edsl 0.1.47__py3-none-any.whl → 0.1.48__py3-none-any.whl

edsl/{results/DatasetExportMixin.py → dataset/dataset_operations_mixin.py}

@@ -1,25 +1,122 @@
-"""Mixin class for exporting results."""
+"""
+This module provides mixin classes that enable powerful data manipulation operations
+across various EDSL list-like objects.
 
+The DataOperationsBase class defines common operations for working with structured data,
+including data transformation, visualization, export, querying, and analysis. These
+operations are inherited by different specialized mixins (DatasetOperationsMixin,
+ResultsOperationsMixin, etc.) which implement class-specific behaviors.
+
+The design pattern used here allows different container types (Results, Dataset, 
+ScenarioList, AgentList) to share the same data manipulation interface, enabling
+fluid operations across different parts of the EDSL ecosystem.
+"""
+
+from abc import ABC, abstractmethod
 import io
 import warnings
 import textwrap
-from typing import Optional, Tuple, Union, List
+from typing import Optional, Tuple, Union, List, TYPE_CHECKING
+from .r.ggplot import GGPlotMethod
 
-from edsl.results.file_exports import CSVExport, ExcelExport, JSONLExport, SQLiteExport
+if TYPE_CHECKING:
+    from docx import Document
+    from .dataset import Dataset
 
+class DataOperationsBase:
+    """
+    Base class providing common data operations for EDSL container objects.
+    
+    This class serves as the foundation for various data manipulation mixins,
+    providing a consistent interface for operations like filtering, aggregation,
+    transformation, visualization, and export across different types of EDSL
+    containers (Results, Dataset, ScenarioList, AgentList).
+    
+    Key functionality categories:
+    
+    1. Data Transformation:
+       - Filtering with `filter()`
+       - Creating new columns with `mutate()`
+       - Reshaping with `long()`, `wide()`, `flatten()`, etc.
+       - Selecting specific columns with `select()`
+    
+    2. Visualization and Display:
+       - Tabular display with `table()`
+       - Plotting with `ggplot2()`
+       - Generating reports with `report()`
+       
+    3. Data Export:
+       - To various formats with `to_csv()`, `to_excel()`, etc.
+       - To other data structures with `to_pandas()`, `to_dicts()`, etc.
+       
+    4. Analysis:
+       - SQL-based querying with `sql()`
+       - Aggregation with `tally()`
+       - Tree-based exploration
+       
+    These operations are designed to be applied fluently in sequence, enabling
+    expressive data manipulation pipelines.
+    """
+
+
+    def ggplot2(
+        self,
+        ggplot_code: str,
+        shape: str = "wide",
+        sql: Optional[str] = None,
+        remove_prefix: bool = True,
+        debug: bool = False,
+        height: float = 4,
+        width: float = 6,
+        factor_orders: Optional[dict] = None,
+    ):
+        """
+        Create visualizations using R's ggplot2 library.
+        
+        This method provides a bridge to R's powerful ggplot2 visualization library,
+        allowing you to create sophisticated plots directly from EDSL data structures.
+        
+        Parameters:
+            ggplot_code: R code string containing ggplot2 commands
+            shape: Data shape to use ("wide" or "long")
+            sql: Optional SQL query to transform data before visualization
+            remove_prefix: Whether to remove prefixes (like "answer.") from column names
+            debug: Whether to display debugging information
+            height: Plot height in inches
+            width: Plot width in inches
+            factor_orders: Dictionary mapping factor variables to their desired order
+            
+        Returns:
+            A plot object that renders in Jupyter notebooks
+            
+        Notes:
+            - Requires R and the ggplot2 package to be installed
+            - Data is automatically converted to a format suitable for ggplot2
+            - The ggplot2 code should reference column names as they appear after
+              any transformations from the shape and remove_prefix parameters
+              
+        Examples:
+            >>> from edsl.results import Results
+            >>> r = Results.example()
+            >>> # The following would create a plot if R is installed (not shown in doctest):
+            >>> # r.ggplot2('''
+            >>> #     ggplot(df, aes(x=how_feeling)) + 
+            >>> #     geom_bar() +
+            >>> #     labs(title="Distribution of Feelings")
+            >>> # ''')
+        """
+        return GGPlotMethod(self).ggplot2(ggplot_code, shape, sql, remove_prefix, debug, height, width, factor_orders)
 
-class DatasetExportMixin:
-    """Mixin class for exporting Dataset objects."""
 
     def relevant_columns(
-        self, data_type: Optional[str] = None, remove_prefix=False
+        self, data_type: Optional[str] = None, remove_prefix:bool=False
     ) -> list:
         """Return the set of keys that are present in the dataset.
 
         :param data_type: The data type to filter by.
         :param remove_prefix: Whether to remove the prefix from the column names.
 
