ai-data-science-team 0.0.0.9012__py3-none-any.whl → 0.0.0.9013__py3-none-any.whl

ai_data_science_team/_version.py

@@ -1 +1 @@
-__version__ = "0.0.0.9012"
+__version__ = "0.0.0.9013"

ai_data_science_team/agents/data_loader_tools_agent.py

@@ -25,6 +25,7 @@ from ai_data_science_team.tools.data_loader import (
     get_file_info,
     search_files_by_pattern,
 )
+from ai_data_science_team.utils.messages import get_tool_call_names
 
 AGENT_NAME = "data_loader_tools_agent"
 
@@ -174,6 +175,12 @@ class DataLoaderToolsAgent(BaseAgent):
             return Markdown(self.response["messages"][0].content)
         else:
             return self.response["messages"][0].content
+    
+    def get_tool_calls(self):
+        """
+        Returns the tool calls made by the agent.
+        """
+        return self.response["tool_calls"]
 
     
 
@@ -204,6 +211,7 @@ def make_data_loader_tools_agent(
         internal_messages: Annotated[Sequence[BaseMessage], operator.add]
         user_instructions: str
         data_loader_artifacts: dict
+        tool_calls: List[str]
         
     def data_loader_agent(state):
         
@@ -253,10 +261,13 @@ def make_data_loader_tools_agent(
             elif isinstance(last_message, dict) and "artifact" in last_message:
                 last_tool_artifact = last_message["artifact"]
 
+        tool_calls = get_tool_call_names(internal_messages)
+        
         return {
             "messages": [last_ai_message], 
             "internal_messages": internal_messages,
             "data_loader_artifacts": last_tool_artifact,
+            "tool_calls": tool_calls,
         }
         
     workflow = StateGraph(GraphState)

ai_data_science_team/ds_agents/eda_tools_agent.py

@@ -19,17 +19,20 @@ from ai_data_science_team.templates import BaseAgent
 from ai_data_science_team.utils.regex import format_agent_name
 
 from ai_data_science_team.tools.eda import (
+    explain_data,
     describe_dataset, 
     visualize_missing, 
     correlation_funnel,
     generate_sweetviz_report,
 )
+from ai_data_science_team.utils.messages import get_tool_call_names
 
 
 AGENT_NAME = "exploratory_data_analyst_agent"
 
 # Updated tool list for EDA
 EDA_TOOLS = [
+    explain_data,
     describe_dataset,
     visualize_missing,
     correlation_funnel,
@@ -162,6 +165,12 @@ class EDAToolsAgent(BaseAgent):
             return Markdown(self.response["messages"][0].content)
         else:
             return self.response["messages"][0].content
+        
+    def get_tool_calls(self):
+        """
+        Returns the tool calls made by the agent.
+        """
+        return self.response["tool_calls"]
 
 def make_eda_tools_agent(
     model: Any,
@@ -191,6 +200,7 @@ def make_eda_tools_agent(
         user_instructions: str
         data_raw: dict
         eda_artifacts: dict
+        tool_calls: list
 
     def exploratory_agent(state):
         print(format_agent_name(AGENT_NAME))
@@ -229,11 +239,14 @@ def make_eda_tools_agent(
                 last_tool_artifact = last_message.artifact
             elif isinstance(last_message, dict) and "artifact" in last_message:
                 last_tool_artifact = last_message["artifact"]
+                
+        tool_calls = get_tool_call_names(internal_messages)
         
         return {
             "messages": [last_ai_message],
             "internal_messages": internal_messages,
             "eda_artifacts": last_tool_artifact,
+            "tool_calls": tool_calls,
         }
     
     workflow = StateGraph(GraphState)

ai_data_science_team/ml_agents/mlflow_tools_agent.py

@@ -27,6 +27,7 @@ from ai_data_science_team.tools.mlflow import (
     mlflow_search_registered_models,
     mlflow_get_model_version_details,
 )
+from ai_data_science_team.utils.messages import get_tool_call_names
 
