Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
@@ -108,10 +108,16 @@ def load_example_files():
|
|
108 |
|
109 |
return None
|
110 |
|
|
|
111 |
def cluster_sentences(sentences, num_clusters):
|
112 |
# Filter sentences with length over 10 characters
|
113 |
sentences = [sentence for sentence in sentences if len(sentence) > 10]
|
114 |
|
|
|
|
|
|
|
|
|
|
|
115 |
# Vectorize the sentences
|
116 |
vectorizer = TfidfVectorizer()
|
117 |
X = vectorizer.fit_transform(sentences)
|
@@ -136,6 +142,7 @@ def cluster_sentences(sentences, num_clusters):
|
|
136 |
# Return the ordered clustered sentences without similarity scores for display
|
137 |
return [[sentence for _, sentence in cluster] for cluster in clustered_sentences]
|
138 |
|
|
|
139 |
# Function to convert text to a downloadable file
|
140 |
def get_text_file_download_link(text_to_download, filename='Output.txt', button_label="💾 Save"):
|
141 |
buffer = BytesIO()
|
|
|
108 |
|
109 |
return None
|
110 |
|
111 |
+
|
112 |
def cluster_sentences(sentences, num_clusters):
|
113 |
# Filter sentences with length over 10 characters
|
114 |
sentences = [sentence for sentence in sentences if len(sentence) > 10]
|
115 |
|
116 |
+
# Check if the number of sentences is less than the desired number of clusters
|
117 |
+
if len(sentences) < num_clusters:
|
118 |
+
# If so, adjust the number of clusters to match the number of sentences
|
119 |
+
num_clusters = len(sentences)
|
120 |
+
|
121 |
# Vectorize the sentences
|
122 |
vectorizer = TfidfVectorizer()
|
123 |
X = vectorizer.fit_transform(sentences)
|
|
|
142 |
# Return the ordered clustered sentences without similarity scores for display
|
143 |
return [[sentence for _, sentence in cluster] for cluster in clustered_sentences]
|
144 |
|
145 |
+
|
146 |
# Function to convert text to a downloadable file
|
147 |
def get_text_file_download_link(text_to_download, filename='Output.txt', button_label="💾 Save"):
|
148 |
buffer = BytesIO()
|