Settings: Add Settings - Measures - Effect Size - Mutual Information …

…/ Pointwise Mutual Information / Pointwise Mutual Information (Cubic) / Pointwise Mutual Information (Squared)

CHANGELOG.md

@@ -21,6 +21,7 @@
 ## [3.6.0](https://github.com/BLKSerene/Wordless/releases/tag/3.6.0) - ??/??/2024
 ### 🎉 New Features
 - Measures: Add effect size - conditional probability / ΔP / squared association ratio
+- Settings: Add Settings - Measures - Effect Size - Mutual Information / Pointwise Mutual Information / Pointwise Mutual Information (Cubic) / Pointwise Mutual Information (Squared)
 - Utils: Add Stanza's Sindhi dependency parser
 
 ### 📌 Bugfixes

wordless/wl_measures/wl_measure_utils.py

@@ -134,3 +134,9 @@ def numpy_log2(a, default = 0):
         return numpy.log2(a, out = numpy.full_like(a, default, dtype = float), where = a > 0)
     else:
         return numpy.log2(a, out = numpy.zeros_like(a, dtype = float), where = a > 0)
+
+def numpy_log10(a, default = 0):
+    if default:
+        return numpy.log10(a, out = numpy.full_like(a, default, dtype = float), where = a > 0)
+    else:
+        return numpy.log10(a, out = numpy.zeros_like(a, dtype = float), where = a > 0)

wordless/wl_measures/wl_measures_effect_size.py

@@ -18,6 +18,8 @@
 
 # pylint: disable=unused-argument
 
+import math
+
 import numpy
 
 from wordless.wl_measures import wl_measures_statistical_significance, wl_measure_utils
@@ -133,10 +135,18 @@ def mi(main, o11s, o12s, o21s, o22s):
     oxxs = o11s + o12s + o21s + o22s
     e11s, e12s, e21s, e22s = wl_measures_statistical_significance.get_freqs_expected(o11s, o12s, o21s, o22s)
 
-    mi_11 = wl_measure_utils.numpy_divide(o11s, oxxs) * wl_measure_utils.numpy_log2(wl_measure_utils.numpy_divide(o11s, e11s))
-    mi_12 = wl_measure_utils.numpy_divide(o12s, oxxs) * wl_measure_utils.numpy_log2(wl_measure_utils.numpy_divide(o12s, e12s))
-    mi_21 = wl_measure_utils.numpy_divide(o21s, oxxs) * wl_measure_utils.numpy_log2(wl_measure_utils.numpy_divide(o21s, e21s))
-    mi_22 = wl_measure_utils.numpy_divide(o22s, oxxs) * wl_measure_utils.numpy_log2(wl_measure_utils.numpy_divide(o22s, e22s))
+    match main.settings_custom['measures']['effect_size']['mi']['base_log']:
+        case 2:
+            numpy_log = wl_measure_utils.numpy_log2
+        case 10:
+            numpy_log = wl_measure_utils.numpy_log10
+        case math.e:
+            numpy_log = wl_measure_utils.numpy_log
+
+    mi_11 = wl_measure_utils.numpy_divide(o11s, oxxs) * numpy_log(wl_measure_utils.numpy_divide(o11s, e11s))
+    mi_12 = wl_measure_utils.numpy_divide(o12s, oxxs) * numpy_log(wl_measure_utils.numpy_divide(o12s, e12s))
+    mi_21 = wl_measure_utils.numpy_divide(o21s, oxxs) * numpy_log(wl_measure_utils.numpy_divide(o21s, e21s))
+    mi_22 = wl_measure_utils.numpy_divide(o22s, oxxs) * numpy_log(wl_measure_utils.numpy_divide(o22s, e22s))
 
     return mi_11 + mi_12 + mi_21 + mi_22
 
@@ -179,21 +189,45 @@ def pct_diff(main, o11s, o12s, o21s, o22s):
 def pmi(main, o11s, o12s, o21s, o22s):
     e11s, _, _, _ = wl_measures_statistical_significance.get_freqs_expected(o11s, o12s, o21s, o22s)
 
-    return wl_measure_utils.numpy_log2(wl_measure_utils.numpy_divide(o11s, e11s))
+    match main.settings_custom['measures']['effect_size']['pmi']['base_log']:
+        case 2:
+            numpy_log = wl_measure_utils.numpy_log2
+        case 10:
+            numpy_log = wl_measure_utils.numpy_log10
+        case math.e:
+            numpy_log = wl_measure_utils.numpy_log
+
+    return numpy_log(wl_measure_utils.numpy_divide(o11s, e11s))
 
