Update app.py

app.py

@@ -15,8 +15,7 @@ hf_sentiment_analyzer = pipeline(
 
 def analyze_hf_sentiment(text):
     if len(text) > 512:
-        temp = text[:511]
-        text = temp
+        text = text[:511]
     result = hf_sentiment_analyzer(text)
     label = result[0]["label"]
     if label == "LABEL_1":
@@ -65,14 +64,6 @@ def display_pie_chart(df, column):
     ax.axis("equal")
     st.pyplot(fig)
 
-    # Add a download button
-    if st.button('Download Pie Chart'):
-        # Save the pie chart as an image file
-        plt.savefig('pie_chart.png')
-        
-        # Offer the image file for download
-        st.download_button(label='Download Pie Chart Image', data=open('pie_chart.png', 'rb').read(), file_name='pie_chart.png', mime='image/png')
-
 # Function to display word cloud
 def display_wordcloud(text_data):
     wordcloud = WordCloud(width=800, height=400, background_color="white").generate(
@@ -83,14 +74,6 @@ def display_wordcloud(text_data):
     ax.axis("off")
     st.pyplot(fig)
 
-    # Add a download button
-    if st.button('Download Word Cloud'):
-        # Save the word cloud as an image file
-        plt.savefig('word_cloud.png')
-        
-        # Offer the image file for download
-        st.download_button(label='Download Word Cloud Image', data=open('word_cloud.png', 'rb').read(), file_name='word_cloud.png', mime='image/png')
-
 # Function to download CSV file
 def download_csv(df):
     csv = df.to_csv(index=False)
@@ -98,366 +81,55 @@ def download_csv(df):
     href = f'<a href="data:file/csv;base64,{b64}" download="sentiment_analysis_results.csv">Download CSV File</a>'
     st.markdown(href, unsafe_allow_html=True)
 
-# Function to count occurrences of keywords and sentiment distribution
-def count_reviews_with_keywords(df,keywords):
-    # keywords=['logistics', 'supply chain', 'cargo', 'shipment', 'freight', 'package', 'tracking']
-    keyword_counts = {keyword: {"Positive": 0, "Negative": 0, "Total": 0} for keyword in keywords}
-
-    for _, row in df.iterrows():
-        review_text = row["review_text"]
-        sentiment = row["Sentiment"]
-
-        for keyword in keywords:
-            if keyword.lower() in review_text.lower():
-                keyword_counts[keyword]["Total"] += 1
-                if sentiment == "Positive":
-                    keyword_counts[keyword]["Positive"] += 1
-                elif sentiment == "Negative":
-                    keyword_counts[keyword]["Negative"] += 1
-
-    return keyword_counts
-
-
 # Streamlit UI
-st.set_page_config(page_title="SentimentAnalysis App", page_icon=":smiley:")
-st.title("SentimentAnalysis App")
+st.set_page_config(page_title="Sentiment Analysis App", page_icon=":smiley:")
+st.title("Sentiment Analysis App")
 
 # Sidebar
 st.sidebar.title("Options")
-input_option = st.sidebar.radio("Select Input Option", ("Free Text", "CSV Files"))
-selected_model = st.sidebar.radio(
-    "Select Sentiment Analysis Model", ("VADER", "TextBlob", "Hugging Face")
+input_option = st.sidebar.select_slider("Select Input Option", options=["Free Text", "CSV Files"])
+selected_model = st.sidebar.select_slider(
+    "Select Sentiment Analysis Model", options=["VADER", "TextBlob", "Hugging Face"]
 )
-result_option = st.sidebar.radio(
+result_option = st.sidebar.select_slider(
     "Select Result Display Option",
-    ("DataFrame", "Pie Chart", "Bar Chart", "Keyword Frequency", "WordCloud", "Comparative Sentiment Analysis"),
+    options=["DataFrame", "Pie Chart", "Bar Chart", "Keyword Frequency", "Word Cloud", "Comparative Sentiment Analysis"],
 )
 
