ai-data-science-team 0.0.0.9014__py3-none-any.whl → 0.0.0.9015__py3-none-any.whl

ai_data_science_team/_version.py

@@ -1 +1 @@
-__version__ = "0.0.0.9014"
+__version__ = "0.0.0.9015"

ai_data_science_team/agents/data_visualization_agent.py

@@ -4,7 +4,6 @@
 # * Agents: Data Visualization Agent
 
 
-
 # Libraries
 from typing import TypedDict, Annotated, Sequence, Literal
 import operator
@@ -17,25 +16,25 @@ from langgraph.checkpoint.memory import MemorySaver
 from langgraph.types import Checkpointer
 
 import os
-import json 
+import json
 import pandas as pd
 
 from IPython.display import Markdown
 
-from ai_data_science_team.templates import(
-    node_func_execute_agent_code_on_data, 
+from ai_data_science_team.templates import (
+    node_func_execute_agent_code_on_data,
     node_func_human_review,
-    node_func_fix_agent_code, 
+    node_func_fix_agent_code,
     node_func_report_agent_outputs,
     create_coding_agent_graph,
     BaseAgent,
 )
 from ai_data_science_team.parsers.parsers import PythonOutputParser
 from ai_data_science_team.utils.regex import (
-    relocate_imports_inside_function, 
-    add_comments_to_top, 
-    format_agent_name, 
-    format_recommended_steps, 
+    relocate_imports_inside_function,
+    add_comments_to_top,
+    format_agent_name,
+    format_recommended_steps,
     get_generic_summary,
 )
 from ai_data_science_team.tools.dataframe import get_dataframe_summary
@@ -48,11 +47,12 @@ LOG_PATH = os.path.join(os.getcwd(), "logs/")
 
 # Class
 
+
 class DataVisualizationAgent(BaseAgent):
     """
     Creates a data visualization agent that can generate Plotly charts based on user-defined instructions or
-    default visualization steps (if any). The agent generates a Python function to produce the visualization, 
-    executes it, and logs the process, including code and errors. It is designed to facilitate reproducible 
+    default visualization steps (if any). The agent generates a Python function to produce the visualization,
+    executes it, and logs the process, including code and errors. It is designed to facilitate reproducible
     and customizable data visualization workflows.
 
     The agent may use default instructions for creating charts unless instructed otherwise, such as:
@@ -124,10 +124,10 @@ class DataVisualizationAgent(BaseAgent):
     llm = ChatOpenAI(model="gpt-4o-mini")
 
     data_visualization_agent = DataVisualizationAgent(
-        model=llm, 
+        model=llm,
         n_samples=30,
-        log=True, 
-        log_path="logs", 
+        log=True,
+        log_path="logs",
         human_in_the_loop=True
     )
 
@@ -141,7 +141,7 @@ class DataVisualizationAgent(BaseAgent):
     )
 
     plotly_graph_dict = data_visualization_agent.get_plotly_graph()
-    # You can render plotly_graph_dict with plotly.io.from_json or 
+    # You can render plotly_graph_dict with plotly.io.from_json or
     # something similar in a Jupyter Notebook.
 
     response = data_visualization_agent.get_response()
@@ -149,21 +149,21 @@ class DataVisualizationAgent(BaseAgent):
 
     Returns
     --------
-    DataVisualizationAgent : langchain.graphs.CompiledStateGraph 
-        A data visualization agent implemented as a compiled state graph. 
+    DataVisualizationAgent : langchain.graphs.CompiledStateGraph
+        A data visualization agent implemented as a compiled state graph.
     """
 
     def __init__(
-        self, 
-        model, 
-        n_samples=30, 
-        log=False, 
-        log_path=None, 
-        file_name="data_visualization.py", 
+        self,
+        model,
+        n_samples=30,
+        log=False,
+        log_path=None,
+        file_name="data_visualization.py",
         function_name="data_visualization",
-        overwrite=True, 
-        human_in_the_loop=False, 
-        bypass_recommended_steps=False, 
+        overwrite=True,
+        human_in_the_loop=False,
+        bypass_recommended_steps=False,
         bypass_explain_code=False,
         checkpointer=None,
     ):
@@ -185,7 +185,7 @@ class DataVisualizationAgent(BaseAgent):
 
     def _make_compiled_graph(self):
         """
-        Create the compiled graph for the data visualization agent. 
+        Create the compiled graph for the data visualization agent.
         Running this method will reset the response to None.
         """
         self.response = None
@@ -201,9 +201,16 @@ class DataVisualizationAgent(BaseAgent):
         # Rebuild the compiled graph
         self._compiled_graph = self._make_compiled_graph()
 
-    async def ainvoke_agent(self, data_raw: pd.DataFrame, user_instructions: str=None, max_retries:int=3, retry_count:int=0, **kwargs):
+    async def ainvoke_agent(
+        self,
+        data_raw: pd.DataFrame,
+        user_instructions: str = None,
+        max_retries: int = 3,
+        retry_count: int = 0,
+        **kwargs,
+    ):
         """
-        Asynchronously invokes the agent to generate a visualization. 
+        Asynchronously invokes the agent to generate a visualization.
         The response is stored in the 'response' attribute.
 
