Upload 12 files

.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
+model_gru_2/variables/variables.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,10 @@
+import streamlit as st
+import eda
+import prediction
+
+page = st.sidebar.selectbox('Pilih Halaman : ', ('Dashboard', 'Prediction'))
+
+if page == 'Dashboard' : 
+    eda.run()
+else:
+    prediction.run()

eda.py

@@ -0,0 +1,135 @@
+import streamlit as st
+import pandas as pd
+import seaborn as sns
+import matplotlib.pyplot as plt
+import plotly.express as px
+from PIL import Image
+
+def run():
+    #Membuat title
+    st.title('Text-Based Twitter Sentiment Analysis')
+
+    #Tambahkan gambar
+    image = Image.open('twittersentiment.jpg')
+    st.image(image, caption = 'Twitter Sentiment')
+
+    #Membuat garis
+    st.markdown('----')
+
+    #Masukkan pandas dataframe
+
+    #Show dataframe
+    df = pd.read_csv('tweets-update.csv')
+    st.dataframe(df)
+    st.write('Source : https://www.kaggle.com/datasets/yasserh/twitter-tweets-sentiment-dataset')
+
+    st.markdown('----')
+    st.title('Exploratory Data Analysis')
+    #Bar Plot
+    st.write('#### Distribution of Sentiments')
+    fig_sentiments = plt.figure(figsize=(10, 6))
+    sns.countplot(x='sentiment', data=df)
+    plt.xlabel('Sentiment Label')
+    plt.ylabel('Count')
+    plt.title('Distribution of Sentiments')
+    st.pyplot(fig_sentiments)
+
+    # Positive Sentiment Tweets Bar
+    st.write('#### Distribution of Text Length for Positive Sentiment Tweets')
+    fig_length_positive = plt.figure(figsize=(14, 7))
+
+    # Handle NaN values in 'text_processed'
+    df['length'] = df['text_processed'].apply(lambda x: len(str(x).split()) if pd.notna(x) else 0)
+
+    ax1 = fig_length_positive.add_subplot(122)
+    sns.histplot(df[df['sentiment']=='positive']['length'], ax=ax1, color='green')
+    describe_positive = df.length[df.sentiment=='positive'].describe().to_frame().round(2)
+
+    ax2 = fig_length_positive.add_subplot(121)
+    ax2.axis('off')
+    font_size = 14
+    bbox = [0, 0, 1, 1]
+    table_positive = ax2.table(cellText=describe_positive.values, rowLabels=describe_positive.index, bbox=bbox, colLabels=describe_positive.columns)
+    table_positive.set_fontsize(font_size)
+    fig_length_positive.suptitle('Distribution of text length for positive sentiment tweets.', fontsize=16)
+
+    st.pyplot(fig_length_positive)
+
+    # negative Sentiment Tweets Bar
+    st.write('#### Distribution of Text Length for negative Sentiment Tweets')
+    fig_length_negative = plt.figure(figsize=(14, 7))
+
+    # Handle NaN values in 'text_processed'
+    df['length'] = df['text_processed'].apply(lambda x: len(str(x).split()) if pd.notna(x) else 0)
+
+    ax1 = fig_length_negative.add_subplot(122)
+    sns.histplot(df[df['sentiment']=='negative']['length'], ax=ax1, color='red')
+    describe_negative = df.length[df.sentiment=='negative'].describe().to_frame().round(2)
+
+    ax2 = fig_length_negative.add_subplot(121)
+    ax2.axis('off')
+    font_size = 14
+    bbox = [0, 0, 1, 1]
+    table_negative = ax2.table(cellText=describe_negative.values, rowLabels=describe_negative.index, bbox=bbox, colLabels=describe_negative.columns)
+    table_negative.set_fontsize(font_size)
+    fig_length_negative.suptitle('Distribution of text length for negative sentiment tweets.', fontsize=16)
+
+    st.pyplot(fig_length_negative)
+
+    # neutral Sentiment Tweets Bar
+    st.write('#### Distribution of Text Length for neutral Sentiment Tweets')
+    fig_length_neutral = plt.figure(figsize=(14, 7))
+
+    # Handle NaN values in 'text_processed'
+    df['length'] = df['text_processed'].apply(lambda x: len(str(x).split()) if pd.notna(x) else 0)
+
+    ax1 = fig_length_neutral.add_subplot(122)
+    sns.histplot(df[df['sentiment']=='neutral']['length'], ax=ax1, color='blue')
+    describe_neutral = df.length[df.sentiment=='neutral'].describe().to_frame().round(2)
+
+    ax2 = fig_length_neutral.add_subplot(121)
+    ax2.axis('off')
+    font_size = 14
+    bbox = [0, 0, 1, 1]
+    table_neutral = ax2.table(cellText=describe_neutral.values, rowLabels=describe_neutral.index, bbox=bbox, colLabels=describe_neutral.columns)
+    table_neutral.set_fontsize(font_size)
+    fig_length_neutral.suptitle('Distribution of text length for neutral sentiment tweets.', fontsize=16)
+
+    st.pyplot(fig_length_neutral)
+
+    # Membuat pie chart
+    st.write('#### Pie Chart - Sentiment Distribution')
+    labels = ['Neutral', 'Positive', 'Negative']
+    size = df['sentiment'].value_counts()
+    colors = ['lightgreen', 'lightskyblue', 'lightcoral']
+    explode = [0.01, 0.01, 0.1]
+
+    fig, axes = plt.subplots(figsize=(6, 5))
+    plt.pie(size, colors=colors, explode=explode,
+            labels=labels, shadow=True, startangle=90, autopct='%.2f%%')
+    plt.title('Sentiment Distribution', fontsize=20)
+    plt.legend()
+
+    st.pyplot(fig)
+    # #Membuat histogram
+    # st.write('#### Histogram of Age')
+    # fig = plt.figure(figsize=(15,5))
+    # sns.histplot(df['Overall'], bins = 30, kde = True)
+    # st.pyplot(fig)
+
+    # #membuat histogram berdasarkan inputan user
+    # st.write('#### Histogram berdasarkan input user')
+    # #kalo mau pake radio button, ganti selectbox jadi radio
+    # option = st.selectbox('Pilih Column : ', ('Age', 'Weight', 'Height', 'ShootingTotal'))
+    # fig = plt.figure(figsize= (15,5))
+    # sns.histplot(df[option], bins = 30, kde = True)
+    # st.pyplot(fig)
+
+    # #Membuat Plotly plot
+
+    # st.write('#### Plotly Plot - ValueEUR vs Overall')
+    # fig = px.scatter(df, x = 'ValueEUR', y = 'Overall', hover_data = ['Name', 'Age'])
+    # st.plotly_chart(fig)
+
+if __name__ == '__main__':
+    run()

