Update app.py

app.py

@@ -1,7 +1,10 @@
 import streamlit as st
 import pandas as pd
 import sqlite3
+import tempfile
+from fpdf import FPDF
 import os
+import re
 import json
 from pathlib import Path
 import plotly.express as px
@@ -83,6 +86,214 @@ if st.session_state.df is not None and st.session_state.show_preview:
     st.subheader("📂 Dataset Preview")
     st.dataframe(st.session_state.df.head())
 
+# Ask GPT-4o for Visualization Suggestions
+def ask_gpt4o_for_visualization(query, df, llm):
+    columns = ', '.join(df.columns)
+    prompt = f"""
+    Analyze the query and suggest the best visualization.
+    Query: "{query}"
+    Available Columns: {columns}
+    Respond in this JSON format:
+    {{
+      "chart_type": "bar/box/line/scatter",
+      "x_axis": "column_name",
+      "y_axis": "column_name",
+      "group_by": "optional_column_name"
+    }}
+    """
+    response = llm.generate(prompt)
+    try:
+        return json.loads(response)
+    except json.JSONDecodeError:
+        st.error("⚠️ GPT-4o failed to generate a valid suggestion.")
+        return None
+
+# Dynamically generate Plotly visualizations based on GPT-4o suggestions
+def generate_visualization(suggestion, df):
+    chart_type = suggestion.get("chart_type", "bar").lower()
+    x_axis = suggestion.get("x_axis")
+    y_axis = suggestion.get("y_axis")
+    group_by = suggestion.get("group_by")
+
+    # Ensure required inputs are available
+    if not x_axis or not y_axis:
+        st.warning("⚠️ GPT-4o did not provide enough information for the visualization.")
+        return None
+
+    # Dynamically select the Plotly function
+    plotly_function = getattr(px, chart_type, None)
+
+    # Handle unsupported chart types gracefully
+    if not plotly_function:
+        st.warning(f"⚠️ Unsupported chart type '{chart_type}' suggested by GPT-4o.")
+        return None
+
+    # Prepare dynamic parameters for Plotly function
+    plot_args = {
+        "data_frame": df,
+        "x": x_axis,
+        "y": y_axis,
+    }
+    if group_by:
+        plot_args["color"] = group_by
+
+    try:
+        # Generate the dynamic visualization
+        fig = plotly_function(**plot_args)
+        fig.update_layout(
+            title=f"{chart_type.title()} Plot of {y_axis.replace('_', ' ').title()} by {x_axis.replace('_', ' ').title()}",
+            xaxis_title=x_axis.replace('_', ' ').title(),
+            yaxis_title=y_axis.replace('_', ' ').title(),
+        )
+        return fig
+
+    except Exception as e:
+        st.error(f"⚠️ Failed to generate visualization: {e}")
+        return None
+
+# Function to create TXT file
+def create_text_report_with_viz_temp(report, conclusion, visualizations):
+    content = f"### Analysis Report\n\n{report}\n\n### Visualizations\n"
+
+    for i, fig in enumerate(visualizations, start=1):
+        fig_title = fig.layout.title.text if fig.layout.title.text else f"Visualization {i}"
+        x_axis = fig.layout.xaxis.title.text if fig.layout.xaxis.title.text else "X-axis"
+        y_axis = fig.layout.yaxis.title.text if fig.layout.yaxis.title.text else "Y-axis"
+
+        content += f"\n{i}. {fig_title}\n"
+        content += f"   - X-axis: {x_axis}\n"
+        content += f"   - Y-axis: {y_axis}\n"
+
+        if fig.data:
+            trace_types = set(trace.type for trace in fig.data)
+            content += f"   - Chart Type(s): {', '.join(trace_types)}\n"
+        else:
+            content += "   - No data available in this visualization.\n"
+
+    content += f"\n\n\n{conclusion}"
+
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".txt", mode='w', encoding='utf-8') as temp_txt:
+        temp_txt.write(content)
+        return temp_txt.name
+
+
+def add_stats_to_figure(fig, df, y_axis, chart_type):
+    # Calculate statistics
+    min_val = df[y_axis].min()
+    max_val = df[y_axis].max()
+    avg_val = df[y_axis].mean()
+    median_val = df[y_axis].median()
+    std_dev_val = df[y_axis].std()
+
+    # Stats summary text
+    stats_text = (
+        f"📊 **Statistics**\n\n"
+        f"- **Min:** ${min_val:,.2f}\n"
+        f"- **Max:** ${max_val:,.2f}\n"
+        f"- **Average:** ${avg_val:,.2f}\n"
+        f"- **Median:** ${median_val:,.2f}\n"
+        f"- **Std Dev:** ${std_dev_val:,.2f}"
+    )
+
+    # Charts suitable for stats annotations
+    if chart_type in ["bar", "line", "scatter"]:
+        # Add annotation box
+        fig.add_annotation(
+            text=stats_text,
+            xref="paper", yref="paper",
+            x=1.05, y=1,
+            showarrow=False,
+            align="left",
+            font=dict(size=12, color="black"),
+            bordercolor="black",
+            borderwidth=1,
+            bgcolor="rgba(255, 255, 255, 0.8)"
+        )
+
+        # Add horizontal lines for min, median, avg, max
+        fig.add_hline(y=min_val, line_dash="dot", line_color="red", annotation_text="Min", annotation_position="bottom right")
+        fig.add_hline(y=median_val, line_dash="dash", line_color="orange", annotation_text="Median", annotation_position="top right")
+        fig.add_hline(y=avg_val, line_dash="dashdot", line_color="green", annotation_text="Avg", annotation_position="top right")
+        fig.add_hline(y=max_val, line_dash="dot", line_color="blue", annotation_text="Max", annotation_position="top right")
+
+    elif chart_type == "box":
+        # Box plots already show distribution (no extra stats needed)
+        pass
+
+    elif chart_type == "pie":
+        # Pie charts don't need statistical overlays
+        st.info("📊 Pie charts focus on proportions. No additional stats displayed.")
+    
+    else:
+        st.warning(f"⚠️ No stats added for unsupported chart type: {chart_type}")
+
+    return fig
+
+
+# Function to create PDF with report text and visualizations
+def create_pdf_report_with_viz(report, conclusion, visualizations):
+    pdf = FPDF()
+    pdf.set_auto_page_break(auto=True, margin=15)
+    pdf.add_page()
+    pdf.set_font("Arial", size=12)
+
+    # Title
+    pdf.set_font("Arial", style="B", size=18)
+    pdf.cell(0, 10, "📊 Analysis Report", ln=True, align="C")
+    pdf.ln(10)
+
+    # Report Content
+    pdf.set_font("Arial", style="B", size=14)
+    pdf.cell(0, 10, "Analysis", ln=True)
+    pdf.set_font("Arial", size=12)
+    pdf.multi_cell(0, 10, report)
+
+    pdf.ln(10)
+    pdf.set_font("Arial", style="B", size=14)
+    pdf.cell(0, 10, "Conclusion", ln=True)
+    pdf.set_font("Arial", size=12)
+    pdf.multi_cell(0, 10, conclusion)
+
+    # Add Visualizations
+    pdf.add_page()
+    pdf.set_font("Arial", style="B", size=16)
+    pdf.cell(0, 10, "📈 Visualizations", ln=True)
+    pdf.ln(5)
+
+    with tempfile.TemporaryDirectory() as temp_dir:
+        for i, fig in enumerate(visualizations, start=1):
+            fig_title = fig.layout.title.text if fig.layout.title.text else f"Visualization {i}"
+            x_axis = fig.layout.xaxis.title.text if fig.layout.xaxis.title.text else "X-axis"
+            y_axis = fig.layout.yaxis.title.text if fig.layout.yaxis.title.text else "Y-axis"
+
+            # Save each visualization as a PNG image
+            img_path = os.path.join(temp_dir, f"viz_{i}.png")
+            fig.write_image(img_path)
+
+            # Insert Title and Description
+            pdf.set_font("Arial", style="B", size=14)
+            pdf.multi_cell(0, 10, f"{i}. {fig_title}")
+            pdf.set_font("Arial", size=12)
+            pdf.multi_cell(0, 10, f"X-axis: {x_axis} | Y-axis: {y_axis}")
+            pdf.ln(3)
+
+            # Embed Visualization
+            pdf.image(img_path, w=170)
+            pdf.ln(10)
+
+        # Save PDF
+        temp_pdf = tempfile.NamedTemporaryFile(delete=False, suffix=".pdf")
+        pdf.output(temp_pdf.name)
+
+    return temp_pdf
+
+def escape_markdown(text):
+    # Ensure text is a string
+    text = str(text)
+    # Escape Markdown characters: *, _, `, ~
+    escape_chars = r"(\*|_|`|~)"
+    return re.sub(escape_chars, r"\\\1", text)
+
 # SQL-RAG Analysis
 if st.session_state.df is not None:
     temp_dir = tempfile.TemporaryDirectory()
@@ -208,31 +419,17 @@ if st.session_state.df is not None:
                 st.markdown(report_result if report_result else "⚠️ No Report Generated.")
 
