edsl 0.1.38.dev4__py3-none-any.whl → 0.1.39__py3-none-any.whl

edsl/results/TableDisplay.py

@@ -1,198 +1,125 @@
-from tabulate import tabulate
-from pathlib import Path
+from typing import (
+    Protocol,
+    List,
+    Any,
+    Optional,
+    TYPE_CHECKING,
+    Sequence,
+    Union,
+    Literal,
+)
 
-from edsl.results.CSSParameterizer import CSSParameterizer
+if TYPE_CHECKING:
+    from edsl.results.Dataset import Dataset
 
+from edsl.results.table_data_class import TableData
 
-class TableDisplay:
-    max_height = 400
-    min_height = 200
+from edsl.results.table_renderers import DataTablesRenderer, PandasStyleRenderer
 
-    @classmethod
-    def get_css(cls):
-        """Load CSS content from the file next to this module"""
-        css_path = Path(__file__).parent / "table_display.css"
-        return css_path.read_text()
+Row = Sequence[Union[str, int, float, bool, None]]
+TableFormat = Literal[
+    "grid", "simple", "pipe", "orgtbl", "rst", "mediawiki", "html", "latex"
+]
+
+
+class TableRenderer(Protocol):
+    """Table renderer protocol"""
+
+    def render_html(self, table_data: TableData) -> str:
+        pass
+
+
+# Modified TableDisplay class
+class TableDisplay:
+    def __init__(
+        self,
+        headers: Sequence[str],
+        data: Sequence[Row],
+        tablefmt: Optional[TableFormat] = None,
+        raw_data_set: "Dataset" = None,
+        renderer_class: Optional[TableRenderer] = None,
+    ):
+        assert len(headers) == len(data[0])  # Check if headers and data are consistent
 
-    def __init__(self, headers, data, tablefmt=None, raw_data_set=None):
         self.headers = headers
         self.data = data
         self.tablefmt = tablefmt
         self.raw_data_set = raw_data_set
 
+        self.renderer_class = renderer_class or PandasStyleRenderer
+
+        # Handle printing parameters from raw_data_set
         if hasattr(raw_data_set, "print_parameters"):
-            if raw_data_set.print_parameters:
-                self.printing_parameters = raw_data_set.print_parameters
-            else:
-                self.printing_parameters = {}
+            self.printing_parameters = (
+                raw_data_set.print_parameters if raw_data_set.print_parameters else {}
+            )
         else:
             self.printing_parameters = {}
 
-    def to_csv(self, filename: str):
-        self.raw_data_set.to_csv(filename)
-
-    def write(self, filename: str):
-        if self.tablefmt is None:
-            table = tabulate(self.data, headers=self.headers, tablefmt="simple")
-        else:
-            table = tabulate(self.data, headers=self.headers, tablefmt=self.tablefmt)
-
-        with open(filename, "w") as file:
-            print("Writing table to", filename)
-            file.write(table)
-
-    def to_pandas(self):
-        return self.raw_data_set.to_pandas()
-
-    def to_list(self):
-        return self.raw_data_set.to_list()
+    def _repr_html_(self) -> str:
+        table_data = TableData(
+            headers=self.headers,
+            data=self.data,
+            parameters=self.printing_parameters,
+            raw_data_set=self.raw_data_set,
+        )
+        return self.renderer_class(table_data).render_html()
 
     def __repr__(self):
         from tabulate import tabulate
 
-        if self.tablefmt is None:
-            return tabulate(self.data, headers=self.headers, tablefmt="simple")
-        else:
-            return tabulate(self.data, headers=self.headers, tablefmt=self.tablefmt)
+        return tabulate(self.data, headers=self.headers, tablefmt=self.tablefmt)
+
+    @classmethod
+    def from_dictionary(
+        cls,
+        dictionary: dict,
+        tablefmt: Optional[TableFormat] = None,
+        renderer: Optional[TableRenderer] = None,
+    ) -> "TableDisplay":
+        headers = list(dictionary.keys())
+        data = [list(dictionary.values())]
+        return cls(headers, data, tablefmt, renderer_class=renderer)
+
+    @classmethod
+    def from_dictionary_wide(
+        cls,
+        dictionary: dict,
+        tablefmt: Optional[TableFormat] = None,
+        renderer: Optional[TableRenderer] = None,
+    ) -> "TableDisplay":
+        headers = ["key", "value"]
+        data = [[k, v] for k, v in dictionary.items()]
+        return cls(headers, data, tablefmt, renderer_class=renderer)
 