 AGENT_NAME = "mlflow_tools_agent"
 
@@ -228,6 +229,12 @@ class MLflowToolsAgent(BaseAgent):
             return Markdown(self.response["messages"][0].content)
         else:
             return self.response["messages"][0].content
+    
+    def get_tool_calls(self):
+        """
+        Returns the tool calls made by the agent.
+        """
+        return self.response["tool_calls"]
             
     
     
@@ -330,10 +337,13 @@ def make_mlflow_tools_agent(
             elif isinstance(last_message, dict) and "artifact" in last_message:
                 last_tool_artifact = last_message["artifact"]
 
+        tool_calls = get_tool_call_names(internal_messages)
+        
         return {
             "messages": [last_ai_message], 
             "internal_messages": internal_messages,
             "mlflow_artifacts": last_tool_artifact,
+            "tool_calls": tool_calls,
         }
 
     

ai_data_science_team/tools/dataframe.py

@@ -74,7 +74,12 @@ def get_dataframe_summary(
     return summaries
 
 
-def _summarize_dataframe(df: pd.DataFrame, dataset_name: str, n_sample=30, skip_stats=False) -> str:
+def _summarize_dataframe(
+    df: pd.DataFrame, 
+    dataset_name: str, 
+    n_sample=30, 
+    skip_stats=False
+) -> str:
     """Generate a summary string for a single DataFrame."""
     # 1. Convert dictionary-type cells to strings
     #    This prevents unhashable dict errors during df.nunique().

ai_data_science_team/tools/eda.py

@@ -2,11 +2,44 @@
 from typing import Annotated, Dict, Tuple, Union
 
 import os
+import tempfile
 
 from langchain.tools import tool
 
 from langgraph.prebuilt import InjectedState  
 
+from ai_data_science_team.tools.dataframe import get_dataframe_summary
+
+
+@tool(response_format='content')
+def explain_data(
+    data_raw: Annotated[dict, InjectedState("data_raw")],
+    n_sample: int = 30,
+    skip_stats: bool = False,
+):
+    """
+    Tool: explain_data
+    Description:
+        Provides an extensive, narrative summary of a DataFrame including its shape, column types,
+        missing value percentages, unique counts, sample rows, and (if not skipped) descriptive stats/info.
+
+    Parameters:
+        data_raw (dict): Raw data.
+        n_sample (int, default=30): Number of rows to display.
+        skip_stats (bool, default=False): If True, omit descriptive stats/info.
+
+    LLM Guidance:
+        Use when a detailed, human-readable explanation is needed—i.e., a full overview is preferred over a concise numerical summary.
+
+    Returns:
+        str: Detailed DataFrame summary.
+    """
+    print("    * Tool: explain_data")
+    import pandas as pd
+    
+    result = get_dataframe_summary(pd.DataFrame(data_raw), n_sample=n_sample, skip_stats=skip_stats)
+    
+    return result
 
 @tool(response_format='content_and_artifact')
 def describe_dataset(
@@ -15,21 +48,33 @@ def describe_dataset(
     """
     Tool: describe_dataset
     Description:
-        Describe the dataset by computing summary
-        statistics using the DataFrame's describe() method.
-        
+        Compute and return summary statistics for the dataset using pandas' describe() method.
+        The tool provides both a textual summary and a structured artifact (a dictionary) for further processing.
+
+    Parameters:
+    -----------
+    data_raw : dict
+        The raw data in dictionary format.
+
+    LLM Selection Guidance:
+    ------------------------
+    Use this tool when:
+      - The request emphasizes numerical descriptive statistics (e.g., count, mean, std, min, quartiles, max).
+      - The user needs a concise statistical snapshot rather than a detailed narrative.
+      - Both a brief text explanation and a structured data artifact (for downstream tasks) are required.
+
     Returns:
     -------
     Tuple[str, Dict]:
-        content: A textual summary of the DataFrame's descriptive statistics.
-        artifact: A dictionary (from DataFrame.describe()) for further inspection.
+        - content: A textual summary indicating that summary statistics have been computed.
+        - artifact: A dictionary (derived from DataFrame.describe()) containing detailed statistical measures.
     """
     print("    * Tool: describe_dataset")
     import pandas as pd
     df = pd.DataFrame(data_raw)
     description_df = df.describe(include='all')
     content = "Summary statistics computed using pandas describe()."
-    artifact = description_df.to_dict()
+    artifact = {'describe_df': description_df.to_dict()}
     return content, artifact
 
