spacr 0.3.34__py3-none-any.whl → 0.3.36__py3-none-any.whl

spacr/ml.py

@@ -732,7 +732,7 @@ def generate_ml_scores(settings):
     
     from .io import _read_and_merge_data, _read_db
     from .plot import plot_plates
-    from .utils import get_ml_results_paths
+    from .utils import get_ml_results_paths, add_column_to_database
     from .settings import set_default_analyze_screen
 
     settings = set_default_analyze_screen(settings)
@@ -835,6 +835,14 @@ def generate_ml_scores(settings):
     figs[1].savefig(feature_importance_fig_path, format='pdf')
     shap_fig.savefig(shap_fig_path, format='pdf')
 
+    if settings['save_to_db']:
+        settings['csv_path'] = data_path
+        settings['db_path'] = os.path.join(src, 'measurements', 'measurements.db')
+        settings['table_name'] = 'png_list'
+        settings['update_column'] = 'predictions'
+        settings['match_column'] = 'prcfo'
+        add_column_to_database(settings)
+
     return [output, plate_heatmap]
 
 def ml_analysis(df, channel_of_interest=3, location_column='col', positive_control='c2', negative_control='c1', exclude=None, n_repeats=10, top_features=30, n_estimators=100, test_size=0.2, model_type='xgboost', n_jobs=-1, remove_low_variance_features=True, remove_highly_correlated_features=True, verbose=False):

spacr/settings.py

@@ -279,6 +279,7 @@ def get_measure_crop_settings(settings={}):
 def set_default_analyze_screen(settings):
     settings.setdefault('src', 'path')
     settings.setdefault('annotation_column', None)
+    settings.setdefault('save_to_db', False)
     settings.setdefault('model_type_ml','xgboost')
     settings.setdefault('heatmap_feature','predictions')
     settings.setdefault('grouping','mean')
@@ -885,6 +886,7 @@ expected_types = {
     "overlay":bool,
     "correlate":bool,
     "target_layer":str,
+    "save_to_db":bool,
     "normalize_input":bool,
 }
 
@@ -897,7 +899,7 @@ categories = {"Paths":[ "src", "grna", "barcodes", "custom_model_path", "dataset
              "Measurements": ["remove_image_canvas", "remove_highly_correlated", "homogeneity", "homogeneity_distances", "radial_dist", "calculate_correlation", "manders_thresholds", "save_measurements", "tables", "image_nr", "dot_size", "filter_by", "remove_highly_correlated_features", "remove_low_variance_features", "channel_of_interest"],
              "Object Image": ["save_png", "dialate_pngs", "dialate_png_ratios", "png_size", "png_dims", "save_arrays", "normalize_by", "crop_mode", "dialate_pngs", "normalize", "use_bounding_box"],
              "Sequencing": ["signal_direction","mode","comp_level","comp_type","save_h5","expected_end","offset","target_sequence","regex", "highlight"],
-             "Generate Dataset":["file_metadata","class_metadata", "annotation_column","annotated_classes", "dataset_mode", "metadata_type_by","custom_measurement", "sample", "size"],
+             "Generate Dataset":["save_to_db","file_metadata","class_metadata", "annotation_column","annotated_classes", "dataset_mode", "metadata_type_by","custom_measurement", "sample", "size"],
              "Hyperparamiters (Training)": ["png_type", "score_threshold","file_type", "train_channels", "epochs", "loss_type", "optimizer_type","image_size","val_split","learning_rate","weight_decay","dropout_rate", "init_weights", "train", "classes", "augment", "amsgrad","use_checkpoint","gradient_accumulation","gradient_accumulation_steps","intermedeate_save","pin_memory"],
              "Hyperparamiters (Embedding)": ["visualize","n_neighbors","min_dist","metric","resnet_features","reduction_method","embedding_by_controls","col_to_compare","log_data"],
              "Hyperparamiters (Clustering)": ["eps","min_samples","analyze_clusters","clustering","remove_cluster_noise"],

