spacr 0.4.12__py3-none-any.whl → 0.4.60__py3-none-any.whl

spacr/utils.py

@@ -78,7 +78,7 @@ def filepaths_to_database(img_paths, settings, source_folder, crop_mode):
 
     parts = png_df['file_name'].apply(lambda x: pd.Series(_map_wells_png(x, timelapse=settings['timelapse'])))
 
-    columns = ['plate', 'row_name', 'column_name', 'field']
+    columns = ['plateID', 'rowID', 'columnID', 'fieldID']
 
     if settings['timelapse']:
         columns = columns + ['time_id']
@@ -113,7 +113,7 @@ def activation_maps_to_database(img_paths, source_folder, settings):
     png_df = pd.DataFrame(img_paths, columns=['png_path'])
     png_df['file_name'] = png_df['png_path'].apply(lambda x: os.path.basename(x))
     parts = png_df['file_name'].apply(lambda x: pd.Series(_map_wells_png(x, timelapse=False)))
-    columns = ['plate', 'row_name', 'column_name', 'field', 'prcfo', 'object']
+    columns = ['plateID', 'rowID', 'columnID', 'fieldID', 'prcfo', 'object']
     png_df[columns] = parts
 
     dataset_name = os.path.splitext(os.path.basename(settings['dataset']))[0]
@@ -136,7 +136,7 @@ def activation_correlations_to_database(df, img_paths, source_folder, settings):
     png_df = pd.DataFrame(img_paths, columns=['png_path'])
     png_df['file_name'] = png_df['png_path'].apply(lambda x: os.path.basename(x))
     parts = png_df['file_name'].apply(lambda x: pd.Series(_map_wells_png(x, timelapse=False)))
-    columns = ['plate', 'row_name', 'column_name', 'field', 'prcfo', 'object']
+    columns = ['plateID', 'rowID', 'columnID', 'fieldID', 'prcfo', 'object']
     png_df[columns] = parts
 
     # Align both DataFrames by file_name
@@ -319,23 +319,30 @@ def load_settings(csv_file_path, show=False, setting_key='setting_key', setting_
 
     return result_dict
 
-
 def save_settings(settings, name='settings', show=False):
     
-    settings_df = pd.DataFrame(list(settings.items()), columns=['Key', 'Value'])
-    if show:
-        display(settings_df)
+    settings_2 = settings.copy()
     
-    if isinstance(settings['src'], list):
-        src = settings['src'][0]
-        #if os.path.exists(src):
-
+    if isinstance(settings_2['src'], list):
+        src = settings_2['src'][0]
         name = f"{name}_list"
     else:
-        src = settings['src']
+        src = settings_2['src']
+        
+    if 'test_mode' in settings_2.keys():
+        settings_2['test_mode'] = False
+        
+        if 'plot' in settings_2.keys():
+            settings_2['plot'] = False
+            
+    settings_df = pd.DataFrame(list(settings_2.items()), columns=['Key', 'Value'])
+    
+    if show:
+        display(settings_df)
 
     settings_csv = os.path.join(src,'settings',f'{name}.csv')
     os.makedirs(os.path.join(src,'settings'), exist_ok=True)
+    print(f"Saving settings to {settings_csv}")
     settings_df.to_csv(settings_csv, index=False)
 
 def print_progress(files_processed, files_to_process, n_jobs, time_ls=None, batch_size=None, operation_type=""):
@@ -550,7 +557,7 @@ def _get_cellpose_batch_size():
 def _extract_filename_metadata(filenames, src, regular_expression, metadata_type='cellvoyager', pick_slice=False, skip_mode='01'):
     
     images_by_key = defaultdict(list)
-    
+
     for filename in filenames:
         match = regular_expression.match(filename)
         if match:
@@ -593,7 +600,7 @@ def _extract_filename_metadata(filenames, src, regular_expression, metadata_type
             except IndexError:
                 print(f"Could not extract information from filename {filename} using provided regex")
         else:
-            print(f"Filename {filename} did not match provided regex")
+            print(f"Filename {filename} did not match provided regex: {regular_expression}")
             continue
         
