Native MI estimators + minor fixes

README.md

@@ -80,7 +80,7 @@ Note that individual operations can only be called directly on individual time-s
 Time-series feature extraction is computationally intensive. 
 To speed up processing, pyhctsa allows you to distribute the workload across multiple CPU cores on your local machine using the `LocalDistributor`:
 ```Python
-from pyhctsa.distributed import LocalDistributor
+from pyhctsa.distribute import LocalDistributor
 from pyhctsa.calculator import FeatureCalculator
 
 # initialize the calculator
@@ -94,21 +94,6 @@ dist = LocalDistributor(n_workers=4)
 res = calc.extract(data, distributor=dist)
 ```
 
-## ℹ️ Note for Windows users
-Some features require Java (JDK) to be installed. If you encounter a `JVM not found` error:
-
-1. Ensure Java Development Kit (JDK) is installed on your system
-   - Download from [Oracle](https://www.oracle.com/java/technologies/downloads/) or use OpenJDK
-   - Minimum version required: JDK 11
-
-2. Before importing pyhctsa, set the `JAVA_HOME` environment variable using the location of the JDK installation on your system:
-```Python
-import os
-os.environ['JAVA_HOME'] = "C:\Program Files\Java\jdk-11" # replace with relevant path
-from pyhctsa.calculator import FeatureCalculator
-# rest of your code...
-```
-
 # 🔑 Licenses
 
 ## Internal licenses
@@ -119,7 +104,6 @@ While the majority of features in _pyhctsa_ rely on standard Python libraries, a
 
 The following external time-series analysis code packages are provided with the software (in the `toolboxes` directory), and are used by our main feature-extraction calculator to compute meaningful structural features from time series:
 
-- Joseph T. Lizier's [Java Information Dynamics Toolkit (JIDT)](https://github.com/jlizier/jidt) for studying  information-theoretic measures of computation in complex systems, version 1.3 (GPL license).
 - Time-series analysis code developed by [Michael Small](https://github.com/m-small) (unlicensed).
 - Max Little's [time-series analysis code](http://www.maxlittle.net/software/index.php) (GPL License).
 - [TISEAN package for nonlinear time-series analysis](http://www.mpipks-dresden.mpg.de/~tisean/Tisean_3.0.1/index.html), version 3.0.1 (GPL license).

docs/source/usage/getting_started.rst

@@ -53,7 +53,7 @@ cores on your local machine using the `LocalDistributor`:
 
 .. code-block:: python
 
-    from pyhctsa.distributed import LocalDistributor
+    from pyhctsa.distribute import LocalDistributor
     from pyhctsa.calculator import FeatureCalculator
 
     # initialize the calculator
@@ -66,16 +66,4 @@ cores on your local machine using the `LocalDistributor`:
     # pass the distributor to the .extract() method
     res = calc.extract(data, distributor=dist)
 
-ℹ️ Note for Windows Users 
--------------------------
-Some features require Java (JDK) to be installed. If you encounter a JVM not found error:
-    1. Ensure Java Development Kit (JDK) is installed on your system
-        - Download from Oracle or use OpenJDK (Minimum version required: JDK 11)
-    2. Before importing `pyhctsa`, set the `JAVA_HOME` environment variable using the location of the JDK installation on your system:
-
-    .. code-block:: python
-
-        import os
-        os.environ['JAVA_HOME'] = "C:\Program Files\Java\jdk-11" # replace with relevant path
-        from pyhctsa.calculator import FeatureCalculator
-        # rest of your code...
+

pyhctsa/calculator.py

@@ -6,6 +6,10 @@
 from typing import Union, Any, Callable
 import logging
 
+logger = logging.getLogger('pyhctsa')
+logger.setLevel(logging.CRITICAL) # only log critical warnings by default
+logger.addHandler(logging.NullHandler())
+
 import numpy as np
 import pandas as pd
 import yaml
@@ -70,7 +74,7 @@ def wrapper(*args, **kwargs):
         if isinstance(result, dict):
             missing = [k for k in keys if k not in result] # log all of the missing keys
             if missing:
-                logging.info(f'Warning: time-series features for func {func} not found {missing}')
+                logger.info(f'Warning: time-series features for func {func} not found {missing}')
             if keep:
                 return {k: result[k] for k in keys if k in result}
             else:
@@ -87,7 +91,7 @@ def _standardise_inputs(data) -> list[np.ndarray]:
         elif data.ndim == 2:
             if data.shape[0] > data.shape[1]:
                 # notify the user to check that the shapes make sense
-                logging.warning(f"Check that the shape of the 2D input is such "
+                logger.warning(f"Check that the shape of the 2D input is such "
                       f"that (n_series, n_samples). Got shape: {data.shape}")
             return [np.asarray(row, dtype=float) for row in data]
         else:
@@ -209,34 +213,36 @@ def _repr_html_(self):
         return _build_repr_html(self.feature_funcs, self._skipped_functions, self.config, self.config_path)
 
