scitex 2.0.0__py2.py3-none-any.whl → 2.1.0__py2.py3-none-any.whl

scitex/io/_save_modules/__init__.py

@@ -30,9 +30,12 @@ from ._hdf5 import _save_hdf5 as save_hdf5
 from ._matlab import _save_matlab as save_matlab
 from ._catboost import _save_catboost as save_catboost
 from ._text import _save_text as save_text
+from ._tex import _save_tex as save_tex
 from ._html import save_html
 from ._image import save_image
 from ._mp4 import _mk_mp4 as save_mp4
+from ._zarr import _save_zarr as save_zarr
+from ._bibtex import save_bibtex
 
 # Import additional save utilities
 from ._listed_dfs_as_csv import _save_listed_dfs_as_csv as save_listed_dfs_as_csv
@@ -55,9 +58,12 @@ __all__ = [
     "save_matlab",
     "save_catboost",
     "save_text",
+    "save_tex",
     "save_html",
     "save_image",
     "save_mp4",
+    "save_zarr",
+    "save_bibtex",
     "save_listed_dfs_as_csv",
     "save_listed_scalars_as_csv",
     "save_optuna_study_as_csv_and_pngs",

scitex/io/_save_modules/_bibtex.py

@@ -0,0 +1,194 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+# Timestamp: "2025-01-19 14:25:00 (ywatanabe)"
+# File: ./src/scitex/io/_save_modules/_bibtex.py
+# ----------------------------------------
+import os
+__FILE__ = __file__
+__DIR__ = os.path.dirname(__FILE__)
+# ----------------------------------------
+
+"""
+BibTeX file saving module for SciTeX IO.
+
+This module provides functionality to save data in BibTeX format,
+supporting both individual entries and collections.
+"""
+
+from scitex import logging
+from typing import List, Dict, Any, Union
+from pathlib import Path
+from datetime import datetime
+
+logger = logging.getLogger(__name__)
+
+
+def save_bibtex(obj: Union[Dict, List[Dict]], spath: str, **kwargs) -> None:
+    """
+    Save data as BibTeX file.
+    
+    Args:
+        obj: Can be:
+            - A single BibTeX entry (dict)
+            - List of BibTeX entries (list of dicts)
+            - A Paper object from scitex.scholar
+            - A PaperCollection object from scitex.scholar
+        spath: Path where the .bib file will be saved
+        **kwargs: Additional arguments
+            - encoding: File encoding (default: utf-8)
+            - add_header: Add header comment (default: True)
+            - append: Append to existing file (default: False)
+            - include_enriched: Include enriched metadata for Paper objects (default: True)
+    
+    The input dict should have structure:
+    {
+        'entry_type': 'article',
+        'key': 'author2023',
+        'fields': {
+            'title': 'Paper Title',
+            'author': 'Author Name',
+            'year': '2023',
+            ...
+        }
+    }
+    """
+    # Check if it's a Paper or PaperCollection from scholar module
+    obj_type = type(obj).__name__
+    if obj_type == 'PaperCollection':
+        # Get BibTeX content from PaperCollection
+        include_enriched = kwargs.get('include_enriched', True)
+        content = obj._to_bibtex(include_enriched=include_enriched)
+        # Write directly so scitex.io.save features work
+        encoding = kwargs.get('encoding', 'utf-8')
+        add_header = kwargs.get('add_header', True)
+        
+        with open(spath, 'w', encoding=encoding) as f:
+            if add_header:
+                f.write(f"% BibTeX bibliography\n")
+                f.write(f"% Generated by SciTeX on {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}\n")
+                f.write(f"% Number of entries: {len(obj._papers)}\n\n")
+            f.write(content)
+        return
+        
+    elif obj_type == 'Paper':
+        # Get BibTeX content from Paper
+        include_enriched = kwargs.get('include_enriched', True)
+        content = obj._to_bibtex(include_enriched=include_enriched)
+        # Write directly so scitex.io.save features work
+        encoding = kwargs.get('encoding', 'utf-8')
+        add_header = kwargs.get('add_header', True)
+        
