Upload 6 files

eda.py

@@ -35,7 +35,7 @@ def app():
     plt.xlabel('Text Length (characters)')
     plt.ylabel('Frequency')
     st.pyplot(plt)
-    st.write("Insight: the numerical values in our data are all normal distributions.")
+    st.write("Insight: text length distribution of our data appears to be right-skewed.")
   elif val == "Sentiment Distribution":
     sentiment_counts = df['feeling'].value_counts()
     st.header('Sentiment Distribution')
@@ -55,6 +55,7 @@ def app():
     st.pyplot(plt)
     st.write("Insight: surprise sentiment has the lowest value of around 900 data")
   elif val == "Word Clouds":
+    plt.title('Word Clouds')
     plot_wordcloud('joy')
     plot_wordcloud('sadness')
     plot_wordcloud('anger')
@@ -69,4 +70,5 @@ def app():
     # Plot stopword count distribution by sentiment
     sns.boxplot(data=temp_b, x='feeling', y='stopword_count')
     plt.title('Stopword Count by Sentiment')
-    st.pyplot(plt)
+    st.pyplot(plt)
+    st.write("Insight: each sentiment has quite a number of stop words outliers")

prediction.py

@@ -21,26 +21,27 @@ def get_feeling(number):
 def load_model():
     return tf.keras.models.load_model('model.keras', custom_objects={'KerasLayer': tf_hub.KerasLayer})
 
+st.session_state.the_model = load_model()
+
 def app():
   st.header('Prediction', divider='rainbow')
 
   user_input = st.text_input("Enter your text here:")
   if 'the_model' not in st.session_state:
     with st.spinner("Loading the model, please wait..."):
-        st.session_state.the_model = load_model()
-  if st.button('Predict', type="secondary"):
-    data = {
-      "text_processed": [
-          user_input
-      ]
-    }
-    df = pd.DataFrame(data)
-    with st.spinner("Making prediction..."):
-      # Replace with your preprocessing and prediction code
-      predictions = st.session_state.the_model.predict(df)
-      predicted_class = np.argmax(predictions, axis=1)
-      the_sentiment = predicted_class[0]
+      if st.button('Predict', type="secondary"):
+        data = {
+          "text_processed": [
+              user_input
+          ]
+        }
+        df = pd.DataFrame(data)
+        with st.spinner("Making prediction..."):
+          # Replace with your preprocessing and prediction code
+          predictions = st.session_state.the_model.predict(df)
+          predicted_class = np.argmax(predictions, axis=1)
+          the_sentiment = predicted_class[0]
 
-      st.write(f"We have predicted that the sentiment of this text is {get_feeling(the_sentiment)}")
-  else:
-    st.write("Click the button to predict!")
+          st.write(f"We have predicted that the sentiment of this text is {get_feeling(the_sentiment)}")
+      else:
+        st.write("Click the button to predict!")