fix: families

constants.py

@@ -1,124 +1,168 @@
-language_subfamilies = {
+low_level_subfamilies = {
+    # Germanic
     "Afrikaans": "West Germanic",
-    "Albanian": "Albanian",
-    "Arabic": "Semitic",
-    "Egyptian Arabic": "Semitic",
-    "Aragonese": "Romance",
-    "Armenian": "Armenian",
-    "Asturian": "Romance",
-    "Azerbaijani": "Oghuz",
-    "Bashkir": "Kypchak",
-    "Basque": "Language Isolate",
     "Bavarian": "Austro-Bavarian",
-    "Belarusian": "East Slavic",
-    "Bengali": "Eastern Indo-Aryan",
-    "Bishnupriya Manipuri": "Eastern Indo-Aryan",
-    "Bosnian": "South Slavic",
-    "Breton": "Brythonic",
-    "Bulgarian": "South Slavic",
-    "Burmese": "Burmish",
-    "Catalan": "Romance",
-    "Cebuano": "Central Philippine",
-    "Chechen": "Nakh-Daghestanian",
-    "Chinese (Simplified)": "Sinitic",
-    "Chinese (Traditional)": "Sinitic",
-    "Min Nan Chinese": "Sinitic",
-    "Chuvash": "Oghur",
-    "Croatian": "South Slavic",
-    "Czech": "West Slavic",
     "Danish": "North Germanic",
     "Dutch": "West Germanic",
     "English": "West Germanic",
-    "Estonian": "Finnic",
-    "Finnish": "Finnic",
-    "French": "Gallo-Romance",
-    "Galician": "Gallo-Romance",
-    "Georgian": "Kartvelian",
     "German": "West Germanic",
-    "Greek": "Hellenic",
-    "Gujarati": "Gujarati",
-    "Haitian": "French-based Creole",
-    "Hebrew": "Semitic",
-    "Hindi": "Central Indo-Aryan",
-    "Hungarian": "Ugric",
     "Icelandic": "North Germanic",
-    "Ido": "Constructed",
-    "Indonesian": "Malayic",
-    "Irish": "Goidelic",
-    "Italian": "Italo-Dalmatian",
-    "Japanese": "Japonic",
-    "Javanese": "Javanic",
-    "Kannada": "Southern Dravidian",
-    "Kazakh": "Kypchak",
-    "Kirghiz": "Kypchak",
-    "Korean": "Koreanic",
-    "Latin": "Italic",
-    "Latvian": "Baltic",
-    "Lithuanian": "Baltic",
-    "Lombard": "Gallo-Italic",
     "Low Saxon": "West Germanic",
     "Luxembourgish": "West Germanic",
-    "Macedonian": "South Slavic",
-    "Malagasy": "Malayic",
-    "Malay": "Malayic",
-    "Malayalam": "Southern Dravidian",
-    "Marathi": "Central Indo-Aryan",
-    "Minangkabau": "Malayic",
-    "Nepali": "Eastern Indo-Aryan",
-    "Newar": "Newaric",
     "Norwegian (Bokmal)": "North Germanic",
     "Norwegian (Nynorsk)": "North Germanic",
-    "Occitan": "Gallo-Romance",
-    "Persian (Farsi)": "Iranian",
-    "Piedmontese": "Gallo-Italic",
-    "Polish": "West Slavic",
-    "Portuguese": "Iberian Romance",
-    "Punjabi": "Punjabi",
-    "Romanian": "Eastern Romance",
-    "Russian": "East Slavic",
     "Scots": "West Germanic",
-    "Serbian": "South Slavic",
-    "Serbo-Croatian": "South Slavic",
-    "Sicilian": "Italo-Dalmatian",
-    "Slovak": "West Slavic",
-    "Slovenian": "South Slavic",
-    "South Azerbaijani": "Oghuz",
-    "Spanish": "Iberian Romance",
-    "Sundanese": "Sundic",
-    "Swahili": "Bantu",
     "Swedish": "North Germanic",
-    "Tagalog": "Central Philippine",
-    "Tajik": "Iranian",
-    "Tamil": "Southern Dravidian",
-    "Tatar": "Kypchak",
-    "Telugu": "Southern Dravidian",
-    "Turkish": "Oghuz",
+    "West Frisian": "West Germanic",
+
+    # Romance
+    "Aragonese": "Ibero-Romance",
+    "Asturian":  "Ibero-Romance",
+    "Catalan":   "Occitano-Romance",