 
@@ -226,8 +271,8 @@ def generate_sweetviz_report(
     data_raw: Annotated[dict, InjectedState("data_raw")],
     target: str = None,
     report_name: str = "sweetviz_report.html",
-    report_directory: str = os.path.join(os.getcwd(), "reports"),
-    open_browser: bool = True,
+    report_directory: str = None,  # <-- Default to None
+    open_browser: bool = False,
 ) -> Tuple[str, Dict]:
     """
     Tool: generate_sweetviz_report
@@ -243,9 +288,10 @@ def generate_sweetviz_report(
     report_name : str, optional
         The file name to save the Sweetviz HTML report. Default is "sweetviz_report.html".
     report_directory : str, optional
-        The directory where the report should be saved. Defaults to a 'reports' directory in the current working directory.
+        The directory where the report should be saved. 
+        If None, a temporary directory is created and used.
     open_browser : bool, optional
-        Whether to open the report in a web browser. Default is True.
+        Whether to open the report in a web browser. Default is False.
     
     Returns:
     --------
@@ -254,28 +300,37 @@ def generate_sweetviz_report(
         artifact: A dictionary with the report file path and optionally the report's HTML content.
     """
     print("    * Tool: generate_sweetviz_report")
+
+    # Import sweetviz
     try:
         import sweetviz as sv
     except ImportError:
         raise ImportError("Please install the 'sweetviz' package to use this tool. Run: pip install sweetviz")
+    
     import pandas as pd
+    
     # Convert injected raw data to a DataFrame.
     df = pd.DataFrame(data_raw)
     
+    # If no directory is specified, use a temporary directory.
+    if not report_directory:
+        report_directory = tempfile.mkdtemp()
+        print(f"    * Using temporary directory: {report_directory}")
+    else:
+        # Ensure user-specified directory exists.
+        if not os.path.exists(report_directory):
+            os.makedirs(report_directory)
+    
     # Create the Sweetviz report.
     report = sv.analyze(df, target_feat=target)
     
-    # Ensure the directory exists; default is os.getcwd()/reports
-    if not os.path.exists(report_directory):
-        os.makedirs(report_directory)
-    
     # Determine the full path for the report.
     full_report_path = os.path.join(report_directory, report_name)
     
     # Save the report to the specified HTML file.
     report.show_html(
         filepath=full_report_path,
-        open_browser=True,
+        open_browser=open_browser,
     )
     
     # Optionally, read the HTML content (if desired to pass along in the artifact).
@@ -285,9 +340,13 @@ def generate_sweetviz_report(
     except Exception:
         html_content = None
     
-    content = f"Sweetviz EDA report generated and saved as '{os.path.abspath(full_report_path)}'."
+    content = (
+        f"Sweetviz EDA report generated and saved as '{os.path.abspath(full_report_path)}'. "
+        f"{'This was saved in a temporary directory.' if 'tmp' in report_directory else ''}"
+    )
     artifact = {
         "report_file": os.path.abspath(full_report_path),
         "report_html": html_content,
     }
     return content, artifact
+

ai_data_science_team/utils/messages.py

@@ -0,0 +1,27 @@
+
+
+
+def get_tool_call_names(messages):
+    """
+    Method to extract the tool call names from a list of LangChain messages.
+    
+    Parameters:
+    ----------
+    messages : list
+        A list of LangChain messages.
+        
+    Returns:
+    -------
+    tool_calls : list
+        A list of tool call names.
+    
+    """
+    tool_calls = []
+    for message in messages:
+        try: 
+            if "tool_call_id" in list(dict(message).keys()):
+                tool_calls.append(message.name)
+        except:
+            pass
+    return tool_calls
+