     def _check_deps(self, module_key, feature_name, config):
-        raw_deps = config.get("dependencies")
+        raw_deps = config.get("dependencies", None)
         if not raw_deps:
             return True
         deps_to_check = [raw_deps] if isinstance(raw_deps, str) else raw_deps
         missing = [dep for dep in deps_to_check if not _check_optional_deps(dep)]
         if missing:
             full_name = f"{module_key}.{feature_name}"
-            logging.info(f"Skipping function '{full_name}' - missing dependencies: {', '.join(missing)}")
+            logger.info(f"Skipping function '{full_name}' - missing dependencies: {', '.join(missing)}")
             self._skipped_functions.append((full_name, missing))
             return False
         return True
 
     def _build_feature_funcs(self):
         feature_funcs = {}
-        skipped_functions = []       
+        self._skipped_functions = []      
         for module_key in self.config.keys():
 
             try:
                 module = importlib.import_module(f"{self._operations_package}.{module_key}")
             except ImportError as e:
-                logging.warning(f"Failed to import module '{module_key}': {e}")
+                logger.warning(f"Failed to import module '{module_key}': {e}")
                 # Skip all functions in this module since we can't import it
                 for feature_name in self.config[module_key].keys():
-                    skipped_functions.append((f"{module_key}.{feature_name}", ["import_error"]))
+                    self._skipped_functions.append((f"{module_key}.{feature_name}", ["import_error"]))
                 continue
 
             # Process features from this module
             for feature_name, feature_config in self.config[module_key].items():
+                if not self._check_deps(module_key, feature_name, feature_config):
+                    continue
                 op_func = getattr(module, feature_name)
                 base_name = feature_config.get("base_name", feature_name)
                 ordered_args = feature_config.get("ordered_args", [])
@@ -270,11 +276,8 @@ def _build_feature_funcs(self):
 
                         feature_funcs[label] = final_func
 
-        # store information about skipped functions for later reference
-        self._skipped_functions = skipped_functions
-        if skipped_functions:
-            logging.info(f"Total functions skipped due to missing dependencies: {len(skipped_functions)}")
-
+        if self._skipped_functions:
+            logger.info(f"Total functions skipped due to missing dependencies: {len(self._skipped_functions)}")
         return feature_funcs
 
     def extract(self, data: Union[ArrayLike, list[ArrayLike]],

pyhctsa/configurations/hctsa.yaml

@@ -77,7 +77,6 @@ correlation:
   add_noise:
     base_name: add_noise
     depedencies:
-      - jpype1
     configs:
       - {tau: 1,   ami_method: 'quantiles', extra_param: 10, zscore: True}
       - {tau: 1,   ami_method: 'even',      extra_param: 10, zscore: True}
@@ -440,38 +439,35 @@ information:
   automutual_info_stats:
     base_name: automutual_info_stats
     dependencies:
-      - jpype1
     configs:
       - {max_tau: 40, est_method: 'gaussian', zscore: True}
       - {max_tau: 20, est_method: 'gaussian', zscore: True}
-      - {max_tau: 40, est_method: 'kraskov1', extra_param: '4', zscore: True}
-      - {max_tau: 20, est_method: 'kraskov1', extra_param: '4', zscore: True}
+      - {max_tau: 40, est_method: 'kraskov1', extra_param: 4, zscore: True}
+      - {max_tau: 20, est_method: 'kraskov1', extra_param: 4, zscore: True}
     legacy_name: IN_AutoMutualInfoStats
     ordered_args: ['max_tau', 'est_method', 'extra_param']
 
