spacr 0.3.60__py3-none-any.whl → 0.3.62__py3-none-any.whl

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):
     """
@@ -4052,7 +4108,7 @@ def measure_test_mode(settings):
 
     return settings
 
-def preprocess_data(df, filter_by, remove_highly_correlated, log_data, exclude):
+def preprocess_data(df, filter_by, remove_highly_correlated, log_data, exclude, column_list=False):
     """
     Preprocesses the given dataframe by applying filtering, removing highly correlated columns,
     applying log transformation, filling NaN values, and scaling the numeric data.
@@ -4076,7 +4132,10 @@ def preprocess_data(df, filter_by, remove_highly_correlated, log_data, exclude):
     # Apply filtering based on the `filter_by` parameter
     if filter_by is not None:
         df, _ = filter_dataframe_features(df, channel_of_interest=filter_by, exclude=exclude)
-        
+            
+    if column_list:
+        df = df[column_list]
+    
     # Select numerical features
     numeric_data = df.select_dtypes(include=['number'])
     
@@ -4181,6 +4240,7 @@ def filter_dataframe_features(df, channel_of_interest, exclude=None, remove_low_
     
     if verbose:
         print("Columns to remove:", count_and_id_columns)
+        
     df = df.drop(columns=count_and_id_columns)
     
     if not channel_of_interest is None:
@@ -4189,6 +4249,9 @@ def filter_dataframe_features(df, channel_of_interest, exclude=None, remove_low_
         if isinstance(channel_of_interest, list):
             feature_strings = [f"channel_{channel}" for channel in channel_of_interest]
             
+        elif isinstance(channel_of_interest, str):
+            feature_strings = [channel_of_interest]
+            
         elif isinstance(channel_of_interest, int):
             feature_string = f"channel_{channel_of_interest}"
             feature_strings = [feature_string]
@@ -5164,3 +5227,33 @@ def rename_columns_in_db(db_path):
     # After closing the 'with' block, run VACUUM outside of any transaction
     with sqlite3.connect(db_path) as conn:
         conn.execute("VACUUM;")
+        
+def group_feature_class(df, feature_groups=['cell', 'cytoplasm', 'nucleus', 'pathogen'], name='compartment'):
+
+    # Function to determine compartment based on multiple matches
+    def find_feature_class(feature, compartments):
+        matches = [compartment for compartment in compartments if re.search(compartment, feature)]
+        if len(matches) > 1:
+            return '-'.join(matches)
+        elif matches:
+            return matches[0]
+        else:
+            return None
+        
+    from .plot import spacrGraph
+
+    df[name] = df['feature'].apply(lambda x: find_feature_class(x, feature_groups))
+    
+    if name == 'channel':
+        df['channel'].fillna('morphology', inplace=True)
+    
+    # Create new DataFrame with summed importance for each compartment and channel
+    importance_sum = df.groupby(name)['importance'].sum().reset_index(name=f'{name}_importance_sum')
+    total_compartment_importance = importance_sum[f'{name}_importance_sum'].sum()
+    importance_sum = pd.concat(
+        [importance_sum,
+         pd.DataFrame(
+             [{name: 'all', '{name}_importance_sum': total_compartment_importance}])]
+        , ignore_index=True)
+    
+    return df

{spacr-0.3.60.dist-info → spacr-0.3.62.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: spacr
-Version: 0.3.60
+Version: 0.3.62
 Summary: Spatial phenotype analysis of crisp screens (SpaCr)
 Home-page: https://github.com/EinarOlafsson/spacr
 Author: Einar Birnir Olafsson

