masster 0.5.16__py3-none-any.whl → 0.5.17__py3-none-any.whl

masster/_version.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 
-__version__ = "0.5.16"
+__version__ = "0.5.17"
 
 
 def get_version():

masster/wizard/wizard.py

@@ -228,9 +228,17 @@ class Wizard:
     that process raw MS data through the complete pipeline: file discovery, feature
     detection, sample processing, study assembly, alignment, merging, and export.
     
-    This simplified version focuses on two core functions:
+    Core functions:
     - create_scripts(): Generate standalone analysis scripts
-    - execute(): Create and run analysis scripts
+    - test_only(): Process only one file for parameter validation
+    - test_and_run(): Test with single file, then run full batch if successful
+    - run(): Execute full batch processing on all files
+    
+    Recommended workflow:
+    1. wizard = Wizard(source="raw_data", folder="output")
+    2. wizard.create_scripts()  # Generate analysis scripts
+    3. wizard.test_only()       # Validate with single file
+    4. wizard.run()             # Process all files
     """
     
     def __init__(
@@ -381,6 +389,9 @@ class Wizard:
             workflow_script_path = self.folder_path / "1_masster_workflow.py"
             workflow_content = self._generate_workflow_script_content(source_info)
             
+            # Apply test mode modifications
+            workflow_content = self._add_test_mode_support(workflow_content)
+            
             with open(workflow_script_path, 'w', encoding='utf-8') as f:
                 f.write(workflow_content)
             files_created.append(str(workflow_script_path))
@@ -458,6 +469,7 @@ class Wizard:
             'Generated by masster wizard',
             '"""',
             '',
+            'import os',
             'import sys',
             'import time',
             'from pathlib import Path',
@@ -466,6 +478,10 @@ class Wizard:
             'from masster.study import Study',
             'from masster import __version__',
             '',
+            '# Test mode configuration',
+            'TEST_MODE = os.environ.get("MASSTER_TEST_MODE", "0") == "1"',
+            'TEST_ONLY = os.environ.get("MASSTER_TEST_ONLY", "0") == "1"  # Only run test, don\'t continue to full batch',
+            '',
             '# Analysis parameters',
             'PARAMS = {',
             '    # === Core Configuration ===',
@@ -474,6 +490,10 @@ class Wizard:
             f'    "polarity": {self.params.polarity!r},  # Ion polarity mode ("positive" or "negative")',
             f'    "num_cores": {self.params.num_cores},  # Number of CPU cores for parallel processing',
             '',
+            '    # === Test Mode ===',
+            '    "test_mode": TEST_MODE,  # Process only first file for testing',
+            '    "test_only": TEST_ONLY,  # Stop after test, don\'t run full batch',
+            '',
             '    # === File Discovery ===',
             f'    "file_extensions": {self.params.file_extensions!r},  # File extensions to search for',
             f'    "search_subfolders": {self.params.search_subfolders},  # Whether to search subdirectories recursively',
@@ -779,71 +799,198 @@ class Wizard:
             f"1. REVIEW PARAMETERS in {workflow_script_name}:",
             f"   In particular, verify the NOISE, CHROM_FWHM, and MIN_SAMPLES_FOR_MERGE",
             "",
-            "2. EXECUTE SAMPLE PROCESSING:",
-            f"   uv run python {workflow_script_name}",
+            "2. TEST SINGLE FILE (RECOMMENDED):",
+            f"   wizard.test_only()  # Validate parameters with first file only",
+            "",
+            "3. EXECUTE FULL BATCH:",
+            f"   wizard.run()        # Process all files",
+            f"   # OR: wizard.test_and_run()  # Test first, then run all",
+            f"   # OR: uv run python {workflow_script_name}",
             "",
-            "3. INTERACTIVE ANALYSIS:",
+            "4. INTERACTIVE ANALYSIS:",
             f"   uv run marimo edit {Path('2_interactive_analysis.py').name}",
             ""]            
         )
         