         Parameters
@@ -223,18 +230,28 @@ class DataVisualizationAgent(BaseAgent):
         -------
         None
         """
-        response = await self._compiled_graph.ainvoke({
-            "user_instructions": user_instructions,
-            "data_raw": data_raw.to_dict(),
-            "max_retries": max_retries,
-            "retry_count": retry_count,
-        }, **kwargs)
+        response = await self._compiled_graph.ainvoke(
+            {
+                "user_instructions": user_instructions,
+                "data_raw": data_raw.to_dict(),
+                "max_retries": max_retries,
+                "retry_count": retry_count,
+            },
+            **kwargs,
+        )
         self.response = response
         return None
 
-    def invoke_agent(self, data_raw: pd.DataFrame, user_instructions: str=None,  max_retries:int=3, retry_count:int=0, **kwargs):
+    def invoke_agent(
+        self,
+        data_raw: pd.DataFrame,
+        user_instructions: str = None,
+        max_retries: int = 3,
+        retry_count: int = 0,
+        **kwargs,
+    ):
         """
-        Synchronously invokes the agent to generate a visualization. 
+        Synchronously invokes the agent to generate a visualization.
         The response is stored in the 'response' attribute.
 
         Parameters
@@ -254,12 +271,15 @@ class DataVisualizationAgent(BaseAgent):
         -------
         None
         """
-        response = self._compiled_graph.invoke({
-            "user_instructions": user_instructions,
-            "data_raw": data_raw.to_dict(),
-            "max_retries": max_retries,
-            "retry_count": retry_count,
-        }, **kwargs)
+        response = self._compiled_graph.invoke(
+            {
+                "user_instructions": user_instructions,
+                "data_raw": data_raw.to_dict(),
+                "max_retries": max_retries,
+                "retry_count": retry_count,
+            },
+            **kwargs,
+        )
         self.response = response
         return None
 
@@ -268,7 +288,9 @@ class DataVisualizationAgent(BaseAgent):
         Retrieves the agent's workflow summary, if logging is enabled.
         """
         if self.response and self.response.get("messages"):
-            summary = get_generic_summary(json.loads(self.response.get("messages")[-1].content))
+            summary = get_generic_summary(
+                json.loads(self.response.get("messages")[-1].content)
+            )
             if markdown:
                 return Markdown(summary)
             else:
@@ -279,7 +301,7 @@ class DataVisualizationAgent(BaseAgent):
         Logs a summary of the agent's operations, if logging is enabled.
         """
         if self.response:
-            if self.response.get('data_visualization_function_path'):
+            if self.response.get("data_visualization_function_path"):
                 log_details = f"""
 ## Data Visualization Agent Log Summary:
 
@@ -288,7 +310,7 @@ Function Path: {self.response.get('data_visualization_function_path')}
 Function Name: {self.response.get('data_visualization_function_name')}
                 """
                 if markdown:
-                    return Markdown(log_details) 
+                    return Markdown(log_details)
                 else:
                     return log_details
 
@@ -380,16 +402,17 @@ Function Name: {self.response.get('data_visualization_function_name')}
 
 # Agent
 
+
 def make_data_visualization_agent(
-    model, 
+    model,
     n_samples=30,
-    log=False, 
-    log_path=None, 
+    log=False,
+    log_path=None,
     file_name="data_visualization.py",
     function_name="data_visualization",
-    overwrite=True, 
-    human_in_the_loop=False, 
-    bypass_recommended_steps=False, 
+    overwrite=True,
+    human_in_the_loop=False,
+    bypass_recommended_steps=False,
     bypass_explain_code=False,
     checkpointer=None,
 ):
@@ -460,25 +483,27 @@ def make_data_visualization_agent(
     app : langchain.graphs.CompiledStateGraph
         The data visualization agent as a state graph.
     """
-    
+
     llm = model
-    
+
     if human_in_the_loop:
         if checkpointer is None:
-            print("Human in the loop is enabled. A checkpointer is required. Setting to MemorySaver().")
+            print(
+                "Human in the loop is enabled. A checkpointer is required. Setting to MemorySaver()."
+            )
             checkpointer = MemorySaver()
-    
+
     # Human in th loop requires recommended steps
     if bypass_recommended_steps and human_in_the_loop:
         bypass_recommended_steps = False
         print("Bypass recommended steps set to False to enable human in the loop.")
-    
+
     # Setup Log Directory
     if log:
         if log_path is None:
             log_path = LOG_PATH
         if not os.path.exists(log_path):
-            os.makedirs(log_path)    
+            os.makedirs(log_path)
 