     return images_by_key
@@ -635,11 +642,11 @@ def _update_database_with_merged_info(db_path, df, table='png_list', columns=['p
     if 'prcfo' not in df.columns:
         print(f'generating prcfo columns')
         try:
-            df['prcfo'] = df['plate'].astype(str) + '_' + df['row_name'].astype(str) + '_' + df['column_name'].astype(str) + '_' + df['field'].astype(str) + '_o' + df['object_label'].astype(int).astype(str)
+            df['prcfo'] = df['plateID'].astype(str) + '_' + df['rowID'].astype(str) + '_' + df['columnID'].astype(str) + '_' + df['fieldID'].astype(str) + '_o' + df['object_label'].astype(int).astype(str)
         except Exception as e:
             print('Merging on cell failed, trying with cell_id')
         try:
-            df['prcfo'] = df['plate'].astype(str) + '_' + df['row_name'].astype(str) + '_' + df['column_name'].astype(str) + '_' + df['field'].astype(str) + '_o' + df['cell_id'].astype(int).astype(str)
+            df['prcfo'] = df['plateID'].astype(str) + '_' + df['rowID'].astype(str) + '_' + df['columnID'].astype(str) + '_' + df['fieldID'].astype(str) + '_o' + df['cell_id'].astype(int).astype(str)
         except Exception as e:
             print(e)
         
@@ -731,7 +738,7 @@ def _map_values(row, values, locs):
     if locs:
         value_dict = {loc: value for value, loc_list in zip(values, locs) for loc in loc_list}
         # Determine if we're dealing with row or column based on first location identifier
-        type_ = 'row_name' if locs[0][0][0] == 'r' else 'column_name'
+        type_ = 'rowID' if locs[0][0][0] == 'r' else 'columnID'
         return value_dict.get(row[type_], None)
     return values[0] if values else None
 
@@ -916,21 +923,21 @@ def _merge_and_save_to_database(morph_df, intensity_df, table_type, source_folde
             merged_df['file_name'] = file_name
             merged_df['path_name'] = os.path.join(source_folder, file_name + '.npy')
             if timelapse:
-                merged_df[['plate', 'row_name', 'column_name', 'field', 'timeid', 'prcf']] = merged_df['file_name'].apply(lambda x: pd.Series(_map_wells(x, timelapse)))
+                merged_df[['plateID', 'rowID', 'columnID', 'fieldID', 'timeid', 'prcf']] = merged_df['file_name'].apply(lambda x: pd.Series(_map_wells(x, timelapse)))
             else:
-                merged_df[['plate', 'row_name', 'column_name', 'field', 'prcf']] = merged_df['file_name'].apply(lambda x: pd.Series(_map_wells(x, timelapse)))
+                merged_df[['plateID', 'rowID', 'columnID', 'fieldID', 'prcf']] = merged_df['file_name'].apply(lambda x: pd.Series(_map_wells(x, timelapse)))
             cols = merged_df.columns.tolist()  # get the list of all columns
             if table_type == 'cell' or table_type == 'cytoplasm':
-                column_list = ['object_label', 'plate', 'row_name', 'column_name', 'field', 'prcf', 'file_name', 'path_name']
+                column_list = ['object_label', 'plateID', 'rowID', 'columnID', 'fieldID', 'prcf', 'file_name', 'path_name']
             elif table_type == 'nucleus' or table_type == 'pathogen':
-                column_list = ['object_label', 'cell_id', 'plate', 'row_name', 'column_name', 'field', 'prcf', 'file_name', 'path_name']
+                column_list = ['object_label', 'cell_id', 'plateID', 'rowID', 'columnID', 'fieldID', 'prcf', 'file_name', 'path_name']
             else:
                 raise ValueError(f"Invalid table_type: {table_type}")
             # Check if all columns in column_list are in cols
             missing_columns = [col for col in column_list if col not in cols]
             if len(missing_columns) == 1 and missing_columns[0] == 'cell_id':
                 missing_columns = False
-                column_list = ['object_label', 'plate', 'row_name', 'column_name', 'field', 'prcf', 'file_name', 'path_name']
+                column_list = ['object_label', 'plateID', 'rowID', 'columnID', 'fieldID', 'prcf', 'file_name', 'path_name']
             if missing_columns:
                 raise ValueError(f"Columns missing in DataFrame: {missing_columns}")
             for i, col in enumerate(column_list):
@@ -1144,42 +1151,22 @@ def _masks_to_masks_stack(masks):
     for idx, mask in enumerate(masks):
         mask_stack.append(mask)
     return mask_stack
-    
+
 def _get_diam(mag, obj):
 
-    if mag == 20:
-        if obj == 'cell':
-            diamiter = 120
-        elif obj == 'nucleus':
-            diamiter = 60
-        elif obj == 'pathogen':
-            diamiter = 20
-        else:
-            raise ValueError("Invalid magnification: Use 20, 40 or 60")
-
-    elif mag == 40:
-        if obj == 'cell':
-            diamiter = 160
-        elif obj == 'nucleus':
-            diamiter = 80
-        elif obj == 'pathogen':
-            diamiter = 40
-        else:
-            raise ValueError("Invalid magnification: Use 20, 40 or 60")
-
-    elif mag == 60:
-        if obj == 'cell':
-            diamiter = 200
-        if obj == 'nucleus':
-            diamiter = 90
-        if obj == 'pathogen':
-            diamiter = 60
-        else:
-            raise ValueError("Invalid magnification: Use 20, 40 or 60")
-    else:
-        raise ValueError("Invalid magnification: Use 20, 40 or 60")
-    
-    return diamiter
+    if obj == 'cell':
+        diamiter = 2 * mag + 80
+        
+    if obj == 'cell_large':
+        diamiter = 2 * mag + 120
+                                
+    if obj == 'nucleus':
+        diamiter = 0.75 * mag + 45
+                                
+    if obj == 'pathogen':
+        diamiter = mag
+                                
+    return int(diamiter)
 
