ai-data-science-team 0.0.0.9015__tar.gz → 0.0.0.9016__tar.gz

{ai_data_science_team-0.0.0.9015/ai_data_science_team.egg-info → ai_data_science_team-0.0.0.9016}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: ai-data-science-team
-Version: 0.0.0.9015
+Version: 0.0.0.9016
 Summary: Build and run an AI-powered data science team.
 Home-page: https://github.com/business-science/ai-data-science-team
 Author: Matt Dancho
@@ -47,6 +47,7 @@ Dynamic: classifier
 Dynamic: description
 Dynamic: description-content-type
 Dynamic: home-page
+Dynamic: license-file
 Dynamic: provides-extra
 Dynamic: requires-dist
 Dynamic: requires-python
@@ -97,9 +98,8 @@ The AI Data Science Team of Copilots includes Agents that specialize data cleani
   - [Companies That Want A Custom AI Data Science Team (And AI Apps)](#companies-that-want-a-custom-ai-data-science-team-and-ai-apps)
   - [Generative AI for Data Scientists Workshop](#generative-ai-for-data-scientists-workshop)
   - [Data Science Agents](#data-science-agents)
+    - [🔥 NEW: Data Science Apps](#-new-data-science-apps)
     - [NEW: Multi-Agents](#new-multi-agents)
-    - [Data Science Apps](#data-science-apps)
-    - [Apps Available Now](#apps-available-now)
       - [🔥 Agentic Applications](#-agentic-applications)
     - [Agents Available Now](#agents-available-now)
       - [Standard Agents](#standard-agents)
@@ -110,11 +110,11 @@ The AI Data Science Team of Copilots includes Agents that specialize data cleani
   - [Disclaimer](#disclaimer)
   - [Installation](#installation)
   - [Usage](#usage)
-    - [Example 1: Feature Engineering with the Feature Engineering Agent](#example-1-feature-engineering-with-the-feature-engineering-agent)
-    - [Example 2: Cleaning Data with the Data Cleaning Agent](#example-2-cleaning-data-with-the-data-cleaning-agent)
+    - [Example: H2O Machine Learning Agent](#example-h2o-machine-learning-agent)
   - [Contributing](#contributing)
   - [License](#license)
 - [Want To Become A Full-Stack Generative AI Data Scientist?](#want-to-become-a-full-stack-generative-ai-data-scientist)
+- [⭐️ Star History](#️-star-history)
 
 ## Companies That Want A Custom AI Data Science Team (And AI Apps)
 
@@ -134,21 +134,24 @@ This project is a work in progress. New data science agents will be released soo
 
 ![AI Data Science Team](/img/ai_data_science_team.jpg) 
 
-### NEW: Multi-Agents
+### 🔥 NEW: Data Science Apps
 
-**🔥 Pandas Data Analyst Agent:** Combines the ability to wrangle, transform, and analyze data with an optional data visualization agent that can create interactive plots.
+**🔥 Open Pandas AI Data Analyst:** Load an Excel or CSV file and ask it questions. Get data and charts back. 
+
+![Pandas Data Analyst App](/img/apps/ai_pandas_data_analyst_app.jpg)
+
+**🔥 SQL Database Agent:** Connects any SQL Database, generates SQL queries from natural language, and returns data as a downloadable table.
 
-![Business Intelligence SQL Agent](/img/multi_agent_pandas_data_analyst.jpg)
+**🔥 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.
 
-### Data Science Apps
+[See all available apps here](/apps)
 
-This is a top secret project I'm working on. It's a multi-agent data science app that performs time series forecasting.
+### NEW: Multi-Agents
 
-![Multi-Agent Data Science App](/img/ai_powered_apps.jpg) 
+**🔥 Pandas Data Analyst Agent:** Combines the ability to wrangle, transform, and analyze data with an optional data visualization agent that can create interactive plots.
 
-### Apps Available Now
+![Pandas Data Analyst Agent](/img/multi_agent_pandas_data_analyst.jpg)
 
-[See all available apps here](/apps)
 
 #### 🔥 Agentic Applications
 
@@ -205,6 +208,14 @@ By using this software, you agree to use it solely for learning purposes.
 
