Spaces:
Runtime error
Runtime error
File size: 3,919 Bytes
f191e18 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 |
from tqdm import tqdm
from itertools import islice
from youtube_comment_downloader import *
from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline
import matplotlib.pyplot as plt
import csv
import streamlit as st
import pandas as pd
import base64
# Inisialisasi model dan tokenizer
pretrained= "mdhugol/indonesia-bert-sentiment-classification"
model = AutoModelForSequenceClassification.from_pretrained(pretrained)
tokenizer = AutoTokenizer.from_pretrained(pretrained)
sentiment_analysis = pipeline("sentiment-analysis", model=model, tokenizer=tokenizer)
label_index = {'LABEL_0': 'positive', 'LABEL_1': 'neutral', 'LABEL_2': 'negative'}
st.title("Youtube Comment Sentimen Analisis")
# Input URL video
video_url = st.text_input("Masukkan URL video YouTube:")
# Input jumlah komentar yang ingin diambil
num_comments = st.number_input("Jumlah komentar yang ingin diambil:", min_value=1, value=10)
# Fungsi untuk analisis sentimen
def analisis_sentimen(text):
result = sentiment_analysis(text)
label = label_index[result[0]['label']]
score = result[0]['score'] * 100
return label, score
if st.button("Mulai Analisis"):
# Inisialisasi YoutubeCommentDownloader
downloader = YoutubeCommentDownloader()
# Mendapatkan komentar
comments = downloader.get_comments_from_url(video_url, sort_by=SORT_BY_POPULAR)
# Membuka file CSV untuk menulis
with open('comments.csv', mode='w', encoding='utf-8', newline='') as file:
# Membuat objek writer
writer = csv.DictWriter(file, fieldnames=['cid', 'text', 'time', 'author', 'channel', 'votes', 'photo', 'heart', 'reply'])
# Menulis header
writer.writeheader()
# Menulis data komentar
for comment in tqdm(islice(comments, num_comments)):
# Menghapus kolom 'time_parsed' dari komentar
comment.pop('time_parsed', None)
writer.writerow(comment)
st.success(f"Komentar berhasil diunduh dan disimpan dalam file 'comments.csv'")
# Membaca data dari file CSV
comments_df = pd.read_csv('comments.csv')
#analisis sentimen
st.info("Memulai analisis sentimen....")
# List untuk menyimpan hasil analisis sentimen
hasil_analisis = []
# Membaca data dari file CSV
with open('comments.csv', mode='r', encoding='utf-8') as file:
reader = csv.DictReader(file)
for row in tqdm(reader):
comment_text = row['text']
label, score = analisis_sentimen(comment_text)
hasil_analisis.append((comment_text, label, score))
# Menampilkan hasil analisis sentimen
st.subheader("Hasil Analisis Sentimen")
#st.write(hasil_analisis)
# Menampilkan histogram
labels, scores = zip(*[(label, score) for _, label, score in hasil_analisis])
plt.hist(labels, bins=30, color='blue', alpha=0.7, edgecolor='black')
plt.xlabel('Skor Sentimen')
plt.ylabel('Jumlah Komentar')
plt.title('Distribusi Sentimen Komentar')
st.pyplot(plt)
# Menghitung jumlah dan persentase
jumlah_positif = labels.count('positive')
jumlah_negatif = labels.count('negative')
jumlah_netral = labels.count('neutral')
total_komentar = len(labels)
persentase_positif = (jumlah_positif / total_komentar) * 100
persentase_negatif = (jumlah_negatif / total_komentar) * 100
persentase_netral = (jumlah_netral / total_komentar) * 100
st.write(f"Total Komentar: {total_komentar}")
st.write(f"Persentase Komentar Positif: {persentase_positif:.2f}% / {jumlah_positif} Komentar")
st.write(f"Persentase Komentar Negatif: {persentase_negatif:.2f}% / {jumlah_negatif} Komentar")
st.write(f"Persentase Komentar Netral: {persentase_netral:.2f}% / {jumlah_netral} Komentar")
# Menampilkan tabel dengan menggunakan st.table()
st.subheader("Data Komentar")
st.table(comments_df)
|