spacr 0.3.80__py3-none-any.whl → 0.4.0__py3-none-any.whl

spacr/utils.py

@@ -1372,40 +1372,6 @@ def annotate_conditions(df, cells=None, cell_loc=None, pathogens=None, pathogen_
 
     return df
 
-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.
-
-    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.
-    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,
@@ -5045,19 +5011,22 @@ def generate_cytoplasm_mask(nucleus_mask, cell_mask):
     return cytoplasm_mask
 
 def add_column_to_database(settings):
-    """
-    Adds a new column to the database table by matching on a common column from the DataFrame.
-    If the column already exists in the database, it adds the column with a suffix.
-    NaN values will remain as NULL in the database.
-    
-    Parameters:
-    - settings: A dictionary containing the following keys:
-        - 'csv_path': Path to the CSV file with the data to be added.
-        - 'db_path': Path to the SQLite database (or connection string for other databases).
-        - 'table_name': The name of the table in the database.
-        - 'update_column': The name of the new column in the DataFrame to add to the database.
-        - 'match_column': The common column used to match rows.
-    """
+    #"""
+    #Adds a new column to the database table by matching on a common column from the DataFrame.
+    #If the column already exists in the database, it adds the column with a suffix.
+    #NaN values will remain as NULL in the database.
+
+    #Parameters:
+    #    settings (dict): A dictionary containing the following keys:
+    #    csv_path (str): Path to the CSV file with the data to be added.
+    #    db_path (str): Path to the SQLite database (or connection string for other databases).
+    #    table_name (str): The name of the table in the database.
+    #    update_column (str): The name of the new column in the DataFrame to add to the database.
+    #    match_column (str): The common column used to match rows.
+
+    #Returns:
+    #    None
+    #"""
 
     # Read the DataFrame from the provided CSV path
     df = pd.read_csv(settings['csv_path'])
@@ -5147,8 +5116,8 @@ def correct_metadata_column_names(df):
         df = df.rename(columns={'plate_name': 'plate'})
     if 'column_name' in df.columns:
         df = df.rename(columns={'column_name': 'column'})
-    if 'column_name' in df.columns:
-        df = df.rename(columns={'column_name': 'column'})
+    if 'col' in df.columns:
+        df = df.rename(columns={'col': 'column'})
     if 'row_name' in df.columns:
         df = df.rename(columns={'row_name': 'row_name'})
     if 'grna_name' in df.columns:
@@ -5242,3 +5211,129 @@ def group_feature_class(df, feature_groups=['cell', 'cytoplasm', 'nucleus', 'pat
         , ignore_index=True)
     