 ## Installation
 
+You can install via PyPI (note that this is a beta version and breaking changes may occur until 0.1.0):
+
+``` bash
+pip install ai-data-science-team
+```
+
+Or, if you want the latest version from GitHub:
+
 ``` bash
 pip install git+https://github.com/business-science/ai-data-science-team.git --upgrade
 ```
@@ -213,55 +224,46 @@ pip install git+https://github.com/business-science/ai-data-science-team.git --u
 
 [See all examples here.](/examples)
 
-### Example 1: Feature Engineering with the Feature Engineering Agent
+### Example: H2O Machine Learning Agent
 
-[See the full example here.](/examples/feature_engineering_agent.ipynb)
+[See the full example here.](https://github.com/business-science/ai-data-science-team/blob/master/examples/ml_agents/h2o_machine_learning_agent.ipynb)
 
 ``` python
-feature_engineering_agent = FeatureEngineeringAgent(model = llm)
-
-feature_engineering_agent.invoke_agent(
-    data_raw = df,
-    user_instructions = "Make sure to scale and center numeric features",
-    target_variable = "Churn",
-    max_retries = 3,
+# Import libraries
+from langchain_openai import ChatOpenAI
+import pandas as pd
+import h2o 
+import os
+from ai_data_science_team.ml_agents import H2OMLAgent
+
+# Load the data
+df = pd.read_csv("data/churn_data.csv")
+df
+
+# Initialize the language model
+os.environ['OPENAI_API_KEY'] = "YOUR_OPENAI_API_KEY"
+llm = ChatOpenAI(model=MODEL)
+llm
+
+# Initialize the H2O ML Agent
+ml_agent = H2OMLAgent(
+    model=llm, 
+    log=True, 
+    log_path="logs/",
+    model_directory="h2o_models/", 
+    enable_mlflow=True, # Use this if you wish to log models to MLflow 
 )
-```
-
-``` bash
----FEATURE ENGINEERING AGENT----
-    * CREATE FEATURE ENGINEER CODE
-    * EXECUTING AGENT CODE
-    * EXPLAIN AGENT CODE
-```
-
-``` python
-feature_engineering_agent.get_data_engineered()
-```
-
-### Example 2: Cleaning Data with the Data Cleaning Agent
-
-[See the full example here.](/examples/data_cleaning_agent.ipynb) 
-
-``` python
-data_cleaning_agent = DataCleaningAgent(model = llm)
+ml_agent
 
-response = data_cleaning_agent.invoke_agent(
-    data_raw = df,
-    user_instructions = "Don't remove outliers when cleaning the data.",
-    max_retries = 3,
+# Run the agent
+ml_agent.invoke_agent(
+    data_raw=df.drop(columns=["customerID"]),
+    user_instructions="Please do classification on 'Churn'. Use a max runtime of 30 seconds.",
+    target_variable="Churn"
 )
-```
-
-``` bash
----DATA CLEANING AGENT----
-    * CREATE DATA CLEANER CODE
-    * EXECUTING AGENT CODE
-    * EXPLAIN AGENT CODE
-```
 
-``` python
-data_cleaning_agent.get_data_cleaned()
+# Retrieve and display the leaderboard of models
+ml_agent.get_leaderboard()
 ```
 
 ## Contributing
@@ -282,4 +284,8 @@ This project is licensed under the MIT License. See LICENSE file for details.
 
 I teach Generative AI Data Science to help you build AI-powered data science apps. [**Register for my next Generative AI for Data Scientists workshop here.**](https://learn.business-science.io/ai-register)
 
+# ⭐️ Star History
 
+[![Star History Chart](https://api.star-history.com/svg?repos=business-science/ai-data-science-team&type=Date)](https://star-history.com/#)
+
+[**Please ⭐ us on GitHub (it takes 2 seconds and means a lot).**](https://github.com/business-science/ai-data-science-team)

{ai_data_science_team-0.0.0.9015 → ai_data_science_team-0.0.0.9016}/README.md

@@ -43,9 +43,8 @@ The AI Data Science Team of Copilots includes Agents that specialize data cleani
   - [Companies That Want A Custom AI Data Science Team (And AI Apps)](#companies-that-want-a-custom-ai-data-science-team-and-ai-apps)
   - [Generative AI for Data Scientists Workshop](#generative-ai-for-data-scientists-workshop)
   - [Data Science Agents](#data-science-agents)
+    - [🔥 NEW: Data Science Apps](#-new-data-science-apps)
     - [NEW: Multi-Agents](#new-multi-agents)
-    - [Data Science Apps](#data-science-apps)
-    - [Apps Available Now](#apps-available-now)
       - [🔥 Agentic Applications](#-agentic-applications)
     - [Agents Available Now](#agents-available-now)
       - [Standard Agents](#standard-agents)
@@ -56,11 +55,11 @@ The AI Data Science Team of Copilots includes Agents that specialize data cleani
   - [Disclaimer](#disclaimer)
   - [Installation](#installation)
   - [Usage](#usage)
-    - [Example 1: Feature Engineering with the Feature Engineering Agent](#example-1-feature-engineering-with-the-feature-engineering-agent)
-    - [Example 2: Cleaning Data with the Data Cleaning Agent](#example-2-cleaning-data-with-the-data-cleaning-agent)
+    - [Example: H2O Machine Learning Agent](#example-h2o-machine-learning-agent)
   - [Contributing](#contributing)
   - [License](#license)
 - [Want To Become A Full-Stack Generative AI Data Scientist?](#want-to-become-a-full-stack-generative-ai-data-scientist)
+- [⭐️ Star History](#️-star-history)
 