-        >>> from edsl.results.Dataset import Dataset
+        >>> from ..dataset import Dataset
         >>> d = Dataset([{'a.b':[1,2,3,4]}])
         >>> d.relevant_columns()
         ['a.b']
@@ -71,7 +168,7 @@ class DatasetExportMixin:
     def num_observations(self):
         """Return the number of observations in the dataset.
 
-        >>> from edsl.results.Results import Results
+        >>> from edsl.results import Results
         >>> Results.example().num_observations()
         4
         """
@@ -89,7 +186,7 @@ class DatasetExportMixin:
 
         return _num_observations
 
-    def _make_tabular(
+    def make_tabular(
         self, remove_prefix: bool, pretty_labels: Optional[dict] = None
     ) -> tuple[list, List[list]]:
         """Turn the results into a tabular format.
@@ -98,10 +195,10 @@ class DatasetExportMixin:
 
         >>> from edsl.results import Results
         >>> r = Results.example()
-        >>> r.select('how_feeling')._make_tabular(remove_prefix = True)
+        >>> r.select('how_feeling').make_tabular(remove_prefix = True)
         (['how_feeling'], [['OK'], ['Great'], ['Terrible'], ['OK']])
 
-        >>> r.select('how_feeling')._make_tabular(remove_prefix = True, pretty_labels = {'how_feeling': "How are you feeling"})
+        >>> r.select('how_feeling').make_tabular(remove_prefix = True, pretty_labels = {'how_feeling': "How are you feeling"})
         (['How are you feeling'], [['OK'], ['Great'], ['Terrible'], ['OK']])
         """
 
@@ -144,7 +241,7 @@ class DatasetExportMixin:
             for value in list_of_values:
                 print(f"{key}: {value}")
 
-    def _get_tabular_data(
+    def get_tabular_data(
         self,
         remove_prefix: bool = False,
         pretty_labels: Optional[dict] = None,
@@ -161,7 +258,7 @@ class DatasetExportMixin:
         if pretty_labels is None:
             pretty_labels = {}
 
-        return self._make_tabular(
+        return self.make_tabular(
             remove_prefix=remove_prefix, pretty_labels=pretty_labels
         )
 
@@ -196,6 +293,8 @@ class DatasetExportMixin:
         pretty_labels: Optional[dict] = None,
     ) -> Optional["FileStore"]:
         """Export the results to a FileStore instance containing CSV data."""
+        from .file_exports import CSVExport
+
         exporter = CSVExport(
             data=self,
             filename=filename,
@@ -212,6 +311,8 @@ class DatasetExportMixin:
         sheet_name: Optional[str] = None,
     ) -> Optional["FileStore"]:
         """Export the results to a FileStore instance containing Excel data."""
+        from .file_exports import  ExcelExport
+
         exporter = ExcelExport(
             data=self,
             filename=filename,
@@ -278,29 +379,51 @@ class DatasetExportMixin:
         transpose_by: str = None,
         remove_prefix: bool = True,
         shape: str = "wide",
-    ) -> Union["pd.DataFrame", str]:
-        """Execute a SQL query and return the results as a DataFrame.
-
-         Args:
-             query: The SQL query to execute
-             shape: The shape of the data in the database (wide or long)
-             remove_prefix: Whether to remove the prefix from the column names
-             transpose: Whether to transpose the DataFrame
-             transpose_by: The column to use as the index when transposing
-             csv: Whether to return the DataFrame as a CSV string
-             to_list: Whether to return the results as a list
-             to_latex: Whether to return the results as LaTeX
-             filename: Optional filename to save the results to
-
-         Returns:
-             DataFrame, CSV string, list, or LaTeX string depending on parameters
-
+    ) -> "Dataset":
+        """
+        Execute SQL queries on the dataset.
+        
+        This powerful method allows you to use SQL to query and transform your data, 
+        combining the expressiveness of SQL with EDSL's data structures. It works by 
+        creating an in-memory SQLite database from your data and executing the query
+        against it.
+        
+        Parameters:
+            query: SQL query string to execute
+            transpose: Whether to transpose the resulting table (rows become columns)
+            transpose_by: Column to use as the new index when transposing
+            remove_prefix: Whether to remove type prefixes (e.g., "answer.") from column names
+            shape: Data shape to use ("wide" or "long")
+                  - "wide": Default tabular format with columns for each field
+                  - "long": Melted format with key-value pairs, useful for certain queries
+        
+        Returns:
+            A Dataset object containing the query results
+            
+        Notes:
+            - The data is stored in a table named "self" in the SQLite database
+            - In wide format, column names include their type prefix unless remove_prefix=True
+            - In long format, the data is melted into columns: row_number, key, value, data_type
+            - Complex objects like lists and dictionaries are converted to strings
+            
         Examples:
             >>> from edsl import Results
-            >>> r = Results.example();
-            >>> len(r.sql("SELECT * FROM self", shape = "wide"))
+            >>> r = Results.example()
+            
+            # Basic selection
+            >>> len(r.sql("SELECT * FROM self", shape="wide"))
             4
-            >>> len(r.sql("SELECT * FROM self", shape = "long"))
+            
+            # Filtering with WHERE clause
+            >>> r.sql("SELECT * FROM self WHERE how_feeling = 'Great'").num_observations()
+            1
+            
+            # Aggregation
+            >>> r.sql("SELECT how_feeling, COUNT(*) as count FROM self GROUP BY how_feeling").keys()
+            ['how_feeling', 'count']
+            
+            # Using long format
+            >>> len(r.sql("SELECT * FROM self", shape="long"))
             172
         """
         import pandas as pd
@@ -316,7 +439,7 @@ class DatasetExportMixin:
             else:
                 df = df.set_index(df.columns[0])
             df = df.transpose()
-        from edsl.results.Dataset import Dataset
+        from .dataset import Dataset
 