spacr/utils.py

@@ -5042,3 +5042,67 @@ def generate_cytoplasm_mask(nucleus_mask, cell_mask):
     cytoplasm_mask = np.where(np.logical_or(nucleus_mask != 0), 0, 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.
+    
+    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.
+    """
+
+    # Read the DataFrame from the provided CSV path
+    df = pd.read_csv(settings['csv_path'])
+
+    # Connect to the SQLite database
+    conn = sqlite3.connect(settings['db_path'])
+    cursor = conn.cursor()
+
+    # Get the existing columns in the database table
+    cursor.execute(f"PRAGMA table_info({settings['table_name']})")
+    columns_in_db = [col[1] for col in cursor.fetchall()]
+
+    # Check if the update column already exists in the database
+    if settings['update_column'] in columns_in_db:
+        # Add a suffix to the column name (e.g., '_new', '_1', or similar)
+        suffix = 1
+        new_column_name = f"{settings['update_column']}_{suffix}"
+        # Ensure uniqueness by incrementing the suffix if needed
+        while new_column_name in columns_in_db:
+            suffix += 1
+            new_column_name = f"{settings['update_column']}_{suffix}"
+        print(f"Column '{settings['update_column']}' already exists. Using new column name: '{new_column_name}'")
+    else:
+        new_column_name = settings['update_column']
+
+    # Add the new column to the database table
+    cursor.execute(f"ALTER TABLE {settings['table_name']} ADD COLUMN {new_column_name} TEXT")
+    print(f"Added new column '{new_column_name}' to the table '{settings['table_name']}'.")
+
+    # Iterate over the DataFrame and update the new column in the database
+    for index, row in df.iterrows():
+        value_to_update = row[settings['update_column']]
+        match_value = row[settings['match_column']]
+
+        # Prepare and execute the SQL update query
+        query = f"""
+            UPDATE {settings['table_name']}
+            SET {new_column_name} = ?
+            WHERE {settings['match_column']} = ?
+        """
+        cursor.execute(query, (value_to_update, match_value))
+
+    # Commit the transaction and close the connection
+    conn.commit()
+    conn.close()
+
+    print(f"Updated '{new_column_name}' in '{settings['table_name']}' using '{settings['match_column']}'.")
+
+
+

{spacr-0.3.34.dist-info → spacr-0.3.36.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: spacr
-Version: 0.3.34
+Version: 0.3.36
 Summary: Spatial phenotype analysis of crisp screens (SpaCr)
 Home-page: https://github.com/EinarOlafsson/spacr
 Author: Einar Birnir Olafsson