 ## Companies That Want A Custom AI Data Science Team (And AI Apps)
 
@@ -80,21 +79,24 @@ This project is a work in progress. New data science agents will be released soo
 
 ![AI Data Science Team](/img/ai_data_science_team.jpg) 
 
-### NEW: Multi-Agents
+### 🔥 NEW: Data Science Apps
 
-**🔥 Pandas Data Analyst Agent:** Combines the ability to wrangle, transform, and analyze data with an optional data visualization agent that can create interactive plots.
+**🔥 Open Pandas AI Data Analyst:** Load an Excel or CSV file and ask it questions. Get data and charts back. 
+
+![Pandas Data Analyst App](/img/apps/ai_pandas_data_analyst_app.jpg)
+
+**🔥 SQL Database Agent:** Connects any SQL Database, generates SQL queries from natural language, and returns data as a downloadable table.
 
-![Business Intelligence SQL Agent](/img/multi_agent_pandas_data_analyst.jpg)
+**🔥 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.
 
-### Data Science Apps
+[See all available apps here](/apps)
 
-This is a top secret project I'm working on. It's a multi-agent data science app that performs time series forecasting.
+### NEW: Multi-Agents
 
-![Multi-Agent Data Science App](/img/ai_powered_apps.jpg) 
+**🔥 Pandas Data Analyst Agent:** Combines the ability to wrangle, transform, and analyze data with an optional data visualization agent that can create interactive plots.
 
-### Apps Available Now
+![Pandas Data Analyst Agent](/img/multi_agent_pandas_data_analyst.jpg)
 
-[See all available apps here](/apps)
 
 #### 🔥 Agentic Applications
 
@@ -151,6 +153,14 @@ By using this software, you agree to use it solely for learning purposes.
 
 ## Installation
 
+You can install via PyPI (note that this is a beta version and breaking changes may occur until 0.1.0):
+
+``` bash
+pip install ai-data-science-team
+```
+
+Or, if you want the latest version from GitHub:
+
 ``` bash
 pip install git+https://github.com/business-science/ai-data-science-team.git --upgrade
 ```
@@ -159,55 +169,46 @@ pip install git+https://github.com/business-science/ai-data-science-team.git --u
 
 [See all examples here.](/examples)
 
-### Example 1: Feature Engineering with the Feature Engineering Agent
+### Example: H2O Machine Learning Agent
 
-[See the full example here.](/examples/feature_engineering_agent.ipynb)
+[See the full example here.](https://github.com/business-science/ai-data-science-team/blob/master/examples/ml_agents/h2o_machine_learning_agent.ipynb)
 
 ``` python
-feature_engineering_agent = FeatureEngineeringAgent(model = llm)
-
-feature_engineering_agent.invoke_agent(
-    data_raw = df,
-    user_instructions = "Make sure to scale and center numeric features",
-    target_variable = "Churn",
-    max_retries = 3,
+# Import libraries
+from langchain_openai import ChatOpenAI
+import pandas as pd
+import h2o 
+import os
+from ai_data_science_team.ml_agents import H2OMLAgent
+
+# Load the data
+df = pd.read_csv("data/churn_data.csv")
+df
+
+# Initialize the language model
+os.environ['OPENAI_API_KEY'] = "YOUR_OPENAI_API_KEY"
+llm = ChatOpenAI(model=MODEL)
+llm
+
+# Initialize the H2O ML Agent
+ml_agent = H2OMLAgent(
+    model=llm, 
+    log=True, 
+    log_path="logs/",
+    model_directory="h2o_models/", 
+    enable_mlflow=True, # Use this if you wish to log models to MLflow 
 )
-```
-
-``` bash
----FEATURE ENGINEERING AGENT----
-    * CREATE FEATURE ENGINEER CODE
-    * EXECUTING AGENT CODE
-    * EXPLAIN AGENT CODE
-```
-
-``` python
-feature_engineering_agent.get_data_engineered()
-```
-
-### Example 2: Cleaning Data with the Data Cleaning Agent
-
-[See the full example here.](/examples/data_cleaning_agent.ipynb) 
-
-``` python
-data_cleaning_agent = DataCleaningAgent(model = llm)
+ml_agent
 
-response = data_cleaning_agent.invoke_agent(
-    data_raw = df,
-    user_instructions = "Don't remove outliers when cleaning the data.",
-    max_retries = 3,
+# Run the agent
+ml_agent.invoke_agent(
+    data_raw=df.drop(columns=["customerID"]),
+    user_instructions="Please do classification on 'Churn'. Use a max runtime of 30 seconds.",
+    target_variable="Churn"
 )
-```
-
-``` bash
----DATA CLEANING AGENT----
-    * CREATE DATA CLEANER CODE
-    * EXECUTING AGENT CODE
-    * EXPLAIN AGENT CODE
-```
 
-``` python
-data_cleaning_agent.get_data_cleaned()
+# Retrieve and display the leaderboard of models
+ml_agent.get_leaderboard()
 ```
 