         return instructions
 
-    def execute(self) -> Dict[str, Any]:
+    def _add_test_mode_support(self, workflow_content: str) -> str:
+        """Add test mode functionality to the generated workflow script."""
+        lines = workflow_content.split('\n')
+        
+        # Insert test mode code after print statements in main function
+        for i, line in enumerate(lines):
+            # Add test mode print after the masster version line
+            if 'print("masster' in line and 'Automated MS Data Analysis")' in line:
+                lines.insert(i + 1, '        if TEST_MODE:')
+                lines.insert(i + 2, '            print("🧪 TEST MODE: Processing single file only")')
+                break
+        
+        # Add mode info after num_cores print
+        for i, line in enumerate(lines):
+            if 'print(f"CPU Cores: {PARAMS[\'num_cores\']}")' in line:
+                lines.insert(i + 1, '        if TEST_MODE:')
+                lines.insert(i + 2, '            print(f"Mode: {\'Test Only\' if TEST_ONLY else \'Test + Full Batch\'}")')
+                break
+                
+        # Add file limitation logic after file listing
+        for i, line in enumerate(lines):
+            if 'print(f"  ... and {len(raw_files) - 5} more")' in line:
+                lines.insert(i + 1, '        ')
+                lines.insert(i + 2, '        # Limit to first file in test mode')
+                lines.insert(i + 3, '        if TEST_MODE:')
+                lines.insert(i + 4, '            raw_files = raw_files[:1]')
+                lines.insert(i + 5, '            print(f"\\n🧪 TEST MODE: Processing only first file: {raw_files[0].name}")')
+                break
+        
+        # Modify num_cores for test mode
+        for i, line in enumerate(lines):
+            if 'PARAMS[\'num_cores\']' in line and 'convert_raw_to_sample5(' in lines[i-2:i+3]:
+                lines[i] = line.replace('PARAMS[\'num_cores\']', 'PARAMS[\'num_cores\'] if not TEST_MODE else 1  # Use single core for test')
+                break
+        
+        # Add test-only exit logic after successful processing
+        for i, line in enumerate(lines):
+            if 'print(f"Successfully processed {len(sample5_files)} files to sample5")' in line:
+                lines.insert(i + 1, '        ')
+                lines.insert(i + 2, '        # Stop here if test-only mode')
+                lines.insert(i + 3, '        if TEST_ONLY:')
+                lines.insert(i + 4, '            print("\\n🧪 TEST ONLY mode: Stopping after successful single file processing")')
+                lines.insert(i + 5, '            print(f"Test file created: {sample5_files[0]}")')
+                lines.insert(i + 6, '            print("\\nTo run full batch, use: wizard.run()")')
+                lines.insert(i + 7, '            total_time = time.time() - start_time')
+                lines.insert(i + 8, '            print(f"\\nTest processing time: {total_time:.1f} seconds")')
+                lines.insert(i + 9, '            return True')
+                break
+                
+        return '\n'.join(lines)
+
+    def test_and_run(self) -> Dict[str, Any]:
         """
-        Execute the sample processing workflow.
+        Test the sample processing workflow with a single file, then run full batch.
         
-        This method:
-        1. Creates scripts if they don't exist (calls create_scripts())
-        2. Runs the 1_masster_workflow.py script to process raw files
+        This method runs the 1_masster_workflow.py script in test mode to process
+        the first raw file for validation, then automatically continues with the 
+        full batch if the test succeeds. The script must already exist - call 
+        create_scripts() first if needed.
         
         Returns:
             Dictionary containing:
-            - status: "success", "error", or "scripts_created"
+            - status: "success" or "error"
             - message: Status message
             - instructions: List of next steps
-            - files_created: List of created file paths (if scripts were created)
+        """
+        return self._execute_workflow(test_mode=True)
+
+    def test_only(self) -> Dict[str, Any]:
+        """
+        Test the sample processing workflow with a single file only.
+        
+        This method runs the 1_masster_workflow.py script in test-only mode to process
+        only the first raw file and then stops (does not continue to full study processing).
+        The script must already exist - call create_scripts() first if needed.
+        
+        Returns:
+            Dictionary containing:
+            - status: "success" or "error"
+            - message: Status message
+            - instructions: List of next steps
+            - test_file: Path to the processed test file (if successful)
+        """
+        return self._execute_workflow(test_mode=True, test_only=True)
+
+    def run(self) -> Dict[str, Any]:
+        """
+        Run the sample processing workflow.
+        
+        This method runs the 1_masster_workflow.py script to process raw files.
+        The script must already exist - call create_scripts() first if needed.
+        
+        Returns:
+            Dictionary containing:
+            - status: "success" or "error"
+            - message: Status message
+            - instructions: List of next steps
+        """
+        return self._execute_workflow(test_mode=False)
+
+    def _execute_workflow(self, test_mode: bool = False, test_only: bool = False) -> Dict[str, Any]:
+        """
+        Execute the workflow script in either test or full mode.
+        
+        Args:
+            test_mode: If True, run in test mode (single file), otherwise full batch
+            test_only: If True, stop after single file test (only used with test_mode=True)
         """
         try:
             workflow_script_path = self.folder_path / "1_masster_workflow.py"
             