{spacr-0.3.34.dist-info → spacr-0.3.36.dist-info}/RECORD

@@ -18,16 +18,16 @@ spacr/io.py,sha256=AARmqn1fMmTgVDwWy8bEYK6SjH-6DZIulgCSPdBTyf0,143370
 spacr/logger.py,sha256=lJhTqt-_wfAunCPl93xE65Wr9Y1oIHJWaZMjunHUeIw,1538
 spacr/measure.py,sha256=BThn_sALgKrwGKnLOGpT4FyoJeRVoTZoP9SXbCtCMRw,54857
 spacr/mediar.py,sha256=FwLvbLQW5LQzPgvJZG8Lw7GniA2vbZx6Jv6vIKu7I5c,14743
-spacr/ml.py,sha256=8i2D9YEC9rSYdbgkuuMLl6adwivWn2Z5BEUjPRsW4t4,48983
+spacr/ml.py,sha256=Wy_H_bI5cD_N4xIZCo3_M-73wVvmCC35tJbLspMOWbg,49341
 spacr/openai.py,sha256=5vBZ3Jl2llYcW3oaTEXgdyCB2aJujMUIO5K038z7w_A,1246
 spacr/plot.py,sha256=PtCSoBmLFlGC7ebmsk-vMlyd7q2ahXgRVaTtAq3w_po,116513
 spacr/sequencing.py,sha256=t18mgpK6rhWuB1LtFOsPxqgpFXxuUmrD06ecsaVQ0Gw,19655
-spacr/settings.py,sha256=7rAvzPkfyfbpY6JQqcTe6PcCghEvLebUgsfKMVBtNyU,75879
+spacr/settings.py,sha256=AzP9NGiXI1MqT69bHObxwDSCUk0kdstBVvl1JpcD_-w,75960
 spacr/sim.py,sha256=1xKhXimNU3ukzIw-3l9cF3Znc_brW8h20yv8fSTzvss,71173
 spacr/submodules.py,sha256=AB7s6-cULsaqz-haAaCtXfGEIi8uPZGT4xoCslUJC3Y,18391
 spacr/timelapse.py,sha256=FSYpUtAVy6xc3lwprRYgyDTT9ysUhfRQ4zrP9_h2mvg,39465
 spacr/toxo.py,sha256=us3pQyULtMTyfTq0MWPn4QJTTmQ6BwAJKChNf75jo3I,10082
-spacr/utils.py,sha256=w4Cht32Mhep7jfXKm5CSpyFLB3lOxiBCQI6PnaYcI3Q,213360
+spacr/utils.py,sha256=iCbweRXWjJgKGbp8DAVC20xUG9nwy2K9cvIsXORAKwA,216043
 spacr/version.py,sha256=axH5tnGwtgSnJHb5IDhiu4Zjk5GhLyAEDRe-rnaoFOA,409
 spacr/resources/MEDIAR/.gitignore,sha256=Ff1q9Nme14JUd-4Q3jZ65aeQ5X4uttptssVDgBVHYo8,152
 spacr/resources/MEDIAR/LICENSE,sha256=yEj_TRDLUfDpHDNM0StALXIt6mLqSgaV2hcCwa6_TcY,1065
@@ -150,9 +150,9 @@ 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-0.3.34.dist-info/LICENSE,sha256=SR-2MeGc6SCM1UORJYyarSWY_A-JaOMFDj7ReSs9tRM,1083
-spacr-0.3.34.dist-info/METADATA,sha256=6C9_x3YSb9ycM9cXRufcPTJG809Cf-hkNYDOdEVXMT0,5949
-spacr-0.3.34.dist-info/WHEEL,sha256=HiCZjzuy6Dw0hdX5R3LCFPDmFS4BWl8H-8W39XfmgX4,91
-spacr-0.3.34.dist-info/entry_points.txt,sha256=BMC0ql9aNNpv8lUZ8sgDLQMsqaVnX5L535gEhKUP5ho,296
-spacr-0.3.34.dist-info/top_level.txt,sha256=GJPU8FgwRXGzKeut6JopsSRY2R8T3i9lDgya42tLInY,6
-spacr-0.3.34.dist-info/RECORD,,
+spacr-0.3.36.dist-info/LICENSE,sha256=SR-2MeGc6SCM1UORJYyarSWY_A-JaOMFDj7ReSs9tRM,1083
+spacr-0.3.36.dist-info/METADATA,sha256=NvcSKD3mIWOPeTDAAbugslvW-1_T0Dzd9k8WzSVNwbY,5949
+spacr-0.3.36.dist-info/WHEEL,sha256=HiCZjzuy6Dw0hdX5R3LCFPDmFS4BWl8H-8W39XfmgX4,91
+spacr-0.3.36.dist-info/entry_points.txt,sha256=BMC0ql9aNNpv8lUZ8sgDLQMsqaVnX5L535gEhKUP5ho,296
+spacr-0.3.36.dist-info/top_level.txt,sha256=GJPU8FgwRXGzKeut6JopsSRY2R8T3i9lDgya42tLInY,6
+spacr-0.3.36.dist-info/RECORD,,