         return Dataset.from_pandas_dataframe(df)
 
@@ -372,6 +495,14 @@ class DatasetExportMixin:
         csv_string = self.to_csv(remove_prefix=remove_prefix).text
         df = pl.read_csv(io.StringIO(csv_string))
         return df
+    
+    def tree(self, node_order: Optional[List[str]] = None) -> "Tree":
+        """Convert the results to a Tree.
+
+        :param node_order: The order of the nodes.
+        """
+        from .dataset_tree import Tree
+        return Tree(self, node_order=node_order)
 
     def to_scenario_list(self, remove_prefix: bool = True) -> list[dict]:
         """Convert the results to a list of dictionaries, one per scenario.
@@ -383,8 +514,7 @@ class DatasetExportMixin:
         >>> r.select('how_feeling').to_scenario_list()
         ScenarioList([Scenario({'how_feeling': 'OK'}), Scenario({'how_feeling': 'Great'}), Scenario({'how_feeling': 'Terrible'}), Scenario({'how_feeling': 'OK'})])
         """
-        from edsl.scenarios.ScenarioList import ScenarioList
-        from edsl.scenarios.Scenario import Scenario
+        from edsl.scenarios import ScenarioList, Scenario
 
         list_of_dicts = self.to_dicts(remove_prefix=remove_prefix)
         scenarios = []
@@ -402,8 +532,7 @@ class DatasetExportMixin:
         >>> r.select('how_feeling').to_agent_list()
         AgentList([Agent(traits = {'how_feeling': 'OK'}), Agent(traits = {'how_feeling': 'Great'}), Agent(traits = {'how_feeling': 'Terrible'}), Agent(traits = {'how_feeling': 'OK'})])
         """
-        from edsl.agents import Agent
-        from edsl.agents.AgentList import AgentList
+        from edsl.agents import Agent, AgentList
 
         list_of_dicts = self.to_dicts(remove_prefix=remove_prefix)
         agents = []
@@ -464,11 +593,11 @@ class DatasetExportMixin:
         >>> r.select('how_feeling').to_list()
         ['OK', 'Great', 'Terrible', 'OK']
 
-        >>> from edsl.results.Dataset import Dataset
+        >>> from edsl.dataset import Dataset
         >>> Dataset([{'a.b': [[1, 9], 2, 3, 4]}]).select('a.b').to_list(flatten = True)
         [1, 9, 2, 3, 4]
 
-        >>> from edsl.results.Dataset import Dataset
+        >>> from edsl.dataset import Dataset
         >>> Dataset([{'a.b': [[1, 9], 2, 3, 4]}, {'c': [6, 2, 3, 4]}]).select('a.b', 'c').to_list(flatten = True)
         Traceback (most recent call last):
         ...
@@ -545,42 +674,18 @@ class DatasetExportMixin:
         if return_link:
             return filename
         
-    def report(self, *fields: Optional[str], top_n: Optional[int] = None, 
-               header_fields: Optional[List[str]] = None, divider: bool = True,
-               return_string: bool = False) -> Optional[str]:
-        """Takes the fields in order and returns a report of the results by iterating through rows.
-        The row number is printed as # Observation: <row number>
-        The name of the field is used as markdown header at level "##" 
-        The content of that field is then printed. 
-        Then the next field and so on. 
-        Once that row is done, a new line is printed and the next row is shown.
-        If in a jupyter notebook, the report is displayed as markdown.
+    def _prepare_report_data(self, *fields: Optional[str], top_n: Optional[int] = None, 
+                            header_fields: Optional[List[str]] = None) -> tuple:
+        """Prepares data for report generation in various formats.
         
