ai-data-science-team 0.0.0.9009__py3-none-any.whl → 0.0.0.9011__py3-none-any.whl

ai_data_science_team/tools/{metadata.py → sql.py}

@@ -1,143 +1,7 @@
-import io
+
 import pandas as pd
 import sqlalchemy as sql
 from sqlalchemy import inspect
-from typing import Union, List, Dict
-
-def get_dataframe_summary(
-    dataframes: Union[pd.DataFrame, List[pd.DataFrame], Dict[str, pd.DataFrame]],
-    n_sample: int = 30,
-    skip_stats: bool = False,
-) -> List[str]:
-    """
-    Generate a summary for one or more DataFrames. Accepts a single DataFrame, a list of DataFrames,
-    or a dictionary mapping names to DataFrames.
-
-    Parameters
-    ----------
-    dataframes : pandas.DataFrame or list of pandas.DataFrame or dict of (str -> pandas.DataFrame)
-        - Single DataFrame: produce a single summary (returned within a one-element list).
-        - List of DataFrames: produce a summary for each DataFrame, using index-based names.
-        - Dictionary of DataFrames: produce a summary for each DataFrame, using dictionary keys as names.
-    n_sample : int, default 30
-        Number of rows to display in the "Data (first 30 rows)" section.
-    skip_stats : bool, default False
-        If True, skip the descriptive statistics and DataFrame info sections.
-        
-    Example:
-    --------
-    ``` python
-    import pandas as pd
-    from sklearn.datasets import load_iris
-    data = load_iris(as_frame=True)
-    dataframes = {
-        "iris": data.frame,
-        "iris_target": data.target,
-    }
-    summaries = get_dataframe_summary(dataframes)
-    print(summaries[0])
-    ```
-
-    Returns
-    -------
-    list of str
-        A list of summaries, one for each provided DataFrame. Each summary includes:
-        - Shape of the DataFrame (rows, columns)
-        - Column data types
-        - Missing value percentage
-        - Unique value counts
-        - First 30 rows
-        - Descriptive statistics
-        - DataFrame info output
-    """
-
-    summaries = []
-
-    # --- Dictionary Case ---
-    if isinstance(dataframes, dict):
-        for dataset_name, df in dataframes.items():
-            summaries.append(_summarize_dataframe(df, dataset_name, n_sample, skip_stats))
-
-    # --- Single DataFrame Case ---
-    elif isinstance(dataframes, pd.DataFrame):
-        summaries.append(_summarize_dataframe(dataframes, "Single_Dataset", n_sample, skip_stats))
-
-    # --- List of DataFrames Case ---
-    elif isinstance(dataframes, list):
-        for idx, df in enumerate(dataframes):
-            dataset_name = f"Dataset_{idx}"
-            summaries.append(_summarize_dataframe(df, dataset_name, n_sample, skip_stats))
-
-    else:
-        raise TypeError(
-            "Input must be a single DataFrame, a list of DataFrames, or a dictionary of DataFrames."
-        )
-
-    return summaries
-
-
-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().
-    df = df.apply(lambda col: col.map(lambda x: str(x) if isinstance(x, dict) else x))
-    
-    # 2. Capture df.info() output
-    buffer = io.StringIO()
-    df.info(buf=buffer)
-    info_text = buffer.getvalue()
-
-    # 3. Calculate missing value stats
-    missing_stats = (df.isna().sum() / len(df) * 100).sort_values(ascending=False)
-    missing_summary = "\n".join([f"{col}: {val:.2f}%" for col, val in missing_stats.items()])
-
-    # 4. Get column data types
-    column_types = "\n".join([f"{col}: {dtype}" for col, dtype in df.dtypes.items()])
-
-    # 5. Get unique value counts
-    unique_counts = df.nunique()  # Will no longer fail on unhashable dict
-    unique_counts_summary = "\n".join([f"{col}: {count}" for col, count in unique_counts.items()])
-
-    # 6. Generate the summary text
-    if not skip_stats:
-        summary_text = f"""
-        Dataset Name: {dataset_name}
-        ----------------------------
-        Shape: {df.shape[0]} rows x {df.shape[1]} columns
-
-        Column Data Types:
-        {column_types}
-
-        Missing Value Percentage:
-        {missing_summary}
-
-        Unique Value Counts:
-        {unique_counts_summary}
-
-        Data (first {n_sample} rows):
-        {df.head(n_sample).to_string()}
-
-        Data Description:
-        {df.describe().to_string()}
-
-        Data Info:
-        {info_text}
-        """
-    else:
-        summary_text = f"""
-        Dataset Name: {dataset_name}
-        ----------------------------
-        Shape: {df.shape[0]} rows x {df.shape[1]} columns
-
-        Column Data Types:
-        {column_types}
-
-        Data (first {n_sample} rows):
-        {df.head(n_sample).to_string()}
-        """
-        
-    return summary_text.strip()
-
 
 
 def get_database_metadata(connection, n_samples=10) -> dict:

