Update streamlit_app.py

src/streamlit_app.py

@@ -15,6 +15,200 @@ def get_pyg_renderer(df: pd.DataFrame):
 
 pipe = getPipeline()
 
+def FileSummaryHelper(df: pd.DataFrame) -> str:
+    """Gathers basiline information about the dataset"""
+    
+    colSummaries = []
+
+    for col in df:
+        colSummaries.append(f"'{col}' | Data Type: {df[col].dtype} | Missing Percentage: {df[col].isna().mean()*100:.2f}%")
+    colTypesAndNulls = "\n".join(colSummaries)
+
+    duplicateVals = df.duplicated(keep=False).sum()
+    totalVals = len(df)
+
+    return f"""
+    The columns of the data have the following datatypes and missing value percentages:
+    {colTypesAndNulls}
+    
+    The dataset has {totalVals} total rows.
+    
+    The dataset has {duplicateVals} duplicated rows.
+    """
+    
+def FileDescriptionAgent(userDesc:str, df: pd.DataFrame) -> str:
+    """Generates a description of the contents of the file based on initial analysis."""
+    
+    userDesc = "" if not userDesc else "I have described the dataset as follows: " + userDesc
+    fileSummary = FileSummaryHelper(df)
+    
+    prompt = f""" You are given a DataFrame `df` with columns: {', '.join(df.columns.tolist())}
+    {fileSummary}
+    {userDesc}
+    
+    Qualitatively describe the dataset in 2-3 concise sentences. Your response must only include the description with no explanations before or after."""
+    
+    messages = [
+       {"role": "system", "content": \
+           "detailed thinking off. You are an insightful Data Analyst."},
+       {"role": "user","content":prompt}
+    ]
+    
+    response = pipe(messages, temperature = 0.2, max_new_tokens = 1024, return_full_text=False)[0]['generated_text']
+    
+    return response
+
+def AnlaysisQuestionAgent(summary:str):
+        
+    messages = [
+        {"role": "system", "content": \
+            """detailed thinking off. You are an inquisitive Data Analyst.
+            Given the following summary of a dataset, create a list of 3 analytical questions, following these rules:
+            
+            Rules
+            -----
+            1. The questions must be answerable through simple Pandas operations with only the given data.
+            2. Your response must only include the three questions in a numbered list. Do not include explanations or caveats before or after.
+            3. Ensure the output list is formated: 1. question1, 2. question2, 3. question3
+            """},
+        {"role":"user","content":summary}
+    ]
+
+    response = pipe(messages, temperature = 0.2, max_new_tokens = 1024, return_full_text=False)[0]['generated_text']
+    
+    parts = re.split(r'\d+\.\s*', response)
+
+    result = [p.strip() for p in parts if p]
+    
+    return result
+
+def CodeGeneratorTool(cols: List[str], query: str) -> str:
+    """Generate a prompt for the LLM to write pandas-only code for a data query (no plotting)."""
+    
+    return f"""
+    Given DataFrame `df` with columns: {', '.join(cols)}
+    Write Python code (pandas **only**, no plotting) to answer:
+    "{query}"
+
+    Rules
+    -----
+    1. Use pandas operations on `df` only.
+    2. Assign the final result to `result`.
+    3. Wrap the snippet in a single ```python code fence (no extra prose).
+    """
+
+def CodeExecutionHelper(code: str, df: pd.DataFrame):
+    """Executes the generated code, returning the result or error"""
+    
+    env = {"pd": pd, "df": df}
+    try:
+        exec(code, {}, env)
+        return env.get("result", None)
+    except Exception as exc:
+        return f"Error executing code: {exc}"
+    
+def CodeExtractorHelper(text: str) -> str:
+    """Extracts the first python code block from the output"""
+    
+    start = text.find("```python")
+    if start == -1:
+        return ""
+    start += len("```python")
+    end = text.find("```", start)
+    if end == -1:
+            return ""
+    return text[start:end].strip()
+    
+def ToolSelectorAgent(query: str, df: pd.DataFrame):
+    """Selects the appropriate tool for the users query"""
+        
+    prompt = CodeGeneratorTool(df.columns.tolist(), query)
+    
+    messages = [
+        {"role": "system", "content": \
+            "detailed thinking off. You are a Python data-analysis expert who writes clean, efficient code. \
+            Solve the given problem with optimal pandas operations. Be concise and focused. \
+            Your response must contain ONLY a properly-closed ```python code block with no explanations before or after. \
+            Ensure your solution is correct, handles edge cases, and follows best practices for data analysis."},
+        {"role": "user", "content": prompt}
+    ]
+        
+    response = pipe(messages, temperature = 0.2, max_new_tokens = 1024, return_full_text=False)[0]['generated_text']
+    return CodeExtractorHelper(response)
+
+def ReasoningPromptGenerator(query: str, result: Any) -> str:
+    """Packages the output into a response, provinding reasoning about the result."""
+    
+    isError = isinstance(result, str) and result.startswith("Error executing code")
+    
+    if isError:
+        desc = result
+    else:
+        desc = str(result)[:300] #why slice it
+    
+    prompt = f"""
+    The user asked: "{query}".
+    The result value is: {desc}
+    Explain in 2-3 concise sentences what this tells about the data (no mention of charts)."""
+    return prompt
+
+def ReasoningAgent(query: str, result: Any):
+    """Executes the reasoning prompt and returns the results and explination to the user"""
+    
+    prompt = ReasoningPromptGenerator(query, result)
+    isError = isinstance(result, str) and result.startswith("Error executing code")
+    
+    messages = [
+        {"role": "system", "content": \
+            "detailed thinking on. You are an insightful data analyst"},
+        {"role": "user","content": prompt}
+        
+    ]
+    
+    response = pipe(messages, temperature = 0.2, max_new_tokens = 1024, return_full_text=False)[0]['generated_text']
+    if "</think>" in response:
+        splitResponse = response.split("</think>",1)
+        response = splitResponse[1]
+        thinking = splitResponse[0]
+    return response, thinking
+    
+def ResponseBuilderTool(question:str)->str:
+    code = ToolSelectorAgent(question, st.session_state.df)
+    result = CodeExecutionHelper(code, st.session_state.df)
+    reasoning_txt, raw_thinking  = ReasoningAgent(question, result)
+    reasoning_txt = reasoning_txt.replace("`", "")
+
+    # Build assistant response
+    
+    if isinstance(result, (pd.DataFrame, pd.Series)):
+        header = f"Result: {len(result)} rows" if isinstance(result, pd.DataFrame) else "Result series"
+    else:
+        header = f"Result: {result}"
+
+    # Show only reasoning thinking in Model Thinking (collapsed by default)
+    thinking_html = ""
+    if raw_thinking:
+        thinking_html = (
+            '<details class="thinking">'
+            '<summary>🧠 Reasoning</summary>'
+            f'<pre>{raw_thinking}</pre>'
+            '</details>'
+        )
+
+    # Code accordion with proper HTML <pre><code> syntax highlighting
+    code_html = (
+        '<details class="code">'
+        '<summary>View code</summary>'
+        '<pre><code class="language-python">'
+        f'{code}'
+        '</code></pre>'
+        '</details>'
+    )
+    
+    # Combine thinking, explanation, and code accordion
+    return f"{header}\n\n{thinking_html}{reasoning_txt}\n\n{code_html}"
+    
+
 def main():
     """Streamlit App"""
     