-            # Check if workflow script exists, create it if not
+            # Check if workflow script exists
             if not workflow_script_path.exists():
-                print("📝 Workflow script not found, creating scripts first...")
-                result = self.create_scripts()
-                if result["status"] != "success":
-                    return result
+                return {
+                    "status": "error",
+                    "message": "Workflow script not found. Please run create_scripts() first.",
+                    "instructions": [
+                        "❌ Missing 1_masster_workflow.py",
+                        "Run: wizard.create_scripts()",
+                        "Then: wizard.run()"
+                    ]
+                }
+            
+            # Setup execution mode
+            if test_only:
+                mode_label = "test-only"
+            elif test_mode:
+                mode_label = "test"
+            else:
+                mode_label = "full batch"
                 
-                print("✅ Scripts created successfully")
-                print(f"📁 Output folder: {self.folder_path}")
+            env = None
+            if test_mode:
+                import os
+                env = os.environ.copy()
+                env['MASSTER_TEST_MODE'] = '1'
+                if test_only:
+                    env['MASSTER_TEST_ONLY'] = '1'
                 
             # Execute the workflow script
-            print(f"🚀 Executing sample processing workflow...")
+            print(f"🚀 Executing {mode_label} processing workflow...")
             print(f"📄 Running: {workflow_script_path.name}")
             print("=" * 60)
             
             import subprocess
             result = subprocess.run([
                 sys.executable, str(workflow_script_path)
-            ], cwd=str(self.folder_path))
+            ], cwd=str(self.folder_path), env=env)
             
             success = result.returncode == 0
             
             if success:
                 print("=" * 60)
-                print("✅ Sample processing completed successfully!")
-                print("📋 Next step: Run interactive analysis")
-                print("   uv run marimo edit 2_interactive_analysis.py")
+                if test_only:
+                    print("✅ Test-only processing completed successfully!")
+                    print("📋 Single file validated - ready for full batch")
+                    print("   wizard.run()")
+                elif test_mode:
+                    print("✅ Test processing completed successfully!")
+                    print("📋 Next step: Run full batch")
+                    print("   wizard.run()")
+                else:
+                    print("✅ Sample processing completed successfully!")
+                    print("📋 Next step: Run interactive analysis")
+                    print("   uv run marimo edit 2_interactive_analysis.py")
                 print("=" * 60)
                 
+                next_step = ("Next: wizard.run()" if test_mode else 
+                           "Next: uv run marimo edit 2_interactive_analysis.py")
+                
                 return {
                     "status": "success",
-                    "message": "Sample processing completed successfully",
+                    "message": f"{mode_label.capitalize()} processing completed successfully",
                     "instructions": [
-                        "✅ Sample processing completed",
-                        "Next: uv run marimo edit 2_interactive_analysis.py"
-                    ],
-                    "files_created": []
+                        f"✅ {mode_label.capitalize()} processing completed",
+                        next_step
+                    ]
                 }
             else:
                 return {
@@ -853,8 +1000,7 @@ class Wizard:
                         "❌ Check the error messages above",
                         "Review parameters in 1_masster_workflow.py",
                         f"Try running manually: python {workflow_script_path.name}"
-                    ],
-                    "files_created": []
+                    ]
                 }
                 
         except Exception as e:
@@ -865,8 +1011,7 @@ class Wizard:
                     "❌ Execution failed",
                     "Check that source files exist and are accessible",
                     "Verify folder permissions"
-                ],
-                "files_created": []
+                ]
             }
 
     def _generate_script_content(self) -> str:
@@ -1175,198 +1320,6 @@ class Wizard:
         return '\n'.join(script_lines)
 