 # Pointwise mutual information (cubic)
 # Reference: Daille, B. (1994). Approche mixte pour l'extraction automatique de terminologie: statistiques lexicales et filtres linguistiques [Doctoral thesis, Paris Diderot University]. Béatrice Daille. http://www.bdaille.com/index.php?option=com_docman&task=doc_download&gid=8&Itemid= | p. 139
 def im3(main, o11s, o12s, o21s, o22s):
     e11s, _, _, _ = wl_measures_statistical_significance.get_freqs_expected(o11s, o12s, o21s, o22s)
 
-    return wl_measure_utils.numpy_log2(wl_measure_utils.numpy_divide(o11s ** 3, e11s))
+    match main.settings_custom['measures']['effect_size']['im3']['base_log']:
+        case 2:
+            numpy_log = wl_measure_utils.numpy_log2
+        case 10:
+            numpy_log = wl_measure_utils.numpy_log10
+        case math.e:
+            numpy_log = wl_measure_utils.numpy_log
+
+    return numpy_log(wl_measure_utils.numpy_divide(o11s ** 3, e11s))
 
 # Pointwise mutual information (squared)
 # Reference: Daille, B. (1995). Combined approach for terminology extraction: Lexical statistics and linguistic filtering. UCREL technical papers (Vol. 5). Lancaster University. | p. 21
 def im2(main, o11s, o12s, o21s, o22s):
     e11s, _, _, _ = wl_measures_statistical_significance.get_freqs_expected(o11s, o12s, o21s, o22s)
 
-    return wl_measure_utils.numpy_log2(wl_measure_utils.numpy_divide(o11s ** 2, e11s))
+    match main.settings_custom['measures']['effect_size']['im2']['base_log']:
+        case 2:
+            numpy_log = wl_measure_utils.numpy_log2
+        case 10:
+            numpy_log = wl_measure_utils.numpy_log10
+        case math.e:
+            numpy_log = wl_measure_utils.numpy_log
+
+    return numpy_log(wl_measure_utils.numpy_divide(o11s ** 2, e11s))
 
 # Poisson collocation measure
 # Reference: Quasthoff, U., & Wolff, C. (2002). The poisson collocation measure and its applications. Proceedings of 2nd International Workshop on Computational Approaches to Collocations. IEEE.

wordless/wl_settings/wl_settings_default.py

@@ -2433,6 +2433,22 @@ def init_settings_default(main):
             'effect_size': {
                 'kilgarriffs_ratio': {
                     'smoothing_param': 1.00
+                },
+
+                'mi': {
+                    'base_log': 2
+                },
+
+                'pmi': {
+                    'base_log': 2
+                },
+
+                'im3': {
+                    'base_log': 2
+                },
+
+                'im2': {
+                    'base_log': 2
                 }
             }
         },

wordless/wl_settings/wl_settings_measures.py

@@ -17,12 +17,16 @@
 # ----------------------------------------------------------------------
 
 import copy
+import math
 
+from PyQt5.QtCore import QCoreApplication
 from PyQt5.QtWidgets import QCheckBox, QGroupBox, QLabel
 
 from wordless.wl_settings import wl_settings
 from wordless.wl_widgets import wl_boxes, wl_layouts, wl_widgets
 
+_tr = QCoreApplication.translate
+
 # Measures - Readability
 class Wl_Settings_Measures_Readability(wl_settings.Wl_Settings_Node):
     def __init__(self, main):
@@ -950,6 +954,34 @@ def apply_settings(self):
         return True
 
 # Measures - Effect Size
+class Wl_Combo_Box_Base_Log(wl_boxes.Wl_Combo_Box):
+    # pylint: disable=inconsistent-return-statements
+
+    def __init__(self, parent):
+        super().__init__(parent)
+
+        self.addItems([
+            '2',
+            '10',
+            _tr('wl_settings_measures', 'Base of natural logarithm')
+        ])
+
+    def get_base_log(self):
+        if self.currentText() == '2':
+            return 2
+        elif self.currentText() == '10':
+            return 10
+        elif self.currentText() == _tr('wl_settings_measures', 'Base of natural logarithm'):
+            return math.e
+
+    def set_base_log(self, base_log):
+        if base_log == 2:
+            self.setCurrentText('2')
+        elif base_log == 10:
+            self.setCurrentText('10')
+        elif base_log == math.e:
+            self.setCurrentText(_tr('wl_settings_measures', 'Base of natural logarithm'))
+
 class Wl_Settings_Measures_Effect_Size(wl_settings.Wl_Settings_Node):
     def __init__(self, main):
         super().__init__(main)
@@ -971,11 +1003,63 @@ def __init__(self, main):
 
         self.group_box_kilgarriffs_ratio.layout().setColumnStretch(2, 1)
 