         Args:
             *fields: The fields to include in the report. If none provided, all fields are used.
             top_n: Optional limit on the number of observations to include.
             header_fields: Optional list of fields to include in the main header instead of as sections.
-            divider: If True, adds a horizontal rule between observations for better visual separation.
-            return_string: If True, returns the markdown string. If False (default in notebooks),
-                          only displays the markdown without returning.
             
         Returns:
-            A string containing the markdown report if return_string is True, otherwise None.
-            
-        Examples:
-            >>> from edsl.results import Results
-            >>> r = Results.example()
-            >>> report = r.select('how_feeling', 'how_feeling_yesterday').report(return_string=True)
-            >>> "# Observation: 1" in report
-            True
-            >>> "## answer.how_feeling" in report
-            True
-            >>> report = r.select('how_feeling').report(header_fields=['answer.how_feeling'], return_string=True)
-            >>> "# Observation: 1 (`how_feeling`: OK)" in report
-            True
+            A tuple containing (field_data, num_obs, fields, header_fields)
         """
-        from edsl.utilities.utilities import is_notebook
-        
         # If no fields specified, use all columns
         if not fields:
             fields = self.relevant_columns()
@@ -607,8 +712,22 @@ class DatasetExportMixin:
         num_obs = self.num_observations()
         if top_n is not None:
             num_obs = min(num_obs, top_n)
+            
+        return field_data, num_obs, fields, header_fields
+
+    def _report_markdown(self, field_data, num_obs, fields, header_fields, divider: bool = True) -> str:
+        """Generates a markdown report from the prepared data.
         
-        # Build the report
+        Args:
+            field_data: Dictionary mapping field names to their values
+            num_obs: Number of observations to include
+            fields: Fields to include as sections
+            header_fields: Fields to include in the observation header
+            divider: If True, adds a horizontal rule between observations
+            
+        Returns:
+            A string containing the markdown report
+        """
         report_lines = []
         for i in range(num_obs):
             # Create header with observation number and any header fields
@@ -642,34 +761,176 @@ class DatasetExportMixin:
             else:
                 report_lines.append("")  # Empty line between observations
         
-        report_text = "\n".join(report_lines)
+        return "\n".join(report_lines)
+
+    def _report_docx(self, field_data, num_obs, fields, header_fields) -> "Document":
+        """Generates a Word document report from the prepared data.
+        
+        Args:
+            field_data: Dictionary mapping field names to their values
+            num_obs: Number of observations to include
+            fields: Fields to include as sections
+            header_fields: Fields to include in the observation header
+            
+        Returns:
+            A docx.Document object containing the report
+        """
+        try:
+            from docx import Document
+            from docx.shared import Pt
+            import json
+        except ImportError:
+            raise ImportError("The python-docx package is required for DOCX export. Install it with 'pip install python-docx'.")
         
-        # In notebooks, display as markdown and optionally return
-        is_nb = is_notebook()
-        if is_nb:
-            from IPython.display import Markdown, display
-            display(Markdown(report_text))
+        doc = Document()
         
-        # Return the string if requested or if not in a notebook
-        if return_string or not is_nb:
+        for i in range(num_obs):
+            # Create header with observation number and any header fields
+            header_text = f"Observation: {i+1}"
+            if header_fields:
+                header_parts = []
+                for field in header_fields:
+                    value = field_data[field][i]
+                    # Get the field name without prefix for cleaner display
+                    display_name = field.split('.')[-1] if '.' in field else field
+                    header_parts.append(f"{display_name}: {value}")
+                if header_parts:
+                    header_text += f" ({', '.join(header_parts)})"
+            
+            heading = doc.add_heading(header_text, level=1)
+            
+            # Add the remaining fields
+            for field in fields:
+                if field not in header_fields:
+                    doc.add_heading(field, level=2)
+                    value = field_data[field][i]
+                    
+                    if isinstance(value, (list, dict)):
+                        # Format structured data with indentation
+                        formatted_value = json.dumps(value, indent=2)
+                        p = doc.add_paragraph()
+                        p.add_run(formatted_value).font.name = 'Courier New'
+                        p.add_run().font.size = Pt(10)
+                    else:
+                        doc.add_paragraph(str(value))
+            
+            # Add page break between observations except for the last one
+            if i < num_obs - 1:
+                doc.add_page_break()
+        
+        return doc
+        
+    def report(self, *fields: Optional[str], top_n: Optional[int] = None, 
+               header_fields: Optional[List[str]] = None, divider: bool = True,
+               return_string: bool = False, format: str = "markdown",
+               filename: Optional[str] = None) -> Optional[Union[str, "docx.Document"]]:
+        """Generates a report of the results by iterating through rows.
+        
+        Args:
+            *fields: The fields to include in the report. If none provided, all fields are used.
+            top_n: Optional limit on the number of observations to include.
+            header_fields: Optional list of fields to include in the main header instead of as sections.
+            divider: If True, adds a horizontal rule between observations (markdown only).
+            return_string: If True, returns the markdown string. If False (default in notebooks),
+                          only displays the markdown without returning.
+            format: Output format - either "markdown" or "docx".
+            filename: If provided and format is "docx", saves the document to this file.
+            
+        Returns:
+            Depending on format and return_string:
+            - For markdown: A string if return_string is True, otherwise None (displays in notebook)
+            - For docx: A docx.Document object, or None if filename is provided (saves to file)
+            
+        Examples:
+            >>> from edsl.results import Results
+            >>> r = Results.example()
+            >>> report = r.select('how_feeling').report(return_string=True)
+            >>> "# Observation: 1" in report
+            True
+            >>> doc = r.select('how_feeling').report(format="docx")
+            >>> isinstance(doc, object)
+            True
+        """
+        from edsl.utilities.utilities import is_notebook
+        
+        # Prepare the data for the report
+        field_data, num_obs, fields, header_fields = self._prepare_report_data(
+            *fields, top_n=top_n, header_fields=header_fields
+        )
+        
+        # Generate the report in the requested format
+        if format.lower() == "markdown":
+            report_text = self._report_markdown(
+                field_data, num_obs, fields, header_fields, divider
+            )
+            
+            # In notebooks, display as markdown
+            is_nb = is_notebook()
+            if is_nb and not return_string:
+                from IPython.display import Markdown, display
+                display(Markdown(report_text))
+                return None
+            
+            # Return the string if requested or if not in a notebook
             return report_text
-        return None
+            
+        elif format.lower() == "docx":
+            doc = self._report_docx(field_data, num_obs, fields, header_fields)
+            
+            # Save to file if filename is provided
+            if filename:
+                doc.save(filename)
+                print(f"Report saved to {filename}")
+                return None
+                
+            return doc
+            
+        else:
+            raise ValueError(f"Unsupported format: {format}. Use 'markdown' or 'docx'.")
 