 
-def create_script(
-    source: str, 
-    folder: str, 
-    filename: str = 'run_masster.py', 
-    polarity: str = "positive",
-    adducts: Optional[List[str]] = None,
-    params: Optional[wizard_def] = None,
-    num_cores: int = 0,
-    **kwargs
-) -> bool:
-    """
-    Create a standalone analysis script without initializing a Wizard instance.
-    
-    This function generates a Python script that replicates automated processing
-    steps with the specified configuration. The script can be executed independently
-    to perform the same analysis.
-    
-    Parameters:
-        source: Directory containing raw data files
-        folder: Output directory for processed study  
-        filename: Filename for the generated script (should end with .py)
-        polarity: Ion polarity mode ("positive" or "negative")
-        adducts: List of adduct specifications (auto-set if None)
-        params: Custom wizard_def parameters (optional)
-        num_cores: Number of CPU cores (0 = auto-detect)
-        **kwargs: Additional parameters to override defaults
-        
-    Returns:
-        True if script was generated successfully, False otherwise
-        
-    Example:
-        >>> from masster.wizard import create_script
-        >>> create_script(
-        ...     source=r'D:\\Data\\raw_files',
-        ...     folder=r'D:\\Data\\output', 
-        ...     filename='run_masster.py',
-        ...     polarity='positive'
-        ... )
-    """
-    
-    try:
-        # Create parameters
-        if params is not None:
-            # Use provided params as base
-            wizard_params = params
-            # Update with provided values
-            wizard_params.source = source
-            wizard_params.folder = folder
-            if polarity != "positive":  # Only override if explicitly different
-                wizard_params.polarity = polarity
-            if num_cores > 0:
-                wizard_params.num_cores = num_cores
-            if adducts is not None:
-                wizard_params.adducts = adducts
-        else:
-            # Create new params with provided values
-            wizard_params = wizard_def(
-                source=source,
-                folder=folder,
-                polarity=polarity,
-                num_cores=max(1, int(multiprocessing.cpu_count() * 0.75)) if num_cores <= 0 else num_cores
-            )
-            
-            if adducts is not None:
-                wizard_params.adducts = adducts
-            
-            # Apply any additional kwargs
-            for key, value in kwargs.items():
-                if hasattr(wizard_params, key):
-                    setattr(wizard_params, key, value)
-        
-        # Ensure study folder exists
-        study_path = Path(folder)
-        study_path.mkdir(parents=True, exist_ok=True)
-        
-        # Create a temporary Wizard instance to generate the script
-        temp_wizard = Wizard(params=wizard_params)
-        
-        # Generate the scripts using the instance method
-        result = temp_wizard.create_scripts()
-        success = result.get("status") == "success"
-        
-        return success
-        
-    except Exception as e:
-        print(f"Failed to create script: {e}")
-        import traceback
-        traceback.print_exc()
-        return False
-
-
-def execute(
-    source: str, 
-    folder: str, 
-    filename: str = 'run_masster.py', 
-    polarity: str = "positive",
-    adducts: Optional[List[str]] = None,
-    params: Optional[wizard_def] = None,
-    num_cores: int = 0,
-    **kwargs
-) -> bool:
-    """
-    Create and execute a standalone analysis script for automated MS data processing.
-    
-    This function generates a Python script with the same parameters as create_script(),
-    but immediately executes it after creation. Combines script generation and execution
-    in a single step.
-    
-    Parameters:
-        source: Directory containing raw data files
-        folder: Output directory for processed study  
-        filename: Filename for the generated script (should end with .py)
-        polarity: Ion polarity mode ("positive" or "negative")
-        adducts: List of adduct specifications (auto-set if None)
-        params: Custom wizard_def parameters (optional)
-        num_cores: Number of CPU cores (0 = auto-detect)
-        **kwargs: Additional parameters to override defaults
-        
-    Returns:
-        True if script was created and executed successfully, False otherwise
-        
-    Example:
-        >>> from masster.wizard import execute
-        >>> execute(
-        ...     source=r'D:\\Data\\raw_files',
-        ...     folder=r'D:\\Data\\output', 
-        ...     polarity='positive'
-        ... )
-    """
-    
-    try:
-        # First, create the script using create_script()
-        script_created = create_script(
-            source=source,
-            folder=folder,
-            filename=filename,
-            polarity=polarity,
-            adducts=adducts,
-            params=params,
-            num_cores=num_cores,
-            **kwargs
-        )
-        
-        if not script_created:
-            print("Failed to create analysis script")
-            return False
-            
-        # Get the full path to the created script
-        study_path = Path(folder)
-        script_path = study_path / Path(filename).name
-        
-        if not script_path.exists():
-            print(f"Script file not found: {script_path}")
-            return False
-            
-        print(f"Executing...")
-        #print("=" * 70)
-        
-        # Execute the script using subprocess with real-time output
-        import subprocess
-        
-        # Run the script with Python, letting it inherit our stdout/stderr
-        try:
-            # Use subprocess.run for direct output inheritance - no capturing/re-printing
-            result = subprocess.run([
-                sys.executable, str(script_path)
-            ], cwd=str(study_path))
-            
-            return_code = result.returncode
-            
-        except Exception as e:
-            print(f"Error during script execution: {e}")
-            return False
-        
-        success = return_code == 0
-        
-        if success:
-            print("=" * 70)
-            print("Script execution completed successfully")
-        else:
-            print("=" * 70)
-            print(f"Script execution failed with return code: {return_code}")
-            
-        return success
-        
-    except Exception as e:
-        print(f"Failed to execute script: {e}")
-        import traceback
-        traceback.print_exc()
-        return False
-
-
 def create_scripts(
     source: str = "", 
     folder: str = "", 