 def _get_object_settings(object_type, settings):
     object_settings = {}
@@ -1323,30 +1310,35 @@ def annotate_conditions(df, cells=None, cell_loc=None, pathogens=None, pathogen_
     """
     
     def _get_type(val):
-        """Determine if a value maps to 'row_name' or 'column_name'."""
+        """Determine if a value maps to 'rowID' or 'columnID'."""
         if isinstance(val, str) and val.startswith('c'):
-            return 'column_name'
+            return 'columnID'
         elif isinstance(val, str) and val.startswith('r'):
-            return 'row_name'
+            return 'rowID'
         return None
 
     def _map_or_default(column_name, values, loc, df):
         """
         Consolidates the logic for mapping values or assigning defaults when loc is None.
-
+    
         Args:
             column_name (str): The column in the DataFrame to annotate.
             values (list/str): The list of values or a single string to annotate.
             loc (list of lists): Location mapping for the values, or None if not used.
             df (pandas.DataFrame): The DataFrame to modify.
         """
-        if isinstance(values, str) or (isinstance(values, list) and loc is None):
-            # Assign all rows the first value in the list or the single string
-            df[column_name] = values if isinstance(values, str) else values[0]
+        if isinstance(values, str) and loc is None:
+            # If a single string is provided and loc is None, assign the value to all rows
+            df[column_name] = values  
+    
+        elif isinstance(values, list) and loc is None:
+            # If a list of values is provided but no loc, assign the first value to all rows
+            df[column_name] = values[0]
+    
         elif values is not None and loc is not None:
-            # Perform the location-based mapping
+            # Perform location-based mapping
             value_dict = {val: key for key, loc_list in zip(values, loc) for val in loc_list}
-            df[column_name] = np.nan
+            df[column_name] = np.nan  # Start with NaN
             for val, key in value_dict.items():
                 loc_type = _get_type(val)
                 if loc_type:
@@ -1390,7 +1382,7 @@ def _split_data(df, group_by, object_type):
     # Ensure 'prcf' column exists by concatenating specific columns
     if 'prcf' not in df.columns:
         try:
-            df['prcf'] = df['plate'].astype(str) + '_' + df['row_name'].astype(str) + '_' + df['column_name'].astype(str) + '_' + df['field'].astype(str)
+            df['prcf'] = df['plateID'].astype(str) + '_' + df['rowID'].astype(str) + '_' + df['columnID'].astype(str) + '_' + df['fieldID'].astype(str)
         except Exception as e:
             print(e)    
     
@@ -1487,7 +1479,7 @@ def _group_by_well(df):
     non_numeric_cols = df.select_dtypes(include=['object']).columns
 
     # Apply mean function to numeric columns and first to non-numeric
-    df_grouped = df.groupby(['plate', 'row_name', 'column_name']).agg({**{col: np.mean for col in numeric_cols}, **{col: 'first' for col in non_numeric_cols}})
+    df_grouped = df.groupby(['plateID', 'rowID', 'columnID']).agg({**{col: np.mean for col in numeric_cols}, **{col: 'first' for col in non_numeric_cols}})
     return df_grouped
 
 ###################################################
@@ -2166,11 +2158,11 @@ def augment_classes(dst, nc, pc, generate=True,move=True):
 def annotate_predictions(csv_loc):
     df = pd.read_csv(csv_loc)
     df['filename'] = df['path'].apply(lambda x: x.split('/')[-1])
-    df[['plate', 'well', 'field', 'object']] = df['filename'].str.split('_', expand=True)
+    df[['plateID', 'well', 'fieldID', 'object']] = df['filename'].str.split('_', expand=True)
     df['object'] = df['object'].str.replace('.png', '')
     
     def assign_condition(row):
-        plate = int(row['plate'])
+        plate = int(row['plateID'])
         col = int(row['well'][1:])
         
         if col > 3:
@@ -2321,7 +2313,7 @@ def check_multicollinearity(x):
 
 def lasso_reg(merged_df, alpha_value=0.01, reg_type='lasso'):
     # Separate predictors and response
-    X = merged_df[['gene', 'grna', 'plate', 'row_name', 'column']]
+    X = merged_df[['gene', 'grna', 'plateID', 'rowID', 'columnID']]
     y = merged_df['pred']
 
