Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
@@ -220,7 +220,7 @@ class SentenceClassifier:
|
|
220 |
class TopicAnalyzer:
|
221 |
def __init__(self, seed_words, sentence_model = "all-MiniLM-L6-v2"):
|
222 |
|
223 |
-
self.umap_model = UMAP(n_neighbors=3, n_components=
|
224 |
|
225 |
self.vectorizer_model = CountVectorizer(
|
226 |
ngram_range=(2, 5)
|
@@ -228,7 +228,7 @@ class TopicAnalyzer:
|
|
228 |
|
229 |
self.representation_model = KeyBERTInspired(top_n_words=10,nr_repr_docs=5)
|
230 |
|
231 |
-
self.representation_model = PartOfSpeech("en_core_web_sm")
|
232 |
|
233 |
self.hdbscan_model = HDBSCAN(
|
234 |
min_cluster_size=4,max_cluster_size=30, metric="euclidean", prediction_data=True
|
|
|
220 |
class TopicAnalyzer:
|
221 |
def __init__(self, seed_words, sentence_model = "all-MiniLM-L6-v2"):
|
222 |
|
223 |
+
self.umap_model = UMAP(n_neighbors=3, n_components=7, min_dist=0.0, metric='cosine')
|
224 |
|
225 |
self.vectorizer_model = CountVectorizer(
|
226 |
ngram_range=(2, 5)
|
|
|
228 |
|
229 |
self.representation_model = KeyBERTInspired(top_n_words=10,nr_repr_docs=5)
|
230 |
|
231 |
+
#self.representation_model = PartOfSpeech("en_core_web_sm")
|
232 |
|
233 |
self.hdbscan_model = HDBSCAN(
|
234 |
min_cluster_size=4,max_cluster_size=30, metric="euclidean", prediction_data=True
|