+        with open(spath, 'w', encoding=encoding) as f:
+            if add_header:
+                f.write(f"% BibTeX entry\n")
+                f.write(f"% Generated by SciTeX on {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}\n\n")
+            f.write(content)
+        return
+    
+    # Handle standard dict format
+    encoding = kwargs.get('encoding', 'utf-8')
+    add_header = kwargs.get('add_header', True)
+    append = kwargs.get('append', False)
+    
+    # Ensure obj is a list
+    if isinstance(obj, dict):
+        entries = [obj]
+    else:
+        entries = obj
+    
+    # Generate BibTeX content
+    lines = []
+    
+    if add_header and not append:
+        lines.extend([
+            f"% BibTeX bibliography",
+            f"% Generated by SciTeX on {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}",
+            f"% Number of entries: {len(entries)}",
+            ""
+        ])
+    
+    # Convert each entry
+    for entry in entries:
+        bibtex_str = _entry_to_bibtex(entry)
+        lines.append(bibtex_str)
+        lines.append("")  # Empty line between entries
+    
+    content = '\n'.join(lines)
+    
+    # Write file
+    mode = 'a' if append else 'w'
+    with open(spath, mode, encoding=encoding) as f:
+        f.write(content)
+
+
+def _entry_to_bibtex(entry: Dict[str, Any]) -> str:
+    """
+    Convert a single entry dict to BibTeX format.
+    
+    Args:
+        entry: Dictionary with 'entry_type', 'key', and 'fields'
+    
+    Returns:
+        BibTeX formatted string
+    """
+    # Extract components
+    entry_type = entry.get('entry_type', 'misc')
+    key = entry.get('key', 'unknown')
+    fields = entry.get('fields', {})
+    
+    # Start building the entry
+    lines = [f"@{entry_type}{{{key},"]
+    
+    # Add fields
+    for field_name, field_value in fields.items():
+        # Escape special characters
+        escaped_value = _escape_bibtex(str(field_value))
+        
+        # Determine if we need braces or quotes
+        if '\n' in escaped_value or '{' in escaped_value or '}' in escaped_value:
+            # Use braces for multi-line or complex values
+            lines.append(f"  {field_name} = {{{escaped_value}}},")
+        else:
+            # Use braces (standard)
+            lines.append(f"  {field_name} = {{{escaped_value}}},")
+    
+    # Remove trailing comma from last field
+    if lines[-1].endswith(','):
+        lines[-1] = lines[-1][:-1]
+    
+    lines.append("}")
+    
+    return '\n'.join(lines)
+
+
+def _escape_bibtex(text: str) -> str:
+    """
+    Escape special characters for BibTeX.
+    
+    Args:
+        text: Text to escape
+    
+    Returns:
+        Escaped text safe for BibTeX
+    """
+    # Special characters that need escaping
+    replacements = {
+        '&': r'\&',
+        '%': r'\%',
+        '$': r'\$',
+        '#': r'\#',
+        '_': r'\_',
+        # Don't escape braces - they're used for formatting
+        # '{': r'\{',
+        # '}': r'\}',
+    }
+    
+    for char, escaped in replacements.items():
+        text = text.replace(char, escaped)
+    
+    return text
+
+
+
+
+# EOF

scitex/io/_save_modules/_csv.py

@@ -83,7 +83,11 @@ def _save_csv(obj, spath: str, **kwargs) -> None:
     elif isinstance(obj, dict):
         pd.DataFrame.from_dict(obj).to_csv(spath, **kwargs)
     else:
-        try:
-            pd.DataFrame({"data": [obj]}).to_csv(spath, **kwargs)
-        except:
-            raise ValueError(f"Unable to save type {type(obj)} as CSV")
+        # Check if it's a PaperCollection or similar object with to_dataframe method
+        if hasattr(obj, 'to_dataframe') and callable(getattr(obj, 'to_dataframe')):
+            obj.to_dataframe().to_csv(spath, **kwargs)
+        else:
+            try:
+                pd.DataFrame({"data": [obj]}).to_csv(spath, **kwargs)
+            except:
+                raise ValueError(f"Unable to save type {type(obj)} as CSV")