{ai_data_science_team-0.0.0.9012.dist-info → ai_data_science_team-0.0.0.9013.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: ai-data-science-team
-Version: 0.0.0.9012
+Version: 0.0.0.9013
 Summary: Build and run an AI-powered data science team.
 Home-page: https://github.com/business-science/ai-data-science-team
 Author: Matt Dancho
@@ -152,7 +152,11 @@ This is a top secret project I'm working on. It's a multi-agent data science app
 
 #### 🔥 Agentic Applications
 
-1. **SQL Database Agent App:** Connects any SQL Database, generates SQL queries from natural language, and returns data as a downloadable table. [See Application](/apps/sql-database-agent-app/)
+1. **NEW Exploratory Data Copilot**: An AI-powered data science app that performs automated exploratory data analysis (EDA) with EDA Reporting, Missing Data Analysis, Correlation Analysis, and more. [See Application](/apps/exploratory-copilot-app/)
+
+![Exploratory Data Copilot](/img/apps/ai_exploratory_copilot.jpg)
+
+2. **SQL Database Agent App:** Connects any SQL Database, generates SQL queries from natural language, and returns data as a downloadable table. [See Application](/apps/sql-database-agent-app/)
 
 ### Agents Available Now
 

{ai_data_science_team-0.0.0.9012.dist-info → ai_data_science_team-0.0.0.9013.dist-info}/RECORD

