spacr 0.3.34__tar.gz → 0.3.35__tar.gz

{spacr-0.3.34/spacr.egg-info → spacr-0.3.35}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: spacr
-Version: 0.3.34
+Version: 0.3.35
 Summary: Spatial phenotype analysis of crisp screens (SpaCr)
 Home-page: https://github.com/EinarOlafsson/spacr
 Author: Einar Birnir Olafsson

{spacr-0.3.34 → spacr-0.3.35}/setup.py

@@ -67,7 +67,7 @@ dependencies = [
 
 setup(
     name="spacr",
-    version="0.3.34",
+    version="0.3.35",
     author="Einar Birnir Olafsson",
     author_email="olafsson@med.umich.com",
     description="Spatial phenotype analysis of crisp screens (SpaCr)",

{spacr-0.3.34 → spacr-0.3.35}/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-0.3.34 → spacr-0.3.35}/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-0.3.34 → spacr-0.3.35}/spacr/utils.py

@@ -5042,3 +5042,44 @@ 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):
+    """
+    Updates a column in the database by matching on a common column from the DataFrame.
+
+    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 column to update in 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()
+
+    # Iterate over the DataFrame and update 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 {settings['update_column']} = ?
+            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 '{settings['update_column']}' in '{settings['table_name']}' using '{settings['match_column']}'.")
+
+

{spacr-0.3.34 → spacr-0.3.35/spacr.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: spacr
-Version: 0.3.34
+Version: 0.3.35
 Summary: Spatial phenotype analysis of crisp screens (SpaCr)
 Home-page: https://github.com/EinarOlafsson/spacr
 Author: Einar Birnir Olafsson