+        # Mutual Information
+        self.group_box_mi = QGroupBox(self.tr('Mutual Information'), self)
+
+        self.label_mi_base_log = QLabel(self.tr('Base of logarithm:'), self)
+        self.combo_box_mi_base_log = Wl_Combo_Box_Base_Log(self)
+
+        self.group_box_mi.setLayout(wl_layouts.Wl_Layout())
+        self.group_box_mi.layout().addWidget(self.label_mi_base_log, 0, 0)
+        self.group_box_mi.layout().addWidget(self.combo_box_mi_base_log, 0, 1)
+
+        self.group_box_mi.layout().setColumnStretch(2, 1)
+
+        # Pointwise Mutual Information
+        self.group_box_pmi = QGroupBox(self.tr('Pointwise Mutual Information'), self)
+
+        self.label_pmi_base_log = QLabel(self.tr('Base of logarithm:'), self)
+        self.combo_box_pmi_base_log = Wl_Combo_Box_Base_Log(self)
+
+        self.group_box_pmi.setLayout(wl_layouts.Wl_Layout())
+        self.group_box_pmi.layout().addWidget(self.label_pmi_base_log, 0, 0)
+        self.group_box_pmi.layout().addWidget(self.combo_box_pmi_base_log, 0, 1)
+
+        self.group_box_pmi.layout().setColumnStretch(2, 1)
+
+        # Pointwise Mutual Information (Cubic)
+        self.group_box_im3 = QGroupBox(self.tr('Pointwise Mutual Information (Cubic)'), self)
+
+        self.label_im3_base_log = QLabel(self.tr('Base of logarithm:'), self)
+        self.combo_box_im3_base_log = Wl_Combo_Box_Base_Log(self)
+
+        self.group_box_im3.setLayout(wl_layouts.Wl_Layout())
+        self.group_box_im3.layout().addWidget(self.label_im3_base_log, 0, 0)
+        self.group_box_im3.layout().addWidget(self.combo_box_im3_base_log, 0, 1)
+
+        self.group_box_im3.layout().setColumnStretch(2, 1)
+
+        # Pointwise Mutual Information (Squared)
+        self.group_box_im2 = QGroupBox(self.tr('Pointwise Mutual Information (Squared)'), self)
+
+        self.label_im2_base_log = QLabel(self.tr('Base of logarithm:'), self)
+        self.combo_box_im2_base_log = Wl_Combo_Box_Base_Log(self)
+
+        self.group_box_im2.setLayout(wl_layouts.Wl_Layout())
+        self.group_box_im2.layout().addWidget(self.label_im2_base_log, 0, 0)
+        self.group_box_im2.layout().addWidget(self.combo_box_im2_base_log, 0, 1)
+
+        self.group_box_im2.layout().setColumnStretch(2, 1)
+
         self.setLayout(wl_layouts.Wl_Layout())
         self.layout().addWidget(self.group_box_kilgarriffs_ratio, 0, 0)
+        self.layout().addWidget(self.group_box_mi, 1, 0)
+        self.layout().addWidget(self.group_box_pmi, 2, 0)
+        self.layout().addWidget(self.group_box_im3, 3, 0)
+        self.layout().addWidget(self.group_box_im2, 4, 0)
 
         self.layout().setContentsMargins(6, 4, 6, 4)
-        self.layout().setRowStretch(1, 1)
+        self.layout().setRowStretch(5, 1)
 
     def load_settings(self, defaults = False):
         if defaults:
@@ -986,8 +1070,32 @@ def load_settings(self, defaults = False):
         # Kilgarriff's Ratio
         self.spin_box_kilgarriffs_ratio_smoothing_param.setValue(settings['kilgarriffs_ratio']['smoothing_param'])
 
+        # Mutual Information
+        self.combo_box_mi_base_log.set_base_log(settings['mi']['base_log'])
+
+        # Pointwise Mutual Information
+        self.combo_box_pmi_base_log.set_base_log(settings['pmi']['base_log'])
+
+        # Pointwise Mutual Information (Cubic)
+        self.combo_box_im3_base_log.set_base_log(settings['im3']['base_log'])
+
+        # Pointwise Mutual Information (Squared)
+        self.combo_box_im2_base_log.set_base_log(settings['im2']['base_log'])
+
     def apply_settings(self):
         # Kilgarriff's Ratio
         self.settings_custom['kilgarriffs_ratio']['smoothing_param'] = self.spin_box_kilgarriffs_ratio_smoothing_param.value()
 
+        # Mutual Information
+        self.settings_custom['mi']['base_log'] = self.combo_box_mi_base_log.get_base_log()
+
+        # Pointwise Mutual Information
+        self.settings_custom['pmi']['base_log'] = self.combo_box_pmi_base_log.get_base_log()
+
+        # Pointwise Mutual Information (Cubic)
+        self.settings_custom['im3']['base_log'] = self.combo_box_im3_base_log.get_base_log()
+
+        # Pointwise Mutual Information (Squared)
+        self.settings_custom['im2']['base_log'] = self.combo_box_im2_base_log.get_base_log()
+
         return True