Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -129,9 +129,12 @@ def preprocess_data(df):
|
|
| 129 |
df['texts'] = df['texts'].apply(lambda x: x.strip()) # Remove leading and trailing whitespaces
|
| 130 |
df = df[df['texts'] != '']
|
| 131 |
|
|
|
|
|
|
|
| 132 |
return df
|
| 133 |
|
| 134 |
def cluster_data(df, num_clusters=5):
|
|
|
|
| 135 |
# Vectorize the text data
|
| 136 |
vectorizer = TfidfVectorizer(stop_words='english')
|
| 137 |
X = vectorizer.fit_transform(df['texts'])
|
|
@@ -147,6 +150,7 @@ def cluster_data(df, num_clusters=5):
|
|
| 147 |
df['PCA1'] = principal_components[:, 0]
|
| 148 |
df['PCA2'] = principal_components[:, 1]
|
| 149 |
|
|
|
|
| 150 |
return df
|
| 151 |
|
| 152 |
def visualize_clusters(df):
|
|
|
|
| 129 |
df['texts'] = df['texts'].apply(lambda x: x.strip()) # Remove leading and trailing whitespaces
|
| 130 |
df = df[df['texts'] != '']
|
| 131 |
|
| 132 |
+
print("Preprocessing completed.")
|
| 133 |
+
|
| 134 |
return df
|
| 135 |
|
| 136 |
def cluster_data(df, num_clusters=5):
|
| 137 |
+
print("Clustering data...")
|
| 138 |
# Vectorize the text data
|
| 139 |
vectorizer = TfidfVectorizer(stop_words='english')
|
| 140 |
X = vectorizer.fit_transform(df['texts'])
|
|
|
|
| 150 |
df['PCA1'] = principal_components[:, 0]
|
| 151 |
df['PCA2'] = principal_components[:, 1]
|
| 152 |
|
| 153 |
+
print("Clustering completed.")
|
| 154 |
return df
|
| 155 |
|
| 156 |
def visualize_clusters(df):
|