import streamlit as st import pandas as pd import numpy as np from preprocessing import TextPreprocessor from model import MisconceptionClassifier from visualization import ResultVisualizer from sklearn.model_selection import train_test_split # Page config st.set_page_config( page_title="Math Misconception Analyzer", layout="wide" ) # Initialize components @st.cache_resource def load_preprocessor(): return TextPreprocessor() @st.cache_resource def load_model(): return MisconceptionClassifier.load_model() preprocessor = load_preprocessor() model = load_model() visualizer = ResultVisualizer() # Main interface st.title("Mathematical Misconception Analyzer") st.write(""" This tool analyzes student responses to identify mathematical misconceptions using advanced NLP techniques. Upload your data to get detailed insights about common misconceptions and patterns. """) # Tabs for different functionalities tab1, tab2, tab3 = st.tabs(["Analyze New Data", "Model Retraining", "Quick Analysis"]) with tab1: # File upload for analysis uploaded_file = st.file_uploader("Upload CSV file for analysis", type=['csv'], key='analysis_upload') if uploaded_file is not None: try: # Load and display data df = pd.read_csv(uploaded_file) st.subheader("Data Preview") st.dataframe(df.head()) # Column selection text_column = st.selectbox( "Select the column containing student responses", df.columns ) label_column = st.selectbox( "Select the column containing misconception labels (if available)", ['None'] + list(df.columns) ) if st.button("Analyze"): with st.spinner("Processing data..."): # Extract features with advanced NLP features = preprocessor.extract_features(df, text_column) # Show feature analysis st.subheader("Text Analysis") col1, col2, col3 = st.columns(3) with col1: st.metric("Average Response Length", f"{features['text_length'].mean():.1f} words") with col2: st.metric("Mathematical Terms Density", f"{features['math_density'].mean():.2f}") with col3: st.metric("Total Responses", len(df)) # Show topic modeling results if available if hasattr(preprocessor, 'topic_keywords'): st.subheader("Topic Analysis") topic_fig = visualizer.plot_topic_distribution( features, preprocessor.topic_keywords ) if topic_fig: st.plotly_chart(topic_fig) # Train model if labels are available if label_column != 'None': # Check if we have enough data if len(df) < 4: st.warning("Dataset is too small for reliable model training. Please provide more samples.") st.stop() X_train, X_test, y_train, y_test = train_test_split( df[text_column], df[label_column], test_size=0.2, random_state=42 ) # Train and evaluate model with st.spinner("Training model..."): model.train(X_train, y_train) predictions = model.predict(X_test) probabilities = model.predict_proba(X_test) metrics = model.get_model_metrics() # Display results st.subheader("Model Performance") # Show cross-validation results if available cv_results = visualizer.plot_model_metrics(metrics) if cv_results is not None: if isinstance(cv_results, tuple): for fig in cv_results: st.plotly_chart(fig) else: st.plotly_chart(cv_results) # Show prediction distribution and confidence col1, col2 = st.columns(2) with col1: st.plotly_chart( visualizer.plot_misconception_distribution( pd.Series(predictions) ) ) with col2: st.plotly_chart( visualizer.plot_confidence_scores( probabilities, model.pipeline.classes_ ) ) # Show embedding clusters st.subheader("Response Embedding Analysis") embeddings = np.array([preprocessor.get_document_embedding(text) for text in X_test]) embedding_fig = visualizer.plot_embedding_clusters( embeddings, y_test ) if embedding_fig is not None: st.plotly_chart(embedding_fig) else: st.info("Not enough samples for meaningful embedding visualization. More data is needed for this analysis.") # Feature importance st.subheader("Feature Importance Analysis") st.plotly_chart( visualizer.plot_feature_importance( model.get_feature_importance() ) ) # Show detailed metrics st.subheader("Classification Report") report_df = pd.DataFrame(metrics['classification_report']).T st.dataframe(report_df) else: st.warning("No labels provided. Only preprocessing results available.") st.write("Extracted Features:") st.dataframe(features) except Exception as e: st.error(f"Error processing file: {str(e)}") with tab2: st.header("Model Retraining") st.write(""" Upload additional labeled data to retrain the model and improve its performance. The model will be updated