Create app.py

app.py

@@ -0,0 +1,55 @@
+import streamlit as st
+import nltk
+from nltk.corpus import stopwords
+from nltk.tokenize import word_tokenize
+from nltk.probability import FreqDist
+import matplotlib.pyplot as plt
+
+
+def process_text(text):
+    # Tokenize the text
+    tokens = word_tokenize(text)
+
+    # Remove stopwords
+    stop_words = set(stopwords.words("english"))
+    filtered_tokens = [word for word in tokens if word.lower() not in stop_words]
+
+    # Calculate word frequency
+    fdist = FreqDist(filtered_tokens)
+
+    # Get the top 10 most common words
+    top_words = fdist.most_common(10)
+
+    return top_words
+
+
+def main():
+    st.title("NLTK Graph Visualization")
+
+    # Upload file
+    uploaded_file = st.file_uploader("Upload a text file", type=["txt"])
+
+    if uploaded_file is not None:
+        # Read file contents
+        text = uploaded_file.read().decode("utf-8")
+
+        # Process the text
+        top_words = process_text(text)
+
+        # Plot word frequency graph
+        words, frequencies = zip(*top_words)
+        plt.bar(words, frequencies)
+        plt.xticks(rotation=45)
+        plt.xlabel("Words")
+        plt.ylabel("Frequency")
+        plt.title("Top 10 Most Common Words")
+        st.pyplot()
+
+        # Display the top words
+        st.subheader("Top 10 Most Common Words")
+        for word, frequency in top_words:
+            st.write(f"- {word}: {frequency}")
+
+
+if __name__ == "__main__":
+    main()