     return df
+
+def delete_intermedeate_files(settings):
+    
+    path_orig = os.path.join(settings['src'], 'orig')
+    path_stack = os.path.join(settings['src'], 'stack')
+    merged_stack = os.path.join(settings['src'], 'merged')
+    path_norm_chan_stack = os.path.join(settings['src'], 'norm_channel_stack')
+    path_1 = os.path.join(settings['src'], '1')
+    path_2 = os.path.join(settings['src'], '2')
+    path_3 = os.path.join(settings['src'], '3')
+    path_4 = os.path.join(settings['src'], '4')
+    path_5 = os.path.join(settings['src'], '5')
+    path_6 = os.path.join(settings['src'], '6')
+    path_7 = os.path.join(settings['src'], '7')
+    path_8 = os.path.join(settings['src'], '8')
+    path_9 = os.path.join(settings['src'], '9')
+    path_10 = os.path.join(settings['src'], '10')
+    
+    paths = [path_stack, path_norm_chan_stack, path_1, path_2, path_3, path_4, path_5, path_6, path_7, path_8, path_9, path_10]
+    
+    merged_len = len(merged_stack)
+    stack_len = len(path_stack)
+    
+    if merged_len == stack_len and stack_len != 0:
+        if 'src' in settings:
+            if os.path.exists(settings['src']):
+                if os.path.exists(path_orig):
+                    for path in paths:
+                        if os.path.exists(path):
+                            try:
+                                shutil.rmtree(path)
+                                print(f"Deleted {path}")
+                            except OSError as e:
+                                print(f"{path} could not be deleted: {e}. Delete manually.")
+                else:
+                    print(f"{path_orig} does not exist.")
+            else:
+                print(f"{settings['src']} does not exist.")
+        else:
+            print("No 'src' key in settings dictionary.")
+        
+def filter_and_save_csv(input_csv, output_csv, column_name, upper_threshold, lower_threshold):
+    """
+    Reads a CSV into a DataFrame, filters rows based on a column for values > upper_threshold and < lower_threshold,
+    and saves the filtered DataFrame to a new CSV file.
+
+    Parameters:
+        input_csv (str): Path to the input CSV file.
+        output_csv (str): Path to save the filtered CSV file.
+        column_name (str): Column name to apply the filters on.
+        upper_threshold (float): Upper threshold for filtering (values greater than this are retained).
+        lower_threshold (float): Lower threshold for filtering (values less than this are retained).
+
+    Returns:
+        None
+    """
+    # Read the input CSV file into a DataFrame
+    df = pd.read_csv(input_csv)
+
+    # Filter rows based on the thresholds
+    filtered_df = df[(df[column_name] > upper_threshold) | (df[column_name] < lower_threshold)]
+
+    # Save the filtered DataFrame to a new CSV file
+    filtered_df.to_csv(output_csv, index=False)
+    display(filtered_df)
+
+    print(f"Filtered DataFrame saved to {output_csv}")
+    
+def extract_tar_bz2_files(folder_path):
+    """
+    Extracts all .tar.bz2 files in the given folder into subfolders with the same name as the tar file.
+    
+    Parameters:
+        folder_path (str): Path to the folder containing .tar.bz2 files.
+    """
+    if not os.path.isdir(folder_path):
+        raise ValueError(f"The provided path '{folder_path}' is not a valid folder.")
+    
+    # Iterate over files in the folder
+    for file_name in os.listdir(folder_path):
+        if file_name.endswith('.tar.bz2'):
+            file_path = os.path.join(folder_path, file_name)
+            extract_folder = os.path.join(folder_path, os.path.splitext(os.path.splitext(file_name)[0])[0])
+            
+            # Create the subfolder for extraction if it doesn't exist
+            os.makedirs(extract_folder, exist_ok=True)
+            
+            # Extract the tar.bz2 file
+            try:
+                with tarfile.open(file_path, 'r:bz2') as tar:
+                    tar.extractall(path=extract_folder)
+                print(f"Extracted: {file_name} -> {extract_folder}")
+            except Exception as e:
+                print(f"Failed to extract {file_name}: {e}")
+            
+            
+def calculate_shortest_distance(df, object1, object2):
+    """
+    Calculate the shortest edge-to-edge distance between two objects (e.g., pathogen and nucleus).
+    
+    Parameters:
+    - df: Pandas DataFrame containing measurements
+    - object1: String, name of the first object (e.g., "pathogen")
+    - object2: String, name of the second object (e.g., "nucleus")
+
+    Returns:
+    - df: Pandas DataFrame with a new column for shortest edge-to-edge distance.
+    """
+
+    # Compute centroid-to-centroid Euclidean distance
+    centroid_distance = np.sqrt(
+        (df[f'{object1}_channel_0_centroid_weighted-0'] - df[f'{object2}_channel_0_centroid_weighted-0'])**2 +
+        (df[f'{object1}_channel_0_centroid_weighted-1'] - df[f'{object2}_channel_0_centroid_weighted-1'])**2
+    )
+
+    # Estimate object radii using Feret diameters
+    object1_radius = df[f'{object1}_feret_diameter_max'] / 2
+    object2_radius = df[f'{object2}_feret_diameter_max'] / 2
+
+    # Compute shortest edge-to-edge distance
+    shortest_distance = centroid_distance - (object1_radius + object2_radius)
+
+    # Ensure distances are non-negative (overlapping objects should have distance 0)
+    df[f'{object1}_{object2}_shortest_distance'] = np.maximum(shortest_distance, 0)
+
+    return df