model_gru_2/fingerprint.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:389fc4a0ba65798fd60fae3ddb562d50ee7ff0de8c3640a8afecc76f1a69bd39
+size 55

model_gru_2/keras_metadata.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5c87c818d04c895d135b4cce0cfc2f03ad071938411898c7986fbcf95e1c591
+size 26812

model_gru_2/saved_model.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edddd288d1bba93e83dd2b36b46b39f7a48f9713ffbc8b8a8c8b511240ecf4fc
+size 3542856

model_gru_2/variables/variables.data-00000-of-00001

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e27d92803de5105255153e03a804dd7aafbc1573ae96f938a8ac59161c12f5a
+size 498765088

prediction.py

@@ -0,0 +1,44 @@
+import streamlit as st
+import numpy as np
+from keras.models import load_model
+from PIL import Image
+from tensorflow.keras.preprocessing.sequence import pad_sequences
+
+# Load the GRU model
+model = load_model('model_gru_2')
+
+def run():
+
+    image = Image.open('twittersentiment.jpg')
+    st.image(image, caption = 'Twitter Sentiment')
+    
+    with st.form('sentiment_prediction'):
+        # Field Input Text
+        input_text = st.text_area('Input Text', '', help='Enter the text for sentiment prediction')
+        
+        # Create a submit button
+        submitted = st.form_submit_button('Predict')
+
+    # Inference
+    if submitted:
+        # Make a prediction using the model
+        # Convert the input text to lowercase (optional)
+        input_text = input_text.lower()
+
+        # Make a prediction using the model
+        predictions = model.predict(np.array([input_text]))
+
+        # Map predicted class to labels
+        predicted_class = np.argmax(predictions[0])
+        class_labels = {0: 'Negative', 1: 'Positive', 2: 'Neutral'}
+        predicted_label = class_labels[predicted_class]
+
+        # Display the results
+        st.write('## Sentiment Prediction:')
+        st.write('Input Text:', input_text)
+        st.write('Predicted Class:', predicted_class)
+        st.write('Predicted Label:', predicted_label)
+        st.write('Prediction Probabilities:', predictions[0])
+
+if __name__ == '__main__':
+    run()

requirements.txt

@@ -0,0 +1,8 @@
+streamlit
+pandas
+seaborn
+matplotlib
+numpy
+plotly
+pillow
+scikit-learn==1.3.2