 ## Contributing
@@ -228,4 +229,8 @@ This project is licensed under the MIT License. See LICENSE file for details.
 
 I teach Generative AI Data Science to help you build AI-powered data science apps. [**Register for my next Generative AI for Data Scientists workshop here.**](https://learn.business-science.io/ai-register)
 
+# ⭐️ Star History
 
+[![Star History Chart](https://api.star-history.com/svg?repos=business-science/ai-data-science-team&type=Date)](https://star-history.com/#)
+
+[**Please ⭐ us on GitHub (it takes 2 seconds and means a lot).**](https://github.com/business-science/ai-data-science-team)

ai_data_science_team-0.0.0.9016/ai_data_science_team/_version.py

@@ -0,0 +1 @@
+__version__ = "0.0.0.9016"

{ai_data_science_team-0.0.0.9015 → ai_data_science_team-0.0.0.9016}/ai_data_science_team/ds_agents/eda_tools_agent.py

@@ -1,5 +1,3 @@
-
-
 from typing import Any, Optional, Annotated, Sequence, Dict
 import operator
 import pandas as pd
@@ -17,10 +15,11 @@ 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,
+    describe_dataset,
+    visualize_missing,
+    generate_correlation_funnel,
     generate_sweetviz_report,
+    generate_dtale_report,
 )
 from ai_data_science_team.utils.messages import get_tool_call_names
 
@@ -32,15 +31,17 @@ EDA_TOOLS = [
     explain_data,
     describe_dataset,
     visualize_missing,
-    correlation_funnel,
+    generate_correlation_funnel,
     generate_sweetviz_report,
+    generate_dtale_report,
 ]
 