     # One-hot encode the categorical predictors
@@ -3099,12 +3091,8 @@ def _get_regex(metadata_type, img_format, custom_regex=None):
         regex = f'(?P<plateID>.*)_(?P<wellID>.*)_T(?P<timeID>.*)F(?P<fieldID>.*)L(?P<laserID>..)A(?P<AID>..)Z(?P<sliceID>.*)C(?P<chanID>.*){img_format}'
     elif metadata_type == 'cq1':
         regex = f'W(?P<wellID>.*)F(?P<fieldID>.*)T(?P<timeID>.*)Z(?P<sliceID>.*)C(?P<chanID>.*){img_format}'
-    elif metadata_type == 'nikon':
-        regex = f'(?P<plateID>.*)_(?P<wellID>.*)_T(?P<timeID>.*)F(?P<fieldID>.*)L(?P<laserID>..)A(?P<AID>..)Z(?P<sliceID>.*)C(?P<chanID>.*){img_format}'
-    elif metadata_type == 'zeis':
-        regex = f'(?P<plateID>.*)_(?P<wellID>.*)_T(?P<timeID>.*)F(?P<fieldID>.*)L(?P<laserID>..)A(?P<AID>..)Z(?P<sliceID>.*)C(?P<chanID>.*){img_format}'
-    elif metadata_type == 'leica':
-        regex = f'(?P<plateID>.*)_(?P<wellID>.*)_T(?P<timeID>.*)F(?P<fieldID>.*)L(?P<laserID>..)A(?P<AID>..)Z(?P<sliceID>.*)C(?P<chanID>.*){img_format}'
+    elif metadata_type == 'auto':
+        regex = f'(?P<plateID>.*)_(?P<wellID>.*)_T(?P<timeID>.*)F(?P<fieldID>.*)L(?P<laserID>.*)C(?P<chanID>.*).tif'     
     elif metadata_type == 'custom':
         regex = f'({custom_regex}){img_format}'
         
@@ -3122,7 +3110,7 @@ def _run_test_mode(src, regex, timelapse=False, test_images=10, random_test=True
 
     if os.path.exists(os.path.join(src, 'orig')):
         src = os.path.join(src, 'orig')
-    
+        
     all_filenames = [filename for filename in os.listdir(src) if regular_expression.match(filename)]
     print(f'Found {len(all_filenames)} files')
     images_by_set = defaultdict(list)
@@ -3164,7 +3152,6 @@ def _choose_model(model_name, device, object_type='cell', restore_type=None, obj
             model_path = os.path.join(current_dir, 'models', 'cp', 'toxo_pv_lumen.CP_model')
             print(model_path)
             model = cp_models.CellposeModel(gpu=torch.cuda.is_available(), model_type=None, pretrained_model=model_path, diam_mean=diameter, device=device)
-            #model = cp_models.Cellpose(gpu=torch.cuda.is_available(), model_type='cyto', device=device)
             print(f'Using Toxoplasma PV lumen model to generate pathogen masks')
             return model
     
@@ -4693,12 +4680,12 @@ def process_vision_results(df, threshold=0.5):
     # Split the 'path' column using _map_wells function
     mapped_values = df['path'].apply(lambda x: _map_wells(x))
     
-    df['plate'] = mapped_values.apply(lambda x: x[0])
-    df['row_name'] = mapped_values.apply(lambda x: x[1])
-    df['column'] = mapped_values.apply(lambda x: x[2])
-    df['field'] = mapped_values.apply(lambda x: x[3])
+    df['plateID'] = mapped_values.apply(lambda x: x[0])
+    df['rowID'] = mapped_values.apply(lambda x: x[1])
+    df['columnID'] = mapped_values.apply(lambda x: x[2])
+    df['fieldID'] = mapped_values.apply(lambda x: x[3])
     df['object'] = df['path'].str.split('_').str[3].str.split('.').str[0]
-    df['prc'] = df['plate'].astype(str) + '_' + df['row_name'].astype(str) + '_' + df['column'].astype(str)
+    df['prc'] = df['plateID'].astype(str) + '_' + df['rowID'].astype(str) + '_' + df['columnID'].astype(str)
     df['cv_predictions'] = (df['pred'] >= threshold).astype(int)
 
     return df
@@ -4945,7 +4932,7 @@ def download_models(repo_id="einarolafsson/models", retries=5, delay=5):
     if not os.path.exists(local_dir):
         os.makedirs(local_dir)
     elif len(os.listdir(local_dir)) > 0:
-        print(f"Models already downloaded to: {local_dir}")
+        #print(f"Models already downloaded to: {local_dir}")
         return local_dir
 