+    "French":    "Gallo-Romance",
+    "Galician":  "Ibero-Romance",
+    "Italian":   "Italo-Dalmatian",
+    "Lombard":   "Gallo-Italic",
+    "Occitan":   "Occitano-Romance",
+    "Piedmontese":"Gallo-Italic",
+    "Portuguese":"Ibero-Romance",
+    "Romanian":  "Eastern Romance",
+    "Sicilian":  "Italo-Dalmatian",
+    "Spanish":   "Ibero-Romance",
+
+    # Slavic
+    "Belarusian":"East Slavic",
+    "Bosnian":   "South Slavic",
+    "Bulgarian": "South Slavic",
+    "Croatian":  "South Slavic",
+    "Czech":     "West Slavic",
+    "Macedonian":"South Slavic",
+    "Polish":    "West Slavic",
+    "Russian":   "East Slavic",
+    "Serbian":   "South Slavic",
+    "Serbo-Croatian":"South Slavic",
+    "Slovak":    "West Slavic",
+    "Slovenian": "South Slavic",
     "Ukrainian": "East Slavic",
-    "Urdu": "Central Indo-Aryan",
-    "Uzbek": "Karluk",
-    "Vietnamese": "Vietic",
-    "Volapük": "Constructed",
+
+    # Celtic
+    "Breton": "Brythonic",
+    "Welsh":  "Brythonic",
+    "Irish":  "Goidelic",
+
+    # Baltic
+    "Latvian": "Baltic",
+    "Lithuanian": "Baltic",
+
+    # Indo-Aryan (Indic)
+    "Bengali":  "Eastern Indo-Aryan",
+    "Bishnupriya Manipuri": "Eastern Indo-Aryan",
+    "Gujarati": "Western Indo-Aryan",
+    "Hindi":    "Central Indo-Aryan",
+    "Marathi":  "Southern Indo-Aryan",
+    "Nepali":   "Northern Indo-Aryan",
+    "Punjabi":  "North-western Indo-Aryan",
+    "Urdu":     "Central Indo-Aryan",
+    "Western Punjabi": "North-western Indo-Aryan",
+
+    # Iranian
+    "Persian (Farsi)": "South-western Iranian",
+    "Tajik":          "South-western Iranian",
+
+    # Turkic
+    "Azerbaijani": "Oghuz",
+    "South Azerbaijani": "Oghuz",
+    "Turkish":     "Oghuz",
+    "Bashkir":     "Kipchak",
+    "Kazakh":      "Kipchak",
+    "Kirghiz":     "Kipchak",
+    "Tatar":       "Kipchak",
+    "Crimean Tatar":"Kipchak",
+    "Chuvash":     "Oghur",
+    "Uzbek":       "Karluk",
+
+    # Uralic
+    "Estonian": "Finnic",
+    "Finnish":  "Finnic",
+    "Hungarian":"Ugric",
+
+    # Dravidian
+    "Kannada":  "Southern Dravidian",
+    "Malayalam":"Southern Dravidian",
+    "Tamil":    "Southern Dravidian",
+    "Telugu":   "South-Central Dravidian",
+
+    # Sinitic (Chinese)
+    "Chinese (Simplified)":   "Mandarin",
+    "Chinese (Traditional)":  "Mandarin",
+    "Min Nan Chinese":        "Southern Min",
+
+    # Other Sino-Tibetan
+    "Burmese": "Burmish",
+    "Newar":   "Newaric",
+
+    # Japonic / Koreanic
+    "Japanese": "Japonic",
+    "Korean":   "Koreanic",
+
+    # Caucasian & Kartvelian
+    "Chechen":  "Nakh",
+    "Georgian": "Kartvelian",
+
+    # Austronesian
+    "Cebuano":     "Central Philippine",
+    "Tagalog":     "Central Philippine",
     "Waray-Waray": "Central Philippine",
-    "Welsh": "Brythonic",
-    "West Frisian": "West Germanic",
-    "Western Punjabi": "Punjabi",
-    "Yoruba": "Yoruboid",
-    "Esperanto": "Constructed",
-    "Crimean Tatar": "Kypchak",
+    "Indonesian":  "Malayic",
+    "Malay":       "Malayic",
+    "Minangkabau": "Malayic",
+    "Javanese":    "Javanese",
+    "Sundanese":   "Sundic",
+    "Malagasy":    "East Barito",
+
+    # Philippine & Oceanic already covered above
+
+    # Vietic & MSEA
+    "Vietnamese": "Vietic",
+
+    # Altaic hypotheses excluded; Kipchak/Oghuz etc already above