{masster-0.5.16.dist-info → masster-0.5.17.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: masster
-Version: 0.5.16
+Version: 0.5.17
 Summary: Mass spectrometry data analysis package
 Project-URL: homepage, https://github.com/zamboni-lab/masster
 Project-URL: repository, https://github.com/zamboni-lab/masster
@@ -681,7 +681,6 @@ Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
 Classifier: Topic :: Scientific/Engineering :: Chemistry
 Requires-Python: >=3.11
 Requires-Dist: alpharaw>=0.4.8
-Requires-Dist: altair>=5.5.0
 Requires-Dist: bokeh>=3.7.3
 Requires-Dist: cmap>=0.6.2
 Requires-Dist: datashader>=0.18.1
@@ -698,7 +697,6 @@ Requires-Dist: pandas>=2.2.0
 Requires-Dist: panel>=1.7.0
 Requires-Dist: polars>=1.0.0
 Requires-Dist: pyopenms>=3.3.0
-Requires-Dist: pyteomics>=4.7.0
 Requires-Dist: pythonnet>=3.0.0
 Requires-Dist: scikit-learn>=1.7.1
 Requires-Dist: scipy>=1.12.0

{masster-0.5.16.dist-info → masster-0.5.17.dist-info}/RECORD

@@ -1,5 +1,5 @@
 masster/__init__.py,sha256=B7zftzdElF2Wb5B7KvkD6TONnMIY-Jxeen3s49dgmzs,1029
-masster/_version.py,sha256=Z0zx-I3UF9xWeA_txpllDTdYf2r9yDzejZAvzbk4n1w,257
+masster/_version.py,sha256=KD2SEuC2rjv2RLni1gIwB7iF2uzGndbyPLJm7M_E38U,257
 masster/chromatogram.py,sha256=iYpdv8C17zVnlWvOFgAn9ns2uFGiF-GgoYf5QVVAbHs,19319
 masster/logger.py,sha256=XT2gUcUIct8LWzTp9n484g5MaB89toT76CGA41oBvfA,18375
 masster/spectrum.py,sha256=TWIgDcl0lveG40cLVZTWGp8-FxMolu-P8EjZyRBtXL4,49850
@@ -67,9 +67,9 @@ masster/study/defaults/study_def.py,sha256=h8dYbi9xv0sesCSQik49Z53IkskMmNtW6ixl7
 masster/wizard/README.md,sha256=mL1A3YWJZOefpJ6D0-HqGLkVRmUlOpwyVFdvJBeeoZM,14149
 masster/wizard/__init__.py,sha256=L9G_datyGSFJjrBVklEVpZVLGXzUhDiWobtiygBH8vQ,669
 masster/wizard/example.py,sha256=xEZFTH9UZ8HKOm6s3JL8Js0Uw5ChnISWBHSZCL32vsM,7983
-masster/wizard/wizard.py,sha256=s3EXEGPI6pKQGgQrhth7sFnF8v_wuivZ8yawnFtjzao,62429
-masster-0.5.16.dist-info/METADATA,sha256=Xn5TySvmG0d9h0nJVYi7r8H0ZzzIBzR_pwydPdTo3aM,45191
-masster-0.5.16.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-masster-0.5.16.dist-info/entry_points.txt,sha256=ZHguQ_vPmdbpqq2uGtmEOLJfgP-DQ1T0c07Lxh30wc8,58
-masster-0.5.16.dist-info/licenses/LICENSE,sha256=bx5iLIKjgAdYQ7sISn7DsfHRKkoCUm1154sJJKhgqnU,35184
-masster-0.5.16.dist-info/RECORD,,
+masster/wizard/wizard.py,sha256=_co4abB8lNNryfqwS3AZtw6TGxw6NLowRjLXTUzJA0o,62994
+masster-0.5.17.dist-info/METADATA,sha256=SnOZZo7h6E7XV_AIjomMkMYAwbibu23vZYyhQnRMEOM,45130
+masster-0.5.17.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+masster-0.5.17.dist-info/entry_points.txt,sha256=ZHguQ_vPmdbpqq2uGtmEOLJfgP-DQ1T0c07Lxh30wc8,58
+masster-0.5.17.dist-info/licenses/LICENSE,sha256=bx5iLIKjgAdYQ7sISn7DsfHRKkoCUm1154sJJKhgqnU,35184
+masster-0.5.17.dist-info/RECORD,,