 # Main content
-progress_label = st.empty()  # Define progress label
-progress_bar = st.progress(0)
-progress = 0
-
-# Directory path to store processed files
-processed_directory = "processed_files"
-
-# Ensure the directory exists, if not create it
-os.makedirs(processed_directory, exist_ok=True)
-
-# List to store processed filenames
-processed_files = []
-
-# Function to get filenames from the processed directory
-def get_processed_filenames():
-    return [
-        f
-        for f in os.listdir(processed_directory)
-        if os.path.isfile(os.path.join(processed_directory, f))
-    ]
-
 if input_option == "Free Text":
     st.subheader("Enter review for sentiment analysis:")
-    user_input = st.text_area("", "")
-    if not user_input:
-        st.info("Enter some text above for sentiment analysis.")
-    else:
-        with st.spinner("Analyzing..."):
-            if selected_model == "Hugging Face":
-                result = analyze_hf_sentiment(user_input)
-            elif selected_model == "VADER":
-                result = analyze_vader_sentiment(user_input)
-            elif selected_model == "TextBlob":
-                result = analyze_textblob_sentiment(user_input)
-        st.write("Sentiment:", result)
+    user_input = st.text_input("", placeholder="Enter your text here")
+    if st.button('Analyze'):
+        if user_input:
+            with st.spinner("Analyzing..."):
+                if selected_model == "Hugging Face":
+                    result = analyze_hf_sentiment(user_input)
+                elif selected_model == "VADER":
+                    result = analyze_vader_sentiment(user_input)
+                elif selected_model == "TextBlob":
+                    result = analyze_textblob_sentiment(user_input)
+            st.write("Sentiment:", result)
+        else:
+            st.error("Please enter some text to analyze.")
 