+
+    # Afro-Asiatic
+    "Arabic":          "Central Semitic",
+    "Egyptian Arabic": "Central Semitic",
+    "Hebrew":          "North-west Semitic",
+
+    # Niger-Congo
+    "Swahili": "Sabaki",
+    "Yoruba":  "Yoruboid",
+
+    # Isolates & special groups
+    "Albanian": "Albanian",
+    "Armenian": "Armenian",
+    "Basque":   "Language Isolate",
+    "Greek":    "Hellenic",
+    "Latin":    "Latino-Faliscan",
+    "Japanese": "Japonic",
+    "Esperanto":"Constructed",
+    "Ido":      "Constructed",
+    "Volapük":  "Constructed",
+    "Haitian":  "French-based Creole",
 }
 
-language_families = {
-    "Afrikaans": "Germanic",
+
+# ── 1. high-level genealogical families ─────────────────────────────────────────
+high_level_families = {
+    "Afrikaans": "Indo-European",
     "Albanian": "Indo-European",
     "Arabic": "Afroasiatic",
     "Egyptian Arabic": "Afroasiatic",
-    "Aragonese": "Romance",
+    "Aragonese": "Indo-European",
     "Armenian": "Indo-European",
-    "Asturian": "Romance",
+    "Asturian": "Indo-European",
     "Azerbaijani": "Turkic",
     "Bashkir": "Turkic",
     "Basque": "Language Isolate",
-    "Bavarian": "Germanic",
+    "Bavarian": "Indo-European",
     "Belarusian": "Indo-European",
     "Bengali": "Indo-European",
     "Bishnupriya Manipuri": "Indo-European",
@@ -126,35 +170,35 @@ language_families = {
     "Breton": "Indo-European",
     "Bulgarian": "Indo-European",
     "Burmese": "Sino-Tibetan",
-    "Catalan": "Romance",
+    "Catalan": "Indo-European",
     "Cebuano": "Austronesian",
-    "Chechen": "Northeast Caucasian",
+    "Chechen": "Northeast Caucasian",
     "Chinese (Simplified)": "Sino-Tibetan",
     "Chinese (Traditional)": "Sino-Tibetan",
     "Min Nan Chinese": "Sino-Tibetan",
     "Chuvash": "Turkic",
     "Croatian": "Indo-European",
     "Czech": "Indo-European",
-    "Danish": "Germanic",
-    "Dutch": "Germanic",
-    "English": "Germanic",
+    "Danish": "Indo-European",
+    "Dutch": "Indo-European",
+    "English": "Indo-European",
     "Estonian": "Uralic",
     "Finnish": "Uralic",
-    "French": "Romance",
-    "Galician": "Romance",
+    "French": "Indo-European",
+    "Galician": "Indo-European",
     "Georgian": "Kartvelian",
-    "German": "Germanic",
+    "German": "Indo-European",
     "Greek": "Indo-European",
     "Gujarati": "Indo-European",
     "Haitian": "Creole",
     "Hebrew": "Afroasiatic",
     "Hindi": "Indo-European",
     "Hungarian": "Uralic",
-    "Icelandic": "Germanic",
+    "Icelandic": "Indo-European",
     "Ido": "Constructed",
     "Indonesian": "Austronesian",
     "Irish": "Indo-European",
-    "Italian": "Romance",
+    "Italian": "Indo-European",
     "Japanese": "Japonic",
     "Javanese": "Austronesian",
     "Kannada": "Dravidian",
@@ -164,9 +208,9 @@ language_families = {
     "Latin": "Indo-European",
     "Latvian": "Indo-European",
     "Lithuanian": "Indo-European",
-    "Lombard": "Romance",
-    "Low Saxon": "Germanic",
-    "Luxembourgish": "Germanic",
+    "Lombard": "Indo-European",
+    "Low Saxon": "Indo-European",
+    "Luxembourgish": "Indo-European",
     "Macedonian": "Indo-European",
     "Malagasy": "Austronesian",
     "Malay": "Austronesian",
@@ -175,27 +219,27 @@ language_families = {
     "Minangkabau": "Austronesian",