-    def long(self):
+    @classmethod
+    def from_dataset(
+        cls,
+        dataset: "Dataset",
+        tablefmt: Optional[TableFormat] = None,
+        renderer: Optional[TableRenderer] = None,
+    ) -> "TableDisplay":
+        headers, data = dataset._tabular()
+        return cls(headers, data, tablefmt, dataset, renderer_class=renderer)
+
+    def long(self) -> "TableDisplay":
+        """Convert to long format"""
         new_header = ["row", "key", "value"]
         new_data = []
         for index, row in enumerate(self.data):
             new_data.extend([[index, k, v] for k, v in zip(self.headers, row)])
-        return TableDisplay(new_header, new_data)
-
-    def _repr_html_(self):
-        if self.tablefmt is not None:
-            return (
-                "<pre>"
-                + tabulate(self.data, headers=self.headers, tablefmt=self.tablefmt)
-                + "</pre>"
-            )
-
-        num_rows = len(self.data)
-        height = min(
-            num_rows * 30 + 50, self.max_height
-        )  # Added extra space for header
+        return TableDisplay(
+            new_header, new_data, self.tablefmt, renderer_class=self.renderer_class
+        )
 
-        if height < self.min_height:
-            height = self.min_height
 
-        html_template = """
-        <style>
-            {css}
-        </style>
-        <div class="table-container">
-            <div class="scroll-table-wrapper">
-                {table}
-            </div>
-        </div>
-        """
-
-        html_content = tabulate(self.data, headers=self.headers, tablefmt="html")
-        html_content = html_content.replace("<table>", '<table class="scroll-table">')
-
-        height_string = f"{height}px"
-        parameters = {"containerHeight": height_string, "headerColor": "blue"}
-        parameters.update(self.printing_parameters)
-        rendered_css = CSSParameterizer(self.get_css()).apply_parameters(parameters)
-
-        return html_template.format(table=html_content, css=rendered_css)
-
-    @classmethod
-    def example(
-        cls,
-        headers=None,
-        data=None,
-        filename: str = "table_example.html",
-        auto_open: bool = True,
-    ):
-        """
-        Creates a standalone HTML file with an example table in an iframe and optionally opens it in a new tab.
-
-        Args:
-            cls: The class itself
-            headers (list): List of column headers. If None, uses example headers
-            data (list): List of data rows. If None, uses example data
-            filename (str): The name of the HTML file to create. Defaults to "table_example.html"
-            auto_open (bool): Whether to automatically open the file in the default web browser. Defaults to True
-
-        Returns:
-            str: The path to the created HTML file
-        """
-        import os
-        import webbrowser
-
-        # Use example data if none provided
-        if headers is None:
-            headers = ["Name", "Age", "City", "Occupation"]
-        if data is None:
-            data = [
-                [
-                    "John Doe",
-                    30,
-                    "New York",
-                    """cls: The class itself
-        headers (list): List of column headers. If None, uses example headers
-        data (list): List of data rows. If None, uses example data
-        filename (str): The name of the HTML file to create. Defaults to "table_example.html"
-        auto_open (bool): Whether to automatically open the file in the default web browser. Defaults to True
-        """,
-                ],
-                ["Jane Smith", 28, "San Francisco", "Designer"],
-                ["Bob Johnson", 35, "Chicago", "Manager"],
-                ["Alice Brown", 25, "Boston", "Developer"],
-                ["Charlie Wilson", 40, "Seattle", "Architect"],
-            ]
-
-        # Create instance with the data
-        instance = cls(headers=headers, data=data)
-
-        # Get the table HTML content
-        table_html = instance._repr_html_()
-
-        # Calculate the appropriate iframe height
-        num_rows = len(data)
-        iframe_height = min(num_rows * 140 + 50, cls.max_height)
-        print(f"Table height: {iframe_height}px")
-
-        # Create the full HTML document
-        html_content = f"""
-        <!DOCTYPE html>
-        <html>
-        <head>
-            <title>Table Display Example</title>
-            <style>
-                body {{
-                    margin: 0;
-                    padding: 20px;
-                    font-family: Arial, sans-serif;
-                }}
-                iframe {{
-                    width: 100%;
-                    height: {iframe_height}px;
-                    border: none;
-                    overflow: hidden;
-                }}
-            </style>
-        </head>
-        <body>
-            <iframe srcdoc='{table_html}'></iframe>
-        </body>
-        </html>
-        """
-
-        # Write the HTML file
-        abs_path = os.path.abspath(filename)
-        with open(filename, "w", encoding="utf-8") as f:
-            f.write(html_content)
-
-        # Open in browser if requested
-        if auto_open:
-            webbrowser.open("file://" + abs_path, new=2)
-
-        return abs_path
+# Example usage:
+if __name__ == "__main__":
+    headers = ["Name", "Age", "City"]
+    data = [["John", 30, "New York"], ["Jane", 25, "London"]]
 
