marvinscham/masterthesis-playground
1
0
Fork 0
mirror of https://github.com/marvinscham/masterthesis-playground.git synced 2025-12-06 10:10:50 +01:00
Code Issues Packages Projects Releases Wiki Activity

Added Perplexity to LDA

Browse Source
This commit is contained in:
Marvin Scham
2025-06-20 02:56:31 +02:00
parent 1ef5cc654c
commit a9343cd79b
6 changed files with 72 additions and 56 deletions
Download Patch File Download Diff File Expand all files Collapse all files

94
lda.ipynb
View File

File diff suppressed because one or more lines are too long

BIN
lda_output/lda_dictionary.gensim
View File

Binary file not shown.

BIN
lda_output/lda_model.gensim
View File

Binary file not shown.

BIN
lda_output/lda_model.gensim.id2word
View File

Binary file not shown.

BIN
lda_output/lda_model.gensim.state
View File

Binary file not shown.

34
lda_output/topic_to_reviews.json
View File

@@ -1207,11 +1207,11 @@
"topics": [ "topics": [
{ {
"topic_id": 2, "topic_id": 2,
"probability": 0.56 "probability": 0.55
} }
], ],
"dominant_topic": 2, "dominant_topic": 2,
"dominant_probability": 0.56 "dominant_probability": 0.55
}, },
{ {
"document_id": 93, "document_id": 93,
@@ -122923,11 +122923,11 @@
}, },
{ {
"topic_id": 2, "topic_id": 2,
"probability": 0.41 "probability": 0.4
} }
], ],
"dominant_topic": 2, "dominant_topic": 2,
"dominant_probability": 0.41 "dominant_probability": 0.4
}, },
{ {
"document_id": 9489, "document_id": 9489,
@@ -216167,11 +216167,11 @@
}, },
{ {
"topic_id": 2, "topic_id": 2,
"probability": 0.5 "probability": 0.51
} }
], ],
"dominant_topic": 2, "dominant_topic": 2,
"dominant_probability": 0.5 "dominant_probability": 0.51
}, },
{ {
"document_id": 16639, "document_id": 16639,
@@ -238519,11 +238519,11 @@
"topics": [ "topics": [
{ {
"topic_id": 2, "topic_id": 2,
"probability": 0.6 "probability": 0.61
} }
], ],
"dominant_topic": 2, "dominant_topic": 2,
"dominant_probability": 0.6 "dominant_probability": 0.61
}, },
{ {
"document_id": 18375, "document_id": 18375,
@@ -383083,11 +383083,11 @@
"topics": [ "topics": [
{ {
"topic_id": 0, "topic_id": 0,
"probability": 0.54 "probability": 0.55
} }
], ],
"dominant_topic": 0, "dominant_topic": 0,
"dominant_probability": 0.54 "dominant_probability": 0.55
}, },
{ {
"document_id": 29573, "document_id": 29573,
@@ -446754,7 +446754,7 @@
"probability": 0.37 "probability": 0.37
} }
], ],
"dominant_topic": 0, "dominant_topic": 2,
"dominant_probability": 0.37 "dominant_probability": 0.37
}, },
{ {
@@ -544884,6 +544884,10 @@
{ {
"topic_id": 0, "topic_id": 0,
"probability": 0.38 "probability": 0.38
},
{
"topic_id": 1,
"probability": 0.35
} }
], ],
"dominant_topic": 0, "dominant_topic": 0,
@@ -596780,10 +596784,6 @@
{ {
"topic_id": 0, "topic_id": 0,
"probability": 0.43 "probability": 0.43
},
{
"topic_id": 2,
"probability": 0.35
} }
], ],
"dominant_topic": 0, "dominant_topic": 0,
@@ -672275,11 +672275,11 @@
"topics": [ "topics": [
{ {
"topic_id": 2, "topic_id": 2,
"probability": 0.42 "probability": 0.41
} }
], ],
"dominant_topic": 2, "dominant_topic": 2,
"dominant_probability": 0.42 "dominant_probability": 0.41
}, },
{ {
"document_id": 52182, "document_id": 52182,