added general alignment file for edictor and mantained the msa file

NOTES.md

@@ -32,6 +32,14 @@ pip install -r requirements.txt
 make wordlist
 ```
 
-In addition to yielding the word list file (`npl_data.tsv`), the script also 
-performs an automatic recognition of sound correspondence patterns,
-the result of which is stored in the file `npl_patterns.tsv`.
+#### Reproduce analysis
+In addition to yielding the word list file (`npl_data.tsv`), the Makefile
+also runs a script that performs the multiple sequence alignment and an 
+automatic recognition of sound correspondence patterns. To do so, please
+type the following:
+
+```shell
+make analysis
+```
+The result of both processes are stored in the files `npl_msaligned` 
+and `npl_patterns.tsv`.

README.md

@@ -53,9 +53,17 @@ pip install -r requirements.txt
 make wordlist
 ```
 
-In addition to yielding the word list file (`npl_data.tsv`), the script also 
-performs an automatic recognition of sound correspondence patterns,
-the result of which is stored in the file `npl_patterns.tsv`.
+#### Reproduce analysis
+In addition to yielding the word list file (`npl_data.tsv`), the Makefile
+also runs a script that performs the multiple sequence alignment and an 
+automatic recognition of sound correspondence patterns. To do so, please
+type the following:
+
+```shell
+make analysis
+```
+The result of both processes are stored in the files `npl_msaligned` 
+and `npl_patterns.tsv`.
 
 
 ## Statistics

analysis/Makefile

@@ -1,2 +1,5 @@
 wordlist:
-	edictor wordlist --name=npl_data --data=../cldf/cldf-metadata.json --preprocessing=realign.py --addon="language_subgroup:subgroup","alignment:alignment","cognacy:cogid","partial_cognacy:cogids","source:source"
+	edictor wordlist --name=npl_data --data=../cldf/cldf-metadata.json --preprocessing=preprocessing.py --addon="language_subgroup:subgroup","alignment:alignment","cognacy:cogid","partial_cognacy:cogids","source:source"
+
+analysis:
+	edictor wordlist --name=npl_msaligned --data=../cldf/cldf-metadata.json --preprocessing=realign.py --addon="language_subgroup:subgroup","alignment:alignment","cognacy:cogid","partial_cognacy:cogids","source:source"

analysis/preprocessing.py

@@ -0,0 +1,18 @@
+from lingpy import Alignments
+from lingpy.compare.partial import Partial
+
+def run(wordlist):
+	D = {0: wordlist.columns}
+	for idx in wordlist:
+		D[idx] = [wordlist[idx, h] for h in D[0]]
+
+	lex = Partial(D, segments='tokens', check=False)
+
+	lex = Alignments(lex, ref="cogids")
+	lex.align(ref='cogids')
+
+	D = {0: wordlist.columns+["alignment"]}
+	for idx in lex:
+		D[idx] = [lex[idx, h] for h in D[0]]
+
+	return lex

analysis/realign.py

@@ -4,7 +4,7 @@
 the sound correspondence pattern identification with LingRex (List 2018).
 """
 import re
-from lingpy import Alignments, LexStat, Wordlist
+from lingpy import Alignments,Wordlist
 from lingpy.compare.partial import Partial
 from lingrex.copar import CoPaR
 from lingpy.read.qlc import reduce_alignment

cldf/README.md

@@ -15,7 +15,7 @@ property | value
 [dc:format](http://purl.org/dc/terms/format) | <ol><li>http://concepticon.clld.org/contributions/Swadesh-1952-200</li></ol>
 [dc:license](http://purl.org/dc/terms/license) | https://creativecommons.org/licenses/by/4.0/
 [dcat:accessURL](http://www.w3.org/ns/dcat#accessURL) | [email protected]:lexibank/northperulex
-[prov:wasDerivedFrom](http://www.w3.org/ns/prov#wasDerivedFrom) | <ol><li><a href="[email protected]:lexibank/northperulex/tree/1e3f230a">[email protected]:lexibank/northperulex 1e3f230a</a></li><li><a href="https://github.com/glottolog/glottolog/tree/v5.2.1">Glottolog v5.2.1</a></li><li><a href="https://github.com/concepticon/concepticon-data/tree/v3.4.0">Concepticon v3.4.0</a></li><li><a href="https://github.com/cldf-clts/clts/tree/v2.3.0">CLTS v2.3.0</a></li></ol>
+[prov:wasDerivedFrom](http://www.w3.org/ns/prov#wasDerivedFrom) | <ol><li><a href="[email protected]:lexibank/northperulex/tree/00241a1d">[email protected]:lexibank/northperulex 00241a1d</a></li><li><a href="https://github.com/glottolog/glottolog/tree/v5.2.1">Glottolog v5.2.1</a></li><li><a href="https://github.com/concepticon/concepticon-data/tree/v3.4.0">Concepticon v3.4.0</a></li><li><a href="https://github.com/cldf-clts/clts/tree/v2.3.0">CLTS v2.3.0</a></li></ol>
 [prov:wasGeneratedBy](http://www.w3.org/ns/prov#wasGeneratedBy) | <ol><li><strong>lingpy-rcParams</strong>: <a href="./lingpy-rcParams.json">lingpy-rcParams.json</a></li><li><strong>python</strong>: 3.9.6</li><li><strong>python-packages</strong>: <a href="./requirements.txt">requirements.txt</a></li></ol>
 [rdf:ID](http://www.w3.org/1999/02/22-rdf-syntax-ns#ID) | northperulex
 [rdf:type](http://www.w3.org/1999/02/22-rdf-syntax-ns#type) | http://www.w3.org/ns/dcat#Distribution

cldf/cldf-metadata.json

@@ -17,7 +17,7 @@
         {
             "rdf:about": "[email protected]:lexibank/northperulex",
             "rdf:type": "prov:Entity",
-            "dc:created": "1e3f230a",
+            "dc:created": "00241a1d",
             "dc:title": "Repository"
         },
         {

cldf/lingpy-rcParams.json

@@ -64,7 +64,7 @@
         10,
         10
     ],
-    "filename": "lingpy-2025-12-24",
+    "filename": "lingpy-2025-12-27",
     "gap_symbol": "-",
     "gap_weight": 0.5,
     "gop": -2,
@@ -123,7 +123,7 @@
     "scorer": {},
     "sonar": true,
     "stress": "\u02c8\u02cc'",
-    "timestamp": "2025-12-24 00:00",
+    "timestamp": "2025-12-27 21:11",
     "tones": "\u00b9\u00b2\u00b3\u2074\u2075\u2076\u2077\u2078\u2079\u2070\u2081\u2082\u2083\u2084\u2085\u2086\u2087\u2088\u2089\u20800123456789\u02e5\u02e6\u02e7\u02e8\u02e9\u02ea\u02eb-\ua708-\ua709-\ua70a-\ua70b-\ua70c-\ua70d-\ua70e-\ua70f-\ua710-\ua711-\ua712-\ua713-\ua714-\ua715-\ua716-\ua717-\ua718-\ua719-\ua71a-\ua700-\ua701-\ua702-\ua703-\ua704-\ua705-\ua706-\ua707",
     "tree_calc": "neighbor",
     "unique_sequences": true,