{ai_data_science_team-0.0.0.9009.dist-info → ai_data_science_team-0.0.0.9011.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: ai-data-science-team
-Version: 0.0.0.9009
+Version: 0.0.0.9011
 Summary: Build and run an AI-powered data science team.
 Home-page: https://github.com/business-science/ai-data-science-team
 Author: Matt Dancho
@@ -27,10 +27,13 @@ Requires-Dist: plotly
 Requires-Dist: streamlit
 Requires-Dist: scikit-learn
 Requires-Dist: xgboost
-Provides-Extra: machine-learning-agent
-Requires-Dist: h2o; extra == "machine-learning-agent"
+Requires-Dist: psutil
+Provides-Extra: machine-learning
+Requires-Dist: h2o; extra == "machine-learning"
+Requires-Dist: mlflow; extra == "machine-learning"
 Provides-Extra: all
 Requires-Dist: h2o; extra == "all"
+Requires-Dist: mlflow; extra == "all"
 Dynamic: author
 Dynamic: author-email
 Dynamic: classifier
@@ -45,7 +48,7 @@ Dynamic: summary
 <div align="center">
   <a href="https://github.com/business-science/ai-data-science-team">
     <picture>
-      <img src="/img/ai_data_science_team_logo.jpg" alt="AI Data Science Team" width="400">
+      <img src="/img/ai_data_science_team_logo_small.jpg" alt="AI Data Science Team" width="400">
   </picture>
   </a>
 </div>
@@ -86,9 +89,12 @@ The AI Data Science Team of Copilots includes Agents that specialize data cleani
   - [Generative AI for Data Scientists Workshop](#generative-ai-for-data-scientists-workshop)
   - [Data Science Agents](#data-science-agents)
     - [NEW: Multi-Agents](#new-multi-agents)
-    - [Coming Soon: Data Science Apps](#coming-soon-data-science-apps)
+    - [Data Science Apps](#data-science-apps)
+    - [Apps Available Now](#apps-available-now)
+      - [🔥 Agentic Applications](#-agentic-applications)
     - [Agents Available Now](#agents-available-now)
-      - [Data Science Agents](#data-science-agents-1)
+      - [Agents](#agents)
+      - [🔥🔥 NEW! Machine Learning Agents](#-new-machine-learning-agents)
       - [Multi-Agents](#multi-agents)
     - [Agents Coming Soon](#agents-coming-soon)
   - [Disclaimer](#disclaimer)
@@ -116,7 +122,7 @@ If you're an aspiring data scientist who wants to learn how to build AI Agents a
 
 This project is a work in progress. New data science agents will be released soon.
 
-![Data Science Team](/img/ai_data_science_team.jpg)
+![AI Data Science Team](/img/ai_data_science_team_.jpg) 
 
 ### NEW: Multi-Agents
 
@@ -124,32 +130,47 @@ This is the internals of the SQL Data Analyst Agent that connects to SQL databas
 
 ![Business Intelligence SQL Agent](/img/multi_agent_sql_data_visualization.jpg)
 
-### Coming Soon: Data Science Apps
+### Data Science Apps
 
 This is a top secret project I'm working on. It's a multi-agent data science app that performs time series forecasting.
 
-![Multi-Agent Data Science App](/img/ai_powered_apps.jpg)
+![Multi-Agent Data Science App](/img/ai_powered_apps.jpg) 
+
+### Apps Available Now
+
+[See all available apps here](/apps)
+
+#### 🔥 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/)
 