@@ -1,20 +1,20 @@
 ai_data_science_team/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-ai_data_science_team/_version.py,sha256=BybGt-zGNDZsdJxDMV3xmjghiRF8jmwG3ov_dt_rM7E,26
+ai_data_science_team/_version.py,sha256=8mQbNYWB914j3xlCMQYaR14g26vq-2SV31Xf8uer_L0,26
 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=V5tJMwGJK0JwrF_H-7r3S0E8UkAY6ci4BGxqjhZiGBI,27352
-ai_data_science_team/agents/data_loader_tools_agent.py,sha256=fnkOvmrXzvTTt1mnAyTlsF_7ZGrkp3P97YU_LgeffMg,8445
+ai_data_science_team/agents/data_loader_tools_agent.py,sha256=23Uuqt-oaJfj3CFRKT7NErNkodXpraXl0HOWvXjMcJs,8802
 ai_data_science_team/agents/data_visualization_agent.py,sha256=tJy9Ehnh9mvAu6H--TXI8esSHmK1RW_L1RDAdn7Xek4,28821
 ai_data_science_team/agents/data_wrangling_agent.py,sha256=LxzphH-TmrFG0GjejGOjulhPq4SsWFo5Y9tk4WEuN4M,32347
 ai_data_science_team/agents/feature_engineering_agent.py,sha256=KmPBkj7WUBz6LFUlDDfQHMi7ujXwsH5P9LWRS-F4tdM,31026
 ai_data_science_team/agents/sql_database_agent.py,sha256=1K2o3NiuKgGKdbMz_Tq9IeQ8xhXjpfGOxx9lArZh1yE,31173
 ai_data_science_team/ds_agents/__init__.py,sha256=dnuagUTebTDHhGXbCt-hZIilzXMSUwyHaEI7sOxhvoE,95
-ai_data_science_team/ds_agents/eda_tools_agent.py,sha256=y65lsBXhQNOGwWealEho6uFxGSTW7FNfvTUZnW8_XNY,7609
+ai_data_science_team/ds_agents/eda_tools_agent.py,sha256=VJkqyQCNxoV0kvUTpUZh8SXTTZ0K1tUlg3jq6LDnpPQ,8009
 ai_data_science_team/ds_agents/modeling_tools_agent.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 ai_data_science_team/ml_agents/__init__.py,sha256=qq3UlDCRV_z4FHQ1jj3YR6zPbA6kuCvYCisj_bHYfO4,190
 ai_data_science_team/ml_agents/h2o_ml_agent.py,sha256=DamR72agrTKfdcdhablmP2mpbj0CqtMonP-QU8p7o9w,33394
 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=zbT0KIsmQp_sEyxzXRguhqx5913Q2yPYyKGU6TUWEM8,11067
+ai_data_science_team/ml_agents/mlflow_tools_agent.py,sha256=bRTT53_pHV0qAYl07iZcwUEYffGH_ZfJICdrLeOUPn4,11394
 ai_data_science_team/multiagents/__init__.py,sha256=aI4GztEwmkexZKT5XHcH3cAjO-xYUhncb3yfPJQDqTA,99
 ai_data_science_team/multiagents/sql_data_analyst.py,sha256=kmmED3gLf5STWWY6ZVJYd7_Pt8NMl6SHyBocuQzRDGk,14193
 ai_data_science_team/multiagents/supervised_data_analyst.py,sha256=uduCYpicga-UCf9nPQktQggW96-HDlqvioYmEdWejtI,158
@@ -24,8 +24,8 @@ ai_data_science_team/templates/__init__.py,sha256=_IcyFUu_mM8dFtttz95h0csJZ-XWDP
 ai_data_science_team/templates/agent_templates.py,sha256=Lezp0ugtIP3m5WUOmjLwghNnjjyQVQecysONeIHWwi0,29133
 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=qSflGDByqqCXv4TjuvOFvGPZmegzeOesb0Y4i4Y0gdQ,4551
-ai_data_science_team/tools/eda.py,sha256=UGD6PC12RsB_UmStvR4TmSqv0noxjM4DkzY-kHjI0-E,10591
+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/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
@@ -33,10 +33,11 @@ ai_data_science_team/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJ
 ai_data_science_team/utils/html.py,sha256=1MBcjNyATi3FPOyVdqf6-_QYCJmDVQWmVPIInUr50dk,628
 ai_data_science_team/utils/logging.py,sha256=7wFOv6GGhXR_RPbh-8p0GyrS608XOnZtiaGK2IbDl_s,2081
 ai_data_science_team/utils/matplotlib.py,sha256=d6DZfCXvZ5Kocxtsp92etIymKW2cRBcUG9GmCOMtgJo,1145
+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-0.0.0.9012.dist-info/LICENSE,sha256=Xif0IRLdd2HGLATxV2EVp91aSY6KOuacRr_6BorKGzA,1084
-ai_data_science_team-0.0.0.9012.dist-info/METADATA,sha256=geRCFLG3YO9uprp_CGKiqCTSThg06L2U6WxVqYKzyM8,12704
-ai_data_science_team-0.0.0.9012.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-ai_data_science_team-0.0.0.9012.dist-info/top_level.txt,sha256=CnoMgOphCoAdGTLueWdCVByVyjwOubaGiTB1lchdy4M,21
-ai_data_science_team-0.0.0.9012.dist-info/RECORD,,
+ai_data_science_team-0.0.0.9013.dist-info/LICENSE,sha256=Xif0IRLdd2HGLATxV2EVp91aSY6KOuacRr_6BorKGzA,1084
+ai_data_science_team-0.0.0.9013.dist-info/METADATA,sha256=z18MmCwNdEgovskYmYmd4CS1I4WKTvh_mSnmzKOaHZs,13021
+ai_data_science_team-0.0.0.9013.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+ai_data_science_team-0.0.0.9013.dist-info/top_level.txt,sha256=CnoMgOphCoAdGTLueWdCVByVyjwOubaGiTB1lchdy4M,21
+ai_data_science_team-0.0.0.9013.dist-info/RECORD,,