Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -117,7 +117,6 @@ def cluster_data(df, num_clusters):
|
|
| 117 |
|
| 118 |
return df, kmeans
|
| 119 |
|
| 120 |
-
|
| 121 |
def generate_wordcloud(df):
|
| 122 |
text = " ".join(df['texts'].tolist())
|
| 123 |
stopwords = set(STOPWORDS)
|
|
@@ -153,6 +152,7 @@ def generate_bar_chart(df, num_clusters_to_display):
|
|
| 153 |
|
| 154 |
category_top_words = df_top_categories.groupby('Category', observed=False)['texts'].apply(lambda x: ' '.join(x)).reset_index()
|
| 155 |
category_top_words['top_word'] = category_top_words['texts'].apply(lambda x: ' '.join([word for word in pd.Series(x.split()).value_counts().index if word not in common_words][:3]))
|
|
|
|
| 156 |
category_sizes = df_top_categories['Category'].value_counts().reset_index()
|
| 157 |
category_sizes.columns = ['Category', 'Count']
|
| 158 |
category_sizes = category_sizes.merge(category_top_words[['Category', 'top_word']], on='Category')
|
|
@@ -175,7 +175,6 @@ def main(file, num_clusters_to_display):
|
|
| 175 |
|
| 176 |
df = preprocess_data(df)
|
| 177 |
|
| 178 |
-
|
| 179 |
wordcloud_img = generate_wordcloud(df)
|
| 180 |
bar_chart_img = generate_bar_chart(df, num_clusters_to_display)
|
| 181 |
|
|
@@ -200,7 +199,7 @@ interface = gr.Interface(
|
|
| 200 |
gr.Image(label="Bar Chart")
|
| 201 |
],
|
| 202 |
title="Unanswered User Queries Categorization",
|
| 203 |
-
description="Categorize
|
| 204 |
)
|
| 205 |
|
| 206 |
interface.launch(share=True)
|
|
|
|
| 117 |
|
| 118 |
return df, kmeans
|
| 119 |
|
|
|
|
| 120 |
def generate_wordcloud(df):
|
| 121 |
text = " ".join(df['texts'].tolist())
|
| 122 |
stopwords = set(STOPWORDS)
|
|
|
|
| 152 |
|
| 153 |
category_top_words = df_top_categories.groupby('Category', observed=False)['texts'].apply(lambda x: ' '.join(x)).reset_index()
|
| 154 |
category_top_words['top_word'] = category_top_words['texts'].apply(lambda x: ' '.join([word for word in pd.Series(x.split()).value_counts().index if word not in common_words][:3]))
|
| 155 |
+
|
| 156 |
category_sizes = df_top_categories['Category'].value_counts().reset_index()
|
| 157 |
category_sizes.columns = ['Category', 'Count']
|
| 158 |
category_sizes = category_sizes.merge(category_top_words[['Category', 'top_word']], on='Category')
|
|
|
|
| 175 |
|
| 176 |
df = preprocess_data(df)
|
| 177 |
|
|
|
|
| 178 |
wordcloud_img = generate_wordcloud(df)
|
| 179 |
bar_chart_img = generate_bar_chart(df, num_clusters_to_display)
|
| 180 |
|
|
|
|
| 199 |
gr.Image(label="Bar Chart")
|
| 200 |
],
|
| 201 |
title="Unanswered User Queries Categorization",
|
| 202 |
+
description="Categorize Unanswered User Queries"
|
| 203 |
)
|
| 204 |
|
| 205 |
interface.launch(share=True)
|