   first_min:
     base_name: first_min
     dependencies:
-      - jpype1
     configs:
       - {min_what: 'ac', zscore: True}
       - {min_what: 'mi-gaussian', zscore: True}
-      - {min_what: 'mi-kraskov2', extra_param: '4', zscore: True}
-      - {min_what: 'mi-hist', extra_param: '5', zscore: True}
-      - {min_what: 'mi-hist', extra_param: '10', zscore: True}
+      - {min_what: 'mi-kraskov2', extra_param: 4, zscore: True}
+      - {min_what: 'mi-hist', extra_param: 5, zscore: True}
+      - {min_what: 'mi-hist', extra_param: 10, zscore: True}
     legacy_name: CO_FirstMin
     ordered_args: ['min_what', 'extra_param']
 
   first_max:
     base_name: first_max
     depedencies:
-      - jpype1
     configs:
       - {max_what: 'ac', zscore: True}
       - {max_what: 'mi-gaussian', zscore: True}
-      - {max_what: 'mi-kraskov2', extra_param: '4', zscore: True}
-      - {max_what: 'mi-hist', extra_param: '5', zscore: True}
-      - {max_what: 'mi-hist', extra_param: '10', zscore: True}
+      - {max_what: 'mi-kraskov2', extra_param: 4, zscore: True}
+      - {max_what: 'mi-hist', extra_param: 5, zscore: True}
+      - {max_what: 'mi-hist', extra_param: 10, zscore: True}
     legacy_name: CO_FirstMin
     ordered_args: ['max_what', 'extra_param']
 

pyhctsa/configurations/module_configs/correlation.yaml

@@ -11,7 +11,6 @@ correlation:
   add_noise:
     base_name: add_noise
     depedencies:
-      - jpype1
     configs:
       - {tau: 1,   ami_method: 'quantiles', extra_param: 10, zscore: True}
       - {tau: 1,   ami_method: 'even',      extra_param: 10, zscore: True}

pyhctsa/configurations/module_configs/information.yaml

@@ -2,38 +2,35 @@ information:
   automutual_info_stats:
     base_name: automutual_info_stats
     dependencies:
-      - jpype1
     configs:
       - {max_tau: 40, est_method: 'gaussian', zscore: True}
       - {max_tau: 20, est_method: 'gaussian', zscore: True}
-      - {max_tau: 40, est_method: 'kraskov1', extra_param: '4', zscore: True}
-      - {max_tau: 20, est_method: 'kraskov1', extra_param: '4', zscore: True}
+      - {max_tau: 40, est_method: 'kraskov1', extra_param: 4, zscore: True}
+      - {max_tau: 20, est_method: 'kraskov1', extra_param: 4, zscore: True}
     legacy_name: IN_AutoMutualInfoStats
     ordered_args: ['max_tau', 'est_method', 'extra_param']
 
   first_min:
     base_name: first_min
     dependencies:
-      - jpype1
     configs:
       - {min_what: 'ac', zscore: True}
       - {min_what: 'mi-gaussian', zscore: True}
-      - {min_what: 'mi-kraskov2', extra_param: '4', zscore: True}
-      - {min_what: 'mi-hist', extra_param: '5', zscore: True}
-      - {min_what: 'mi-hist', extra_param: '10', zscore: True}
+      - {min_what: 'mi-kraskov2', extra_param: 4, zscore: True}
+      - {min_what: 'mi-hist', extra_param: 5, zscore: True}
+      - {min_what: 'mi-hist', extra_param: 10, zscore: True}
     legacy_name: CO_FirstMin
     ordered_args: ['min_what', 'extra_param']
 
   first_max:
     base_name: first_max
-    depedencies:
-      - jpype1
+    dependencies:
     configs:
       - {max_what: 'ac', zscore: True}
       - {max_what: 'mi-gaussian', zscore: True}
-      - {max_what: 'mi-kraskov2', extra_param: '4', zscore: True}
-      - {max_what: 'mi-hist', extra_param: '5', zscore: True}
-      - {max_what: 'mi-hist', extra_param: '10', zscore: True}
+      - {max_what: 'mi-kraskov2', extra_param: 4, zscore: True}
+      - {max_what: 'mi-hist', extra_param: 5, zscore: True}
+      - {max_what: 'mi-hist', extra_param: 10, zscore: True}
     legacy_name: CO_FirstMin
     ordered_args: ['max_what', 'extra_param']