     # Define GraphState for the router
     class GraphState(TypedDict):
@@ -496,12 +521,11 @@ def make_data_visualization_agent(
         data_visualization_error: str
         max_retries: int
         retry_count: int
-        
+
     def chart_instructor(state: GraphState):
-        
         print(format_agent_name(AGENT_NAME))
         print("    * CREATE CHART GENERATOR INSTRUCTIONS")
-        
+
         recommend_steps_prompt = PromptTemplate(
             template="""
             You are a supervisor that is an expert in providing instructions to a chart generator agent for plotting. 
@@ -514,25 +538,23 @@ def make_data_visualization_agent(
             Previously Recommended Instructions (if any):
             {recommended_steps}
             
-            DATA: 
+            DATA SUMMARY: 
             {all_datasets_summary}
             
-            Formulate chart generator instructions by informing the chart generator of what type of plotly plot to use (e.g. bar, line, scatter, etc) to best represent the data. 
+            IMPORTANT:
+            
+            - Formulate chart generator instructions by informing the chart generator of what type of plotly plot to use (e.g. bar, line, scatter, etc) to best represent the data. 
+            - Think about how best to convey the information in the data to the user.
+            - If the user does not specify a type of plot, select the appropriate chart type based on the data summary provided and the user's question and how best to show the results.
+            - Come up with an informative title from the user's question and data provided. Also provide X and Y axis titles.
+            
+            CHART TYPE SELECTION TIPS:
             
-            Come up with an informative title from the user's question and data provided. Also provide X and Y axis titles.
+            - If a numeric column has less than 10 unique values, consider this column to be treated as a categorical column. Pick a chart that is appropriate for categorical data.
+            - If a numeric column has more than 10 unique values, consider this column to be treated as a continuous column. Pick a chart that is appropriate for continuous data.       
             
-            Instruct the chart generator to use the following theme colors, sizes, etc:
             
-            - Start with the "plotly_white" template
-            - Use a white background
-            - Use this color for bars and lines:
-                'blue': '#3381ff',
-            - Base Font Size: 8.8 (Used for x and y axes tickfont, any annotations, hovertips)
-            - Title Font Size: 13.2
-            - Line Size: 0.65 (specify these within the xaxis and yaxis dictionaries)
-            - Add smoothers or trendlines to scatter plots unless not desired by the user
-            - Do not use color_discrete_map (this will result in an error)
-            - Hover tip size: 8.8
+            RETURN FORMAT:
             
             Return your instructions in the following format:
             CHART GENERATOR INSTRUCTIONS: 
@@ -542,51 +564,61 @@ def make_data_visualization_agent(
             1. Do not include steps to save files.
             2. Do not include unrelated user instructions that are not related to the chart generation.
             """,
-            input_variables=["user_instructions", "recommended_steps", "all_datasets_summary"]
-            
+            input_variables=[
+                "user_instructions",
+                "recommended_steps",
+                "all_datasets_summary",
+            ],
         )
-        
+
         data_raw = state.get("data_raw")
         df = pd.DataFrame.from_dict(data_raw)
 
-        all_datasets_summary = get_dataframe_summary([df], n_sample=n_samples, skip_stats=False)
-        
+        all_datasets_summary = get_dataframe_summary(
+            [df], n_sample=n_samples, skip_stats=False
+        )
+
         all_datasets_summary_str = "\n\n".join(all_datasets_summary)
 
-        chart_instructor = recommend_steps_prompt | llm 
-        
-        recommended_steps = chart_instructor.invoke({
-            "user_instructions": state.get("user_instructions"),
-            "recommended_steps": state.get("recommended_steps"),
-            "all_datasets_summary": all_datasets_summary_str
-        })
-        
+        chart_instructor = recommend_steps_prompt | llm
+
+        recommended_steps = chart_instructor.invoke(
+            {
+                "user_instructions": state.get("user_instructions"),
+                "recommended_steps": state.get("recommended_steps"),
+                "all_datasets_summary": all_datasets_summary_str,
+            }
+        )
+
         return {
-            "recommended_steps": format_recommended_steps(recommended_steps.content.strip(), heading="# Recommended Data Cleaning Steps:"),
-            "all_datasets_summary": all_datasets_summary_str
+            "recommended_steps": format_recommended_steps(
+                recommended_steps.content.strip(),
+                heading="# Recommended Data Cleaning Steps:",
+            ),
+            "all_datasets_summary": all_datasets_summary_str,
         }
-        
+
     def chart_generator(state: GraphState):
-        
         print("    * CREATE DATA VISUALIZATION CODE")
 
