+    """
+    Base class for experiments.
+    Orchestrates the experiment pipeline using a pluggable metrics backend.
+    """
+
+    def __init__(self, config: ExpBaseConfig):
+        self.config = config
+        self.metric_backend = None
+
+    # -----------------------
+    # PerfCalc Required Methods
+    # -----------------------
+    def get_dataset_name(self):
+        return self.config.get_dataset_cfg().get_name()
+
+    def get_experiment_name(self):
+        return self.config.get_cfg_name()
+
+    def get_metric_backend(self):
+        if not self.metric_backend:
+            self.metric_backend = self.prepare_metrics(self.config.get_metric_cfg())
+        return self.metric_backend
+
+    # -----------------------
+    # Abstract Experiment Steps
+    # -----------------------
+    @abstractmethod
+    def init_general(self, general_cfg):
+        """Setup general settings like SEED, logging, env variables."""
+        pass
+
+    @abstractmethod
+    def prepare_dataset(self, dataset_cfg):
+        """Load/prepare dataset."""
+        pass
+
+    @abstractmethod
+    def prepare_metrics(self, metric_cfg) -> MetricsBackend:
+        """
+        Prepare the metrics for the experiment.
+        This method should be implemented in subclasses.
+        """
+        pass
+
+    @abstractmethod
+    def exec_exp(self, *args, **kwargs):
+        """Run experiment process, e.g.: training/evaluation loop.
+        Return: raw_metrics_data, and extra_data as input for calc_and_save_exp_perfs
+        """
+        pass
+
+    def eval_exp(self):
+        """Optional: re-run evaluation from saved results."""
+        pass
+
+    # -----------------------
+    # Main Experiment Runner
+    # -----------------------
+    def run_exp(self, do_calc_metrics=True, *args, **kwargs):
+        """
+        Run the whole experiment pipeline.
+        Params:
+            + 'outfile' to save csv file results,
+            + 'outdir' to set output directory for experiment results.
+            + 'return_df' to return a DataFrame of results instead of a dictionary.
+
+        Full pipeline:
+            1. Init
+            2. Dataset
+            3. Metrics Preparation
+            4. Save Config
+            5. Execute
+            6. Calculate & Save Metrics
+        """
+        self.init_general(self.config.get_general_cfg())
+        self.prepare_dataset(self.config.get_dataset_cfg())
+
+        # Save config before running
+        self.config.save_to_outdir()
+
+        # Execute experiment
+        results = self.exec_exp(*args, **kwargs)
+        if do_calc_metrics:
+            metrics_data, extra_data = results
+            # Calculate & Save metrics
+            perf_results = self.calc_and_save_exp_perfs(
+                raw_metrics_data=metrics_data, extra_data=extra_data, *args, **kwargs
+            )
+            return perf_results
+        else:
+            return results

{halib-0.1.67 → halib-0.1.73}/halib.egg-info/PKG-INFO

@@ -1,57 +1,24 @@
-Metadata-Version: 2.4
+Metadata-Version: 2.1
 Name: halib
-Version: 0.1.67
+Version: 0.1.73
 Summary: Small library for common tasks
 Author: Hoang Van Ha
 Author-email: hoangvanhauit@gmail.com
+License: UNKNOWN
+Platform: UNKNOWN
 Classifier: Programming Language :: Python :: 3
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Operating System :: OS Independent
 Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 License-File: LICENSE.txt
-Requires-Dist: arrow
-Requires-Dist: click
-Requires-Dist: enlighten
-Requires-Dist: kaleido==0.1.*
-Requires-Dist: loguru
-Requires-Dist: more-itertools
-Requires-Dist: moviepy
-Requires-Dist: networkx
-Requires-Dist: numpy
-Requires-Dist: omegaconf
-Requires-Dist: opencv-python
-Requires-Dist: pandas
-Requires-Dist: Pillow
-Requires-Dist: Pyarrow
-Requires-Dist: pycurl
-Requires-Dist: python-telegram-bot
-Requires-Dist: requests
-Requires-Dist: rich
-Requires-Dist: scikit-learn
-Requires-Dist: matplotlib
-Requires-Dist: seaborn
-Requires-Dist: plotly
-Requires-Dist: pygwalker
-Requires-Dist: tabulate
-Requires-Dist: itables
-Requires-Dist: timebudget
-Requires-Dist: tqdm
-Requires-Dist: tube_dl
-Requires-Dist: wandb
-Requires-Dist: dataclass-wizard
-Dynamic: author
-Dynamic: author-email
-Dynamic: classifier
-Dynamic: description
-Dynamic: description-content-type
-Dynamic: license-file
-Dynamic: requires-dist
-Dynamic: requires-python
-Dynamic: summary
 
 Helper package for coding and automation
 
+**Version 0.1.73**
+
++ `research/base_exp`: add base experiment class to handle common experiment tasks, including performance calculation and saving results.
+
 **Version 0.1.67**
 
 + now use `uv` for venv management
@@ -188,3 +155,5 @@ New Features
 New Features
 
 + add support to upload local to google drive.
+
+

{halib-0.1.67 → halib-0.1.73}/halib.egg-info/SOURCES.txt

@@ -26,6 +26,8 @@ halib/online/gdrive_mkdir.py
 halib/online/gdrive_test.py
 halib/online/projectmake.py
 halib/research/__init__.py
+halib/research/base_config.py
+halib/research/base_exp.py
 halib/research/dataset.py
 halib/research/metrics.py
 halib/research/perfcalc.py

{halib-0.1.67 → halib-0.1.73}/setup.py

@@ -8,7 +8,7 @@ with open("requirements.txt") as f:
 
 setuptools.setup(
     name="halib",
-    version="0.1.67",
+    version="0.1.73",
     author="Hoang Van Ha",
     author_email="hoangvanhauit@gmail.com",
     description="Small library for common tasks",