@@ -27,10 +221,86 @@ def main():
         if("df" not in st.session_state) or (st.session_state.get("current_file") != file.name):
                 st.session_state.df = pd.read_csv(file)
                 st.session_state.current_file = file.name
+                with st.spinner("Summarizing..."):
+                    st.session_state.file_summary = FileDescriptionAgent("",st.session_state.df)
+        st.markdown("### Data Summary:")
+        st.text(st.session_state.file_summary)
         
         pygApp = get_pyg_renderer(st.session_state.df)
         pygApp.explorer(default_tab="data")
         
+        st.markdown(
+            """
+            <style>
+                section[data-testid="stSidebar"] {
+                    width: 500px !important; # Set the width to your desired value
+                }
+            </style>
+            """,
+            unsafe_allow_html=True,
+        )
+        
+        with st.sidebar:
+            st.markdown("## Analysis Discussion:")
+            
+            if("first_question" not in st.session_state):
+                st.session_state.first_question = ""
+            
+            if("num_question_asked" not in st.session_state):
+                st.session_state.num_question_asked = 0
+                
+            if("messages" not in st.session_state):
+                st.session_state.messages = []
+            
+            if st.session_state.num_question_asked == 0:
+                with st.spinner("Preparing Anlaysis..."):
+                    if("analsyis_questions" not in st.session_state):
+                        st.session_state.analsyis_questions = AnlaysisQuestionAgent(st.session_state.file_summary)
+                
+                with st.container():        
+                    if q1:= st.button(st.session_state.analsyis_questions[0]):
+                        st.session_state.first_question = st.session_state.analsyis_questions[0]
+                    if q2:= st.button(st.session_state.analsyis_questions[1]):
+                        st.session_state.first_question = st.session_state.analsyis_questions[1]
+                    if q3:= st.button(st.session_state.analsyis_questions[2]):
+                        st.session_state.first_question = st.session_state.analsyis_questions[2]
+                
+                    chat = st.chat_input("Something else...")
+                    if chat:
+                        st.session_state.first_question = chat
+
+                    st.session_state.num_question_asked += 1 if(q1 or q2 or q3 or chat is not None) else 0
+                    if st.session_state.num_question_asked == 1:
+                        st.session_state.messages.append({"role": "user", "content": st.session_state.first_question})               
+                    st.rerun()
+
+            elif st.session_state.num_question_asked == 1:
+                with st.container():
+                    for msg in st.session_state.messages:
+                        with st.chat_message(msg["role"]):
+                            st.markdown(msg["content"], unsafe_allow_html=True)
+                with st.spinner("Working …"):
+                    st.session_state.messages.append({
+                        "role": "assistant",
+                        "content": ResponseBuilderTool(st.session_state.first_question)
+                    })     
+                st.session_state.num_question_asked += 1
+                st.rerun()
+                        
+            else:
+                with st.container():
+                    for msg in st.session_state.messages:
+                        with st.chat_message(msg["role"]):
+                            st.markdown(msg["content"], unsafe_allow_html=True)
+                if user_q := st.chat_input("Ask about your data…"):
+                    st.session_state.messages.append({"role": "user", "content": user_q})                            
+                    with st.spinner("Working …"):
+                        st.session_state.messages.append({
+                            "role": "assistant",
+                            "content": ResponseBuilderTool(user_q)
+                        })     
+                    st.session_state.num_question_asked += 1
+                    st.rerun()
   
 if __name__ == "__main__":
     main()