{spacr-0.3.80.dist-info → spacr-0.4.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: spacr
-Version: 0.3.80
+Version: 0.4.0
 Summary: Spatial phenotype analysis of crisp screens (SpaCr)
 Home-page: https://github.com/EinarOlafsson/spacr
 Author: Einar Birnir Olafsson
@@ -32,6 +32,7 @@ Requires-Dist: monai>=1.3.0
 Requires-Dist: captum<1.0,>=0.7.0
 Requires-Dist: seaborn<1.0,>=0.13.2
 Requires-Dist: matplotlib<4.0,>=3.8.3
+Requires-Dist: matplotlib-venn<2.0,>=1.1
 Requires-Dist: adjustText<2.0,>=1.2.0
 Requires-Dist: bottleneck<2.0,>=1.3.6
 Requires-Dist: numexpr<3.0,>=2.8.4

{spacr-0.3.80.dist-info → spacr-0.4.0.dist-info}/RECORD

@@ -1,4 +1,4 @@
-spacr/__init__.py,sha256=fvk5JfLpOqUA1W0yPcsVZnS9qbpXFOceFk09LKolVfw,1627
+spacr/__init__.py,sha256=KgkkUyqbm4kh8bwxWeFpp4rilNE0y0RkeylPvS-cTLY,1395
 spacr/__main__.py,sha256=bkAJJD2kjIqOP-u1kLvct9jQQCeUXzlEjdgitwi1Lm8,75
 spacr/app_annotate.py,sha256=W9eLPa_LZIvXsXx_-0iDFEU938LBDvRy6prXo0qF4KQ,2533
 spacr/app_classify.py,sha256=urTP_wlZ58hSyM5a19slYlBxN0PdC-9-ga0hvq8CGWc,165
@@ -9,27 +9,27 @@ 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=3u2qKmPmTlswvE1uKTF4gi7KQ3sJBHV9No_ysgk7JCU,48487
-spacr/deep_spacr.py,sha256=V3diLyxX-0_F5UxhX_b94ROOvL9eoLvnoUmF3nMBqPQ,43250
+spacr/core.py,sha256=lKeqmsVrGQ8cPU_WkoNGNBWrk-gtR1RkRkwDdnJ0u64,48829
+spacr/deep_spacr.py,sha256=AsAbehxPChAq65YVPuFqCt5JabdeO8AwVWZmcmyLeFw,58020
 spacr/gui.py,sha256=ARyn9Q_g8HoP-cXh1nzMLVFCKqthY4v2u9yORyaQqQE,8230
-spacr/gui_core.py,sha256=6NKv8ebqC9Zuior4f2-L1By_Pjtt-RPCrEgnRuE9P54,45576
-spacr/gui_elements.py,sha256=I_eSYF1RkAG0zsa-ZiQT0EaaVvUpucULCuWCowO6t4E,138248
-spacr/gui_utils.py,sha256=u9RoIOWpAXFEOnUlLpMQZrc1pWSg6omZsJMIhJdRv_g,41211
-spacr/io.py,sha256=LF6lpphw7GSeuoHQijPykjKNF56wNTFEWFZuDQp3O6Q,145739
+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/logger.py,sha256=lJhTqt-_wfAunCPl93xE65Wr9Y1oIHJWaZMjunHUeIw,1538
-spacr/measure.py,sha256=2lK-ZcTxLM-MpXV1oZnucRD9iz5aprwahRKw9IEqshg,55085
+spacr/measure.py,sha256=jmOnLBudq3TuY723Cfo1EJBn67P6rlEvL6I-2FSkUgI,55315
 spacr/mediar.py,sha256=FwLvbLQW5LQzPgvJZG8Lw7GniA2vbZx6Jv6vIKu7I5c,14743
-spacr/ml.py,sha256=x19S8OsR5omb8e6MU9I99Nz95J_QvM5siyk-zaAU3p8,82866
+spacr/ml.py,sha256=MrIAtUUxMOibWVL1SjCUnYlizawCp3l3SeY4Y9yEsPw,97251
 spacr/openai.py,sha256=5vBZ3Jl2llYcW3oaTEXgdyCB2aJujMUIO5K038z7w_A,1246
