Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,40 +1,93 @@
-import altair as alt
-import numpy as np
-import pandas as pd
 import streamlit as st
+import pandas as pd
+import re
+import tensorflow as tf
+import tensorflow_hub as tf_hub
+from nltk.corpus import stopwords
+from nltk.tokenize import word_tokenize
+from tensorflow.keras.models import load_model
+from Sastrawi.Stemmer.StemmerFactory import StemmerFactory
+import nltk
+
+# Use /tmp for NLTK data (writable in Hugging Face Spaces)
+nltk_data_dir = "/tmp/nltk_data"
+nltk.data.path.append(nltk_data_dir)
+
+# Download the stopwords and punkt resources
+nltk.download('stopwords', download_dir=nltk_data_dir)
+nltk.download('punkt_tab', download_dir=nltk_data_dir)
+
+# Load the trained model
+model = tf.keras.models.load_model('src/model_final.keras',
+                                   custom_objects={'KerasLayer': tf_hub.KerasLayer})
+# Load stopwords
+# Define Stopwords
+stpwds_id = list(set(stopwords.words('indonesian')))
+stpwds_id.append('oh')
+
+# Define Stemming
+stemmer = StemmerFactory().create_stemmer()
+
+# Create A Function for Text Preprocessing
+
+def text_preprocessing(text):
+  # Case folding
+  text = text.lower()
+
+  # Mention removal
+  text = re.sub("@[A-Za-z0-9_]+", " ", text)
+
+  # Hashtags removal
+  text = re.sub("#[A-Za-z0-9_]+", " ", text)
+
+  # Newline removal (\n)
+  text = re.sub(r"\\n", " ",text)
+
+  # Whitespace removal
+  text = text.strip()
+
+  # URL removal
+  text = re.sub(r"http\S+", " ", text)
+  text = re.sub(r"www.\S+", " ", text)
+
+  # Non-letter removal (such as emoticon, symbol (like μ, $, 兀), etc
+  text = re.sub("[^A-Za-z\s']", " ", text)
+
+  # Tokenization
+  tokens = word_tokenize(text)
+
+  # Stopwords removal
+  tokens = [word for word in tokens if word not in stpwds_id]
+
+  # Stemming
+  tokens = [stemmer.stem(word) for word in tokens]
+
+  # Combining Tokens
+  text = ' '.join(tokens)
+
+  return text
+    
+hub_layer = tf_hub.KerasLayer(
+    "https://www.kaggle.com/models/google/nnlm/TensorFlow2/id-dim128-with-normalization/1",
+    input_shape=[],
+    dtype=tf.string,
+    trainable=False
+)
+# Define the Streamlit interface
+st.title('Sentiment Analysis App')
+
+# Get user input
+user_input = st.text_area("Enter the text for sentiment analysis:")
+
+if st.button('Analyze'):
+    if user_input:
+        # Preprocess the input text
+        processed_text = text_preprocessing(user_input)
+        data_inf = hub_layer([processed_text]) 
+        prediction = model.predict(data_inf)
+        sentiment = "Positive" if prediction[0] > 0.5 else "Negative"
 
-"""
-# Welcome to Streamlit!
-
-Edit `/streamlit_app.py` to customize this app to your heart's desire :heart:.
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
-
-In the meantime, below is an example of what you can do with just a few lines of code:
-"""
-
-num_points = st.slider("Number of points in spiral", 1, 10000, 1100)
-num_turns = st.slider("Number of turns in spiral", 1, 300, 31)
-
-indices = np.linspace(0, 1, num_points)
-theta = 2 * np.pi * num_turns * indices
-radius = indices
-
-x = radius * np.cos(theta)
-y = radius * np.sin(theta)
-
-df = pd.DataFrame({
-    "x": x,
-    "y": y,
-    "idx": indices,
-    "rand": np.random.randn(num_points),
-})
-
-st.altair_chart(alt.Chart(df, height=700, width=700)
-    .mark_point(filled=True)
-    .encode(
-        x=alt.X("x", axis=None),
-        y=alt.Y("y", axis=None),
-        color=alt.Color("idx", legend=None, scale=alt.Scale()),
-        size=alt.Size("rand", legend=None, scale=alt.Scale(range=[1, 150])),
-    ))
+        # Display the result
+        st.write(f"Sentiment: {sentiment}")
+    else:
+        st.write("Please enter some text.")