Upload supplementary files

Supplementary_files/1-Order_species_by_rarety.py

@@ -0,0 +1,35 @@
+#!/usr/bin/python3.10
+# -*- coding: utf-8 -*-
+
+"""************************
+AnkIdentification - Supplementary code 1 : Order species by rarety.
+Aurélien VALENTIN - from 06/11/2022 to 29/12/2022
+************************"""
+# Importation and initialisation
+import json, sys
+dict_plants = {}
+
+# Definition of the progressbar function, from https://gist.github.com/ChesterChowWOV/2b35c551b339adbf459363322aac5b4b
+def progressbar(it, prefix = "", size = 60, file = sys.stdout):
+    count = len(it)
+    def show(j):
+        x = int(size*j/count)
+        file.write("{}[{}{}] {}/{} {}%\r".format(prefix, "█"*x, "."*(size-x), j, count, round(j / count * 100, 2)))
+        file.flush()
+    show(0)
+    for i, item in enumerate(it):
+        yield item
+        show(i + 1)
+    file.write("\n")
+    file.flush()
+
+with open("multimedia.txt", encoding="utf-8") as fpi:
+    fpi.readline()
+    for line in progressbar(fpi.readlines(), "Counting", 40):
+        species = line.split("\t")[5].split(" ")[0] + " " + line.split("\t")[5].split(" ")[1]
+        try: dict_plants[species] += 1
+        except: dict_plants[species] = 1
+
+dict_plants_sorted = dict(sorted(dict_plants.items(), key=lambda item: item[1], reverse=True))
+
+with open("_dict_species_by_rarety.json", "w") as fpo: json.dump(dict_plants_sorted, fpo)

Supplementary_files/2-Attributing_families.py

@@ -0,0 +1,34 @@
+#!/usr/bin/python3.10
+# -*- coding: utf-8 -*-
+
+"""************************
+AnkIdentification - Supplementary code 2 : Attributing its family to each species.
+Aurélien VALENTIN - from 06/11/2022 to 29/12/2022
+************************"""
+
+# Importation and initialisation
+import json, sys
+dict_classification = {}
+
+# Definition of the progressbar function, from https://gist.github.com/ChesterChowWOV/2b35c551b339adbf459363322aac5b4b
+def progressbar(it, prefix = "", size = 60, file = sys.stdout):
+    count = len(it)
+    def show(j):
+        x = int(size*j/count)
+        file.write("{}[{}{}] {}/{} {}%\r".format(prefix, "█"*x, "."*(size-x), j, count, round(j / count * 100, 2)))
+        file.flush()
+    show(0)
+    for i, item in enumerate(it):
+        yield item
+        show(i + 1)
+    file.write("\n")
+    file.flush()
+
+# Creation of the dictionary and the corresponding json file
+with open("classification.txt", encoding="utf-8") as classification:
+    classification.readline()
+    for line in progressbar(classification.readlines(), "Computing", 40):
+        if line.split("\t")[4] == "SPECIES":
+            dict_classification[line.split("\t")[3].split(" ")[0] + " " + line.split("\t")[3].split(" ")[1]] = line.split("\t")[7]
+
+with open("_dict_classification.json", "w") as fpo : json.dump(dict_classification, fpo)