-        
         if bypass_recommended_steps:
             print(format_agent_name(AGENT_NAME))
-            
+
             data_raw = state.get("data_raw")
             df = pd.DataFrame.from_dict(data_raw)
 
-            all_datasets_summary = get_dataframe_summary([df], n_sample=n_samples, skip_stats=False)
-            
+            all_datasets_summary = get_dataframe_summary(
+                [df], n_sample=n_samples, skip_stats=False
+            )
+
             all_datasets_summary_str = "\n\n".join(all_datasets_summary)
-            
+
             chart_generator_instructions = state.get("user_instructions")
-            
+
         else:
             all_datasets_summary_str = state.get("all_datasets_summary")
             chart_generator_instructions = state.get("recommended_steps")
-        
+
         prompt_template = PromptTemplate(
             template="""
             You are a chart generator agent that is an expert in generating plotly charts. You must use plotly or plotly.express to produce plots.
@@ -628,65 +660,76 @@ def make_data_visualization_agent(
             2. Do not include unrelated user instructions that are not related to the chart generation.
             
             """,
-            input_variables=["chart_generator_instructions", "all_datasets_summary", "function_name"]
+            input_variables=[
+                "chart_generator_instructions",
+                "all_datasets_summary",
+                "function_name",
+            ],
         )
 
         data_visualization_agent = prompt_template | llm | PythonOutputParser()
-        
-        response = data_visualization_agent.invoke({
-            "chart_generator_instructions": chart_generator_instructions,
-            "all_datasets_summary": all_datasets_summary_str,
-            "function_name": function_name
-        })
-        
+
+        response = data_visualization_agent.invoke(
+            {
+                "chart_generator_instructions": chart_generator_instructions,
+                "all_datasets_summary": all_datasets_summary_str,
+                "function_name": function_name,
+            }
+        )
+
         response = relocate_imports_inside_function(response)
         response = add_comments_to_top(response, agent_name=AGENT_NAME)
-        
+
         # For logging: store the code generated:
         file_path, file_name_2 = log_ai_function(
             response=response,
             file_name=file_name,
             log=log,
             log_path=log_path,
-            overwrite=overwrite
+            overwrite=overwrite,
         )
-        
+
         return {
             "data_visualization_function": response,
             "data_visualization_function_path": file_path,
             "data_visualization_function_file_name": file_name_2,
             "data_visualization_function_name": function_name,
-            "all_datasets_summary": all_datasets_summary_str
+            "all_datasets_summary": all_datasets_summary_str,
         }
-    
+
     # Human Review
-        
+
     prompt_text_human_review = "Are the following data visualization instructions correct? (Answer 'yes' or provide modifications)\n{steps}"
-    
+
     if not bypass_explain_code:
-        def human_review(state: GraphState) -> Command[Literal["chart_instructor", "explain_data_visualization_code"]]:
+
+        def human_review(
+            state: GraphState,
+        ) -> Command[Literal["chart_instructor", "explain_data_visualization_code"]]:
             return node_func_human_review(
                 state=state,
                 prompt_text=prompt_text_human_review,
-                yes_goto= 'explain_data_visualization_code',
+                yes_goto="explain_data_visualization_code",
                 no_goto="chart_instructor",
                 user_instructions_key="user_instructions",
                 recommended_steps_key="recommended_steps",
                 code_snippet_key="data_visualization_function",
             )
     else:
-        def human_review(state: GraphState) -> Command[Literal["chart_instructor", "__end__"]]:
+
+        def human_review(
+            state: GraphState,
+        ) -> Command[Literal["chart_instructor", "__end__"]]:
             return node_func_human_review(
                 state=state,
                 prompt_text=prompt_text_human_review,
-                yes_goto= '__end__',
+                yes_goto="__end__",
                 no_goto="chart_instructor",
                 user_instructions_key="user_instructions",
                 recommended_steps_key="recommended_steps",
-                code_snippet_key="data_visualization_function", 
+                code_snippet_key="data_visualization_function",
             )
-    
-        
+
     def execute_data_visualization_code(state):
         return node_func_execute_agent_code_on_data(
             state=state,
@@ -697,9 +740,9 @@ def make_data_visualization_agent(
             agent_function_name=state.get("data_visualization_function_name"),
             pre_processing=lambda data: pd.DataFrame.from_dict(data),
             # post_processing=lambda df: df.to_dict() if isinstance(df, pd.DataFrame) else df,
-            error_message_prefix="An error occurred during data visualization: "
+            error_message_prefix="An error occurred during data visualization: ",
         )
-    
+
     def fix_data_visualization_code(state: GraphState):
         prompt = """
         You are a Data Visualization Agent. Your job is to create a {function_name}() function that can be run on the data provided. The function is currently broken and needs to be fixed.
@@ -719,14 +762,14 @@ def make_data_visualization_agent(
             state=state,
             code_snippet_key="data_visualization_function",
             error_key="data_visualization_error",
-            llm=llm,  
+            llm=llm,
             prompt_template=prompt,
             agent_name=AGENT_NAME,
             log=log,
             file_path=state.get("data_visualization_function_path"),
             function_name=state.get("data_visualization_function_name"),
         )
-    
+
     # Final reporting node
     def report_agent_outputs(state: GraphState):
         return node_func_report_agent_outputs(
@@ -740,9 +783,9 @@ def make_data_visualization_agent(
             ],
             result_key="messages",
             role=AGENT_NAME,
-            custom_title="Data Visualization Agent Outputs"
+            custom_title="Data Visualization Agent Outputs",
         )
-        
+
     # Define the graph
     node_functions = {
         "chart_instructor": chart_instructor,
@@ -752,7 +795,7 @@ def make_data_visualization_agent(
         "fix_data_visualization_code": fix_data_visualization_code,
         "report_agent_outputs": report_agent_outputs,
     }
-    
+
     app = create_coding_agent_graph(
         GraphState=GraphState,
         node_functions=node_functions,
@@ -769,5 +812,5 @@ def make_data_visualization_agent(
         bypass_explain_code=bypass_explain_code,
         agent_name=AGENT_NAME,
     )
-        
+
     return app