 if input_option == "CSV Files":
-    st.subheader("Select CSV files for sentiment analysis:")
-
-    # Uploading new file
-    files = st.file_uploader(
-        "Upload New File", type=["csv"], accept_multiple_files=True
-    )
-    if files:
-        # Process uploaded new files
-        for file in files:
-            if file.type != "text/csv":
-                st.warning(
-                    "Uploaded file is not a CSV file. Please upload a CSV file only."
-                )
-            else:
-                df = pd.read_csv(file)
-                if "review_text" not in df.columns:
-                    st.warning(
-                        "Uploaded CSV file doesn't contain 'review_text' column. Please check the CSV file format."
-                    )
+    st.subheader("Upload CSV files for sentiment analysis:")
+    uploaded_files = st.file_uploader("Choose a CSV file", accept_multiple_files=True)
+    if st.button('Start Analysis'):
+        if uploaded_files:
+            for uploaded_file in uploaded_files:
+                df = pd.read_csv(uploaded_file)
+                if 'review_text' in df.columns:
+                    df['Sentiment'] = df['review_text'].apply(lambda x: analyze_hf_sentiment(x) if selected_model == "Hugging Face" else (analyze_vader_sentiment(x) if selected_model == "VADER" else analyze_textblob_sentiment(x)))
+                    if result_option == "DataFrame":
+                        display_dataframe(df)
+                    elif result_option == "Pie Chart":
+                        display_pie_chart(df, 'Sentiment')
+                    elif result_option == "Word Cloud":
+                        combined_text = ' '.join(df['review_text'])
+                        display_wordcloud(combined_text)
                 else:
-                    total_rows = len(df)
-
-                    sentiments_v = []
-                    sentiments_tb = []
-                    sentiments_hf = []
-
-                    for review_text in df["review_text"]:
-                        sentiments_v.append(analyze_vader_sentiment(review_text))
-                        sentiments_tb.append(analyze_textblob_sentiment(review_text))
-                        sentiments_hf.append(analyze_hf_sentiment(review_text))
-                        progress += 1
-                        progress_label.text(f"{progress}/{total_rows}")
-                        progress_bar.progress(min(progress / total_rows, 1.0))
-
-                    df["VADER Sentiment"] = sentiments_v
-                    df["TextBlob Sentiment"] = sentiments_tb
-                    df["HuggingFace Sentiment"] = sentiments_hf
-
-                    # Save processed file with modified filename
-                    new_filename = os.path.splitext(file.name)[0] + "1.csv"
-                    df.to_csv(
-                        os.path.join(processed_directory, new_filename), index=False
-                    )
-                    st.success(f"New file processed and saved as {new_filename}")
-
-    # List of already processed files
-    processed_files = get_processed_filenames()
-    selected_files = st.multiselect("Select from Processed Files", processed_files)
-
-    if not files and not selected_files:
-        st.info(
-            "Upload a new CSV file or select from processed files above for sentiment analysis."
-        )
-
-    all_dfs = []
-
-    # Process already selected files
-    for file_name in selected_files:
-        df = pd.read_csv(os.path.join(processed_directory, file_name))
-        all_dfs.append(df)
-
-    # Results
-    if all_dfs:
-        combined_df = pd.concat(all_dfs, ignore_index=True)
-        if selected_model == "TextBlob":
-            result = "TextBlob Sentiment"
-            combined_df.drop(
-                columns=["VADER Sentiment", "HuggingFace Sentiment"],
-                inplace=True,
-            )
-        elif selected_model == "VADER":
-            result = "VADER Sentiment"
-            combined_df.drop(
-                columns=["TextBlob Sentiment", "HuggingFace Sentiment"],
-                inplace=True,
-            )
-        elif selected_model == "Hugging Face":
-            result = "HuggingFace Sentiment"
-            combined_df.drop(
-                columns=["TextBlob Sentiment", "VADER Sentiment"],
-                inplace=True,
-            )
-        combined_df.rename(columns={result: "Sentiment"}, inplace=True)
-
-        if result_option == "DataFrame":
-            st.subheader("Sentiment Analysis Results")
-            display_dataframe(combined_df)
-            download_csv(combined_df)
-        elif result_option == "Pie Chart":
-            st.subheader("Sentiment Distribution")
-            display_pie_chart(combined_df, "Sentiment")
-        elif result_option == "Bar Chart":
-            # Calculate value counts
-            sentiment_counts = combined_df["Sentiment"].value_counts()
-            # Display bar chart
-            st.bar_chart(sentiment_counts)
-
-            # Add a download button
-            if st.button('Download Sentiment Counts Chart'):
-                # Plot the bar chart
-                fig, ax = plt.subplots()
-                sentiment_counts.plot(kind='bar', ax=ax)
-                plt.xlabel('Sentiment')
-                plt.ylabel('Count')
-                plt.title('Sentiment Counts')
-                plt.xticks(rotation=45, ha='right')
-                plt.tight_layout()
-                
-                # Save the bar chart as an image file
-                plt.savefig('sentiment_counts_chart.png')
-                
-                # Offer the image file for download
-                st.download_button(label='Download Sentiment Counts Chart Image', data=open('sentiment_counts_chart.png', 'rb').read(), file_name='sentiment_counts_chart.png', mime='image/png')
-
-        elif result_option == "Keyword Frequency":
-            st.subheader("Keyword Frequency")
-
-            # List of keywords
-            keywords = [
-                "delivery",
-                "shipping",
-                "parcel",
-                "package",
-                "tracking",
-                "shipment",
-                "cargo",
-                "freight",
-                "automation",
-                "automated",
-                "robotic",
-                "robots",
-                "AI",
-                "artificial intelligence",
-                "machine learning",
-                "chatbot",
-                "virtual assistant",