                 # Step 4: Generate Visualizations
-                visualizations = []
-
-                fig_salary = px.box(st.session_state.df, x="job_title", y="salary_in_usd",
-                                    title="Salary Distribution by Job Title")
-                visualizations.append(fig_salary)
-
-                fig_experience = px.bar(
-                    st.session_state.df.groupby("experience_level")["salary_in_usd"].mean().reset_index(),
-                    x="experience_level", y="salary_in_usd",
-                    title="Average Salary by Experience Level"
-                )
-                visualizations.append(fig_experience)
 
-                fig_employment = px.box(st.session_state.df, x="employment_type", y="salary_in_usd",
-                                        title="Salary Distribution by Employment Type")
-                visualizations.append(fig_employment)
 
                 # Step 5: Insert Visual Insights
                 st.markdown("### Visual Insights")
-                for fig in visualizations:
-                    st.plotly_chart(fig, use_container_width=True)
+
 
                 # Step 6: Display Concise Conclusion
                 #st.markdown("#### Conclusion")
-                st.markdown(conclusion_result if conclusion_result else "⚠️ No Conclusion Generated.")
+
+                safe_conclusion = escape_markdown(conclusion_result if conclusion_result else "⚠️ No Conclusion Generated.")
+                st.markdown(safe_conclusion)
 
     # Full Data Visualization Tab
     with tab2:
@@ -262,4 +459,3 @@ with st.sidebar:
     st.header("📚 Reference:")
     st.markdown("[SQL Agents w CrewAI & Llama 3 - Plaban Nayak](https://github.com/plaban1981/Agents/blob/main/SQL_Agents_with_CrewAI_and_Llama_3.ipynb)")
 
-