ai_data_science_team/agents/data_wrangling_agent.py

@@ -702,6 +702,7 @@ def make_data_wrangling_agent(
             
             Important Notes:
             1. Do Not use Print statements to display the data. Return the data frame instead with the data wrangling operation performed.
+            2. Do not plot graphs. Only return the data frame.
             
             Make sure to explain any non-trivial steps with inline comments. Follow user instructions. Comment code thoroughly.
             

ai_data_science_team/multiagents/pandas_data_analyst.py

@@ -132,10 +132,10 @@ class PandasDataAnalyst(BaseAgent):
         """Returns a summary of the workflow."""
         if self.response and self.response.get("messages"):
             agents = [msg.role for msg in self.response["messages"]]
-            agent_labels = [f"- **Agent {i+1}:** {role}" for i, role in enumerate(agents)]
+            agent_labels = [f"- **Agent {i+1}:** {role}\n" for i, role in enumerate(agents)]
             header = f"# Pandas Data Analyst Workflow Summary\n\nThis workflow contains {len(agents)} agents:\n\n" + "\n".join(agent_labels)
             reports = [get_generic_summary(json.loads(msg.content)) for msg in self.response["messages"]]
-            summary = "\n" +header + "\n\n".join(reports)
+            summary = "\n\n" + header + "\n\n".join(reports)
             return Markdown(summary) if markdown else summary
 
     @staticmethod
@@ -177,15 +177,15 @@ def make_pandas_data_analyst(
     
     routing_preprocessor_prompt = PromptTemplate(
         template="""
-        You are an expert in routing decisions for a Pandas Data Manipulation Wrangling Agent, a Charting Visualization Agent, and a Pandas Table Agent. Your job is to:
+        You are an expert in routing decisions for a Pandas Data Manipulation Wrangling Agent, a Charting Visualization Agent, and a Pandas Table Agent. Your job is to tell the agents which actions to perform and determine the correct routing for the incoming user question:
         
-        1. Determine what the correct format for a Users Question should be for use with a Pandas Data Wrangling Agent based on the incoming user question. Anything related to data wrangling and manipulation should be passed along.
+        1. Determine what the correct format for a Users Question should be for use with a Pandas Data Wrangling Agent based on the incoming user question. Anything related to data wrangling and manipulation should be passed along. Anything related to data analysis can be handled by the Pandas Agent. Anything that uses Pandas can be passed along. Tables can be returned from this agent. Don't pass along anything about plotting or visualization.
         2. Determine whether or not a chart should be generated or a table should be returned based on the users question.
         3. If a chart is requested, determine the correct format of a Users Question should be used with a Data Visualization Agent. Anything related to plotting and visualization should be passed along.
         