-                "customer support",
-                "real-time",
-                "instant",
-                "live update",
-                "status",
-                "IoT",
-                "internet of things",
-                "connected devices",
-                "smart technology",
-                "blockchain",
-                "ledger",
-                "transparency",
-                "security",
-                "sustainability",
-                "eco-friendly",
-                "green logistics",
-                "carbon footprint",
-                "customer service",
-                "support",
-                "experience",
-                "satisfaction",
-                "data analytics",
-                "big data",
-                "analysis",
-                "insights",
-                "cloud computing",
-                "cloud-based",
-                "digital infrastructure",
-                "storage",
-                "5G",
-                "connectivity",
-                "network speed",
-                "wireless",
-                "drone",
-                "aerial delivery",
-                "UAV",
-                "drone shipping",
-                "augmented reality",
-                "AR",
-                "virtual reality",
-                "VR",
-                "3D printing",
-                "additive manufacturing",
-                "custom parts",
-                "prototyping",
-                "inventory management",
-                "stock levels",
-                "warehouse management",
-                "storage solutions",
-                "supply chain",
-                "logistics",
-                "supply network",
-                "distribution",
-                "eco-packaging",
-                "sustainable materials",
-                "recycling",
-                "waste reduction",
-                "digital platform",
-                "e-commerce",
-                "online shopping",
-                "online order",
-                "cybersecurity",
-                "data protection",
-                "privacy",
-                "encryption",
-                "predictive modeling",
-                "forecasting",
-                "demand planning",
-                "trend analysis",
-                "robotics",
-                "automated vehicles",
-                "self-driving cars",
-                "logistics automation",
-                "visibility",
-                "supply chain visibility",
-                "track and trace",
-                "monitoring",
-                "integration",
-                "ERP",
-                "supply chain integration",
-                "software",
-                "optimization",
-                "efficiency",
-                "process improvement",
-                "lean logistics",
-                "personalization",
-                "customization",
-                "tailored services",
-                "personal touch",
-                "ethical sourcing",
-                "fair trade",
-                "labor rights",
-                "ethical business",
-                "user experience",
-                "UX",
-                "customer journey",
-                "service design",
-                "visibility",
-            ]
-            text_data = " ".join(combined_df["review_text"])
-            keyword_frequency = (
-                pd.Series(text_data.split()).value_counts().reset_index()
-            )
-            keyword_frequency.columns = ["Keyword", "Frequency"]
-
-            # Filter keyword frequency for specific keywords
-            filtered_keyword_frequency = keyword_frequency[
-                keyword_frequency["Keyword"].isin(keywords)
-            ]
-
-            # Display bar chart for filtered keyword frequency
-            st.bar_chart(filtered_keyword_frequency.set_index("Keyword"))
-
-             # Add a download button
-            if st.button('Download Keyword Frequency Chart'):
-                # Plot the bar chart
-                fig, ax = plt.subplots()
-                filtered_keyword_frequency.plot(kind='bar', x='Keyword', y='Frequency', ax=ax)
-                plt.xticks(rotation=45, ha='right')
-                plt.tight_layout()
-                
-                # Save the bar chart as an image file
-                plt.savefig('keyword_frequency_chart.png')
-                
-                # Offer the image file for download
-                st.download_button(label='Download Keyword Frequency Chart Image', data=open('keyword_frequency_chart.png', 'rb').read(), file_name='keyword_frequency_chart.png', mime='image/png')
-        elif result_option == "Word Cloud":
-            st.subheader("Word Cloud")
-            text_data = " ".join(combined_df["review_text"])
-            display_wordcloud(text_data)
+                    st.error("CSV must contain 'review_text' column.")
         else:
-            st.subheader("Comparative Sentiment Analysis")            
-            supply_chain_areas = {
-                'logistics': ['logistics', 'supply chain', 'cargo', 'shipment', 'freight', 'package', 'tracking'],
-                'delivery': ['delivery', 'shipping', 'courier', 'postal', 'parcel'],
-                'inventory': ['inventory', 'stock', 'storage', 'warehouse', 'security’'],
-                'customer service': ['customer service', 'support', 'helpdesk', 'service center', 'experience', 'refund'],
-                'procurement': ['procurement', 'sourcing', 'purchasing', 'buying', 'order'],
-                'distribution': ['distribution', 'supply network', 'distribution center'],
-                'manufacturing': ['manufacturing', 'production', 'assembly', 'quality', 'defect']
-            }
-
-            supply_chain_area = st.sidebar.radio(
-                "Select Supply Chain Area",
-                ("logistics", "delivery", "inventory", "customer service", "procurement", "distribution","manufacturing"),
-            )
-            # Call the function to count occurrences of keywords and sentiment distribution
-            keyword_counts = count_reviews_with_keywords(combined_df,supply_chain_areas[supply_chain_area])
-
-            # Convert keyword_counts to DataFrame
-            df_counts = pd.DataFrame(keyword_counts).transpose()
-
-            # Plot dual bar chart horizontally
-            st.bar_chart(df_counts[["Positive", "Negative"]], use_container_width=True, height=500)            
+            st.error("Please upload a CSV file.")