scitex/io/_save_modules/_excel.py

@@ -1,11 +1,11 @@
 #!/usr/bin/env python3
 # -*- coding: utf-8 -*-
-# Timestamp: "2025-06-12 12:59:00 (ywatanabe)"
-# File: /ssh:sp:/home/ywatanabe/proj/.claude-worktree/scitex_repo/src/scitex/io/_save_modules/_excel.py
+# Timestamp: "2025-10-01 20:31:51 (ywatanabe)"
+# File: /ssh:sp:/home/ywatanabe/proj/scitex_repo/src/scitex/io/_save_modules/_excel.py
 # ----------------------------------------
+from __future__ import annotations
 import os
-
-__FILE__ = "./src/scitex/io/_save_modules/_excel.py"
+__FILE__ = __file__
 __DIR__ = os.path.dirname(__FILE__)
 # ----------------------------------------
 
@@ -13,37 +13,196 @@ __DIR__ = os.path.dirname(__FILE__)
 Excel saving functionality for scitex.io.save
 """
 
-import pandas as pd
 import numpy as np
+import pandas as pd
+
+
+def _generate_pval_variants():
+    connectors = ["", "_", "-"]
+    pval_bases = ["pvalue", "p"]
+    adjusted_variants = ["", "adjusted", "adj"]
+
+    pval_variants = []
+    for base in pval_bases:
+        for conn in connectors:
+            for adj in adjusted_variants:
+                if adj:
+                    variant = f"{base}{conn}{adj}"
+                else:
+                    if base == "p":
+                        variant = f"{base}{conn}value" if conn else base
+                    else:
+                        variant = base
+                if variant not in pval_variants:
+                    pval_variants.append(variant)
+
+    pval_variants.extend(["padj", "p-val"])
+    pval_variants = sorted(set(pval_variants))
+    return pval_variants
+
+
+def _is_statistical_results(df):
+    """
+    Check if DataFrame contains statistical test results.
 
+    Parameters
+    ----------
+    df : pd.DataFrame
+        DataFrame to check
+
+    Returns
+    -------
+    bool
+        True if DataFrame appears to contain statistical test results
+    """
+    if not isinstance(df, pd.DataFrame):
+        return False
+
+    # Check for characteristic statistical test fields
+    PVAL_VARIANTS = _generate_pval_variants()
+    return any(col in df.columns for col in PVAL_VARIANTS)
+
+
+def _apply_stats_styling(df, spath):
+    """Apply conditional formatting to statistical results in Excel.
 