         Use the following criteria on how to route the the initial user question:
         
-        From the incoming user question, remove any details about the format of the final response as either a Chart or Table and return only the important part of the incoming user question that is relevant for the SQL generator agent. This will be the 'user_instructions_data_wrangling'. If 'None' is found, return the original user question.
+        From the incoming user question, remove any details about the format of the final response as either a Chart or Table and return only the important part of the incoming user question that is relevant for the Pandas Data Wrangling and Transformation agent. This will be the 'user_instructions_data_wrangling'. If 'None' is found, return the original user question.
         
         Next, determine if the user would like a data visualization ('chart') or a 'table' returned with the results of the Data Wrangling Agent. If unknown, not specified or 'None' is found, then select 'table'.  
         

ai_data_science_team/multiagents/sql_data_analyst.py

@@ -301,24 +301,13 @@ class SQLDataAnalyst(BaseAgent):
         markdown: bool
             If True, returns the summary as a Markdown-formatted string.
         """
-        if self.response and self.get_response()['messages']:
-            
-            agents = [self.get_response()['messages'][i].role for i in range(len(self.get_response()['messages']))]
-            
-            agent_labels = []
-            for i in range(len(agents)):
-                agent_labels.append(f"- **Agent {i+1}:** {agents[i]}")
-            
-            # Construct header
-            header = f"# SQL Data Analyst Workflow Summary Report\n\nThis agentic workflow contains {len(agents)} agents:\n\n" + "\n".join(agent_labels)
-            
-            reports = []
-            for msg in self.get_response()['messages']:
-                reports.append(get_generic_summary(json.loads(msg.content)))
-                
-            if markdown:
-                return Markdown(header + "\n\n".join(reports))
-            return "\n\n".join(reports)
+        if self.response and self.response.get("messages"):
+            agents = [msg.role for msg in self.response["messages"]]
+            agent_labels = [f"- **Agent {i+1}:** {role}\n" for i, role in enumerate(agents)]
+            header = f"# SQL Data Analyst Workflow Summary\n\nThis workflow contains {len(agents)} agents:\n\n" + "\n".join(agent_labels)
+            reports = [get_generic_summary(json.loads(msg.content)) for msg in self.response["messages"]]
+            summary = "\n\n" + header + "\n\n".join(reports)
+            return Markdown(summary) if markdown else summary
     
     
 

ai_data_science_team/tools/eda.py

@@ -235,6 +235,7 @@ def correlation_funnel(
     df_correlated = df_binarized.correlate(target=full_target, method=corr_method)
     
     # Attempt to generate a static plot.
+    encoded = None
     try:
         # Here we assume that your DataFrame has a method plot_correlation_funnel.
         fig = df_correlated.plot_correlation_funnel(engine='plotnine', height=600)
@@ -248,6 +249,7 @@ def correlation_funnel(
         encoded = {"error": str(e)}
     
     # Attempt to generate a Plotly plot.
+    fig_dict = None
     try:
         fig = df_correlated.plot_correlation_funnel(engine='plotly')
         fig_json = pio.to_json(fig)

{ai_data_science_team-0.0.0.9014.dist-info → ai_data_science_team-0.0.0.9015.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: ai-data-science-team
-Version: 0.0.0.9014
+Version: 0.0.0.9015
 Summary: Build and run an AI-powered data science team.
 Home-page: https://github.com/business-science/ai-data-science-team
 Author: Matt Dancho
@@ -136,9 +136,9 @@ This project is a work in progress. New data science agents will be released soo
 
 ### NEW: Multi-Agents
 
-This is the internals of the SQL Data Analyst Agent that connects to SQL databases to pull data into the data science environment. It creates pipelines to automate data extraction, performs Joins, Aggregations, and other SQL Query operations. And it includes a Data Visualization Agent that creates visualizations to help you understand your data.:
+**🔥 Pandas Data Analyst Agent:** Combines the ability to wrangle, transform, and analyze data with an optional data visualization agent that can create interactive plots.
 