     def tally(
         self, *fields: Optional[str], top_n: Optional[int] = None, output="Dataset"
     ) -> Union[dict, "Dataset"]:
-        """Tally the values of a field or perform a cross-tab of multiple fields.
-
-        :param fields: The field(s) to tally, multiple fields for cross-tabulation.
-
-        >>> from edsl.results import Results
-        >>> r = Results.example()
-        >>> r.select('how_feeling').tally('answer.how_feeling', output = "dict")
-        {'OK': 2, 'Great': 1, 'Terrible': 1}
-        >>> from edsl.results.Dataset import Dataset
-        >>> expected = Dataset([{'answer.how_feeling': ['OK', 'Great', 'Terrible']}, {'count': [2, 1, 1]}])
-        >>> r.select('how_feeling').tally('answer.how_feeling', output = "Dataset") == expected
-        True
+        """
+        Count frequency distributions of values in specified fields.
+        
+        This method tallies the occurrence of unique values within one or more fields,
+        similar to a GROUP BY and COUNT in SQL. When multiple fields are provided, it
+        performs cross-tabulation across those fields.
+        
+        Parameters:
+            *fields: Field names to tally. If none provided, uses all available fields.
+            top_n: Optional limit to return only the top N most frequent values.
+            output: Format for results, either "Dataset" (recommended) or "dict".
+        
+        Returns:
+            By default, returns a Dataset with columns for the field(s) and a 'count' column.
+            If output="dict", returns a dictionary mapping values to counts.
+            
+        Notes:
+            - For single fields, returns counts of each unique value
+            - For multiple fields, returns counts of each unique combination of values
+            - Results are sorted in descending order by count
+            - Fields can be specified with or without their type prefix
+            
+        Examples:
+            >>> from edsl import Results
+            >>> r = Results.example()
+            
+            # Single field frequency count
+            >>> r.select('how_feeling').tally('answer.how_feeling', output="dict")
+            {'OK': 2, 'Great': 1, 'Terrible': 1}
+            
+            # Return as Dataset (default)
+            >>> from edsl.dataset import Dataset
+            >>> expected = Dataset([{'answer.how_feeling': ['OK', 'Great', 'Terrible']}, {'count': [2, 1, 1]}])
+            >>> r.select('how_feeling').tally('answer.how_feeling', output="Dataset") == expected
+            True
+            
+            # Multi-field cross-tabulation - exact output varies based on data
+            >>> result = r.tally('how_feeling', 'how_feeling_yesterday')
+            >>> 'how_feeling' in result.keys() and 'how_feeling_yesterday' in result.keys() and 'count' in result.keys()
+            True
         """
         from collections import Counter
 