     "Nepali": "Indo-European",
     "Newar": "Sino-Tibetan",
-    "Norwegian (Bokmal)": "Germanic",
-    "Norwegian (Nynorsk)": "Germanic",
-    "Occitan": "Romance",
+    "Norwegian (Bokmal)": "Indo-European",
+    "Norwegian (Nynorsk)": "Indo-European",
+    "Occitan": "Indo-European",
     "Persian (Farsi)": "Indo-European",
-    "Piedmontese": "Romance",
+    "Piedmontese": "Indo-European",
     "Polish": "Indo-European",
-    "Portuguese": "Romance",
+    "Portuguese": "Indo-European",
     "Punjabi": "Indo-European",
-    "Romanian": "Romance",
+    "Romanian": "Indo-European",
     "Russian": "Indo-European",
-    "Scots": "Germanic",
+    "Scots": "Indo-European",
     "Serbian": "Indo-European",
     "Serbo-Croatian": "Indo-European",
-    "Sicilian": "Romance",
+    "Sicilian": "Indo-European",
     "Slovak": "Indo-European",
     "Slovenian": "Indo-European",
     "South Azerbaijani": "Turkic",
-    "Spanish": "Romance",
+    "Spanish": "Indo-European",
     "Sundanese": "Austronesian",
     "Swahili": "Niger-Congo",
-    "Swedish": "Germanic",
+    "Swedish": "Indo-European",
     "Tagalog": "Austronesian",
     "Tajik": "Indo-European",
     "Tamil": "Dravidian",
@@ -209,9 +253,138 @@ language_families = {
     "Volapük": "Constructed",
     "Waray-Waray": "Austronesian",
     "Welsh": "Indo-European",
-    "West Frisian": "Germanic",
+    "West Frisian": "Indo-European",
     "Western Punjabi": "Indo-European",
     "Yoruba": "Niger-Congo",
     "Esperanto": "Constructed",
     "Crimean Tatar": "Turkic",
 }
+
+# ── 2. primary branches (first subdivision inside each family) ────────────────
+primary_families_branches = {
+    # Indo-European
+    "Afrikaans": "Germanic",
+    "Albanian": "Albanian",
+    "Aragonese": "Romance",
+    "Armenian": "Armenian",
+    "Asturian": "Romance",
+    "Bavarian": "Germanic",
+    "Belarusian": "Slavic",
+    "Bengali": "Indo-Aryan",
+    "Bishnupriya Manipuri": "Indo-Aryan",
+    "Bosnian": "Slavic",
+    "Breton": "Celtic",
+    "Bulgarian": "Slavic",
+    "Catalan": "Romance",
+    "Croatian": "Slavic",
+    "Czech": "Slavic",
+    "Danish": "Germanic",
+    "Dutch": "Germanic",
+    "English": "Germanic",
+    "French": "Romance",
+    "Galician": "Romance",
+    "German": "Germanic",
+    "Greek": "Hellenic",
+    "Gujarati": "Indo-Aryan",
+    "Hindi": "Indo-Aryan",
+    "Icelandic": "Germanic",
+    "Irish": "Celtic",
+    "Italian": "Romance",
+    "Latin": "Italic",
+    "Latvian": "Baltic",
+    "Lithuanian": "Baltic",
+    "Lombard": "Romance",
+    "Low Saxon": "Germanic",
+    "Luxembourgish": "Germanic",
+    "Macedonian": "Slavic",
+    "Marathi": "Indo-Aryan",
+    "Nepali": "Indo-Aryan",
+    "Norwegian (Bokmal)": "Germanic",
+    "Norwegian (Nynorsk)": "Germanic",
+    "Occitan": "Romance",
+    "Persian (Farsi)": "Iranian",
+    "Piedmontese": "Romance",
+    "Polish": "Slavic",
+    "Portuguese": "Romance",
+    "Punjabi": "Indo-Aryan",
+    "Romanian": "Romance",
+    "Russian": "Slavic",
+    "Scots": "Germanic",
+    "Serbian": "Slavic",
+    "Serbo-Croatian": "Slavic",
+    "Sicilian": "Romance",
+    "Slovak": "Slavic",
+    "Slovenian": "Slavic",
+    "Spanish": "Romance",
+    "Swedish": "Germanic",
+    "Tajik": "Iranian",
+    "Ukrainian": "Slavic",
+    "Urdu": "Indo-Aryan",
