ai-data-science-team 0.0.0.9005__py3-none-any.whl → 0.0.0.9007__py3-none-any.whl

ai_data_science_team/tools/data_analysis.py

@@ -1,116 +0,0 @@
-import io
-import pandas as pd
-from typing import Union, List, Dict
-
-def summarize_dataframes(
-    dataframes: Union[pd.DataFrame, List[pd.DataFrame], Dict[str, pd.DataFrame]]
-) -> 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.
-        
-    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 = summarize_dataframes(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))
-
-    # --- Single DataFrame Case ---
-    elif isinstance(dataframes, pd.DataFrame):
-        summaries.append(_summarize_dataframe(dataframes, "Single_Dataset"))
-
-    # --- 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))
-
-    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) -> 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()])
-
-    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 30 rows):
-    {df.head(30).to_string()}
-
-    Data Description:
-    {df.describe().to_string()}
-
-    Data Info:
-    {info_text}
-    """
-    return summary_text.strip()

ai_data_science_team-0.0.0.9005.dist-info/RECORD

@@ -1,19 +0,0 @@
-ai_data_science_team/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-ai_data_science_team/_version.py,sha256=7tA8TocqCCzLkcB4ptV6bn3k5ni-0TGZvGnVBzmbeIc,26
-ai_data_science_team/orchestration.py,sha256=xiIFOsrLwPdkSmtme7wNCCGv8XopnMTNElNzlZokL-4,303
-ai_data_science_team/agents/__init__.py,sha256=DtwQgyeG3Q4rQ-NrMbva-jshVQyULaWW1RrnETQGZOY,270
-ai_data_science_team/agents/data_cleaning_agent.py,sha256=0K-CgngGjamRk_QzMqNkplrI-ddCbtruQ7kjGrsRIN8,14390
-ai_data_science_team/agents/data_wrangling_agent.py,sha256=uQBJ8vQwrXubQgaI9_UoNZnVQjIEBUOh3dTmNdg326k,14581
-ai_data_science_team/agents/feature_engineering_agent.py,sha256=QEqXTsfjllUj4Wgsw4nNGUT6r9Y6q629ZNgqGy3Dbbk,15921
-ai_data_science_team/templates/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-ai_data_science_team/templates/agent_templates.py,sha256=gT48Pq9KlrrrF0yigodGl_BdptmowTJ2rEWUqh7g5E0,15410
-ai_data_science_team/tools/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-ai_data_science_team/tools/data_analysis.py,sha256=V7e6_fZA01mosFf5VcLwBcpiMVf7fClZMjTrj-egK-o,3715
-ai_data_science_team/tools/logging.py,sha256=EU5EMg4Y0-Yhqf1vAEFg0eRvSTx8uF0LTOAKss8-T2M,2073
-ai_data_science_team/tools/parsers.py,sha256=BAi-fJT7BBt9nRS3w5n9LDTsu7JAJsH8CAI9-Qf7jCs,2086
-ai_data_science_team/tools/regex.py,sha256=KTH2SXPJT8Tzmj7CufyeET-FbA9BMhRzFlPKr4Tan3g,2320
-ai_data_science_team-0.0.0.9005.dist-info/LICENSE,sha256=Xif0IRLdd2HGLATxV2EVp91aSY6KOuacRr_6BorKGzA,1084
-ai_data_science_team-0.0.0.9005.dist-info/METADATA,sha256=PC6rJR965hPu02LtZrzHICkd3QeWzh2A35axTLjE9hM,5840
-ai_data_science_team-0.0.0.9005.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
-ai_data_science_team-0.0.0.9005.dist-info/top_level.txt,sha256=CnoMgOphCoAdGTLueWdCVByVyjwOubaGiTB1lchdy4M,21
-ai_data_science_team-0.0.0.9005.dist-info/RECORD,,