with the new data while maintaining its existing knowledge. """) # Training history st.subheader("Training History") history_fig = visualizer.plot_training_history(model.get_training_history()) if history_fig: st.plotly_chart(history_fig) else: st.info("No training history available yet.") # File upload for retraining retrain_file = st.file_uploader("Upload CSV file for retraining", type=['csv'], key='retrain_upload') if retrain_file is not None: try: # Load new data new_data = pd.read_csv(retrain_file) st.write("New Training Data Preview:") st.dataframe(new_data.head()) # Column selection for retraining text_col = st.selectbox( "Select the column containing student responses", new_data.columns, key='retrain_text_col' ) label_col = st.selectbox( "Select the column containing misconception labels", new_data.columns, key='retrain_label_col' ) if st.button("Retrain Model"): with st.spinner("Retraining model with new data..."): # Split new data X_new_train, X_new_test, y_new_train, y_new_test = train_test_split( new_data[text_col], new_data[label_col], test_size=0.2, random_state=42 ) # Retrain model model.train(X_new_train, y_new_train, is_retraining=True) # Save updated model model.save_model() # Evaluate on new test data new_predictions = model.predict(X_new_test) new_probabilities = model.predict_proba(X_new_test) new_metrics = model.get_model_metrics() # Show updated performance st.subheader("Updated Model Performance") # Show cross-validation results cv_results = visualizer.plot_model_metrics(new_metrics) if cv_results is not None: if isinstance(cv_results, tuple): for fig in cv_results: st.plotly_chart(fig) else: st.plotly_chart(cv_results) # Show updated training history st.subheader("Updated Training History") updated_history_fig = visualizer.plot_training_history(model.get_training_history()) if updated_history_fig: st.plotly_chart(updated_history_fig) st.success("Model successfully retrained and saved!") except Exception as e: st.error(f"Error during retraining: {str(e)}") with tab3: st.header("Quick Misconception Analysis") st.write(""" Enter a student's response to analyze potential mathematical misconceptions. The model will identify the type of misconception and provide confidence scores. """) # Single response analysis student_response = st.text_area( "Enter student response", placeholder="Example: When multiplying decimals, more decimal places means bigger number" ) if st.button("Analyze Response"): if student_response: with st.spinner("Analyzing response..."): # Get prediction and probability prediction = model.predict([student_response])[0] probabilities = model.predict_proba([student_response])[0] # Show results st.subheader("Analysis Results") # Show detected misconception with high emphasis st.markdown(f""" ### Detected Misconception: **{prediction}** """) # Show confidence scores st.subheader("Confidence Scores") probs_df = pd.DataFrame({ 'Misconception Type': model.pipeline.classes_, 'Confidence': probabilities }).sort_values('Confidence', ascending=False) st.dataframe(probs_df) # Extract features for insight features = preprocessor.preprocess_text(student_response) # Show key mathematical elements detected st.subheader("Key Mathematical Elements Detected") col1, col2, col3 = st.columns(3) with col1: st.metric("Numbers Found", features['numbers_found']) with col2: st.metric("Operations Found", features['operations_found']) with col3: st.metric("Math Terms", features['math_terms_found']) else: st.warning("Please enter a student response to analyze.") # Sample data with st.expander("Sample Data Format"): st.write(""" Upload a CSV file with the following columns: - student_response: Text responses from students - misconception_label: Category of mathematical misconception (optional) Example misconception categories: - number_properties - decimal_operations - fraction_operations - fraction_comparison - decimal_comparison """) sample_data = pd.DataFrame({ 'student_response': [ "I think negative numbers can't have square roots", "When multiplying decimals, more decimal places means bigger number", "Adding fractions means adding numerators and denominators separately", "The larger the denominator, the larger the fraction", "0.1 is greater than 0.9 because 1 is less than 9" ], 'misconception_label': [ 'number_properties', 'decimal_operations', 'fraction_operations', 'fraction_comparison', 'decimal_comparison' ] }) st.dataframe(sample_data)