Update main.py

main.py

@@ -1,3 +1,171 @@
+# import streamlit as st
+# import pandas as pd
+# from app_config import AppConfig  # Import the configurations class
+# from data_processor import DataProcessor  # Import the data analysis class
+# from visualization import Visualization  # Import the data viz class
+# from ai_analysis import AIAnalysis  # Import the ai analysis class
+# from sidebar import Sidebar  # Import the Sidebar class
+
+
+# def main():
+#     # Initialize the app configuration
+#     app_config = AppConfig()
+
+#     # Initialize the sidebar
+#     sidebar = Sidebar()
+#     sidebar.display()
+
+#     # Initialize the data processor
+#     data_processor = DataProcessor()
+
+#     # Initialize the visualization handler
+#     visualization = Visualization()
+
+#     # Initialize the AI analysis handler
+#     ai_analysis = AIAnalysis(data_processor.client)
+
+#     st.title("Literacy Implementation Record Data Analysis")
+
+#     # Add the descriptive text
+#     st.markdown("""
+#     This tool summarizes implementation record data for student attendance, engagement, and intervention dosage to address hypothesis #1: Have Students Received Adequate Instruction?
+#     """)
+
+#     # Date selection option
+#     date_option = st.radio(
+#         "Select data range:",
+#         ("All Data", "Date Range")
+#     )
+
+#     # Initialize start and end date variables
+#     start_date = None
+#     end_date = None
+
+#     if date_option == "Date Range":
+#         # Prompt user to enter start and end dates
+#         start_date = st.date_input("Start Date")
+#         end_date = st.date_input("End Date")
+
+#         # Ensure start date is before end date
+#         if start_date > end_date:
+#             st.error("Start date must be before end date.")
+#             return
+
+#     # File uploader
+#     uploaded_file = st.file_uploader("Upload your Excel file", type=["xlsx"])
+
+#     if uploaded_file is not None:
+#         try:
+#             # Read the Excel file into a DataFrame
+#             df = data_processor.read_excel(uploaded_file)
+
+#             # Format the session data
+#             df = data_processor.format_session_data(df)
+
+#             # Replace student names with initials
+#             df = data_processor.replace_student_names_with_initials(df)
+
+#             # Filter data if date range is selected
+#             if date_option == "Date Range":
+#                 # Convert start_date and end_date to datetime
+#                 start_date = pd.to_datetime(start_date).date()
+#                 end_date = pd.to_datetime(end_date).date()
+
+#                 # Filter the DataFrame based on the selected date range
+#                 df = df[(df['Date of Session'] >= start_date) & (df['Date of Session'] <= end_date)]
+
+
+#             st.subheader("Uploaded Data")
+#             st.write(df)
+
+#             # Ensure expected column is available
+#             if DataProcessor.INTERVENTION_COLUMN not in df.columns:
+#                 st.error(f"Expected column '{DataProcessor.INTERVENTION_COLUMN}' not found.")
+#                 return
+
+            
+#             #MOVE
+#             # Compute Intervention Session Statistics
+#             intervention_stats = data_processor.compute_intervention_statistics(df)
+#             st.subheader("Intervention Dosage")
+#             st.write(intervention_stats)
+
+#             # Plot and download intervention statistics
+#             # intervention_fig = visualization.plot_intervention_statistics(intervention_stats)
+#             # visualization.download_chart(intervention_fig, "intervention_statistics_chart.png")
+
+#             # Plot and download intervention statistics: Two-column layout for the visualization and intervention frequency
+#             col1, col2 = st.columns([3, 1])  # Set the column width ratio
+            
+#             with col1:
+#                 intervention_fig = visualization.plot_intervention_statistics(intervention_stats)
+            
+#             with col2:
+#                 intervention_frequency = intervention_stats['Intervention Dosage (%)'].values[0]
+#                 # Display the "Intervention Frequency (%)" text
+#                 st.markdown("<h3 style='color: #358E66;'>Intervention Dosage</h3>", unsafe_allow_html=True)
+#                 # Display the frequency value below it
+#                 st.markdown(f"<h1 style='color: #358E66;'>{intervention_frequency}%</h1>", unsafe_allow_html=True)
+
+#             visualization.download_chart(intervention_fig, "intervention_statistics_chart.png")
+            
+#             # Compute Student Metrics
+#             student_metrics_df = data_processor.compute_student_metrics(df)
+#             st.subheader("Student Attendance and Engagement")
+#             st.write(student_metrics_df)
+
+#             # Compute Student Metric Averages
+#             attendance_avg_stats, engagement_avg_stats = data_processor.compute_average_metrics(student_metrics_df)
+
+#             # Plot and download student metrics
+#             student_metrics_fig = visualization.plot_student_metrics(student_metrics_df, attendance_avg_stats, engagement_avg_stats)
+#             visualization.download_chart(student_metrics_fig, "student_metrics_chart.png")
+
+#             # Evaluate each student and build decision tree diagrams
+#             student_metrics_df['Evaluation'] = student_metrics_df.apply(
+#                 lambda row: data_processor.evaluate_student(row), axis=1
+#             )
+#             st.subheader("Student Evaluations")
+#             st.write(student_metrics_df[['Student', 'Evaluation']])
+            
+#             # # Build and display decision tree diagrams for each student
+#             # for index, row in student_metrics_df.iterrows():
+#             #     tree_diagram = visualization.build_tree_diagram(row)
+#             #     st.graphviz_chart(tree_diagram.source)
+
+#             # Build and display decision tree diagrams for each student
+#             for index, row in student_metrics_df.iterrows():
+#                 tree_diagram = visualization.build_tree_diagram(row)
+                
+#                 # Get the student's name from the DataFrame
+#                 student_name = row['Student']
+                
+#                 # Use st.expander to wrap the graphviz chart with the student's name
+#                 with st.expander(f"{student_name} Decision Tree", expanded=False):
+#                     st.graphviz_chart(tree_diagram.source)
+            
+#             # Prepare input for the language model
+#             llm_input = ai_analysis.prepare_llm_input(student_metrics_df)
+
+#             # Generate Notes and Recommendations using Hugging Face LLM
+#             with st.spinner("Generating AI analysis..."):
+#                 recommendations = ai_analysis.prompt_response_from_hf_llm(llm_input)
+
+#             st.subheader("AI Analysis")
+#             st.markdown(recommendations)
+
+#             # Download AI output
+#             ai_analysis.download_llm_output(recommendations, "llm_output.txt")
+
+#         except Exception as e:
+#             st.error(f"Error processing the file: {str(e)}")
+
+# if __name__ == '__main__':
+#     main()
+
+
+
+
 import streamlit as st
 import pandas as pd
 from app_config import AppConfig  # Import the configurations class
@@ -71,44 +239,44 @@ def main():
                 start_date = pd.to_datetime(start_date).date()
                 end_date = pd.to_datetime(end_date).date()
 
