First commit

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+best_model.keras filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,27 @@
+import streamlit as st
+import eda
+import model
+
+
+st.set_page_config(
+    page_title="Home page")
+navigasi = st.sidebar.selectbox('Page Selector :', 
+                                ('Home Page','Model Prediksi', 'EDA'))
+
+if navigasi == 'Home Page':
+    st.header('Home Page') 
+    st.write('')
+    st.image('https://i.pinimg.com/originals/db/05/a0/db05a03b2adcfedd15c8b91e48cb99a4.gif')
+    st.write('Graded Challenge 7')
+    st.write('Made By : Angger Rizky Firdaus')
+    st.write('From : HCK - 012')
+    st.write('Project ini adalah membuat project Natural Language Processing untuk Sentiment Analysis')
+    st.write('')
+    st.caption('Silahkan pilih menu di Select Box pada sebelah kiri layar :) ')
+    st.write('')
+    st.write('')
+
+elif navigasi == 'Model Prediksi':
+    model.run()
+else :
+    eda.run()

best_model.keras

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b61bcf44e5b2c87025a9c9cb45b6fc0b3085970ded0e0d4f1b00828658458320
+size 5851481

eda.py

@@ -0,0 +1,70 @@
+#Import library
+import pandas as pd 
+import numpy as np
+import streamlit as st 
+
+#library for visualization
+import matplotlib.pyplot as plt
+import seaborn as sns
+import plotly.express as px
+from wordcloud import WordCloud
+
+st.set_page_config(
+    page_title="Tweet Sentiment Pilkada 2017 EDA")
+#function untuk menjalakan streamlit model predictor
+def run():
+    # Set title
+    st.title('Tweet Sentiment Pilkada DKI Jakarta 2017 Dataset : Exploratory Data Analysis')
+
+
+
+    #pemisah(garis2)
+    st.markdown('----')
+
+    #image
+    st.image('https://images.bisnis.com/posts/2017/02/13/628337/foto.jpg')
+    st.text('desc : kertas pemilu kepala daerah DKI Jakarta 2017')
+    st.text('img source : bisnis.com')
+
+
+    #load dataset
+    df = pd.read_csv('dataset_tweet_sentiment_pilkada_DKI_2017.csv')
+
+    #title df
+    st.subheader('Tweet Sentiment Pilkada DKI Jakarta 2017 Dataframe')
+    #show dataframe in streamlit
+    st.dataframe(df.head(20))
+    st.markdown('----')
+
+    st.subheader('Exploratory Data Analysis (EDA)')
+
+
+    #visualisasi interaktif piechart
+    st.markdown('#### Visualisasi Pie Chart')
+    opsi2 = st.selectbox(' Choose the feature : ', ('Pasangan Calon', 'Sentiment'))
+    fig, ax = plt.subplots(figsize=(8, 8))
+    df[opsi2].value_counts().plot(kind='pie', autopct='%1.1f%%', ax=ax)
+    ax.set_title(f'{opsi2} Pie Chart')
+    ax.set_ylabel('')
+    st.pyplot(fig)
+    st.text(f'{opsi2} piechart')
+    if opsi2 == 'Pasangan Calon':
+        st.write('Dataset ini memiliki perbandingan jumlah tweet untuk setiap pasangan calon yang seimbang yaitu pada 33.3% untuk calon Ahok-Djarot, Agus-Sylvi, dan Anies-Sandi.')
+    else:
+        st.write('Dataset ini memiliki perbandingan jumlah sentimen positive dan negative yang seimbang yaitu 50% untuk sentimen positive dan negative. Dataset yang seimbang akan berdampak baik pada proses training data karena model akan mempelajari data dengan baik. ')
+
+    #visualisasi kolom kolom martial_status, education level, dan sex terhadap default status next month
+    # Ambil data teks dari DataFrame (misalnya eda['Text Tweet'])
+    all_tweets_text = ' '.join(df['Text Tweet'])
+
+    # Membuat WordCloud
+    wordcloud = WordCloud(width=800, height=400, background_color='white', min_font_size=10, max_words=8).generate(all_tweets_text)
+
+    # Menampilkan WordCloud menggunakan Streamlit
+    st.title("WordCloud of Tweets")
+    st.image(wordcloud.to_array(), use_column_width=True)
+    st.write('Berdasarkan visualisasi wordcloud diatas, berikut adalah 8 kata yang paling banyak muncul pada tweet di dataset ini seperti pilkadadki2017, yang, AHY, AniesSandi, dan, di, AhokDjarot,dan Ahok.')
+
+
+if __name__ == "__main__":
+    run()

model.py

@@ -0,0 +1,66 @@
+import streamlit as st
+import pandas as pd
+from keras.models import load_model
+import numpy as np
+import re
+from Sastrawi.Stemmer.StemmerFactory import StemmerFactory
+from nltk.tokenize import word_tokenize
+import tensorflow as tf
+
+st.set_page_config(
+    page_title="Indonesian Sentiment Analysis")
+stw = pd.read_csv('https://raw.githubusercontent.com/rizalespe/Dataset-Sentimen-Analisis-Bahasa-Indonesia/master/stopword_tweet_pilkada_DKI_2017.csv')
+stpwds_id = stw.values.tolist()
+stpwds_id.append(['ada'])
+stemmer = StemmerFactory().create_stemmer()
+model = tf.keras.models.load_model('best_model.keras')
+
+
+
+def run():
+    st.title("Indonesian Sentiment Analysis App")
+    st.image('https://i.pinimg.com/originals/52/ad/6a/52ad6a11c1dcb1692ff9e321bd520167.gif')
+    st.subheader("Enter text to analyze sentiment")
+
+    user_input = st.text_area("Input Text", "")
+    if st.button("Analyze"):
+        # Case folding
+        text1 = user_input.lower()
+        # Mention removal
+        text2 = re.sub("@[A-Za-z0-9_]+", " ", text1)
+        # Hashtags removal
+        text3 = re.sub("#[A-Za-z0-9_]+", " ", text2)
+        # Newline removal (\n)
+        text4 = re.sub(r"\\n", " ",text3)
+        # Whitespace removal
+        text5 = text4.strip()
+        # URL removal
+        text6 = re.sub(r"http\S+", " ", text5)
+        text7 = re.sub(r"www.\S+", " ", text6)
+        # Non-letter removal (such as emoticon, symbol (like μ, $, 兀), etc
+        text8 = re.sub("[^A-Za-z\s']", " ", text7)
+        # Tokenization
+        tokens = word_tokenize(text8)
+        # Stopwords removal
+        # tokens = [word for word in tokens if word not in stpwds_id]
+        tokens1 = []
+        for word in tokens:
+                    if word not in stpwds_id:
+                        tokens1.append(word)
+        # Stemming
+        #   tokens2 = [stemmer.stem(word) for word in tokens]
+        tokens2 = []
+        for word in tokens1:
+            tokens2.append(stemmer.stem(word))
+        # Combining Tokens
+        text8 = ' '.join(tokens2)
+        
+        pred = model.predict([[text8]])
+        if pred > 0.3:
+            sentiment = "Positive"
+        else:
+             sentiment = "Negative"
+        st.write(f"Sentiment: {sentiment}")
+
+if __name__ == "__main__":
+    run()

requirements.txt

@@ -0,0 +1,12 @@
+seaborn
+pandas
+matplotlib
+pickleshare
+tensorflow == 2.14.0
+keras == 2.14.0
+numpy
+plotly
+PySastrawi == 1.2.0
+nltk == 3.8.1
+re
+wordcloud