     attempt = 0
@@ -5113,24 +5100,24 @@ def fill_holes_in_mask(mask):
 
 def correct_metadata_column_names(df):
     if 'plate_name' in df.columns:
-        df = df.rename(columns={'plate_name': 'plate'})
+        df = df.rename(columns={'plate_name': 'plateID'})
     if 'column_name' in df.columns:
-        df = df.rename(columns={'column_name': 'column'})
+        df = df.rename(columns={'column_name': 'columnID'})
     if 'col' in df.columns:
-        df = df.rename(columns={'col': 'column'})
+        df = df.rename(columns={'col': 'columnID'})
     if 'row_name' in df.columns:
-        df = df.rename(columns={'row_name': 'row_name'})
+        df = df.rename(columns={'row_name': 'rowID'})
     if 'grna_name' in df.columns:
         df = df.rename(columns={'grna_name': 'grna'})
     if 'plate_row' in df.columns:
-        df[['plate', 'row_name']] = df['plate_row'].str.split('_', expand=True)
+        df[['plateID', 'rowID']] = df['plate_row'].str.split('_', expand=True)
     return df
 
-def control_filelist(folder, mode='column', values=['01','02']):
+def control_filelist(folder, mode='columnID', values=['01','02']):
     files = os.listdir(folder)
-    if mode is 'column':
+    if mode is 'columnID':
         filtered_files = [file for file in files if file.split('_')[1][1:] in values]
-    if mode is 'row_name':
+    if mode is 'rowID':
         filtered_files = [file for file in files if file.split('_')[1][:1] in values]
     return filtered_files
     
@@ -5148,12 +5135,12 @@ def rename_columns_in_db(db_path):
             columns_info = cursor.fetchall()
             column_names = [col[1] for col in columns_info]
 
-            # Check if columns 'row' or 'col' exist
+            # Check if columns 'rowID' or 'columnID' exist
             columns_to_rename = {}
             if 'row' in column_names:
-                columns_to_rename['row'] = 'row_name'
+                columns_to_rename['row'] = 'rowID'
             if 'col' in column_names:
-                columns_to_rename['col'] = 'column_name'
+                columns_to_rename['col'] = 'columnID'
             
             # Rename columns if necessary
             if columns_to_rename:
@@ -5337,3 +5324,170 @@ def calculate_shortest_distance(df, object1, object2):
     df[f'{object1}_{object2}_shortest_distance'] = np.maximum(shortest_distance, 0)
 
