Update app.py

app.py

@@ -2,6 +2,12 @@ import streamlit as st
 import pandas as pd
 import datetime
 import io
+import nltk
+from nltk.tokenize import sent_tokenize
+from sklearn.feature_extraction.text import CountVectorizer
+from sklearn.decomposition import LatentDirichletAllocation
+
+nltk.download('punkt')
 
 def save_text_as_file(text, file_type):
     current_time = datetime.datetime.now().strftime("%Y%m%d_%H%M%S")
@@ -21,41 +27,38 @@ def save_csv_as_excel(text):
             file_name = f"csv_without_header_{datetime.datetime.now().strftime('%Y%m%d_%H%M%S')}.xlsx"
         df.to_excel(file_name, index=False, header=header)
         st.success(f"CSV data saved as {file_name}")
+        st.dataframe(df)
     except pd.errors.EmptyDataError:
         st.error("The pasted text does not contain valid CSV data.")
 
-def create_demo_excel_file():
-    data = {
-        "Name": ["John", "Alice", "Bob"],
-        "Age": [25, 30, 35],
-        "City": ["New York", "London", "Paris"]
-    }
-    df = pd.DataFrame(data)
-    file_name = "demo_excel_file.xlsx"
-    df.to_excel(file_name, index=False)
-    st.success(f"Demo Excel file created: {file_name}")
+def split_sentences(text):
+    sentences = sent_tokenize(text)
+    return "\n".join(sentences)
 
-def main():
-    st.title("AI UI for Text Processing")
+def perform_nlp(text):
+    sentences = sent_tokenize(text)
+    
+    # Topic Modeling
+    vectorizer = CountVectorizer(stop_words='english')
+    X = vectorizer.fit_transform(sentences)
+    lda = LatentDirichletAllocation(n_components=3, random_state=42)
+    lda.fit(X)
+    topics = lda.transform(X)
     
-    st.markdown("""
-    ## Pandas Cheat Sheet
+    # Display topics
+    st.subheader("Topic Modeling")
+    for i, topic in enumerate(topics):
+        st.write(f"Topic {i+1}:")
+        topic_words = ", ".join([vectorizer.get_feature_names_out()[i] for i in topic.argsort()[:-6:-1]])
+        st.write(topic_words)
     
-    | Lesson | Code Example |
-    |--------|-------------|
-    | 1. Import xlsx | `df = pd.read_excel('data.xlsx')` |
-    | 2. Export xlsx | `df.to_excel('output.xlsx', index=False)` |
-    | 3. Create DataFrame | `df = pd.DataFrame(data)` |
-    | 4. Apply function to DataFrame | `df['Column'] = df['Column'].apply(lambda x: x.capitalize())` |
-    | 5. Reduce columns | `df = df[['Column1', 'Column2']]` |
-    | 6. Aggregate data | `df_agg = df.groupby('Column').mean()` |
-    | 7. Create Plotly graph | `fig = px.bar(df, x='Column1', y='Column2')` |
-    | 8. Map values | `df['Column'] = df['Column'].map({'Old': 'New'})` |
-    | 9. Capitalize column | `df['Column'] = df['Column'].str.capitalize()` |
-    | 10. Filter DataFrame | `df_filtered = df[df['Column'] > 10]` |
-    | 11. Sort DataFrame | `df_sorted = df.sort_values('Column')` |
-    | 12. Merge DataFrames | `df_merged = pd.merge(df1, df2, on='Column')` |
-    """)
+    # Word Frequency
+    word_freq = pd.Series(" ".join(sentences).split()).value_counts()[:10]
+    st.subheader("Word Frequency")
+    st.bar_chart(word_freq)
+
+def main():
+    st.title("AI UI for Text Processing")
     
     text_input = st.text_area("Paste your text here")
     if st.button("Process Text"):
@@ -64,15 +67,13 @@ def main():
         else:
             if "," in text_input or "\t" in text_input:
                 save_csv_as_excel(text_input)
-            elif text_input.startswith("#") or text_input.startswith("- "):
-                save_text_as_file(text_input, "md")
-            elif "def" in text_input or "import" in text_input:
-                save_text_as_file(text_input, "py")
+            elif "." in text_input or "!" in text_input or "?" in text_input:
+                sentences = split_sentences(text_input)
+                st.subheader("Sentences")
+                st.write(sentences)
+                perform_nlp(text_input)
             else:
                 save_text_as_file(text_input, "txt")
-    
-    if st.button("Create Demo Excel File"):
-        create_demo_excel_file()
 
 if __name__ == "__main__":
     main()