Added Top2Vec, updated BERTopic variations

Updated BERTopic, added lowprep version
Added Perplexity to LDA
2025-12-07 02:30:50 +01:00 · 2025-06-23 18:58:56 +02:00 · 2025-06-20 02:57:35 +02:00 · 2025-06-20 02:56:31 +02:00
16 changed files with 223226 additions and 105762 deletions
--- a/.gitignore
+++ b/.gitignore
@@ -3,3 +3,4 @@
 __pycache__/
 **.bertopic
 history*.json
+model.pkl
--- a/bertopic.ipynb
+++ b/bertopic.ipynb
--- a/bertopic/visualization.html
+++ b/bertopic/visualization.html
--- a/bertopic_lowprep.ipynb
+++ b/bertopic_lowprep.ipynb
--- a/lda.ipynb
+++ b/lda.ipynb
--- a/lda_output/lda_dictionary.gensim
+++ b/lda_output/lda_dictionary.gensim
--- a/lda_output/lda_model.gensim
+++ b/lda_output/lda_model.gensim
--- a/lda_output/lda_model.gensim.id2word
+++ b/lda_output/lda_model.gensim.id2word
--- a/lda_output/lda_model.gensim.state
+++ b/lda_output/lda_model.gensim.state
--- a/lda_output/topic_to_reviews.json
+++ b/lda_output/topic_to_reviews.json
@@ -1207,11 +1207,11 @@
      "topics": [
        {
          "topic_id": 2,
-          "probability": 0.56
+          "probability": 0.55
        }
      ],
      "dominant_topic": 2,
-      "dominant_probability": 0.56
+      "dominant_probability": 0.55
    },
    {
      "document_id": 93,
@@ -122923,11 +122923,11 @@
        },
        {
          "topic_id": 2,
-          "probability": 0.41
+          "probability": 0.4
        }
      ],
      "dominant_topic": 2,
-      "dominant_probability": 0.41
+      "dominant_probability": 0.4
    },
    {
      "document_id": 9489,
@@ -216167,11 +216167,11 @@
        },
        {
          "topic_id": 2,
-          "probability": 0.5
+          "probability": 0.51
        }
      ],
      "dominant_topic": 2,
-      "dominant_probability": 0.5
+      "dominant_probability": 0.51
    },
    {
      "document_id": 16639,
@@ -238519,11 +238519,11 @@
      "topics": [
        {
          "topic_id": 2,
-          "probability": 0.6
+          "probability": 0.61
        }
      ],
      "dominant_topic": 2,
-      "dominant_probability": 0.6
+      "dominant_probability": 0.61
    },
    {
      "document_id": 18375,
@@ -383083,11 +383083,11 @@
      "topics": [
        {
          "topic_id": 0,
-          "probability": 0.54
+          "probability": 0.55
        }
      ],
      "dominant_topic": 0,
-      "dominant_probability": 0.54
+      "dominant_probability": 0.55
    },
    {
      "document_id": 29573,
@@ -446754,7 +446754,7 @@
          "probability": 0.37
        }
      ],
-      "dominant_topic": 0,
+      "dominant_topic": 2,
      "dominant_probability": 0.37
    },
    {
@@ -544884,6 +544884,10 @@
        {
          "topic_id": 0,
          "probability": 0.38
+        },
+        {
+          "topic_id": 1,
+          "probability": 0.35
        }
      ],
      "dominant_topic": 0,
@@ -596780,10 +596784,6 @@
        {
          "topic_id": 0,
          "probability": 0.43
-        },
-        {
-          "topic_id": 2,
-          "probability": 0.35
        }
      ],
      "dominant_topic": 0,
@@ -672275,11 +672275,11 @@
      "topics": [
        {
          "topic_id": 2,
-          "probability": 0.42
+          "probability": 0.41
        }
      ],
      "dominant_topic": 2,
-      "dominant_probability": 0.42
+      "dominant_probability": 0.41
    },
    {
      "document_id": 52182,
--- a/processed_texts_lowprep.pkl
+++ b/processed_texts_lowprep.pkl
--- a/processed_texts_top2vec.pkl
+++ b/processed_texts_top2vec.pkl
--- a/top2vec.ipynb
+++ b/top2vec.ipynb
--- a/top2vec/corpus.pkl
+++ b/top2vec/corpus.pkl
--- a/top2vec/dictionary.pkl
+++ b/top2vec/dictionary.pkl
--- a/top2vec/tokens.pkl
+++ b/top2vec/tokens.pkl
Author	SHA1	Message	Date
Marvin Scham	bfff8f7d96	Added Top2Vec, updated BERTopic variations	2025-06-23 18:58:56 +02:00
Marvin Scham	3e5669d213	Updated BERTopic, added lowprep version	2025-06-20 02:57:35 +02:00
Marvin Scham	a9343cd79b	Added Perplexity to LDA	2025-06-20 02:56:31 +02:00