     return df
+
+def format_path_for_system(path):
+    """
+    Takes a file path and reformats it to be compatible with the current operating system.
+    
+    Args:
+        path (str): The file path to be formatted.
+
+    Returns:
+        str: The formatted path for the current operating system.
+    """
+    system = platform.system()
+    
+    # Convert Windows-style paths to Unix-style (Linux/macOS)
+    if system in ["Linux", "Darwin"]:  # Darwin is macOS
+        formatted_path = path.replace("\\", "/")
+    
+    # Convert Unix-style paths to Windows-style
+    elif system == "Windows":
+        formatted_path = path.replace("/", "\\")
+    
+    else:
+        raise ValueError(f"Unsupported OS: {system}")
+    
+    # Normalize path to ensure consistency
+    new_path = os.path.normpath(formatted_path)
+    if os.path.exists(new_path):
+        print(f"Found path: {new_path}")
+    else:
+        print(f"Path not found: {new_path}")
+        
+    return new_path
+
+
+def normalize_src_path(src):
+    """
+    Ensures that the 'src' value is properly formatted as either a list of strings or a single string.
+
+    Args:
+        src (str or list): The input source path(s).
+
+    Returns:
+        list or str: A correctly formatted list if the input was a list (or string representation of a list),
+                     otherwise a single string.
+    """
+    if isinstance(src, list):
+        return src  # Already a list, return as-is
+
+    if isinstance(src, str):
+        try:
+            # Check if it is a string representation of a list
+            evaluated_src = ast.literal_eval(src)
+            if isinstance(evaluated_src, list) and all(isinstance(item, str) for item in evaluated_src):
+                return evaluated_src  # Convert to real list
+        except (SyntaxError, ValueError):
+            pass  # Not a valid list, treat as a string
+
+        return src  # Return as a string if not a list
+
+    raise ValueError(f"Invalid type for 'src': {type(src).__name__}, expected str or list")
+
+def generate_image_path_map(root_folder, valid_extensions=("tif", "tiff", "png", "jpg", "jpeg", "bmp", "czi", "nd2", "lif")):
+    """
+    Recursively scans a folder and its subfolders for images, then creates a mapping of:
+    {original_image_path: new_image_path}, where the new path includes all subfolder names.
+
+    Args:
+        root_folder (str): The root directory to scan for images.
+        valid_extensions (tuple): Tuple of valid image file extensions.
+
+    Returns:
+        dict: A dictionary mapping original image paths to their new paths.
+    """
+    image_path_map = {}
+
+    for dirpath, _, filenames in os.walk(root_folder):
+        for file in filenames:
+            ext = file.lower().split('.')[-1]
+            if ext in valid_extensions:
+                # Get relative path of the image from root_folder
+                relative_path = os.path.relpath(dirpath, root_folder)
+                
+                # Construct new filename: Embed folder hierarchy into the name
+                folder_parts = relative_path.split(os.sep)  # Get all folder names
+                folder_info = "_".join(folder_parts) if folder_parts else ""  # Join with underscores
+                
+                # Generate new filename
+                new_filename = f"{folder_info}_{file}" if folder_info else file
+
+                # Store in dictionary (original path -> new path)
+                original_path = os.path.join(dirpath, file)
+                new_path = os.path.join(root_folder, new_filename)
+                image_path_map[original_path] = new_path
+
+    return image_path_map
+
+def copy_images_to_consolidated(image_path_map, root_folder):
+    """
+    Copies images from their original locations to a 'consolidated' folder,
+    renaming them according to the generated dictionary.
+
+    Args:
+        image_path_map (dict): Dictionary mapping {original_path: new_path}.
+        root_folder (str): The root directory where the 'consolidated' folder will be created.
+    """
+    
+    consolidated_folder = os.path.join(root_folder, "consolidated")
+    os.makedirs(consolidated_folder, exist_ok=True)  # Ensure 'consolidated' folder exists
+    files_processed = 0
+    files_to_process = len(image_path_map)
+    time_ls= []
+    
+    for original_path, new_path in image_path_map.items():
+        
+        start = time.time()
+        new_filename = os.path.basename(new_path)  # Extract only the new filename
+        new_file_path = os.path.join(consolidated_folder, new_filename)  # Place in 'consolidated' folder
+        
+        shutil.copy2(original_path, new_file_path)  # Copy file with metadata preserved
+        
+        files_processed += 1
+        stop = time.time()
+        duration = (stop - start)
+        time_ls.append(duration)
+        
+        print_progress(files_processed, files_to_process, n_jobs=1, time_ls=time_ls, batch_size=None, operation_type=f'Consolidating images')
+        #print(f"Copied: {original_path} -> {new_file_path}")
+        
+def correct_metadata(df):
+    
+    #if 'object' in df.columns:
+    #    df['objectID'] = df['object']
+        
+    if 'object_name' in df.columns:
+        df['objectID'] = df['object_name']
+    
+    if 'field_name' in df.columns:
+        df['fieldID'] = df['field_name']
+    
+    if 'plate' in df.columns:
+        df['plateID'] = df['plate']
+    
+    if 'plate_name' in df.columns:
+        df['plateID'] = df['plate_name']
+    
+    if 'row' in df.columns:
+        df = df.rename(columns={'row': 'rowID'})
+        
+    if 'row_name' in df.columns:
+        df = df.rename(columns={'row_name': 'rowID'})
+        
+    if 'col' in df.columns:
+        df = df.rename(columns={'col': 'columnID'})
+        
+    if 'column' in df.columns:
+        df = df.rename(columns={'column': 'columnID'})
+        
+    if 'column_name' in df.columns:
+        df = df.rename(columns={'column_name': 'columnID'})
+        
+    if 'field' in df.columns:
+        df = df.rename(columns={'field': 'fieldID'})
+
+    if 'field_name' in df.columns:
+        df = df.rename(columns={'field_name': 'fieldID'})
+    
+    return df

{spacr-0.4.12.dist-info → spacr-0.4.60.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: spacr
-Version: 0.4.12
+Version: 0.4.60
 Summary: Spatial phenotype analysis of crisp screens (SpaCr)
 Home-page: https://github.com/EinarOlafsson/spacr
 Author: Einar Birnir Olafsson
@@ -41,6 +41,7 @@ Requires-Dist: pillow<11.0,>=10.2.0
 Requires-Dist: tifffile>=2023.4.12
 Requires-Dist: nd2reader<4.0,>=3.3.0
 Requires-Dist: czifile
+Requires-Dist: readlif
 Requires-Dist: imageio<3.0,>=2.34.0
 Requires-Dist: pingouin<1.0,>=0.5.5
 Requires-Dist: umap-learn<1.0,>=0.5.6