+    # Using default (Pandas) renderer
+    table1 = TableDisplay(headers, data)
 
-if __name__ == "__main__":
-    TableDisplay.example()
+    # Using DataTables renderer
+    table2 = TableDisplay(headers, data, renderer=DataTablesRenderer())

edsl/results/TextEditor.py

@@ -0,0 +1,50 @@
+try:
+    import gradio as gr
+except ImportError:
+    print("Gradio is not installed. Please install it using `pip install gradio`")
+
+import time
+
+
+class TextEditor:
+    def __init__(self, initial_text=""):
+        self.text = initial_text
+        self._text_saved = False
+
+    def save_text(self, new_text):
+        self.text = new_text
+        self._text_saved = True
+        return "Text saved successfully!"
+
+    def edit_gui(self):
+        js_code = """
+        async (text) => {
+            await navigator.clipboard.writeText(text);
+            return "Copied to clipboard!";
+        }
+        """
+
+        with gr.Blocks() as interface:
+            text_area = gr.Textbox(
+                value=self.text, lines=10, label="Edit Text", placeholder="Type here..."
+            )
+
+            with gr.Row():
+                save_btn = gr.Button("Save")
+                copy_btn = gr.Button("Copy to Clipboard")
+
+            output = gr.Textbox(label="Status")
+
+            save_btn.click(fn=self.save_text, inputs=[text_area], outputs=[output])
+
+            # Add copy functionality
+            copy_btn.click(
+                fn=None, inputs=text_area, outputs=output, api_name=False, js=js_code
+            )
+
+        interface.launch(share=False, prevent_thread_lock=True)
+
+        while not self._text_saved:
+            time.sleep(0.1)
+
+        return self.text

edsl/results/__init__.py

@@ -1,2 +1,2 @@
-from edsl.results.Result import Result
+# from edsl.results.Result import Result
 from edsl.results.Results import Results