Supplementary_files/3-1-Get_the_list_of_all_plants.py

@@ -0,0 +1,42 @@
+#!/usr/bin/python3.10
+# -*- coding: utf-8 -*-
+
+"""************************
+AnkIdentification - Supplementary code 3-1 : Creating the list of all plant species.
+Aurélien VALENTIN - from 06/11/2022 to 29/12/2022
+************************"""
+
+# Importation and initialisation
+import json, sys
+dict_common_names = {}
+
+# Definition of the progressbar function, from https://gist.github.com/ChesterChowWOV/2b35c551b339adbf459363322aac5b4b
+def progressbar(it, prefix="", size=60, file=sys.stdout):
+    count = len(it)
+    def show(j):
+        x = int(size*j/count)
+        file.write("{}[{}{}] {}/{} {}%\r".format(prefix, "█"*x, "."*(size-x), j, count, round(j/count * 100, 2)))
+        file.flush()
+    show(0)
+    for i, item in enumerate(it):
+        yield item
+        show(i+1)
+    file.write("\n")
+    file.flush()
+
+# Creation of the list
+with open("0229588-220831081235567.csv", encoding="utf-8") as fpi:
+    fpi.readline()
+    for line in progressbar(fpi.readlines(), "Processing species", 40):
+        try:
+            specie = line.split("\t")[1].split(" ")[0] + " " + line.split("\t")[1].split(" ")[1]
+            dict_common_names[specie] = ""
+            # Looking for another scientific name accepted
+            specie2 = line.split("\t")[3].split(" ")[0] + " " + line.split("\t")[3].split(" ")[1]
+            if specie2 != specie:
+                dict_common_names[specie2] = ""
+        except: pass
+
+# Generation of the json file
+with open("_dict_species_raw.json", "w") as fpo : json.dump(dict_common_names, fpo)
+print(dict_common_names)

Supplementary_files/3-2-Attributing_vernacular_names.py

@@ -0,0 +1,69 @@
+#!/usr/bin/python3.10
+# -*- coding: utf-8 -*-
+
+"""************************
+AnkIdentification - Supplementary code 3-2 : Attributing its varnacular name(s) (VN) to each species.
+Aurélien VALENTIN - from 06/11/2022 to 29/12/2022
+************************"""
+
+# Importation and initialisation
+import xml.etree.ElementTree as ET
+import sys, json, lxml.etree, lxml.builder
+with open("_dict_species_raw.json", "r") as fpi: common_names = json.load(fpi)
+
+# Definition of the progressbar function, from https://gist.github.com/ChesterChowWOV/2b35c551b339adbf459363322aac5b4b
+def progressbar(it, prefix = "", size = 60, file = sys.stdout):
+    count = len(list(myroot))
+    def show(j):
+        x = int(size*j/count)
+        file.write("{}[{}{}] {}/{} {}%\r".format(prefix, "█"*x, "."*(size-x), j, count, round(j / count * 100, 2)))
+        file.flush()
+    show(0)
+    for i, item in enumerate(it):
+        yield item
+        show(i + 1)
+    file.write("\n")
+    file.flush()
+
+# Computing of the 7 fragments of the original files (because it is a very huge one)
+for file_number in range(1, 7):
+    file_number = str(file_number)
+    print("File number ", file_number)
+
+    # Parsing of the xml file
+    mytree = ET.parse(file_number + '.xml')
+    globals()[f"common_names_{file_number}"] = {}
+    myroot = mytree.getroot()
+    E = lxml.builder.ElementMaker()
+    ROOT = E.root
+    DOC = E.doc
+    PAGE = E.page
+    TEXT = E.text
+    TITLE = E.title
+    the_doc = ROOT()
+
+    for page in progressbar(myroot.iter("page"), "Searching plant species", 40):
+        specie = page.find("title").text
+        if specie in common_names.keys():
+            try:
+                # Checking of French names
+                VN = page.find("revision").find("text").text.split("{{VN")[1].split("}}")[0].replace("\n", " ")
+                try: globals()[f"common_names_{file_number}"][specie] = {"fr": VN.split("fr=")[1].split("|")[0].strip("}}").strip(" ")}
+                except:
+                    try:
+                        # Otherwise, cheking for an English one
+                        New_VN = VN.split("en=")[1].split("|")[0].strip("}}").strip(" ")
+                        if New_VN != "": globals()[f"common_names_{file_number}"][specie] = {"fr": "en " + New_VN}
+                    except:
+                        pass
+                try:
+                    # Also storing of English vernacular names
+                    New_VN = VN.split("en=")[1].split("|")[0].strip("}}").strip(" ")
+                    if New_VN != "": globals()[f"common_names_{file_number}"][specie]["en"] = New_VN
+                except: pass
+            except: pass
+
+    # Creation of a json file for each fragments
+    print("Storing")
+    with open("_dict_species_" + file_number + ".json", "w") as fpo : json.dump(globals()[f"common_names_{file_number}"], fpo)
+    print(globals()[f"common_names_{file_number}"])