@@ -684,7 +945,9 @@ class DatasetExportMixin:
             f in self.relevant_columns() or f in relevant_columns_without_prefix
             for f in fields
         ):
-            raise ValueError("One or more specified fields are not in the dataset.")
+            raise ValueError("One or more specified fields are not in the dataset."
+                             f"The available fields are: {self.relevant_columns()}"
+                             )
 
         if len(fields) == 1:
             field = fields[0]
@@ -695,13 +958,18 @@ class DatasetExportMixin:
         for value in values:
             if isinstance(value, list):
                 value = tuple(value)
-
-        tally = dict(Counter(values))
+        try:
+            tally = dict(Counter(values))
+        except TypeError:
+            tally = dict(Counter([str(v) for v in values]))
+        except Exception as e:
+            raise ValueError(f"Error tallying values: {e}")
+        
         sorted_tally = dict(sorted(tally.items(), key=lambda item: -item[1]))
         if top_n is not None:
             sorted_tally = dict(list(sorted_tally.items())[:top_n])
 
-        from edsl.results.Dataset import Dataset
+        from ..dataset import Dataset
 
         if output == "dict":
             # why did I do this?
@@ -732,27 +1000,44 @@ class DatasetExportMixin:
             keys.append("count")
             return sl.reorder_keys(keys).to_dataset()
 
-    def flatten(self, field, keep_original=False):
+    def flatten(self, field: str, keep_original: bool = False) -> "Dataset":
         """
-        Flatten a field containing a list of dictionaries into separate fields.
-
-        >>> from edsl.results.Dataset import Dataset
-        >>> Dataset([{'a': [{'a': 1, 'b': 2}]}, {'c': [5] }]).flatten('a')
-        Dataset([{'c': [5]}, {'a.a': [1]}, {'a.b': [2]}])
-
-
-        >>> Dataset([{'answer.example': [{'a': 1, 'b': 2}]}, {'c': [5] }]).flatten('answer.example')
-        Dataset([{'c': [5]}, {'answer.example.a': [1]}, {'answer.example.b': [2]}])
-
-
-        Args:
-            field: The field to flatten
-            keep_original: If True, keeps the original field in the dataset
-
+        Expand a field containing dictionaries into separate fields.
+        
+        This method takes a field that contains a list of dictionaries and expands
+        it into multiple fields, one for each key in the dictionaries. This is useful
+        when working with nested data structures or results from extraction operations.
+        
+        Parameters:
+            field: The field containing dictionaries to flatten
+            keep_original: Whether to retain the original field in the result
+            
         Returns:
-            A new dataset with the flattened fields
+            A new Dataset with the dictionary keys expanded into separate fields
+            
+        Notes:
+            - Each key in the dictionaries becomes a new field with name pattern "{field}.{key}"
+            - All dictionaries in the field must have compatible structures
+            - If a dictionary is missing a key, the corresponding value will be None
+            - Non-dictionary values in the field will cause a warning
+            
+        Examples:
+            >>> from edsl.dataset import Dataset
+            
+            # Basic flattening of nested dictionaries
+            >>> Dataset([{'a': [{'a': 1, 'b': 2}]}, {'c': [5]}]).flatten('a')
+            Dataset([{'c': [5]}, {'a.a': [1]}, {'a.b': [2]}])
+            
+            # Works with prefixed fields too
+            >>> Dataset([{'answer.example': [{'a': 1, 'b': 2}]}, {'c': [5]}]).flatten('answer.example')
+            Dataset([{'c': [5]}, {'answer.example.a': [1]}, {'answer.example.b': [2]}])
+            
+            # Keep the original field if needed
+            >>> d = Dataset([{'a': [{'a': 1, 'b': 2}]}, {'c': [5]}])
+            >>> d.flatten('a', keep_original=True)
+            Dataset([{'a': [{'a': 1, 'b': 2}]}, {'c': [5]}, {'a.a': [1]}, {'a.b': [2]}])
         """
-        from edsl.results.Dataset import Dataset
+        from ..dataset import Dataset
 
         # Ensure the dataset isn't empty
         if not self.data:
@@ -853,7 +1138,7 @@ class DatasetExportMixin:
             A new Dataset with unpacked columns
 
         Examples:
-            >>> from edsl.results.Dataset import Dataset
+            >>> from edsl.dataset import Dataset
             >>> d = Dataset([{'data': [[1, 2, 3], [4, 5, 6]]}])
             >>> d.unpack_list('data')
             Dataset([{'data': [[1, 2, 3], [4, 5, 6]]}, {'data_1': [1, 4]}, {'data_2': [2, 5]}, {'data_3': [3, 6]}])
@@ -861,7 +1146,7 @@ class DatasetExportMixin:
             >>> d.unpack_list('data', new_names=['first', 'second', 'third'])
             Dataset([{'data': [[1, 2, 3], [4, 5, 6]]}, {'first': [1, 4]}, {'second': [2, 5]}, {'third': [3, 6]}])
         """
-        from edsl.results.Dataset import Dataset
+        from .dataset import Dataset
 
         # Create a copy of the dataset
         result = Dataset(self.data.copy())
@@ -919,7 +1204,7 @@ class DatasetExportMixin:
             KeyError: If the field_name doesn't exist in the dataset.
             
