spacr 0.3.61__py3-none-any.whl → 0.3.62__py3-none-any.whl

spacr/io.py

@@ -1777,7 +1777,7 @@ def _read_and_join_tables(db_path, table_names=['cell', 'cytoplasm', 'nucleus',
         png_list_df['cell_id'] = png_list_df['cell_id'].str[1:].astype(int)
         png_list_df.rename(columns={'cell_id': 'object_label'}, inplace=True)
         if 'cell' in dataframes:
-            join_cols = ['object_label', 'plate', 'row_name', 'column_name']
+            join_cols = ['object_label', 'plate', 'row_name', 'column_name','field']
             dataframes['cell'] = pd.merge(dataframes['cell'], png_list_df, on=join_cols, how='left')
         else:
             print("Cell table not found in database tables.")
@@ -2276,7 +2276,7 @@ def _read_db(db_loc, tables):
     conn.close() # Close the connection
     return dfs
     
-def _read_and_merge_data(locs, tables, verbose=False, nuclei_limit=False, pathogen_limit=False):
+def _read_and_merge_data_v1(locs, tables, verbose=False, nuclei_limit=False, pathogen_limit=False):
     
     from .utils import _split_data
     
@@ -2443,7 +2443,135 @@ def _read_and_merge_data(locs, tables, verbose=False, nuclei_limit=False, pathog
     if 'pathogen' in tables:
         obj_df_ls.append(pathogens)
         