edsl/results/file_exports.py

@@ -0,0 +1,252 @@
+from abc import ABC, abstractmethod
+import io
+import csv
+import base64
+from typing import Optional, Union, Tuple, List, Any, Dict
+from openpyxl import Workbook
+
+from edsl.scenarios.FileStore import FileStore
+
+
+class FileExport(ABC):
+    def __init__(
+        self,
+        data: Any,
+        filename: Optional[str] = None,
+        remove_prefix: bool = False,
+        pretty_labels: Optional[Dict[str, str]] = None,
+    ):
+        self.data = data
+        self.filename = filename  # or self._get_default_filename()
+        self.remove_prefix = remove_prefix
+        self.pretty_labels = pretty_labels
+
+    @property
+    def mime_type(self) -> str:
+        """Return the MIME type for this export format."""
+        return self.__class__.mime_type
+
+    @property
+    def suffix(self) -> str:
+        """Return the file suffix for this format."""
+        return self.__class__.suffix
+
+    @property
+    def is_binary(self) -> bool:
+        """Whether the format is binary or text-based."""
+        return self.__class__.is_binary
+
+    def _get_default_filename(self) -> str:
+        """Generate default filename for this format."""
+        return f"results.{self.suffix}"
+
+    def _create_filestore(self, data: Union[str, bytes]) -> "FileStore":
+        """Create a FileStore instance with encoded data."""
+        if isinstance(data, str):
+            base64_string = base64.b64encode(data.encode()).decode()
+        else:
+            base64_string = base64.b64encode(data).decode()
+
+        from edsl.scenarios.FileStore import FileStore
+
+        path = self.filename or self._get_default_filename()
+
+        fs = FileStore(
+            path=path,
+            mime_type=self.mime_type,
+            binary=self.is_binary,
+            suffix=self.suffix,
+            base64_string=base64_string,
+        )
+
+        if self.filename is not None:
+            fs.write(self.filename)
+            return None
+        return fs
+
+    @abstractmethod
+    def format_data(self) -> Union[str, bytes]:
+        """Convert the input data to the target format."""
+        pass
+
+    def export(self) -> Optional["FileStore"]:
+        """Export the data to a FileStore instance."""
+        formatted_data = self.format_data()
+        return self._create_filestore(formatted_data)
+
+
+class JSONLExport(FileExport):
+    mime_type = "application/jsonl"
+    suffix = "jsonl"
+    is_binary = False
+
+    def format_data(self) -> str:
+        output = io.StringIO()
+        for entry in self.data:
+            key, values = list(entry.items())[0]
+            output.write(f'{{"{key}": {values}}}\n')
+        return output.getvalue()
+
+
+class TabularExport(FileExport, ABC):
+    """Base class for exports that use tabular data."""
+
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+        self.header, self.rows = self.data._get_tabular_data(
+            remove_prefix=self.remove_prefix, pretty_labels=self.pretty_labels
+        )
+
+
+class CSVExport(TabularExport):
+    mime_type = "text/csv"
+    suffix = "csv"
+    is_binary = False
+
+    def format_data(self) -> str:
+        output = io.StringIO()
+        writer = csv.writer(output)
+        writer.writerow(self.header)
+        writer.writerows(self.rows)
+        return output.getvalue()
+
+
+class ExcelExport(TabularExport):
+    mime_type = "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
+    suffix = "xlsx"
+    is_binary = True
+
+    def __init__(self, *args, sheet_name: Optional[str] = None, **kwargs):
+        super().__init__(*args, **kwargs)
+        self.sheet_name = sheet_name or "Results"
+
+    def format_data(self) -> bytes:
+        wb = Workbook()
+        ws = wb.active
+        ws.title = self.sheet_name
+
+        # Write header
+        for col, value in enumerate(self.header, 1):
+            ws.cell(row=1, column=col, value=value)
+
+        # Write data rows
+        for row_idx, row_data in enumerate(self.rows, 2):
+            for col, value in enumerate(row_data, 1):
+                ws.cell(row=row_idx, column=col, value=value)
+
+        # Save to bytes buffer
+        buffer = io.BytesIO()
+        wb.save(buffer)
+        buffer.seek(0)
+        return buffer.getvalue()
+
+
+import sqlite3
+from typing import Any
+
+
+class SQLiteExport(TabularExport):
+    mime_type = "application/x-sqlite3"
+    suffix = "db"
+    is_binary = True
+
+    def __init__(
+        self, *args, table_name: str = "results", if_exists: str = "replace", **kwargs
+    ):
+        """
+        Initialize SQLite export.
+
+        Args:
+            table_name: Name of the table to create
+            if_exists: How to handle existing table ('fail', 'replace', or 'append')
+        """
+        super().__init__(*args, **kwargs)
+        self.table_name = table_name
+        self.if_exists = if_exists
+
+    def _get_column_types(self) -> list[tuple[str, str]]:
+        """Infer SQL column types from the data."""
+        column_types = []
+
+        # Check first row of data for types
+        if self.rows:
+            first_row = self.rows[0]
+            for header, value in zip(self.header, first_row):
+                if isinstance(value, bool):
+                    sql_type = "BOOLEAN"
+                elif isinstance(value, int):
+                    sql_type = "INTEGER"
+                elif isinstance(value, float):
+                    sql_type = "REAL"
+                else:
+                    sql_type = "TEXT"
+                column_types.append((header, sql_type))
+        else:
+            # If no data, default to TEXT
+            column_types = [(header, "TEXT") for header in self.header]
+
+        return column_types
+
+    def _create_table(self, cursor: sqlite3.Cursor) -> None:
+        """Create the table with appropriate schema."""
+        column_types = self._get_column_types()
+
+        # Drop existing table if replace mode
+        if self.if_exists == "replace":
+            cursor.execute(f"DROP TABLE IF EXISTS {self.table_name}")
+        elif self.if_exists == "fail":
+            cursor.execute(
+                f"SELECT name FROM sqlite_master WHERE type='table' AND name=?",
+                (self.table_name,),
+            )
+            if cursor.fetchone():
+                raise ValueError(f"Table {self.table_name} already exists")
+
+        # Create table
+        columns = ", ".join(f'"{col}" {dtype}' for col, dtype in column_types)
+        create_table_sql = f"""
+        CREATE TABLE IF NOT EXISTS {self.table_name} (
+            {columns}
+        )
+        """
+        cursor.execute(create_table_sql)
+
+    def format_data(self) -> bytes:
+        """Convert the data to a SQLite database file."""
+        buffer = io.BytesIO()
+
+        # Create in-memory database
+        conn = sqlite3.connect(":memory:")
+        cursor = conn.cursor()
+
+        # Create table and insert data
+        self._create_table(cursor)
+
+        # Prepare placeholders for INSERT
+        placeholders = ",".join(["?" for _ in self.header])
+        insert_sql = f"INSERT INTO {self.table_name} ({','.join(self.header)}) VALUES ({placeholders})"
+
+        # Insert data
+        cursor.executemany(insert_sql, self.rows)
+        conn.commit()
+
+        # Save to file buffer
+        conn.backup(sqlite3.connect(buffer))
+        conn.close()
+
+        buffer.seek(0)
+        return buffer.getvalue()
+
+    def _validate_params(self) -> None:
+        """Validate initialization parameters."""
+        valid_if_exists = {"fail", "replace", "append"}
+        if self.if_exists not in valid_if_exists:
+            raise ValueError(
+                f"if_exists must be one of {valid_if_exists}, got {self.if_exists}"
+            )
+
+        # Validate table name (basic SQLite identifier validation)
+        if not self.table_name.isalnum() and not all(c in "_" for c in self.table_name):
+            raise ValueError(
+                f"Invalid table name: {self.table_name}. Must contain only alphanumeric characters and underscores."
+            )

