Create app.py

app.py

@@ -0,0 +1,160 @@
+import streamlit as st
+import pandas as pd
+from transformers import pipeline
+import re
+
+# Model configurations
+MODELS = {
+    "English": "MarieAngeA13/Sentiment-Analysis-BERT",
+    "Danish": "larskjeldgaard/senda"
+}
+
+# Page config
+st.set_page_config(
+    page_title="Multi-language Sentiment Analyzer",
+    page_icon="🎭",
+    layout="wide"
+)
+
+# Load custom CSS
+with open('style.css') as f:
+    st.markdown(f'<style>{f.read()}</style>', unsafe_allow_html=True)
+
+def process_sentiment(text, pipeline):
+    """Process sentiment for a single text entry"""
+    try:
+        result = pipeline(str(text))
+        # Convert sentiment to lowercase
+        return result[0]['label'].lower(), result[0]['score']
+    except Exception as e:
+        st.warning(f"Error processing text: {text[:50]}... Error: {str(e)}")
+        return "unknown", 0.0
+
+# App layout
+col1, col2, col3 = st.columns([1, 2, 1])
+with col2:
+    st.title("🎭 Multi-language Sentiment Analysis")
+    
+    selected_language = st.selectbox(
+        "Select Language",
+        options=list(MODELS.keys()),
+        index=0
+    )
+    
+    st.markdown("""
+        <div class="privacy-notice">
+            ⚠️ <b>Privacy Notice:</b> Your data is processed in memory and not stored.
+        </div>
+        """, unsafe_allow_html=True)
+
+    uploaded_file = st.file_uploader("Upload a CSV file with text", type=["csv"])
+
+    if uploaded_file:
+        try:
+            df = pd.read_csv(uploaded_file)
+            if "text" not in df.columns:
+                st.error("CSV must contain a 'text' column")
+            else:
+                with st.spinner(f"📊 Analyzing sentiments in {selected_language}..."):
+                    def clean_transcript_text(text):
+                        speaker_timestamp_pattern = r'Speaker: Speaker [A-Z], Start Time: \d+\.\d+ - End Time: \d+\.\d+'
+                        timestamp_pattern = r'Start Time: \d+\.\d+ - End Time: \d+\.\d+'
+                        cleaned_text = re.sub(speaker_timestamp_pattern, '', text)
+                        if cleaned_text == text:
+                            cleaned_text = re.sub(timestamp_pattern, '', text)
+                        cleaned_text = re.sub(r'\s+', ' ', cleaned_text)
+                        return cleaned_text.strip()
+                    
+                    df['cleaned_text'] = df['text'].apply(clean_transcript_text)
+
+                    sentiment_pipeline = pipeline(
+                        "text-classification",
+                        model=MODELS[selected_language],
+                        truncation=True,
+                        max_length=512
+                    )
+                    
+                    results = [process_sentiment(text, sentiment_pipeline) for text in df["cleaned_text"]]
+                    df["sentiment"] = [r[0] for r in results]
+                    df["confidence"] = [r[1] for r in results]
+
+                    st.markdown("### 📈 Analysis Results")
+                    
+                    # Fix the sentiment counting logic
+                    if selected_language == 'English':
+                        pos_count = len(df[df["sentiment"] == "positive"])
+                        neu_count = len(df[df["sentiment"] == "neutral"])
+                        neg_count = len(df[df["sentiment"] == "negative"])
+                    else:  # Danish
+                        pos_count = len(df[df["sentiment"] == "positiv"])
+                        neu_count = len(df[df["sentiment"] == "neutral"])
+                        neg_count = len(df[df["sentiment"] == "negativ"])
+
+                    metric_col1, metric_col2, metric_col3, metric_col4 = st.columns(4)
+                    
+                    with metric_col1:
+                        st.metric(
+                            "Positive Sentiments",
+                            f"{pos_count} ({pos_count/len(df)*100:.1f}%)"
+                        )
+                    with metric_col2:
+                        st.metric(
+                            "Neutral Sentiments",
+                            f"{neu_count} ({neu_count/len(df)*100:.1f}%)"
+                        )
+                    with metric_col3:
+                        st.metric(
+                            "Negative Sentiments",
+                            f"{neg_count} ({neg_count/len(df)*100:.1f}%)"
+                        )
+                    with metric_col4:
+                        st.metric(
+                            "Average Confidence",
+                            f"{df['confidence'].mean():.1%}"
+                        )
+
+                    st.markdown("#### Preview")
+                    
+                    preview_df = df[["cleaned_text", "sentiment", "confidence"]].head()
+                    preview_df["confidence"] = preview_df["confidence"].apply(lambda x: f"{x:.1%}")
+                    
+                    def highlight_sentiment(val):
+                        if val in ["positive", "positiv"]:
+                            return 'background-color: rgba(0, 255, 0, 0.2)'
+                        elif val in ["negative", "negativ"]:
+                            return 'background-color: rgba(255, 0, 0, 0.2)'
+                        elif val == "neutral":
+                            return 'background-color: rgba(128, 128, 128, 0.2)'
+                        return ''
+                    
+                    st.dataframe(
+                        preview_df.style.applymap(highlight_sentiment, subset=['sentiment']),
+                        use_container_width=True
+                    )
+
+                    st.markdown("### 💾 Download Results")
+                    csv_data = df.to_csv(index=False)
+                    st.download_button(
+                        label="Download Complete Analysis",
+                        data=csv_data,
+                        file_name=f"sentiment_results_{selected_language.lower()}.csv",
+                        mime="text/csv"
+                    )
+
+        except Exception as e:
+            st.error(f"Error processing file: {str(e)}")
+            st.error("Full error details:")
+            st.code(str(e))
+    else:
+        st.markdown("""
+            <div class="instructions">
+                <h4>📝 How to use:</h4>
+                <ol>
+                    <li>Select your desired language</li>
+                    <li>Prepare a CSV file with a column named "text"</li>
+                    <li>Upload your file using the button above</li>
+                    <li>Wait for the analysis to complete</li>
+                    <li>Download the results with sentiment labels</li>
+                </ol>
+            </div>
+            """, unsafe_allow_html=True)