-![Business Intelligence SQL Agent](/img/multi_agent_sql_data_visualization.jpg)
+![Business Intelligence SQL Agent](/img/multi_agent_pandas_data_analyst.jpg)
 
 ### Data Science Apps
 
@@ -182,7 +182,8 @@ This is a top secret project I'm working on. It's a multi-agent data science app
 
 #### Multi-Agents
 
-1. **SQL Data Analyst Agent:** Connects to SQL databases to pull data into the data science environment. Creates pipelines to automate data extraction. Performs Joins, Aggregations, and other SQL Query operations. Includes a Data Visualization Agent that creates visualizations to help you understand your data. [See Example](https://github.com/business-science/ai-data-science-team/blob/master/examples/multiagents/sql_data_analyst.ipynb)
+1. **🔥🔥 Pandas Data Analyst Agent:** Combines the ability to wrangle, transform, and analyze data with an optional data visualization agent that can create interactive plots. [See Example](https://github.com/business-science/ai-data-science-team/blob/master/examples/multiagents/pandas_data_analyst.ipynb)
+2. **🔥🔥 SQL Data Analyst Agent:** Connects to SQL databases to pull data into the data science environment. Creates pipelines to automate data extraction. Performs Joins, Aggregations, and other SQL Query operations. Includes a Data Visualization Agent that creates visualizations to help you understand your data. [See Example](https://github.com/business-science/ai-data-science-team/blob/master/examples/multiagents/sql_data_analyst.ipynb)
 
 ### Agents Coming Soon
 

{ai_data_science_team-0.0.0.9014.dist-info → ai_data_science_team-0.0.0.9015.dist-info}/RECORD