-def save_excel(obj, spath, **kwargs):
-    """Handle Excel file saving.
-    
     Parameters
     ----------
-    obj : pd.DataFrame, dict, or np.ndarray
+    df : pd.DataFrame
+        Statistical results DataFrame
+    spath : str
+        Path to Excel file
+
+    Notes
+    -----
+    Color coding for p-values:
+    - Red background: p < 0.001 (***)
+    - Orange background: p < 0.01 (**)
+    - Yellow background: p < 0.05 (*)
+    - Light gray: p >= 0.05 (ns)
+    """
+    try:
+        from openpyxl import load_workbook
+        from openpyxl.styles import Font, PatternFill
+    except ImportError:
+        return
+
+    wb = load_workbook(spath)
+    ws = wb.active
+
+    fill_red = PatternFill(
+        start_color="FF6B6B", end_color="FF6B6B", fill_type="solid"
+    )
+    fill_orange = PatternFill(
+        start_color="FFA500", end_color="FFA500", fill_type="solid"
+    )
+    fill_yellow = PatternFill(
+        start_color="FFE66D", end_color="FFE66D", fill_type="solid"
+    )
+    fill_gray = PatternFill(
+        start_color="E8E8E8", end_color="E8E8E8", fill_type="solid"
+    )
+    font_bold = Font(bold=True)
+
+    PVAL_VARIANTS = _generate_pval_variants()
+    pval_cols = [col for col in df.columns if col in PVAL_VARIANTS]
+
+    for pval_col in pval_cols:
+        pvalue_col_idx = df.columns.get_loc(pval_col) + 1
+
+        for row_idx, pvalue in enumerate(df[pval_col], start=2):
+            cell = ws.cell(row=row_idx, column=pvalue_col_idx)
+            if pd.notna(pvalue):
+                if pvalue < 0.001:
+                    cell.fill = fill_red
+                    cell.font = font_bold
+                elif pvalue < 0.01:
+                    cell.fill = fill_orange
+                    cell.font = font_bold
+                elif pvalue < 0.05:
+                    cell.fill = fill_yellow
+                    cell.font = font_bold
+                else:
+                    cell.fill = fill_gray
+
+            if pd.notna(pvalue) and pvalue < 0.05:
+                for col_idx in range(1, len(df.columns) + 1):
+                    ws.cell(row=row_idx, column=col_idx).font = font_bold
+
+    for column in ws.columns:
+        max_length = 0
+        column_letter = column[0].column_letter
+        for cell in column:
+            try:
+                if len(str(cell.value)) > max_length:
+                    max_length = len(str(cell.value))
+            except:
+                pass
+        adjusted_width = min(max_length + 2, 50)
+        ws.column_dimensions[column_letter].width = adjusted_width
+
+    ws.freeze_panes = "A2"
+    wb.save(spath)
+
+
+def save_excel(obj, spath, style=True, **kwargs):
+    """Handle Excel file saving with optional statistical formatting.
+
+    Parameters
+    ----------
+    obj : pd.DataFrame, dict, list of dict, or np.ndarray
         Object to save as Excel file
     spath : str
         Path where Excel file will be saved
+    style : bool, default True
+        If True, automatically apply conditional formatting to statistical results
+        (p-values colored by significance level). Set to False to disable styling.
     **kwargs
         Additional keyword arguments passed to pandas.DataFrame.to_excel()
-        
+
     Raises
     ------
     ValueError
         If object type cannot be saved as Excel file
+
+    Notes
+    -----
+    When saving statistical test results (DataFrames with 'pvalue' column),
+    automatic conditional formatting is applied unless style=False:
+
+    - Red background: p < 0.001 (***)
+    - Orange background: p < 0.01 (**)
+    - Yellow background: p < 0.05 (*)
+    - Light gray: p >= 0.05 (ns)
+    - Bold font for significant results (p < 0.05)
+
+    Examples
+    --------
+    >>> import scitex as stx
+    >>> results = stx.stats.test_ttest_ind(x, y)
+    >>> stx.io.save(results, 'results.xlsx')  # Auto-styled
+    >>> stx.io.save(results, 'results.xlsx', style=False)  # No styling
     """
+    # Convert to DataFrame
     if isinstance(obj, pd.DataFrame):
-        obj.to_excel(spath, index=False, **kwargs)
+        df = obj
     elif isinstance(obj, dict):
         df = pd.DataFrame(obj)
-        df.to_excel(spath, index=False, **kwargs)
+    elif isinstance(obj, list):
+        # Handle list of dicts (common for multiple test results)
+        df = pd.DataFrame(obj)
     elif isinstance(obj, np.ndarray):
         df = pd.DataFrame(obj)
-        df.to_excel(spath, index=False, **kwargs)
     else:
-        raise ValueError(f"Cannot save object of type {type(obj)} as Excel file")
+        raise ValueError(
+            f"Cannot save object of type {type(obj)} as Excel file"
+        )
+
+    # Save to Excel
+    df.to_excel(spath, index=False, **kwargs)
 
+    # Apply styling if enabled and data contains statistical results
+    if style and _is_statistical_results(df):
+        _apply_stats_styling(df, spath)
 
-# EOF
+# EOF