         Examples:
-            >>> from edsl.results.Dataset import Dataset
+            >>> from .dataset import Dataset
             >>> d = Dataset([{'a': [1, 2, 3]}, {'b': [4, 5, 6]}])
             >>> d.drop('a')
             Dataset([{'b': [4, 5, 6]}])
@@ -929,7 +1214,7 @@ class DatasetExportMixin:
             ...
             KeyError: "Field 'c' not found in dataset"
         """
-        from edsl.results.Dataset import Dataset
+        from .dataset import Dataset
         
         # Check if field exists in the dataset
         if field_name not in self.relevant_columns():
@@ -959,14 +1244,15 @@ class DatasetExportMixin:
             >>> r.select('how_feeling', 'how_feeling_yesterday').remove_prefix().relevant_columns()
             ['how_feeling', 'how_feeling_yesterday']
             
-            >>> from edsl.results.Dataset import Dataset
+            >>> from edsl.dataset import Dataset
             >>> d = Dataset([{'a.x': [1, 2, 3]}, {'b.x': [4, 5, 6]}])
-            >>> d.remove_prefix()
-            Traceback (most recent call last):
-            ...
-            ValueError: Removing prefixes would result in duplicate column names: ['x']
+            >>> # d.remove_prefix()
+        
+        Traceback (most recent call last):
+        ...
+        ValueError: Removing prefixes would result in duplicate column names: ['x']
         """
-        from edsl.results.Dataset import Dataset
+        from .dataset import Dataset
         
         # Get all column names
         columns = self.relevant_columns()
@@ -1002,6 +1288,204 @@ class DatasetExportMixin:
         return Dataset(new_data)
 
