Spaces:
Sleeping
Sleeping
Commit
·
939efdd
1
Parent(s):
0525d89
Update app.py
Browse files
app.py
CHANGED
|
@@ -2,6 +2,8 @@
|
|
| 2 |
import pandas as pd
|
| 3 |
newsdf_sample = pd.read_excel("200_sample_each_20newsgroup_4k_tfidf.xlsx",engine="openpyxl")
|
| 4 |
|
|
|
|
|
|
|
| 5 |
#preprocessing for better tokenization (needed for tfidf)
|
| 6 |
import nltk
|
| 7 |
nltk.download('stopwords')
|
|
|
|
| 2 |
import pandas as pd
|
| 3 |
newsdf_sample = pd.read_excel("200_sample_each_20newsgroup_4k_tfidf.xlsx",engine="openpyxl")
|
| 4 |
|
| 5 |
+
print("file size",len(newsdf_sample))
|
| 6 |
+
|
| 7 |
#preprocessing for better tokenization (needed for tfidf)
|
| 8 |
import nltk
|
| 9 |
nltk.download('stopwords')
|