-    return merged_df, obj_df_ls  
+    return merged_df, obj_df_ls 
+
+def _read_and_merge_data(locs, tables, verbose=False, nuclei_limit=10, pathogen_limit=10):
+    from .io import _read_db
+    from .utils import _split_data
+
+    # Initialize an empty dictionary to store DataFrames by table name
+    data_dict = {table: [] for table in tables}
+
+    # Extract plate DataFrames
+    for loc in locs:
+        db_dfs = _read_db(loc, tables)
+        for table, df in zip(tables, db_dfs):
+            data_dict[table].append(df)
+
+    # Concatenate rows across locations for each table
+    for table, dfs in data_dict.items():
+        if dfs:
+            data_dict[table] = pd.concat(dfs, axis=0)
+        if verbose:
+            print(f"{table}: {len(data_dict[table])}")
+
+    # Initialize merged DataFrame with 'cells' if available
+    merged_df = pd.DataFrame()
+
+    # Process each table
+    if 'cell' in data_dict:
+        cells = data_dict['cell'].copy()
+        cells = cells.assign(object_label=lambda x: 'o' + x['object_label'].astype(int).astype(str))
+        cells = cells.assign(prcfo=lambda x: x['prcf'] + '_' + x['object_label'])
+        cells_g_df, metadata = _split_data(cells, 'prcfo', 'object_label')
+        merged_df = cells_g_df.copy()
+        if verbose:
+            print(f'cells: {len(cells)}, cells grouped: {len(cells_g_df)}')
+
+    if 'cytoplasm' in data_dict:
+        cytoplasms = data_dict['cytoplasm'].copy()
+        cytoplasms = cytoplasms.assign(object_label=lambda x: 'o' + x['object_label'].astype(int).astype(str))
+        cytoplasms = cytoplasms.assign(prcfo=lambda x: x['prcf'] + '_' + x['object_label'])
+        
+        if not 'cell' in data_dict:
+            merged_df, metadata = _split_data(cytoplasms, 'prcfo', 'object_label')
+            
+            if verbose:
+                print(f'nucleus: {len(cytoplasms)}, cytoplasms grouped: {len(merged_df)}')
+            
+        else:
+            cytoplasms_g_df, _ = _split_data(cytoplasms, 'prcfo', 'object_label')
+            merged_df = merged_df.merge(cytoplasms_g_df, left_index=True, right_index=True)
+            
+            if verbose:
+                print(f'cytoplasms: {len(cytoplasms)}, cytoplasms grouped: {len(cytoplasms_g_df)}')
+
+    if 'nucleus' in data_dict:
+        nucleus = data_dict['nucleus'].copy()
+        nucleus = nucleus.dropna(subset=['cell_id'])
+        nucleus = nucleus.assign(object_label=lambda x: 'o' + x['object_label'].astype(int).astype(str))
+        nucleus = nucleus.assign(cell_id=lambda x: 'o' + x['cell_id'].astype(int).astype(str))
+        nucleus = nucleus.assign(prcfo=lambda x: x['prcf'] + '_' + x['cell_id'])
+        nucleus['nucleus_prcfo_count'] = nucleus.groupby('prcfo')['prcfo'].transform('count')
+        if not nuclei_limit:
+            nucleus = nucleus[nucleus['nucleus_prcfo_count'] == 1]
+            
+        if all(key not in data_dict for key in ['cell', 'cytoplasm']):
+            merged_df, metadata = _split_data(nucleus, 'prcfo', 'cell_id')
+            
+            if verbose:
+                print(f'nucleus: {len(nucleus)}, nucleus grouped: {len(merged_df)}')
+            
+        else:
+            nucleus_g_df, _ = _split_data(nucleus, 'prcfo', 'cell_id')
+            merged_df = merged_df.merge(nucleus_g_df, left_index=True, right_index=True)
+            
+            if verbose:
+                print(f'nucleus: {len(nucleus)}, nucleus grouped: {len(nucleus_g_df)}')
+
+    if 'pathogen' in data_dict:
+        pathogens = data_dict['pathogen'].copy()
+        pathogens = pathogens.dropna(subset=['cell_id'])
+        pathogens = pathogens.assign(object_label=lambda x: 'o' + x['object_label'].astype(int).astype(str))
+        pathogens = pathogens.assign(cell_id=lambda x: 'o' + x['cell_id'].astype(int).astype(str))
+        pathogens = pathogens.assign(prcfo=lambda x: x['prcf'] + '_' + x['cell_id'])
+        pathogens['pathogen_prcfo_count'] = pathogens.groupby('prcfo')['prcfo'].transform('count')
+
+        if isinstance(pathogen_limit, bool) and not pathogen_limit:
+            pathogens = pathogens[pathogens['pathogen_prcfo_count'] <= 1]
+        elif isinstance(pathogen_limit, (float, int)):
+            pathogens = pathogens[pathogens['pathogen_prcfo_count'] <= int(pathogen_limit)]
+
+        if all(key not in data_dict for key in ['cell', 'cytoplasm', 'nucleus']):
+            merged_df, metadata = _split_data(pathogens, 'prcfo', 'cell_id')
+            
+            if verbose:
+                print(f'pathogens: {len(pathogens)}, pathogens grouped: {len(merged_df)}')
+            
+        else:
+            pathogens_g_df, _ = _split_data(pathogens, 'prcfo', 'cell_id')
+            merged_df = merged_df.merge(pathogens_g_df, left_index=True, right_index=True)
+        
+            if verbose:
+                print(f'pathogens: {len(pathogens)}, pathogens grouped: {len(pathogens_g_df)}')
+            
+    if 'png_list' in data_dict:
+        png_list = data_dict['png_list'].copy()
+        png_list_g_df_numeric, png_list_g_df_non_numeric = _split_data(png_list, 'prcfo', 'cell_id')
+        png_list_g_df_non_numeric.drop(columns=['plate','row_name','column_name','field','file_name','cell_id', 'prcf'], inplace=True)
+        if verbose:
+            print(f'png_list: {len(png_list)}, png_list grouped: {len(png_list_g_df_numeric)}')
+        merged_df = merged_df.merge(png_list_g_df_numeric, left_index=True, right_index=True)
+        merged_df = merged_df.merge(png_list_g_df_non_numeric, left_index=True, right_index=True)
+        
+    # Add prc (plate row column) and prcfo (plate row column field object) columns
+    metadata = metadata.assign(prc=lambda x: x['plate'] + '_' + x['row_name'] + '_' + x['column_name'])
+    cells_well = metadata.groupby('prc')['object_label'].nunique().reset_index(name='cells_per_well')
+    metadata = metadata.merge(cells_well, on='prc')
+    metadata = metadata.assign(prcfo=lambda x: x['plate'] + '_' + x['row_name'] + '_' + x['column_name'] + '_' + x['field'] + '_' + x['object_label'])
+    metadata.set_index('prcfo', inplace=True)
+    
+    # Merge metadata with final merged DataFrame
+    merged_df = metadata.merge(merged_df, left_index=True, right_index=True).dropna(axis=1)
+    merged_df.drop(columns=['label_list_morphology', 'label_list_intensity'], errors='ignore', inplace=True)
+    
+    if verbose:
+        print(f'Generated dataframe with: {len(merged_df.columns)} columns and {len(merged_df)} rows')
+    
+    # Prepare object DataFrames for output
+    obj_df_ls = [data_dict[table] for table in ['cell', 'cytoplasm', 'nucleus', 'pathogen'] if table in data_dict]
+    
+    return merged_df, obj_df_ls
     