 
+from functools import wraps
+
+def to_dataset(func):
+    """
+    Decorator that ensures functions receive a Dataset object as their first argument.
+    
+    This decorator automatically converts various EDSL container objects (Results,
+    AgentList, ScenarioList) to Dataset objects before passing them to the decorated
+    function. This allows methods defined in DataOperationsBase to work seamlessly
+    across different container types without duplicating conversion logic.
+    
+    Parameters:
+        func: The function to decorate
+        
+    Returns:
+        A wrapped function that ensures its first argument is a Dataset
+        
+    Notes:
+        - For Results objects, calls select() to convert to a Dataset
+        - For AgentList and ScenarioList objects, calls their to_dataset() method
+        - For Dataset objects, passes them through unchanged
+        - This decorator is used internally by the mixin system to enable method sharing
+    """
+    @wraps(func)
+    def wrapper(self, *args, **kwargs):
+        """Execute the function with self converted to a Dataset if needed."""
+        # Convert to Dataset based on the class type
+        if self.__class__.__name__ == "Results":
+            dataset_self = self.select()
+        elif self.__class__.__name__ == "AgentList":
+            dataset_self = self.to_dataset()
+        elif self.__class__.__name__ == "ScenarioList":
+            dataset_self = self.to_dataset()
+        else:
+            dataset_self = self
+            
+        # Call the function with the converted self
+        return func(dataset_self, *args, **kwargs)
+
+    # Mark the wrapper as being wrapped by to_dataset
+    wrapper._is_wrapped = True
+    return wrapper
+
+
+def decorate_methods_from_mixin(cls, mixin_cls):
+    """
+    Apply the to_dataset decorator to methods inherited from a mixin class.
+    
+    This function is part of EDSL's method inheritance system. It takes methods
+    from a source mixin class, applies the to_dataset decorator to them, and adds
+    them to a target class. This enables the sharing of data manipulation methods
+    across different container types while ensuring they receive the right data type.
+    
+    The function is careful not to override methods that are already defined in
+    more specific parent classes, preserving the method resolution order (MRO).
+    
+    Parameters:
+        cls: The target class to add decorated methods to
+        mixin_cls: The source mixin class providing the methods
+        
+    Returns:
+        The modified target class with decorated methods added
+        
+    Notes:
+        - Only public methods (not starting with "_") are decorated and added
+        - Methods already defined in more specific parent classes are not overridden
+        - Methods from DataOperationsBase are not skipped to ensure all base methods are available
+    """
+    # Get all attributes, including inherited ones
+    for attr_name in dir(mixin_cls):
+        # Skip magic methods and private methods
+        if not attr_name.startswith('_'):
+            attr_value = getattr(mixin_cls, attr_name)
+            if callable(attr_value):
+                # Check if the method is already defined in the class's MRO
+                # but skip DataOperationsBase methods
+                for base in cls.__mro__[1:]:  # Skip the class itself
+                    if (attr_name in base.__dict__ and 
+                        base is not DataOperationsBase):
+                        # Method is overridden in a more specific class, skip decorating
+                        break
+                else:
+                    # Method not overridden, safe to decorate
+                    setattr(cls, attr_name, to_dataset(attr_value))
+    return cls
+
+# def decorate_methods_from_mixin(cls, mixin_cls):
+#     """Decorates all methods from mixin_cls with to_dataset decorator."""
+    
+#     # Get all attributes, including inherited ones
+#     for attr_name in dir(mixin_cls):
+#         # Skip magic methods and private methods
+#         if not attr_name.startswith('_'):
+#             attr_value = getattr(mixin_cls, attr_name)
+#             if callable(attr_value):
+#                 setattr(cls, attr_name, to_dataset(attr_value))
+#     return cls
+
+class DatasetOperationsMixin(DataOperationsBase):
+    """
+    Mixin providing data manipulation operations for Dataset objects.
+    
+    This mixin class is the cornerstone of EDSL's data manipulation system. It directly 
+    inherits methods from DataOperationsBase without requiring conversion, as it's
+    designed specifically for the Dataset class. It serves as the primary implementation
+    of all data operations methods that other container types will inherit and adapt 
+    through the to_dataset decorator.
+    
+    The design follows a standard mixin pattern where common functionality is defined
+    in a standalone class that can be "mixed in" to other classes. In EDSL's case,
+    this allows different container types (Results, AgentList, ScenarioList) to share
+    the same powerful data manipulation interface.
+    
+    Key features:
+    
+    1. Data Transformation:
+       - Filtering with `filter()`
+       - Creating new columns with `mutate()`
+       - Reshaping with `long()`, `wide()`, `flatten()`, etc.
+       - Selecting specific data with `select()`
+    
+    2. Visualization:
+       - Table display with `table()`
+       - R integration with `ggplot2()`
+       - Report generation with `report()`
+    
+    3. Data Export:
+       - To files with `to_csv()`, `to_excel()`, etc.
+       - To other formats with `to_pandas()`, `to_dicts()`, etc.
+    
+    4. Analysis:
+       - SQL queries with `sql()`
+       - Aggregation with `tally()`
+       - Tree-based exploration with `tree()`
+    
+    This mixin is designed for fluent method chaining, allowing complex data manipulation
+    pipelines to be built in an expressive and readable way.
+    """
+    pass
+
+class ResultsOperationsMixin(DataOperationsBase):
+    """
+    Mixin providing data operations for Results objects.
+    
+    This mixin adapts DatasetOperationsMixin methods to work with Results objects.
+    When a method is called on a Results object, it's automatically converted to
+    a Dataset first via the to_dataset decorator applied in __init_subclass__.
+    
+    This allows Results objects to have the same data manipulation capabilities
+    as Dataset objects without duplicating code.
+    """
+    def __init_subclass__(cls, **kwargs):
+        """
+        Automatically decorate all methods from DatasetOperationsMixin.
+        
+        This hook runs when a class inherits from ResultsOperationsMixin,
+        applying the to_dataset decorator to all methods from DatasetOperationsMixin.
+        """
+        super().__init_subclass__(**kwargs)
+        decorate_methods_from_mixin(cls, DatasetOperationsMixin)
+
+class ScenarioListOperationsMixin(DataOperationsBase):
+    """
+    Mixin providing data operations for ScenarioList objects.
+    
+    This mixin adapts DatasetOperationsMixin methods to work with ScenarioList objects.
+    ScenarioList objects are converted to Dataset objects before method execution
+    via the to_dataset decorator applied in __init_subclass__.
+    """
+    def __init_subclass__(cls, **kwargs):
+        """
+        Automatically decorate all methods from DatasetOperationsMixin.
+        
+        This hook runs when a class inherits from ScenarioListOperationsMixin,
+        applying the to_dataset decorator to all methods from DatasetOperationsMixin.
+        """
+        super().__init_subclass__(**kwargs)
+        decorate_methods_from_mixin(cls, DatasetOperationsMixin)
+
+class AgentListOperationsMixin(DataOperationsBase):
+    """
+    Mixin providing data operations for AgentList objects.
+    
+    This mixin adapts DatasetOperationsMixin methods to work with AgentList objects.
+    AgentList objects are converted to Dataset objects before method execution
+    via the to_dataset decorator applied in __init_subclass__.
+    """
+    def __init_subclass__(cls, **kwargs):
+        """
+        Automatically decorate all methods from DatasetOperationsMixin.
+        
+        This hook runs when a class inherits from AgentListOperationsMixin,
+        applying the to_dataset decorator to all methods from DatasetOperationsMixin.
+        """
+        super().__init_subclass__(**kwargs)
+        decorate_methods_from_mixin(cls, DatasetOperationsMixin)
+
+
 if __name__ == "__main__":
     import doctest