+
 class EDAToolsAgent(BaseAgent):
     """
     An Exploratory Data Analysis Tools Agent that interacts with EDA tools to generate summary statistics,
     missing data visualizations, correlation funnels, EDA reports, etc.
-    
+
     Parameters:
     ----------
     model : langchain.llms.base.LLM
@@ -52,9 +53,9 @@ class EDAToolsAgent(BaseAgent):
     checkpointer : Checkpointer, optional
         The checkpointer for the agent.
     """
-    
+
     def __init__(
-        self, 
+        self,
         model: Any,
         create_react_agent_kwargs: Optional[Dict] = {},
         invoke_react_agent_kwargs: Optional[Dict] = {},
@@ -64,18 +65,18 @@ class EDAToolsAgent(BaseAgent):
             "model": model,
             "create_react_agent_kwargs": create_react_agent_kwargs,
             "invoke_react_agent_kwargs": invoke_react_agent_kwargs,
-            "checkpointer": checkpointer
+            "checkpointer": checkpointer,
         }
         self._compiled_graph = self._make_compiled_graph()
         self.response = None
-        
+
     def _make_compiled_graph(self):
         """
         Creates the compiled state graph for the EDA agent.
         """
         self.response = None
         return make_eda_tools_agent(**self._params)
-    
+
     def update_params(self, **kwargs):
         """
         Updates the agent's parameters and rebuilds the compiled graph.
@@ -83,16 +84,13 @@ class EDAToolsAgent(BaseAgent):
         for k, v in kwargs.items():
             self._params[k] = v
         self._compiled_graph = self._make_compiled_graph()
-        
+
     async def ainvoke_agent(
-        self, 
-        user_instructions: str = None, 
-        data_raw: pd.DataFrame = None, 
-        **kwargs
+        self, user_instructions: str = None, data_raw: pd.DataFrame = None, **kwargs
     ):
         """
         Asynchronously runs the agent with user instructions and data.
-        
+
         Parameters:
         ----------
         user_instructions : str, optional
@@ -105,20 +103,17 @@ class EDAToolsAgent(BaseAgent):
                 "user_instructions": user_instructions,
                 "data_raw": data_raw.to_dict() if data_raw is not None else None,
             },
-            **kwargs
+            **kwargs,
         )
         self.response = response
         return None
-    
+
     def invoke_agent(
-        self, 
-        user_instructions: str = None, 
-        data_raw: pd.DataFrame = None, 
-        **kwargs
+        self, user_instructions: str = None, data_raw: pd.DataFrame = None, **kwargs
     ):
         """
         Synchronously runs the agent with user instructions and data.
-        
+
         Parameters:
         ----------
         user_instructions : str, optional
@@ -131,24 +126,26 @@ class EDAToolsAgent(BaseAgent):
                 "user_instructions": user_instructions,
                 "data_raw": data_raw.to_dict() if data_raw is not None else None,
             },
-            **kwargs
+            **kwargs,
         )
         self.response = response
         return None
-    
+
     def get_internal_messages(self, markdown: bool = False):
         """
         Returns internal messages from the agent response.
         """
         pretty_print = "\n\n".join(
-            [f"### {msg.type.upper()}\n\nID: {msg.id}\n\nContent:\n\n{msg.content}" 
-             for msg in self.response["internal_messages"]]
+            [
+                f"### {msg.type.upper()}\n\nID: {msg.id}\n\nContent:\n\n{msg.content}"
+                for msg in self.response["internal_messages"]
+            ]
         )
         if markdown:
             return Markdown(pretty_print)
         else:
             return self.response["internal_messages"]
-    
+
     def get_artifacts(self, as_dataframe: bool = False):
         """
         Returns the EDA artifacts from the agent response.
@@ -157,7 +154,7 @@ class EDAToolsAgent(BaseAgent):
             return pd.DataFrame(self.response["eda_artifacts"])
         else:
             return self.response["eda_artifacts"]
-    
+
     def get_ai_message(self, markdown: bool = False):
         """
         Returns the AI message from the agent response.
@@ -166,13 +163,14 @@ 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,
     create_react_agent_kwargs: Optional[Dict] = {},
@@ -181,7 +179,7 @@ def make_eda_tools_agent(
 ):
     """
     Creates an Exploratory Data Analyst Agent that can interact with EDA tools.
-    
+
     Parameters:
     ----------
     model : Any
@@ -192,13 +190,13 @@ def make_eda_tools_agent(
         Additional kwargs for agent invocation.
     checkpointer : Checkpointer, optional
         The checkpointer for the agent.
-    
+
     Returns:
     -------
     app : langgraph.graph.CompiledStateGraph
         The compiled state graph for the EDA agent.
     """
-    
+
     class GraphState(AgentState):
         internal_messages: Annotated[Sequence[BaseMessage], operator.add]
         user_instructions: str
@@ -209,11 +207,9 @@ def make_eda_tools_agent(
     def exploratory_agent(state):
         print(format_agent_name(AGENT_NAME))
         print("    * RUN REACT TOOL-CALLING AGENT FOR EDA")
-        
-        tool_node = ToolNode(
-            tools=EDA_TOOLS
-        )
-        
+
+        tool_node = ToolNode(tools=EDA_TOOLS)
+
         eda_agent = create_react_agent(
             model,
             tools=tool_node,
@@ -221,7 +217,7 @@ def make_eda_tools_agent(
             **create_react_agent_kwargs,
             checkpointer=checkpointer,
         )
-        
+
         response = eda_agent.invoke(
             {
                 "messages": [("user", state["user_instructions"])],
@@ -229,13 +225,13 @@ def make_eda_tools_agent(
             },
             invoke_react_agent_kwargs,
         )
-        
+
         print("    * POST-PROCESSING EDA RESULTS")
-        
-        internal_messages = response['messages']
+
+        internal_messages = response["messages"]
         if not internal_messages:
             return {"internal_messages": [], "eda_artifacts": None}
-        
+
         last_ai_message = AIMessage(internal_messages[-1].content, role=AGENT_NAME)
         last_tool_artifact = None
         if len(internal_messages) > 1:
@@ -244,24 +240,24 @@ 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)
     workflow.add_node("exploratory_agent", exploratory_agent)
     workflow.add_edge(START, "exploratory_agent")
     workflow.add_edge("exploratory_agent", END)
-    
+
     app = workflow.compile(
         checkpointer=checkpointer,
         name=AGENT_NAME,
     )
-    
+
     return app