 ### Agents Available Now
 
-#### Data Science Agents
+#### Agents
+
+1. **Data Wrangling Agent:** Merges, Joins, Preps and Wrangles data into a format that is ready for data analysis. [See Example](https://github.com/business-science/ai-data-science-team/blob/master/examples/data_wrangling_agent.ipynb)
+2. **Data Visualization Agent:** Creates visualizations to help you understand your data. Returns JSON serializable plotly visualizations. [See Example](https://github.com/business-science/ai-data-science-team/blob/master/examples/data_visualization_agent.ipynb)
+3. **🔥 Data Cleaning Agent:** Performs Data Preparation steps including handling missing values, outliers, and data type conversions. [See Example](https://github.com/business-science/ai-data-science-team/blob/master/examples/data_cleaning_agent.ipynb)
+4. **Feature Engineering Agent:** Converts the prepared data into ML-ready data. Adds features to increase predictive accuracy of ML models. [See Example](https://github.com/business-science/ai-data-science-team/blob/master/examples/feature_engineering_agent.ipynb)
+5. **🔥 SQL Database 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. [See Example](https://github.com/business-science/ai-data-science-team/blob/master/examples/sql_database_agent.ipynb)
+6. **Data Loader Tools Agent:** Loads data from various sources including CSV, Excel, Parquet, and Pickle files. [See Example](https://github.com/business-science/ai-data-science-team/blob/master/examples/data_loader_tools_agent.ipynb)
+
+
+#### 🔥🔥 NEW! Machine Learning Agents
+
+1. **🔥 H2O Machine Learning Agent:** Builds and logs 100's of high-performance machine learning models. [See Example](https://github.com/business-science/ai-data-science-team/blob/master/examples/ml_agents/h2o_machine_learning_agent.ipynb)
+2. **🔥 MLflow Tools Agent (MLOps):** This agent has 11+ tools for managing models, ML projects, and making production ML predictions with MLflow. [See Example](https://github.com/business-science/ai-data-science-team/blob/master/examples/ml_agents/mlflow_tools_agent.ipynb)
 
-1. **Data Wrangling Agent:** Merges, Joins, Preps and Wrangles data into a format that is ready for data analysis.
-2. **Data Visualization Agent:** Creates visualizations to help you understand your data. Returns JSON serializable plotly visualizations.
-3. **Data Cleaning Agent:** Performs Data Preparation steps including handling missing values, outliers, and data type conversions.
-4. **Feature Engineering Agent:** Converts the prepared data into ML-ready data. Adds features to increase predictive accuracy of ML models.
-5. **SQL Database 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.
 
 #### 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.
+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)
 
 ### Agents Coming Soon
 
 1. **Data Analyst:** Analyzes data structure, creates exploratory visualizations, and performs correlation analysis to identify relationships.
-2. **Machine Learning Agent:** Builds and logs the machine learning models.
-3. **Interpretability Agent:** Performs Interpretable ML to explain why the model returned predictions including which features were the most important to the model.
-4. **Supervisor:** Forms task list. Moderates sub-agents. Returns completed assignment. 
+2. **Interpretability Agent:** Performs Interpretable ML to explain why the model returned predictions including which features were the most important to the model.
+3. **Supervisor:** Forms task list. Moderates sub-agents. Returns completed assignment. 
 
 ## Disclaimer
 

ai_data_science_team-0.0.0.9011.dist-info/RECORD

@@ -0,0 +1,36 @@
+ai_data_science_team/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+ai_data_science_team/_version.py,sha256=2kHKuNhTDtlOUMah-41rNdTSBWrq3Lr4KsZbtsfHvPE,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_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/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/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
+ai_data_science_team/parsers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+ai_data_science_team/parsers/parsers.py,sha256=hIsMZXRHz9hqs8R1ebymKA7D6NxOf5UVMpDAr_gGhE8,2027
+ai_data_science_team/templates/__init__.py,sha256=_IcyFUu_mM8dFtttz95h0csJZ-XWDP3cEFuf22-R5RM,330
+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/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
+ai_data_science_team/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+ai_data_science_team/utils/logging.py,sha256=7wFOv6GGhXR_RPbh-8p0GyrS608XOnZtiaGK2IbDl_s,2081
+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-0.0.0.9011.dist-info/LICENSE,sha256=Xif0IRLdd2HGLATxV2EVp91aSY6KOuacRr_6BorKGzA,1084
+ai_data_science_team-0.0.0.9011.dist-info/METADATA,sha256=LxSjuOR2ArtBi-jauFoWQx7TGakHg7TJ8leKQIi7fmk,11854
+ai_data_science_team-0.0.0.9011.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+ai_data_science_team-0.0.0.9011.dist-info/top_level.txt,sha256=CnoMgOphCoAdGTLueWdCVByVyjwOubaGiTB1lchdy4M,21
+ai_data_science_team-0.0.0.9011.dist-info/RECORD,,