-spacr/plot.py,sha256=gXC7y3uT4sx8KRODeSFWQG_A1CylsuJ5B7HYe_un6so,165177
+spacr/plot.py,sha256=p4AY5EWmVNPMqFD0I4NARJkvJA5gTErbDDYqDMU18pc,169479
 spacr/sequencing.py,sha256=ClUfwPPK6rNUbUuiEkzcwakzVyDKKUMv9ricrxT8qQY,25227
-spacr/settings.py,sha256=xTFTD04H8uXRJ5m4Pnr4Znhx0f_FxdgStMPXol3apxM,80888
+spacr/settings.py,sha256=e6QWZ5o6Im02_t-3GQh3H4kksMTQmIZ1Rbh3BeQmmsw,84000
 spacr/sim.py,sha256=1xKhXimNU3ukzIw-3l9cF3Znc_brW8h20yv8fSTzvss,71173
 spacr/stats.py,sha256=mbhwsyIqt5upsSD346qGjdCw7CFBa0tIS7zHU9e0jNI,9536
-spacr/submodules.py,sha256=SK8YEs850LAx30YAiwap7ecLpp1_p-bci6H-Or0GLoA,55500
+spacr/submodules.py,sha256=e_JNMGBHakEra_2pstHFmgI1NhF9TybfvTNDAegVsl0,67626
 spacr/timelapse.py,sha256=KGfG4L4-QnFfgbF7L6C5wL_3gd_rqr05Foje6RsoTBg,39603
-spacr/toxo.py,sha256=z2nT5aAze3NUIlwnBQcnkARihDwoPfqOgQIVoUluyK0,25087
-spacr/utils.py,sha256=SiUcctyUETEX_GZ-Nflba5whZiEjJynncaH-xcZPK1k,222242
+spacr/toxo.py,sha256=TmuhejSIPLBvsgeblsUgSvBFCR1gOkApyTKidooJ5Us,26044
+spacr/utils.py,sha256=m4MZiNbmQpZD78eu5DNmxk4cU_tk2VeVLCe_R_7YShY,226287
 spacr/version.py,sha256=axH5tnGwtgSnJHb5IDhiu4Zjk5GhLyAEDRe-rnaoFOA,409
 spacr/resources/MEDIAR/.gitignore,sha256=Ff1q9Nme14JUd-4Q3jZ65aeQ5X4uttptssVDgBVHYo8,152
 spacr/resources/MEDIAR/LICENSE,sha256=yEj_TRDLUfDpHDNM0StALXIt6mLqSgaV2hcCwa6_TcY,1065
@@ -152,9 +152,9 @@ 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-0.3.80.dist-info/LICENSE,sha256=SR-2MeGc6SCM1UORJYyarSWY_A-JaOMFDj7ReSs9tRM,1083
-spacr-0.3.80.dist-info/METADATA,sha256=Q0YV4N-C8XyUHH8HFW_k9ryAftcU8v9oMxNhgzvU8cA,6032
-spacr-0.3.80.dist-info/WHEEL,sha256=HiCZjzuy6Dw0hdX5R3LCFPDmFS4BWl8H-8W39XfmgX4,91
-spacr-0.3.80.dist-info/entry_points.txt,sha256=BMC0ql9aNNpv8lUZ8sgDLQMsqaVnX5L535gEhKUP5ho,296
-spacr-0.3.80.dist-info/top_level.txt,sha256=GJPU8FgwRXGzKeut6JopsSRY2R8T3i9lDgya42tLInY,6
-spacr-0.3.80.dist-info/RECORD,,
+spacr-0.4.0.dist-info/LICENSE,sha256=SR-2MeGc6SCM1UORJYyarSWY_A-JaOMFDj7ReSs9tRM,1083
+spacr-0.4.0.dist-info/METADATA,sha256=uloYFy8DrWtHZvy5W47jBRNUEF_SeX4nLZ0OL2wMizc,6072
+spacr-0.4.0.dist-info/WHEEL,sha256=HiCZjzuy6Dw0hdX5R3LCFPDmFS4BWl8H-8W39XfmgX4,91
+spacr-0.4.0.dist-info/entry_points.txt,sha256=BMC0ql9aNNpv8lUZ8sgDLQMsqaVnX5L535gEhKUP5ho,296
+spacr-0.4.0.dist-info/top_level.txt,sha256=GJPU8FgwRXGzKeut6JopsSRY2R8T3i9lDgya42tLInY,6
+spacr-0.4.0.dist-info/RECORD,,