Many wordlist updates

wordlist/00-desiquintans-nounlist.txt

@@ -3199,7 +3199,6 @@ JADE
 JAGUAR
 JAIL
 JAILHOUSE
-JALAPEÑO
 JAM
 JAR
 JASMINE

wordlist/01-errored-lemmatized-words.csv

@@ -1,4 +1,14 @@
 WORD,ATTEMPTED_LEMMATIZATION,LEMMATIZER
+BELOVED,BELOVE,SPACY
+BLEED,BLEE,SPACY
+EMBED,EMBE,SPACY
+EXCEED,EXCEE,SPACY
+FORTHCOMING,FORTHCOME,SPACY
+NAKED,NAKE,SPACY
+NON-PROFIT,NON,SPACY
+ONGOING,ONGOE,SPACY
+RENOWNED,RENOWNE,SPACY
+SKILLED,SKILLE,SPACY
 ADVERTISING,ADVERTISE,SPACY
 BOSS,BOS,WORDNET
 COMICS,COMIC_STRIP,SPACY
@@ -24,15 +34,8 @@ LESS,LE,WORDNET
 THEMSELVES,THEMSELVE,SPACY
 PERHAPS,PERHAP,SPACY
 OURSELVES,OURSELVE,SPACY
-EXCEED,EXCEE,SPACY
-BLEED,BLEE,SPACY
-NAKED,NAKE,SPACY
-SKILLED,SKILLE,SPACY
-BELOVED,BELOVE,SPACY
 LEST,L,SPACY
 WICKED,WICKE,SPACY
-EMBED,EMBE,SPACY
-ONGOING,ONGOE,SPACY
 ASHAMED,ASHAME,SPACY
 CREED,CREE,SPACY
 VIS,VI,WORDNET
@@ -43,14 +46,11 @@ UNCHANGED,UNCHANGE,SPACY
 UNPUBLISHED,UNPUBLISHE,SPACY
 BIS,BI,WORDNET
 UNEMPLOYED,UNEMPLOYE,SPACY
-FORTHCOMING,FORTHCOME,SPACY
 METAPHYSICS,METAPHYSIC,SPACY
 UNAFFECTED,UNAFFECTE,SPACY
-RENOWNED,RENOWNE,SPACY
 TALENTED,TALENTE,SPACY
 UNFINISHED,UNFINISHE,SPACY
 MS,M,WORDNET
-AESTHETICS,AESTHETIC,WORDNET
 INFRARED,INFRARE,SPACY
 DISINTERESTED,DISINTERESTE,SPACY
 OS,O,WORDNET
@@ -244,7 +244,6 @@ GASWORKS,GASWORK,SPACY
 BULLETED,BULLETE,SPACY
 ARTEL,ROTL,WORDNET
 HEARTSTRINGS,HEARTSTRING,SPACY
-INCREMENTING,INCREMENTE,SPACY
 UNCLEARED,UNCLEARE,SPACY
 CONSOLS,CONSOL,SPACY
 MUDFLATS,MUDFLAT,SPACY
@@ -438,7 +437,6 @@ COSMONAUTICS,COSMONAUTIC,SPACY
 WHOLEGRAINS,WHOLEGRAIN,SPACY
 NEEDMENTS,NEEDMENT,SPACY
 ACHATES,ACHATE,SPACY
-PRECOMPILING,PRECOMPILE,SPACY
 BALUSTERED,BALUSTERE,SPACY
 JUGGINS,JUGGIN,SPACY
 UNCONFIGURED,UNCONFIGURE,SPACY
@@ -475,7 +473,6 @@ REEDING,REEDE,SPACY
 INTERCROSSING,INTERCROSSE,SPACY
 UNDEDUCTED,UNDEDUCTE,SPACY
 AGOGICS,AGOGIC,SPACY
-UNATTENDING,UNATTENDE,SPACY
 OVERMASTED,OVERMASTE,SPACY
 GILES,GILE,SPACY
 NONCOPYRIGHTED,NONCOPYRIGHTE,SPACY
@@ -523,7 +520,6 @@ EUPHRATES,EUPHRATE,SPACY
 TROWING,TROWE,SPACY
 LACEUPS,LACEUP,SPACY
 ALIPED,ALIPE,SPACY
-TALIPED,TALIPE,SPACY
 RAMSES,RAMSE,SPACY
 CENTRONICS,CENTRONIC,SPACY
 MITHRAS,MITHRA,WORDNET