edsl/results/{Selector.py → results_selector.py}

@@ -1,7 +1,12 @@
-from typing import Union, List, Dict, Any
+from typing import Union, List, Dict, Any, Optional
+import sys
 from collections import defaultdict
 from edsl.results.Dataset import Dataset
 
+from edsl.exceptions.results import ResultsColumnNotFoundError
+
+from edsl.utilities.is_notebook import is_notebook
+
 
 class Selector:
     def __init__(
@@ -19,11 +24,17 @@ class Selector:
         self._fetch_list = fetch_list_func
         self.columns = columns
 
-    def select(self, *columns: Union[str, List[str]]) -> "Dataset":
-        columns = self._normalize_columns(columns)
-        to_fetch = self._get_columns_to_fetch(columns)
-        # breakpoint()
-        new_data = self._fetch_data(to_fetch)
+    def select(self, *columns: Union[str, List[str]]) -> Optional[Dataset]:
+        try:
+            columns = self._normalize_columns(columns)
+            to_fetch = self._get_columns_to_fetch(columns)
+            new_data = self._fetch_data(to_fetch)
+        except ResultsColumnNotFoundError as e:
+            if is_notebook():
+                print("Error:", e, file=sys.stderr)
+                return None
+            else:
+                raise e
         return Dataset(new_data)
 
     def _normalize_columns(self, columns: Union[str, List[str]]) -> tuple:
@@ -63,17 +74,16 @@ class Selector:
             search_in_list = self.columns
         else:
             search_in_list = [s.split(".")[1] for s in self.columns]
-        # breakpoint()
         matches = [s for s in search_in_list if s.startswith(partial_name)]
         return [partial_name] if partial_name in matches else matches
 
     def _validate_matches(self, column: str, matches: List[str]):
         if len(matches) > 1:
-            raise ValueError(
+            raise ResultsColumnNotFoundError(
                 f"Column '{column}' is ambiguous. Did you mean one of {matches}?"
             )
         if len(matches) == 0 and ".*" not in column:
-            raise ValueError(f"Column '{column}' not found in data.")
+            raise ResultsColumnNotFoundError(f"Column '{column}' not found in data.")
 
     def _parse_column(self, column: str) -> tuple[str, str]:
         if "." in column:
@@ -89,11 +99,11 @@ class Selector:
         close_matches = difflib.get_close_matches(column, self._key_to_data_type.keys())
         if close_matches:
             suggestions = ", ".join(close_matches)
-            raise KeyError(
+            raise ResultsColumnNotFoundError(
                 f"Column '{column}' not found in data. Did you mean: {suggestions}?"
             )
         else:
-            raise KeyError(f"Column {column} not found in data")
+            raise ResultsColumnNotFoundError(f"Column {column} not found in data")
 
     def _process_column(self, data_type: str, key: str, to_fetch: Dict[str, List[str]]):
         data_types = self._get_data_types_to_return(data_type)
@@ -108,13 +118,13 @@ class Selector:
                     self.items_in_order.append(f"{dt}.{k}")
 
         if not found_once:
-            raise ValueError(f"Key {key} not found in data.")
+            raise ResultsColumnNotFoundError(f"Key {key} not found in data.")
 
     def _get_data_types_to_return(self, parsed_data_type: str) -> List[str]:
         if parsed_data_type == "*":
             return self.known_data_types
         if parsed_data_type not in self.known_data_types:
-            raise ValueError(
+            raise ResultsColumnNotFoundError(
                 f"Data type {parsed_data_type} not found in data. Did you mean one of {self.known_data_types}"
             )
         return [parsed_data_type]