@@ -1,11 +1,11 @@
 ai_data_science_team/__init__.py,sha256=LmogkhGnxvvVe1ukJM6I6lXy4B7SuCr5eXZpwjyDMKQ,444
-ai_data_science_team/_version.py,sha256=D4dUl-fYnimOU_VSzvrmJm30_IoaF_9m9dTLp8HE6rQ,26
+ai_data_science_team/_version.py,sha256=c-XrUvZG3E6SWR9NMQqLxISzMZJUpsnK0FlIEMHAOls,27
 ai_data_science_team/orchestration.py,sha256=xiIFOsrLwPdkSmtme7wNCCGv8XopnMTNElNzlZokL-4,303
 ai_data_science_team/agents/__init__.py,sha256=Gnotza9SKr_0IxuaX8k1nsZK48wXkkeZcGcrR1EqNks,668
 ai_data_science_team/agents/data_cleaning_agent.py,sha256=aZLhnN2EBlY_hmAg_r73dwi1w5utSFNEgEs8aWl8Cho,27991
 ai_data_science_team/agents/data_loader_tools_agent.py,sha256=TFKzYqV6cvU-sMbfL-hg8-NgF_Hz3nysGFldvb5K3fM,9327
-ai_data_science_team/agents/data_visualization_agent.py,sha256=eUSTzTOm5aLJ6Cqnk-hRuXeVbYyy0RIzN8_0LLy0P9o,29387
-ai_data_science_team/agents/data_wrangling_agent.py,sha256=6tiDO1i-5s2Ju6_MsLoJMflUuRSf_1oTSsSKcLlgzEc,33376
+ai_data_science_team/agents/data_visualization_agent.py,sha256=IHNagAVY4XIRfyKKj3jdJZV0vUpzBqqnQBVbzP1lZj0,29829
+ai_data_science_team/agents/data_wrangling_agent.py,sha256=jyBrEfLsgIqSF6xcmRgnkzvNqJfkXdjn6FDefQij62o,33439
 ai_data_science_team/agents/feature_engineering_agent.py,sha256=xZGDFnmM6wx4bi3e4c_dNOZzGcxBmX8k0iveL7dlA-k,31608
 ai_data_science_team/agents/sql_database_agent.py,sha256=fln8unefn5Jd2exeyGs-9PljyLXAK60HI81tJACYeCY,31726
 ai_data_science_team/ds_agents/__init__.py,sha256=dnuagUTebTDHhGXbCt-hZIilzXMSUwyHaEI7sOxhvoE,95
@@ -16,8 +16,8 @@ ai_data_science_team/ml_agents/h2o_ml_agent.py,sha256=S0uayngaVwVUyA4zy05QYlq5NX
 ai_data_science_team/ml_agents/h2o_ml_tools_agent.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 ai_data_science_team/ml_agents/mlflow_tools_agent.py,sha256=QImaZnS8hPdrU7GI6pZ0dUDO-LXx40MSA3XyMDppIh0,12003
 ai_data_science_team/multiagents/__init__.py,sha256=5tpmZBQ_UT5SKDCS_NivZhN19HEStKIcstiqSXPXDl0,208
-ai_data_science_team/multiagents/pandas_data_analyst.py,sha256=O662v-75tLqHHrVNjncsPeR2FB4MWSWruJRIF-YO-fg,13581
-ai_data_science_team/multiagents/sql_data_analyst.py,sha256=Fpue6WcX9x18kEH3kfEi8kkFoG9HhQ1AZiWw6Y6FXOo,18502
+ai_data_science_team/multiagents/pandas_data_analyst.py,sha256=6JvcGFvDH7_ozRo-RQvjA_to5R27c7ZSEdKt4VQGL6U,13935
+ai_data_science_team/multiagents/sql_data_analyst.py,sha256=ZZx3Edzff6zf27iPl8lUGoqaZkPaJQtCJIgNx9wdCZY,18232
 ai_data_science_team/multiagents/supervised_data_analyst.py,sha256=uduCYpicga-UCf9nPQktQggW96-HDlqvioYmEdWejtI,158
 ai_data_science_team/parsers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 ai_data_science_team/parsers/parsers.py,sha256=hIsMZXRHz9hqs8R1ebymKA7D6NxOf5UVMpDAr_gGhE8,2027
@@ -26,7 +26,7 @@ ai_data_science_team/templates/agent_templates.py,sha256=QHRNZVmIfeClEef2Fr2Wb9J
 ai_data_science_team/tools/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 ai_data_science_team/tools/data_loader.py,sha256=ITs_6UAJ0m9h68R9_LruiaJSElv9l7SxTQYryI7YZPY,14702
 ai_data_science_team/tools/dataframe.py,sha256=cckplDWu9SsA_PRo89pYsyVCmBE0PoDIwMv6tuLunT4,4572
-ai_data_science_team/tools/eda.py,sha256=KoryXso_5zOPDq7jwcUAMEXV-AIzpWb62zzbUHVtgtM,12687
+ai_data_science_team/tools/eda.py,sha256=orabE8qaYj5TC5n7CRS6rHOPkyBVxr488631AwkVKVg,12726
 ai_data_science_team/tools/h2o.py,sha256=gSK0f2FULfAfipFTTjDMUS6DjHwFFvvl4jxshr6QpS0,38997
 ai_data_science_team/tools/mlflow.py,sha256=8NTkSOvbTk01GOmwFaMkLBRse80w9Kk7Ypi6Fv4kTII,29475
 ai_data_science_team/tools/sql.py,sha256=vvz_CiOg6GqXo2_mlF4kq5IS6if79dpaizAgLR9sRyg,4784
@@ -37,8 +37,8 @@ ai_data_science_team/utils/matplotlib.py,sha256=d6DZfCXvZ5Kocxtsp92etIymKW2cRBcU
 ai_data_science_team/utils/messages.py,sha256=feWIPGsv8ly9jpNnS97SoPsn1feaY1Km0VCbHTbRpI8,549
 ai_data_science_team/utils/plotly.py,sha256=nST-NG0oizKVHhH6HsjHUpTUumq9bCccBdxjuaJWnVQ,504
 ai_data_science_team/utils/regex.py,sha256=lwarbLqTA2VfNQSyqKCl-PBlH_0WH3zXZvYGBYGUiu4,5144
-ai_data_science_team-0.0.0.9014.dist-info/LICENSE,sha256=Xif0IRLdd2HGLATxV2EVp91aSY6KOuacRr_6BorKGzA,1084
-ai_data_science_team-0.0.0.9014.dist-info/METADATA,sha256=a35LbXyxf_XiP82m_P5HLFwPrmuzXkNWbyfzGge7dHA,13021
-ai_data_science_team-0.0.0.9014.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-ai_data_science_team-0.0.0.9014.dist-info/top_level.txt,sha256=CnoMgOphCoAdGTLueWdCVByVyjwOubaGiTB1lchdy4M,21
-ai_data_science_team-0.0.0.9014.dist-info/RECORD,,
+ai_data_science_team-0.0.0.9015.dist-info/LICENSE,sha256=Xif0IRLdd2HGLATxV2EVp91aSY6KOuacRr_6BorKGzA,1084
+ai_data_science_team-0.0.0.9015.dist-info/METADATA,sha256=tIcThz7trmAG6TZAnDHxy8ntBslXMKS5xSUbvaTygyQ,13164
+ai_data_science_team-0.0.0.9015.dist-info/WHEEL,sha256=jB7zZ3N9hIM9adW7qlTAyycLYW9npaWKLRzaoVcLKcM,91
+ai_data_science_team-0.0.0.9015.dist-info/top_level.txt,sha256=CnoMgOphCoAdGTLueWdCVByVyjwOubaGiTB1lchdy4M,21
+ai_data_science_team-0.0.0.9015.dist-info/RECORD,,

{ai_data_science_team-0.0.0.9014.dist-info → ai_data_science_team-0.0.0.9015.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.8.0)
+Generator: setuptools (75.8.2)
 Root-Is-Purelib: true
 Tag: py3-none-any