{spacr-0.4.12.dist-info → spacr-0.4.60.dist-info}/RECORD

@@ -9,28 +9,28 @@ spacr/app_sequencing.py,sha256=DjG26jy4cpddnV8WOOAIiExtOe9MleVMY4MFa5uTo5w,157
 spacr/app_umap.py,sha256=ZWAmf_OsIKbYvolYuWPMYhdlVe-n2CADoJulAizMiEo,153
 spacr/cellpose.py,sha256=RBHMs2vwXcfkj0xqAULpALyzJYXddSRycgZSzmwI7v0,14755
 spacr/chat_bot.py,sha256=n3Fhqg3qofVXHmh3H9sUcmfYy9MmgRnr48663MVdY9E,1244
-spacr/core.py,sha256=lKeqmsVrGQ8cPU_WkoNGNBWrk-gtR1RkRkwDdnJ0u64,48829
-spacr/deep_spacr.py,sha256=WN64EaQqF87JZg3Uan46t5Y28xsAGD2KMjr2ht6CyDs,54563
+spacr/core.py,sha256=ghesCiRKxdHqnujztb9XiuhhZ-3gBs7aQIIzvqaf-iI,51409
+spacr/deep_spacr.py,sha256=055tIo3WP3elGFiIuSZaLURgu2XyUDxAdbw5ezASEqM,54526
 spacr/gui.py,sha256=ARyn9Q_g8HoP-cXh1nzMLVFCKqthY4v2u9yORyaQqQE,8230
-spacr/gui_core.py,sha256=U0A7waKgWq_Es9fMwcZbXUZYGzCqt2bgfY3HbxiFXnw,47466
-spacr/gui_elements.py,sha256=HmITDncklKwtdFhxLhtYXOwndsRfgwWIPVi83VlXHB4,146419
-spacr/gui_utils.py,sha256=0rDF23BUGcmjSJvfCiLoxhlGJdHkio1jTxyCzrMXr-g,41211
-spacr/io.py,sha256=oqJwDJWksVdWE0bRAwytTOsjlL0o-J9lr_pQaw2cQ4Y,138288
+spacr/gui_core.py,sha256=AYXZpdKMRezJfS7Xcfztdc2yco6lV21ovwkyKQGbIZg,56206
+spacr/gui_elements.py,sha256=5a3BOpctBPklsT1NungqS72h1Bg1FArUndE0OfvWD8Y,152646
+spacr/gui_utils.py,sha256=dWVPFwDj793Z3ERG4mMC0hI0MKkOrvXJpUYlcjpCBsU,41357
+spacr/io.py,sha256=eZj5RCqje3xb_4BwPC0ASBqI-c7_6EeQYv8zrQf0tCc,159371
 spacr/logger.py,sha256=lJhTqt-_wfAunCPl93xE65Wr9Y1oIHJWaZMjunHUeIw,1538
-spacr/measure.py,sha256=jmOnLBudq3TuY723Cfo1EJBn67P6rlEvL6I-2FSkUgI,55315
+spacr/measure.py,sha256=Z3u4BU5RzcY82IZuboQ0OsxuXaPVwOlH65Rw6FrL5z4,55045
 spacr/mediar.py,sha256=FwLvbLQW5LQzPgvJZG8Lw7GniA2vbZx6Jv6vIKu7I5c,14743
-spacr/ml.py,sha256=MrIAtUUxMOibWVL1SjCUnYlizawCp3l3SeY4Y9yEsPw,97251
+spacr/ml.py,sha256=XCRZeX7UkbMctQICIoskeWVx8CCmmCoHNauUOAkfFq0,91692
 spacr/openai.py,sha256=5vBZ3Jl2llYcW3oaTEXgdyCB2aJujMUIO5K038z7w_A,1246
-spacr/plot.py,sha256=Q5TbsR2NUWhA7z4HyF_2_FAEBFSNMU-G3UNDbRzW6mM,169485
-spacr/sequencing.py,sha256=ClUfwPPK6rNUbUuiEkzcwakzVyDKKUMv9ricrxT8qQY,25227
-spacr/settings.py,sha256=fEk-9LSSvV1wGsn6xTaJWY7wF7_u8Fc-S1DaDHqZU3I,83997
+spacr/plot.py,sha256=lmpIJozfxMyOyGAMno4j-C7NPjDYRMr29SDAnrV-bb4,170815
+spacr/sequencing.py,sha256=EY12RdW5QRKpHDRQCw1QoAlxCq8FK2v6WoVa5uuDBXQ,26745
+spacr/settings.py,sha256=j2H5OieJKwu-TITlfP5tAnUGUhBjng8ECy3jXm3JMb8,86599
 spacr/sim.py,sha256=1xKhXimNU3ukzIw-3l9cF3Znc_brW8h20yv8fSTzvss,71173