 def _read_mask(mask_path):
     mask = imageio2.imread(mask_path)

spacr/utils.py

@@ -1371,7 +1371,7 @@ def annotate_conditions(df, cells=None, cell_loc=None, pathogens=None, pathogen_
 
     return df
 
-def _split_data(df, group_by, object_type):
+def _split_data_v1(df, group_by, object_type):
     """
     Splits the input dataframe into numeric and non-numeric parts, groups them by the specified column,
     and returns the grouped dataframes.
@@ -1385,16 +1385,72 @@ def _split_data(df, group_by, object_type):
     grouped_numeric (pandas.DataFrame): The grouped dataframe containing numeric columns.
     grouped_non_numeric (pandas.DataFrame): The grouped dataframe containing non-numeric 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)
+        except Exception as e:
+            print(e)    
+    
     df['prcfo'] = df['prcf'] + '_' + df[object_type]
     df = df.set_index(group_by, inplace=False)
 
     df_numeric = df.select_dtypes(include=np.number)
     df_non_numeric = df.select_dtypes(exclude=np.number)
+    
+    []
 
     grouped_numeric = df_numeric.groupby(df_numeric.index).mean()
     grouped_non_numeric = df_non_numeric.groupby(df_non_numeric.index).first()
 
     return pd.DataFrame(grouped_numeric), pd.DataFrame(grouped_non_numeric)
+
+def _split_data(df, group_by, object_type):
+    """
+    Splits the input dataframe into numeric and non-numeric parts, groups them by the specified column,
+    and returns the grouped dataframes with conditional aggregation.
+
+    Parameters:
+    df (pandas.DataFrame): The input dataframe.
+    group_by (str): The column name to group the dataframes by.
+    object_type (str): The column name to concatenate with 'prcf' to create a new column 'prcfo'.
+
+    Returns:
+    grouped_numeric (pandas.DataFrame): The grouped dataframe containing numeric columns with conditional aggregation.
+    grouped_non_numeric (pandas.DataFrame): The grouped dataframe containing non-numeric columns.
+    """
+    
+    # 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)
+        except Exception as e:
+            print(e)    
+    
+    # Create the 'prcfo' column
+    df['prcfo'] = df['prcf'] + '_' + df[object_type]
+    df = df.set_index(group_by, inplace=False)
+
+    # Split the DataFrame into numeric and non-numeric parts
+    df_numeric = df.select_dtypes(include=np.number)
+    df_non_numeric = df.select_dtypes(exclude=np.number)
+
+    # Define keywords for columns to be summed instead of averaged
+    sum_keywords = ['area', 'perimeter', 'convex_area', 'bbox_area', 'filled_area', 'major_axis_length', 'minor_axis_length', 'equivalent_diameter']
+
+    # Create a dictionary for custom aggregation
+    agg_dict = {}
+    for column in df_numeric.columns:
+        if any(keyword in column for keyword in sum_keywords):
+            agg_dict[column] = 'sum'
+        else:
+            agg_dict[column] = 'mean'
+
+    # Apply custom aggregation
+    grouped_numeric = df_numeric.groupby(df_numeric.index).agg(agg_dict)
+    grouped_non_numeric = df_non_numeric.groupby(df_non_numeric.index).first()
+
+    return pd.DataFrame(grouped_numeric), pd.DataFrame(grouped_non_numeric)
     
 def _calculate_recruitment(df, channel):
     """
@@ -5184,7 +5240,7 @@ def group_feature_class(df, feature_groups=['cell', 'cytoplasm', 'nucleus', 'pat
         else:
             return None
         
-    from spacr.plot import spacrGraph
+    from .plot import spacrGraph
 
     df[name] = df['feature'].apply(lambda x: find_feature_class(x, feature_groups))
     

{spacr-0.3.61.dist-info → spacr-0.3.62.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: spacr
-Version: 0.3.61
+Version: 0.3.62
 Summary: Spatial phenotype analysis of crisp screens (SpaCr)
 Home-page: https://github.com/EinarOlafsson/spacr
 Author: Einar Birnir Olafsson