wordlist/01-lemmatized-words.py

@@ -22,12 +22,20 @@ nlp = spacy.load("en_core_web_trf", disable=["parser", "ner"])
 print("Loading initial wordlist")
 
 words = []
-with open("./00-dsiquintans-nounlist.txt", "r") as infile:
-    for line in infile:
-        words.append(line.split(",")[0].strip())
-with gzip.open("./00-frequency-list.csv.gz", "r") as infile:
+
+for file in [
+    "./00-oxford-5000.txt",
+    "./00-desiquintans-nounlist.txt",
+    "./00-frequency-list.csv.gz",
+]:
+    if file.endswith(".gz"):
+        with gzip.open(file, "r") as infile:
             for line in infile:
                 words.append(line.decode("ascii").split(",")[0])
+    else:
+        with open(file, "r") as infile:
+            for line in infile:
+                words.append(line.split(",")[0].strip())
 
 # Remove header
 words = words[1:]
@@ -36,7 +44,8 @@ print(words[0:5])
 
 print("Lemmatizing words")
 
-seen_lemmatizations = set()
+# seen_lemmatizations = set()
+seen_words = set()
 
 with open("./01-errored-lemmatized-words.csv", "w") as erroutfile:
     erroutfile.write("WORD,ATTEMPTED_LEMMATIZATION,LEMMATIZER\n")
@@ -44,27 +53,33 @@ with open("./01-errored-lemmatized-words.csv", "w") as erroutfile:
     with gzip.open("./01-lemmatized-words.csv.gz", "w") as outfile:
         outfile.write("WORD,LEMMATIZED_WORD,LEMMATIZER\n".encode("ascii"))
 
+        # Make a progress bar so logs can be printed
         iter = tqdm(words)
 
-        for word in iter:
+        # Zip (progress bar-ed) word list with nlp.pipe so nlp can process chunks at a time
+        for (word, spacy_word) in zip(iter, nlp.pipe(words)):
             lemmatized_words = [
-                # Wordnet
                 (wordnet.lemmatize(word.lower()).upper(), "WORDNET"),
-                # Spacy
-                (nlp(word)[0].lemma_.upper().upper(), "SPACY"),
+                (spacy_word[0].lemma_.upper(), "SPACY"),
             ]
 
             for lemmatized_word, lemmatizer in lemmatized_words:
-                if word == lemmatized_word:
-                    continue
+                # if word == lemmatized_word:
+                #     # This word is its own lemmatization
+                #     continue
 
-                if (word, lemmatized_word) in seen_lemmatizations:
-                    continue
+                # Skip words if we've already lemmatized them
+                # if (word, lemmatized_word) in seen_lemmatizations: continue
+                # seen_lemmatizations.add((word, lemmatized_word))
 
-                seen_lemmatizations.add((word, lemmatized_word))
+                # Skip words if they've already been added
+                if lemmatized_word in seen_words:
+                    iter.write(f"{lemmatized_word} ({lemmatizer})\talready in seen_words")
+                    continue
+                seen_words.add(lemmatized_word)
 
                 if lemmatized_word not in words:
-                    iter.write(f"{lemmatized_word} ({lemmatizer}) not in all_words")
+                    iter.write(f"{lemmatized_word} ({lemmatizer})\tnot in all_words")
                     erroutfile.write(f"{word},{lemmatized_word},{lemmatizer}\n")
                     continue