ai_data_science_team-0.0.0.9009.dist-info/RECORD

@@ -1,28 +0,0 @@
-ai_data_science_team/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-ai_data_science_team/_version.py,sha256=IEp7uHd_8RlLYvLFCpp_wJCutdvJI7cJ73IN0GzK3ts,26
-ai_data_science_team/orchestration.py,sha256=xiIFOsrLwPdkSmtme7wNCCGv8XopnMTNElNzlZokL-4,303
-ai_data_science_team/agents/__init__.py,sha256=KSwxfciazWyaDG-xM93SadiIyT6X4d3uJLTdvHvVKq0,553
-ai_data_science_team/agents/data_cleaning_agent.py,sha256=OWJ3tEA5cy2fo92bTmKS8CDA48ZRRqmWg2kH7cacjDM,27337
-ai_data_science_team/agents/data_visualization_agent.py,sha256=pm7yln3GI91mOAjwDveenWwYXtJqh990oFvsoFhX3aA,28864
-ai_data_science_team/agents/data_wrangling_agent.py,sha256=UUoejYBmVFdM4At_CKQjYUyFHkaloowdd6yAElfeV9Q,32332
-ai_data_science_team/agents/feature_engineering_agent.py,sha256=bngc0COOYa8AolJwQrNuO1aDRgwBCp6LCN9_otIscWk,31011
-ai_data_science_team/agents/sql_database_agent.py,sha256=M_7IBOu7ISZZEtDAC9KGQIE7FPaXSyQ5IdD8vu91_DM,31164
-ai_data_science_team/ml_agents/__init__.py,sha256=fA5uX6dSVMAf2ApmBJXEArbnKNmsmuE0nbBsCeNAksk,86
-ai_data_science_team/ml_agents/h2o_ml_agent.py,sha256=h6kz8ZPw7ApCdfrKBqggHfBnwBJ3kDSzLMwxMxz_2tM,55181
-ai_data_science_team/multiagents/__init__.py,sha256=aI4GztEwmkexZKT5XHcH3cAjO-xYUhncb3yfPJQDqTA,99
-ai_data_science_team/multiagents/sql_data_analyst.py,sha256=2gETU9O5t9R5Ut1kEW1T3H-6Sh8xDzDfQmFV3i5lMKs,14233
-ai_data_science_team/multiagents/supervised_data_analyst.py,sha256=uduCYpicga-UCf9nPQktQggW96-HDlqvioYmEdWejtI,158
-ai_data_science_team/templates/__init__.py,sha256=_IcyFUu_mM8dFtttz95h0csJZ-XWDP3cEFuf22-R5RM,330
-ai_data_science_team/templates/agent_templates.py,sha256=pphuitXUVv21ljr_H-aof6Xq78KvDY0adF3K6lXGEz4,29107
-ai_data_science_team/tools/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-ai_data_science_team/tools/logging.py,sha256=7wFOv6GGhXR_RPbh-8p0GyrS608XOnZtiaGK2IbDl_s,2081
-ai_data_science_team/tools/metadata.py,sha256=3lPxLEUr3I9AF6wIKx5en-GV6JVkpUHDSLQxKj1N5Gs,9313
-ai_data_science_team/tools/parsers.py,sha256=BAi-fJT7BBt9nRS3w5n9LDTsu7JAJsH8CAI9-Qf7jCs,2086
-ai_data_science_team/tools/regex.py,sha256=lwarbLqTA2VfNQSyqKCl-PBlH_0WH3zXZvYGBYGUiu4,5144
-ai_data_science_team/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-ai_data_science_team/utils/plotly.py,sha256=nST-NG0oizKVHhH6HsjHUpTUumq9bCccBdxjuaJWnVQ,504
-ai_data_science_team-0.0.0.9009.dist-info/LICENSE,sha256=Xif0IRLdd2HGLATxV2EVp91aSY6KOuacRr_6BorKGzA,1084
-ai_data_science_team-0.0.0.9009.dist-info/METADATA,sha256=iMIyksmkPmuj9TI_oIa1lXGJYKVspxhWvflBJ1zlW0o,9875
-ai_data_science_team-0.0.0.9009.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-ai_data_science_team-0.0.0.9009.dist-info/top_level.txt,sha256=CnoMgOphCoAdGTLueWdCVByVyjwOubaGiTB1lchdy4M,21
-ai_data_science_team-0.0.0.9009.dist-info/RECORD,,