{spacr-0.3.61.dist-info → spacr-0.3.62.dist-info}/RECORD

@@ -15,7 +15,7 @@ spacr/gui.py,sha256=ARyn9Q_g8HoP-cXh1nzMLVFCKqthY4v2u9yORyaQqQE,8230
 spacr/gui_core.py,sha256=N7R7yvfK_dJhOReM_kW3Ci8Bokhi1OzsxeKqvSGdvV4,41460
 spacr/gui_elements.py,sha256=EKlvEg_4_je7jciEdR3NTgPrcTraowa2e2RUt-xqd6M,138254
 spacr/gui_utils.py,sha256=u9RoIOWpAXFEOnUlLpMQZrc1pWSg6omZsJMIhJdRv_g,41211
-spacr/io.py,sha256=p-ky3yjtoSSvdsktPXVy_dx8dHgMeWqUZOtOwwfrk2o,136108
+spacr/io.py,sha256=0cBVmhqMaPkdEXib5Vhp19FC_1qfaK_NgtoImuDuwGU,142664
 spacr/logger.py,sha256=lJhTqt-_wfAunCPl93xE65Wr9Y1oIHJWaZMjunHUeIw,1538
 spacr/measure.py,sha256=2lK-ZcTxLM-MpXV1oZnucRD9iz5aprwahRKw9IEqshg,55085
 spacr/mediar.py,sha256=FwLvbLQW5LQzPgvJZG8Lw7GniA2vbZx6Jv6vIKu7I5c,14743
@@ -28,7 +28,7 @@ spacr/sim.py,sha256=1xKhXimNU3ukzIw-3l9cF3Znc_brW8h20yv8fSTzvss,71173
 spacr/submodules.py,sha256=Xq4gjvooHN8S7cTk5PIAkd7XD2c7CMVqNpeo8GCvtHc,42489
 spacr/timelapse.py,sha256=KGfG4L4-QnFfgbF7L6C5wL_3gd_rqr05Foje6RsoTBg,39603
 spacr/toxo.py,sha256=z2nT5aAze3NUIlwnBQcnkARihDwoPfqOgQIVoUluyK0,25087
-spacr/utils.py,sha256=tqIKiSc30xEX0IlfSpoctFJQDVnGHDAX7l1VakRCBuY,220601
+spacr/utils.py,sha256=vvciLh1gH0nsrCWQw3taUcDjxP59wme3gqrejeNO05w,222943
 spacr/version.py,sha256=axH5tnGwtgSnJHb5IDhiu4Zjk5GhLyAEDRe-rnaoFOA,409
 spacr/resources/MEDIAR/.gitignore,sha256=Ff1q9Nme14JUd-4Q3jZ65aeQ5X4uttptssVDgBVHYo8,152
 spacr/resources/MEDIAR/LICENSE,sha256=yEj_TRDLUfDpHDNM0StALXIt6mLqSgaV2hcCwa6_TcY,1065
@@ -151,9 +151,9 @@ 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-0.3.61.dist-info/LICENSE,sha256=SR-2MeGc6SCM1UORJYyarSWY_A-JaOMFDj7ReSs9tRM,1083
-spacr-0.3.61.dist-info/METADATA,sha256=2jlzT9lkaXx01IWlYMYrpf24p48qDHvrRLZm-YUUl-0,6032
-spacr-0.3.61.dist-info/WHEEL,sha256=HiCZjzuy6Dw0hdX5R3LCFPDmFS4BWl8H-8W39XfmgX4,91
-spacr-0.3.61.dist-info/entry_points.txt,sha256=BMC0ql9aNNpv8lUZ8sgDLQMsqaVnX5L535gEhKUP5ho,296
-spacr-0.3.61.dist-info/top_level.txt,sha256=GJPU8FgwRXGzKeut6JopsSRY2R8T3i9lDgya42tLInY,6
-spacr-0.3.61.dist-info/RECORD,,
+spacr-0.3.62.dist-info/LICENSE,sha256=SR-2MeGc6SCM1UORJYyarSWY_A-JaOMFDj7ReSs9tRM,1083
+spacr-0.3.62.dist-info/METADATA,sha256=Ox14lWGxbXuMW36MriYHppKcZDqD_4HopfbcLAi8dLc,6032
+spacr-0.3.62.dist-info/WHEEL,sha256=HiCZjzuy6Dw0hdX5R3LCFPDmFS4BWl8H-8W39XfmgX4,91
+spacr-0.3.62.dist-info/entry_points.txt,sha256=BMC0ql9aNNpv8lUZ8sgDLQMsqaVnX5L535gEhKUP5ho,296
+spacr-0.3.62.dist-info/top_level.txt,sha256=GJPU8FgwRXGzKeut6JopsSRY2R8T3i9lDgya42tLInY,6
+spacr-0.3.62.dist-info/RECORD,,