{spacr-0.3.60.dist-info → spacr-0.3.62.dist-info}/RECORD

@@ -1,6 +1,6 @@
 spacr/__init__.py,sha256=CZtAdU5etLcb9dVmz-4Y7Hjhw3ubjMzfjG0L5ybyFVA,1592
 spacr/__main__.py,sha256=bkAJJD2kjIqOP-u1kLvct9jQQCeUXzlEjdgitwi1Lm8,75
-spacr/app_annotate.py,sha256=zGmAJplDOckhaUZijkHgbFH9LJNbd6TolU2hamplOBc,2769
+spacr/app_annotate.py,sha256=W9eLPa_LZIvXsXx_-0iDFEU938LBDvRy6prXo0qF4KQ,2533
 spacr/app_classify.py,sha256=urTP_wlZ58hSyM5a19slYlBxN0PdC-9-ga0hvq8CGWc,165
 spacr/app_make_masks.py,sha256=pqDhRpluiHZz-kPX2Zh_KbYe4TsU43qYBa_7f-rsjpw,1694
 spacr/app_mask.py,sha256=l-dBY8ftzCMdDe6-pXc2Nh_u-idNL9G7UOARiLJBtds,153
@@ -9,26 +9,26 @@ 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=dW9RrAKFLfVsFhX0-kaVMc2T7b47Ky0pTXK-CEVOeWQ,48235
+spacr/core.py,sha256=3u2qKmPmTlswvE1uKTF4gi7KQ3sJBHV9No_ysgk7JCU,48487
 spacr/deep_spacr.py,sha256=HdOcNU8cHcE_19nP7_5uTz-ih3E169ffr2Hm--NvMvA,43255
 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=Ud6hRRPhombKjeGUhlleEr9I75SNnFj8UD11yKfp9Wo,40860
-spacr/io.py,sha256=VHs6h8o0gBEyKxfdNqEhpzjQXPrj7UGG47DwHeUyUDw,143390
+spacr/gui_utils.py,sha256=u9RoIOWpAXFEOnUlLpMQZrc1pWSg6omZsJMIhJdRv_g,41211
+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
-spacr/ml.py,sha256=aberLbvUM9F6uNpEOFHzn8_w-fiW0sDG3jVb6TDxakI,68275
+spacr/ml.py,sha256=aLDeeaAl0d4-RP1CzFHPqz5br2HrFbJhvPexEm9lvSI,68198
 spacr/openai.py,sha256=5vBZ3Jl2llYcW3oaTEXgdyCB2aJujMUIO5K038z7w_A,1246
-spacr/plot.py,sha256=Y5_VuRHNsIH7iezK8kWXHg9fwh5sW3S34ncIFshbBco,157893
+spacr/plot.py,sha256=zITe54dzQRz-gk_ZT0qJyARuUWJivIBKW8V4rjUH8SE,160320
 spacr/sequencing.py,sha256=ClUfwPPK6rNUbUuiEkzcwakzVyDKKUMv9ricrxT8qQY,25227
-spacr/settings.py,sha256=6_GB1QQw_w_4yq8dH-Ypc4rJw__Cgs6g_BnR9bIjdZI,77669
+spacr/settings.py,sha256=zANLspVmllDZeYjQWIfrHN3VkVgicnYGTduv30MmQ18,77257
 spacr/sim.py,sha256=1xKhXimNU3ukzIw-3l9cF3Znc_brW8h20yv8fSTzvss,71173
-spacr/submodules.py,sha256=dn-QSKX6ZqyyEr8_v69jVGpB-wd3KbaMRacIA8DXONU,28155
+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=5XGA0aPray3DzCAgwJjPRlsaxsuSRJyTTTZ7rNDTRTg,219202
+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-0.3.60.dist-info/LICENSE,sha256=SR-2MeGc6SCM1UORJYyarSWY_A-JaOMFDj7ReSs9tRM,1083
-spacr-0.3.60.dist-info/METADATA,sha256=UF63-vN6-XEslhGhnotkQz6JanIajbV56bKcSEaEIjE,6032
-spacr-0.3.60.dist-info/WHEEL,sha256=HiCZjzuy6Dw0hdX5R3LCFPDmFS4BWl8H-8W39XfmgX4,91
-spacr-0.3.60.dist-info/entry_points.txt,sha256=BMC0ql9aNNpv8lUZ8sgDLQMsqaVnX5L535gEhKUP5ho,296
-spacr-0.3.60.dist-info/top_level.txt,sha256=GJPU8FgwRXGzKeut6JopsSRY2R8T3i9lDgya42tLInY,6
-spacr-0.3.60.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,,