+    "West Frisian": "Germanic",
+    "Western Punjabi": "Indo-Aryan",
+    "Welsh": "Celtic",
+
+    # Afroasiatic
+    "Arabic": "Semitic",
+    "Egyptian Arabic": "Semitic",
+    "Hebrew": "Semitic",
+
+    # Turkic
+    "Azerbaijani": "Oghuz",
+    "South Azerbaijani": "Oghuz",
+    "Turkish": "Oghuz",
+    "Bashkir": "Kipchak",
+    "Kazakh": "Kipchak",
+    "Kirghiz": "Kipchak",
+    "Tatar": "Kipchak",
+    "Crimean Tatar": "Kipchak",
+    "Chuvash": "Oghur",
+    "Uzbek": "Karluk",
+
+    # Uralic
+    "Estonian": "Finnic",
+    "Finnish": "Finnic",
+    "Hungarian": "Ugric",
+
+    # Sino-Tibetan
+    "Chinese (Simplified)": "Sinitic",
+    "Chinese (Traditional)": "Sinitic",
+    "Min Nan Chinese": "Sinitic",
+    "Burmese": "Tibeto-Burman",
+    "Newar": "Tibeto-Burman",
+
+    # Austronesian
+    "Cebuano": "Malayo-Polynesian",
+    "Indonesian": "Malayo-Polynesian",
+    "Javanese": "Malayo-Polynesian",
+    "Malagasy": "Malayo-Polynesian",
+    "Malay": "Malayo-Polynesian",
+    "Minangkabau": "Malayo-Polynesian",
+    "Sundanese": "Malayo-Polynesian",
+    "Tagalog": "Philippine",
+    "Waray-Waray": "Philippine",
+
+    # Dravidian
+    "Kannada": "South Dravidian",
+    "Malayalam": "South Dravidian",
+    "Tamil": "South Dravidian",
+    "Telugu": "South-Central Dravidian",
+
+    # Niger-Congo
+    "Swahili": "Atlantic-Congo",
+    "Yoruba": "Atlantic-Congo",
+
+    # Misc. single-branch families
+    "Basque": "Language Isolate",
+    "Chechen": "Nakh",
+    "Georgian": "Kartvelian",
+    "Japanese": "Japonic",
+    "Korean": "Koreanic",
+    "Vietnamese": "Vietic",
+
+    # Creole & Constructed
+    "Haitian": "French-based Creole",
+    "Esperanto": "Constructed",
+    "Ido": "Constructed",
+    "Volapük": "Constructed",
+}

utils.py

@@ -5,9 +5,8 @@ import numpy as np
 from sklearn.manifold import TSNE
 import umap
 from sklearn.cluster import KMeans
-from scipy.spatial import KDTree
 from adjustText import adjust_text
-from constants import language_families, language_subfamilies
+from constants import high_level_families, primary_families_branches
 
 
 def filter_languages_by_families(matrix, languages, families):
@@ -24,7 +23,7 @@ def filter_languages_by_families(matrix, languages, families):
     filtered_languages = [
         (i, lang)
         for i, lang in enumerate(languages)
-        if language_families[lang] in families
+        if high_level_families[lang] in families
     ]
     filtered_indices = [i for i, lang in filtered_languages]
     filtered_languages = [lang for i, lang in filtered_languages]
@@ -48,7 +47,7 @@ def get_dynamic_color_map(n_colors):
 
 
 def cluster_languages_by_families(languages):
-    lang_families = [language_families[lang] for lang in languages]
+    lang_families = [high_level_families[lang] for lang in languages]
     legend = sorted(set(lang_families))
     clusters = [legend.index(family) for family in lang_families]
     return clusters, legend
@@ -56,7 +55,7 @@ def cluster_languages_by_families(languages):
 
 def cluster_languages_by_subfamilies(languages):
     labels = [
-        language_families[lang] + f" ({language_subfamilies[lang]})"
+        high_level_families[lang] + f" ({primary_families_branches[lang]})"
         for lang in languages
     ]
     legend = sorted(set(labels))