Spaces:
Sleeping
Sleeping
Deploy-app
commited on
Update main.py
Browse files
main.py
CHANGED
@@ -1,22 +1,29 @@
|
|
1 |
-
|
2 |
import pandas as pd
|
3 |
import numpy as np
|
|
|
4 |
import matplotlib.pyplot as plt
|
5 |
import seaborn as sns
|
6 |
import pickle
|
7 |
import nltk
|
8 |
import tensorflow as tf
|
9 |
import re
|
10 |
-
|
|
|
|
|
|
|
|
|
|
|
11 |
from nltk.corpus import stopwords
|
12 |
from nltk.tokenize import word_tokenize, sent_tokenize
|
|
|
|
|
|
|
13 |
from sklearn.model_selection import train_test_split
|
14 |
-
from sklearn.metrics import classification_report, accuracy_score, confusion_matrix
|
15 |
-
|
16 |
-
from
|
17 |
-
from transformers import TFBertForSequenceClassification
|
18 |
-
nltk.download('punkt')
|
19 |
-
nltk.download('stopwords')
|
20 |
|
21 |
df = pd.read_csv("dataset_tweet_sentiment_pilkada_DKI_2017.csv")
|
22 |
|
|
|
1 |
+
# Mengimpor pustaka yang diperlukan
|
2 |
import pandas as pd
|
3 |
import numpy as np
|
4 |
+
import sklearn.manifold as manifold
|
5 |
import matplotlib.pyplot as plt
|
6 |
import seaborn as sns
|
7 |
import pickle
|
8 |
import nltk
|
9 |
import tensorflow as tf
|
10 |
import re
|
11 |
+
|
12 |
+
# Mengunduh tokenizer dan stopwords
|
13 |
+
nltk.download('punkt')
|
14 |
+
nltk.download('stopwords')
|
15 |
+
|
16 |
+
# Mengimpor komponen dari NLTK
|
17 |
from nltk.corpus import stopwords
|
18 |
from nltk.tokenize import word_tokenize, sent_tokenize
|
19 |
+
|
20 |
+
|
21 |
+
# Mengimpor komponen dari scikit-learn dan transformers
|
22 |
from sklearn.model_selection import train_test_split
|
23 |
+
from sklearn.metrics import classification_report, accuracy_score, confusion_matrix, roc_curve, auc
|
24 |
+
from sklearn.manifold import TSNE
|
25 |
+
from wordcloud import WordCloud
|
26 |
+
from transformers import BertTokenizer, TFBertForSequenceClassification
|
|
|
|
|
27 |
|
28 |
df = pd.read_csv("dataset_tweet_sentiment_pilkada_DKI_2017.csv")
|
29 |
|