 spacr/sp_stats.py,sha256=mbhwsyIqt5upsSD346qGjdCw7CFBa0tIS7zHU9e0jNI,9536
 spacr/stats.py,sha256=mbhwsyIqt5upsSD346qGjdCw7CFBa0tIS7zHU9e0jNI,9536
-spacr/submodules.py,sha256=mb2g0igUTws7y6xW1zIJw1E7eQyxsjEj5mk2Z-Qd8uw,67629
-spacr/timelapse.py,sha256=KGfG4L4-QnFfgbF7L6C5wL_3gd_rqr05Foje6RsoTBg,39603
-spacr/toxo.py,sha256=TmuhejSIPLBvsgeblsUgSvBFCR1gOkApyTKidooJ5Us,26044
-spacr/utils.py,sha256=of2t5Tq_RKdJ1QRDo4nJ3oEVev_6s2Oko3-lBxl4ScU,226293
+spacr/submodules.py,sha256=dNiUqwDYwJ2J1s3DkwGLOTB-TzyGq_GXoojpCrLMm7A,82812
+spacr/timelapse.py,sha256=lh3Aev5S7Ou1YWPBYBYeSGU0I-NPb0-4znYfm2NYf_I,39629
+spacr/toxo.py,sha256=GoNfgyH-NJx3WOzNQPgzODir7Jp65fs7UM46XpzcrUo,26056
+spacr/utils.py,sha256=20FRbevoFmPA61vS50tR48g6DpGkIvInGPv9nE810gQ,231668
 spacr/version.py,sha256=axH5tnGwtgSnJHb5IDhiu4Zjk5GhLyAEDRe-rnaoFOA,409
 spacr/resources/MEDIAR/.gitignore,sha256=Ff1q9Nme14JUd-4Q3jZ65aeQ5X4uttptssVDgBVHYo8,152
 spacr/resources/MEDIAR/LICENSE,sha256=yEj_TRDLUfDpHDNM0StALXIt6mLqSgaV2hcCwa6_TcY,1065
@@ -153,9 +153,9 @@ spacr/resources/icons/umap.png,sha256=dOLF3DeLYy9k0nkUybiZMe1wzHQwLJFRmgccppw-8b
 spacr/resources/images/plate1_E01_T0001F001L01A01Z01C02.tif,sha256=Tl0ZUfZ_AYAbu0up_nO0tPRtF1BxXhWQ3T3pURBCCRo,7958528
 spacr/resources/images/plate1_E01_T0001F001L01A02Z01C01.tif,sha256=m8N-V71rA1TT4dFlENNg8s0Q0YEXXs8slIn7yObmZJQ,7958528
 spacr/resources/images/plate1_E01_T0001F001L01A03Z01C03.tif,sha256=Pbhk7xn-KUP6RSIhJsxQcrHFImBm3GEpLkzx7WOc-5M,7958528
-spacr-0.4.12.dist-info/LICENSE,sha256=SR-2MeGc6SCM1UORJYyarSWY_A-JaOMFDj7ReSs9tRM,1083
-spacr-0.4.12.dist-info/METADATA,sha256=mSEI7oQQ8wHvVWQwzELtk2bpV_Bil3OhhteOJ3SoY68,6073
-spacr-0.4.12.dist-info/WHEEL,sha256=HiCZjzuy6Dw0hdX5R3LCFPDmFS4BWl8H-8W39XfmgX4,91
-spacr-0.4.12.dist-info/entry_points.txt,sha256=BMC0ql9aNNpv8lUZ8sgDLQMsqaVnX5L535gEhKUP5ho,296
-spacr-0.4.12.dist-info/top_level.txt,sha256=GJPU8FgwRXGzKeut6JopsSRY2R8T3i9lDgya42tLInY,6
-spacr-0.4.12.dist-info/RECORD,,
+spacr-0.4.60.dist-info/LICENSE,sha256=SR-2MeGc6SCM1UORJYyarSWY_A-JaOMFDj7ReSs9tRM,1083
+spacr-0.4.60.dist-info/METADATA,sha256=Na4GGSJEuobmjgAo8HSbejQ0h8E1etVHb249v5oBB6Y,6096
+spacr-0.4.60.dist-info/WHEEL,sha256=HiCZjzuy6Dw0hdX5R3LCFPDmFS4BWl8H-8W39XfmgX4,91
+spacr-0.4.60.dist-info/entry_points.txt,sha256=BMC0ql9aNNpv8lUZ8sgDLQMsqaVnX5L535gEhKUP5ho,296
+spacr-0.4.60.dist-info/top_level.txt,sha256=GJPU8FgwRXGzKeut6JopsSRY2R8T3i9lDgya42tLInY,6
+spacr-0.4.60.dist-info/RECORD,,