halib 0.1.89__tar.gz → 0.1.91__tar.gz

{halib-0.1.89 → halib-0.1.91}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: halib
-Version: 0.1.89
+Version: 0.1.91
 Summary: Small library for common tasks
 Author: Hoang Van Ha
 Author-email: hoangvanhauit@gmail.com
@@ -52,7 +52,10 @@ Dynamic: summary
 
 Helper package for coding and automation
 
-**Version 0.1.89**
+**Version 0.1.91**
++ `research/param_gen`: add `ParamGen` class to generate parameter list from yaml file for hyperparameter search (grid search, random search, etc.)
+
+**Version 0.1.90**
 
 + `research/profiler`: add `zProfiler` class to measure execution time of contexts and steps, with support for dynamic color scales in plots.
 

{halib-0.1.89 → halib-0.1.91}/README.md

@@ -1,6 +1,9 @@
 Helper package for coding and automation
 
-**Version 0.1.89**
+**Version 0.1.91**
++ `research/param_gen`: add `ParamGen` class to generate parameter list from yaml file for hyperparameter search (grid search, random search, etc.)
+
+**Version 0.1.90**
 
 + `research/profiler`: add `zProfiler` class to measure execution time of contexts and steps, with support for dynamic color scales in plots.
 

halib-0.1.91/halib/research/params_gen.py

@@ -0,0 +1,108 @@
+from typing import Dict, Any, List
+import numpy as np
+from ..common import *
+from ..filetype import yamlfile
+import yaml
+import os
+
+class ParamGen:
+
+    @staticmethod
+    def build_from_file(params_file):
+        builder = ParamGen(params_file)
+        return builder.params
+
+    def __init__(self, params_file=None):
+        self.params = {}
+        assert os.path.isfile(params_file), f"params_file not found: {params_file}"
+        self.params = self._build(params_file)
+
+    def _expand_param(self, param_name: str, config: Dict[str, Any]) -> List[Any]:
+        """
+        Validates and expands the values for a single parameter configuration.
+
+        Args:
+            param_name: The name of the parameter being processed.
+            config: The configuration dictionary for this parameter.
+
+        Returns:
+            A list of the expanded values for the parameter.
+
+        Raises:
+            TypeError: If the configuration or its values have an incorrect type.
+            ValueError: If the configuration is missing keys or has an invalid structure.
+        """
+        # 1. Validate the configuration structure
+        if not isinstance(config, dict):
+            raise TypeError(f"Config for '{param_name}' must be a dictionary.")
+
+        if "type" not in config or "values" not in config:
+            raise ValueError(
+                f"Config for '{param_name}' must contain 'type' and 'values' keys."
+            )
+
+        gen_type = config["type"]
+        values = config["values"]
+
+        # 2. Handle the generation based on type
+        if gen_type == "list":
+            # Ensure values are returned as a list, even if a single item was provided
+            return values if isinstance(values, list) else [values]
+
+        elif gen_type == "range":
+            if not isinstance(values, list) or len(values) != 3:
+                raise ValueError(
+                    f"For 'range' type on '{param_name}', 'values' must be a list of 3 numbers "
+                    f"[start, end, step], but got: {values}"
+                )
+
+            start, end, step = values
+            if all(isinstance(v, int) for v in values):
+                return list(range(start, end, step))
+            elif all(isinstance(v, (int, float)) for v in values):
+                # Use numpy for floating point ranges
+                temp_list = list(np.arange(start, end, step))
+                # convert to float (not np.float)
+                return [float(v) for v in temp_list]
+            else:
+                raise TypeError(
+                    f"All 'values' for 'range' on '{param_name}' must be numbers."
+                )
+
+        else:
+            raise ValueError(
+                f"Invalid 'type' for '{param_name}': '{gen_type}'. Must be 'list' or 'range'."
+            )
+
+    def _build(self, params_file):
+        """
+        Builds a full optimization configuration by expanding parameter values based on their type.
+
+        This function processes a dictionary where each key is a parameter name and each value
+        is a config dict specifying the 'type' ('list' or 'range') and 'values' for generation.
+
+        Args:
+            opt_cfg: The input configuration dictionary.
+                    Example:
+                    {
+                        "learning_rate": {"type": "range", "values": [0.01, 0.1, 0.01]},
+                        "optimizer": {"type": "list", "values": ["adam", "sgd"]},
+                        "epochs": {"type": "list", "values": 100}
+                    }
+
+        Returns:
+            A dictionary with parameter names mapped to their fully expanded list of values.
+        """
+        cfg_raw_dict = yamlfile.load_yaml(params_file, to_dict=True)
+        if not isinstance(cfg_raw_dict, dict):
+            raise TypeError("The entire opt_cfg must be a dictionary.")
+
+        # Use a dictionary comprehension for a clean and efficient build
+        return {
+            param_name: self._expand_param(param_name, config)
+            for param_name, config in cfg_raw_dict.items()
+        }
+
+    def save(self, outfile):
+        with open(outfile, "w") as f:
+            yaml.dump(self.params, f)

{halib-0.1.89 → halib-0.1.91}/halib/research/profiler.py

@@ -97,12 +97,11 @@ class zProfiler:
         assert (
             len(ctx_step_dict.keys()) > 0
         ), "step_dict must have only one key (step_name) for detail."
-
+        normed_ctx_step_dict = {}
         for step_name, time_list in ctx_step_dict.items():
-            normed_ctx_step_dict = {}
             if not isinstance(ctx_step_dict[step_name], list):
                 raise ValueError(f"Step data for {step_name} must be a list")
-            step_name = list(ctx_step_dict.keys())[0]
+            # step_name = list(ctx_step_dict.keys())[0] # ! debug
             normed_time_ls = []
             for idx, time_data in enumerate(time_list):
                 elapsed_time = -1
@@ -111,7 +110,7 @@ class zProfiler:
                     elapsed_time = end - start
                 normed_time_ls.append((idx, elapsed_time))  # including step
             normed_ctx_step_dict[step_name] = normed_time_ls
-            return normed_ctx_step_dict
+        return normed_ctx_step_dict
 
     def get_report_dict(self, with_detail=False):
         report_dict = {}

{halib-0.1.89 → halib-0.1.91}/halib.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: halib
-Version: 0.1.89
+Version: 0.1.91
 Summary: Small library for common tasks
 Author: Hoang Van Ha
 Author-email: hoangvanhauit@gmail.com
@@ -52,7 +52,10 @@ Dynamic: summary
 
 Helper package for coding and automation
 
-**Version 0.1.89**
+**Version 0.1.91**
++ `research/param_gen`: add `ParamGen` class to generate parameter list from yaml file for hyperparameter search (grid search, random search, etc.)
+
+**Version 0.1.90**
 
 + `research/profiler`: add `zProfiler` class to measure execution time of contexts and steps, with support for dynamic color scales in plots.
 

{halib-0.1.89 → halib-0.1.91}/halib.egg-info/SOURCES.txt

@@ -31,6 +31,7 @@ halib/research/base_exp.py
 halib/research/dataset.py
 halib/research/metrics.py
 halib/research/mics.py
+halib/research/params_gen.py
 halib/research/perfcalc.py
 halib/research/perftb.py
 halib/research/plot.py

{halib-0.1.89 → halib-0.1.91}/setup.py

@@ -8,7 +8,7 @@ with open("requirements.txt") as f:
 
 setuptools.setup(
     name="halib",
-    version="0.1.89",
+    version="0.1.91",
     author="Hoang Van Ha",
     author_email="hoangvanhauit@gmail.com",
     description="Small library for common tasks",