-                # Filter the DataFrame based on the selected date range
-                df = df[(df['Date of Session'] >= start_date) & (df['Date of Session'] <= end_date)]
-
+                # Identify the date column
+                date_column = next((col for col in df.columns if col in ["Date of Session", "Date"]), None)
+                if date_column:
+                    # Filter the DataFrame based on the selected date range
+                    df = df[(df[date_column] >= start_date) & (df[date_column] <= end_date)]
+                else:
+                    st.error("Date column not found in the data.")
+                    return
 
             st.subheader("Uploaded Data")
             st.write(df)
 
-            # Ensure expected column is available
-            if DataProcessor.INTERVENTION_COLUMN not in df.columns:
-                st.error(f"Expected column '{DataProcessor.INTERVENTION_COLUMN}' not found.")
+            # Ensure the intervention column is determined
+            intervention_column = data_processor.get_intervention_column(df)
+            if intervention_column not in df.columns:
+                st.error(f"Expected column '{intervention_column}' not found.")
                 return
 
-            
-            #MOVE
             # Compute Intervention Session Statistics
             intervention_stats = data_processor.compute_intervention_statistics(df)
             st.subheader("Intervention Dosage")
             st.write(intervention_stats)
 
-            # Plot and download intervention statistics
-            # intervention_fig = visualization.plot_intervention_statistics(intervention_stats)
-            # visualization.download_chart(intervention_fig, "intervention_statistics_chart.png")
-
             # Plot and download intervention statistics: Two-column layout for the visualization and intervention frequency
             col1, col2 = st.columns([3, 1])  # Set the column width ratio
-            
+
             with col1:
                 intervention_fig = visualization.plot_intervention_statistics(intervention_stats)
-            
+
             with col2:
                 intervention_frequency = intervention_stats['Intervention Dosage (%)'].values[0]
-                # Display the "Intervention Frequency (%)" text
+                # Display the "Intervention Dosage (%)" text
                 st.markdown("<h3 style='color: #358E66;'>Intervention Dosage</h3>", unsafe_allow_html=True)
                 # Display the frequency value below it
                 st.markdown(f"<h1 style='color: #358E66;'>{intervention_frequency}%</h1>", unsafe_allow_html=True)
 
             visualization.download_chart(intervention_fig, "intervention_statistics_chart.png")
-            
+
             # Compute Student Metrics
             student_metrics_df = data_processor.compute_student_metrics(df)
             st.subheader("Student Attendance and Engagement")
@@ -127,23 +295,18 @@ def main():
             )
             st.subheader("Student Evaluations")
             st.write(student_metrics_df[['Student', 'Evaluation']])
-            
-            # # Build and display decision tree diagrams for each student
-            # for index, row in student_metrics_df.iterrows():
-            #     tree_diagram = visualization.build_tree_diagram(row)
-            #     st.graphviz_chart(tree_diagram.source)
 
             # Build and display decision tree diagrams for each student
             for index, row in student_metrics_df.iterrows():
                 tree_diagram = visualization.build_tree_diagram(row)
-                
+
                 # Get the student's name from the DataFrame
                 student_name = row['Student']
-                
+
                 # Use st.expander to wrap the graphviz chart with the student's name
                 with st.expander(f"{student_name} Decision Tree", expanded=False):
                     st.graphviz_chart(tree_diagram.source)
-            
+
             # Prepare input for the language model
             llm_input = ai_analysis.prepare_llm_input(student_metrics_df)