Upload 6 files

eda.py

@@ -2,10 +2,8 @@ import streamlit as st
 import pandas as pd
 import matplotlib.pyplot as plt
 import seaborn as sns
-import nltk
-nltk.download('stopwords')
-from nltk.corpus import stopwords
-from wordcloud import WordCloud
+# from nltk.corpus import stopwords
+# from wordcloud import WordCloud
 
 def app():
   df_original = pd.read_csv("data.csv", delimiter=";")
@@ -15,17 +13,17 @@ def app():
   temp_a = df.copy()
   temp_a['text_length'] = temp_a['text'].apply(len)
   st.header('Exploratory Data Analysis', divider='rainbow')
-  eda_list = ["Text Length Distribution", "Sentiment Distribution", "Word Clouds", "Boxplot Distributions"]
+  eda_list = ["Text Length Distribution", "Sentiment Distribution", "Word Clouds", "Stopwords Boxplot Distributions"]
   val = st.sidebar.radio("Choose plot to show", eda_list)
-  stop_words = set(stopwords.words('english'))
-  def plot_wordcloud(sentiment):
-    text = ' '.join(df[df['feeling'] == sentiment]['text'])
-    wordcloud = WordCloud(stopwords=stop_words, background_color='white').generate(text)
-    plt.figure(figsize=(10, 6))
-    plt.imshow(wordcloud, interpolation='bilinear')
-    plt.axis('off')
-    plt.title(f"Word Cloud for {sentiment} Sentiment")
-    st.pyplot(plt)
+  # stop_words = set(stopwords.words('english'))
+  # def plot_wordcloud(sentiment):
+  #   text = ' '.join(df[df['feeling'] == sentiment]['text'])
+  #   wordcloud = WordCloud(stopwords=stop_words, background_color='white').generate(text)
+  #   plt.figure(figsize=(10, 6))
+  #   plt.imshow(wordcloud, interpolation='bilinear')
+  #   plt.axis('off')
+  #   plt.title(f"Word Cloud for {sentiment} Sentiment")
+  #   st.pyplot(plt)
   if val == "Text Length Distribution":
     # Plot distribution
     st.header('Text Length Distribution')
@@ -55,9 +53,18 @@ def app():
     st.pyplot(plt)
     st.write("Insight: surprise sentiment has the lowest value of around 900 data")
   elif val == "Word Clouds":
-    plot_wordcloud('joy')
-    plot_wordcloud('sadness')
-    plot_wordcloud('anger')
-    plot_wordcloud('love')
-    plot_wordcloud('surprise')
-    plot_wordcloud('fear')
+    # plot_wordcloud('joy')
+    # plot_wordcloud('sadness')
+    # plot_wordcloud('anger')
+    # plot_wordcloud('love')
+    # plot_wordcloud('surprise')
+    # plot_wordcloud('fear')
+    pass
+  elif val == "Stopwords Boxplot Distributions":
+    temp_b = df.copy()
+    temp_b['stopword_count'] = temp_b['text'].apply(lambda x: sum(1 for word in x.split() if word.lower() in stop_words))
+
+    # 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)

prediction.py

@@ -0,0 +1,39 @@
+import streamlit as st
+import pandas as pd
+import numpy as np
+import tensorflow as tf
+import tensorflow_hub as tf_hub
+
+number_to_feeling = {
+  '0': 'sadness',
+  '1': 'anger',
+  '2': 'love',
+  '3': 'surprise',
+  '4': 'fear',
+  '5': 'joy'
+}
+
+def get_feeling(number):
+  # Convert the number to string to match the keys in the dictionary
+  feeling = number_to_feeling.get(str(number), "Unknown feeling")
+  return feeling
+
+def app():
+  st.header('Prediction', divider='rainbow')
+
+  user_input = st.text_input("Enter your text here:")
+  the_model = tf.keras.models.load_model('model.keras', custom_objects={'KerasLayer': tf_hub.KerasLayer})
+  if st.button('Predict', type="secondary"):
+    data = {
+      "text_processed": [
+          user_input
+      ]
+    }
+    df = pd.DataFrame(data)
+    predictions = 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!")