Change Re-zip structure

Author: M-Jafarkhani

.github/workflows/run-benchmark.yml

@@ -115,7 +115,9 @@ jobs:
 
       - name: Re-zip provenance folder
         run: |
-          zip -r "./${SNAKEMAKE_PROVENANCE_FILE}.zip" "./${SNAKEMAKE_PROVENANCE_FILE}"
+          cd "./${SNAKEMAKE_PROVENANCE_FILE}"
+          zip -r "../${SNAKEMAKE_PROVENANCE_FILE}.zip" .
+
 
       - name: Upload RoCrate Zip file onto RoHub
         shell: bash -l {0}

benchmarks/linear-elastic-plate-with-hole/plot_provenance.py

@@ -9,7 +9,7 @@
 def parse_args():
     """
     Parse command-line arguments for the provenance processing script.
-    
+
     Returns:
         argparse.Namespace: Parsed arguments containing:
             - provenance_folderpath: Path to the folder with RO-Crate data
@@ -43,14 +43,14 @@ def parse_args():
 def sparql_result_to_dataframe(results):
     """
     Convert SPARQL query results into a pandas DataFrame.
-    
+
     Extracts variable bindings from each result row using asdict() and converts
     RDF values to Python native types using toPython().
-    
+
     Args:
-        results (rdflib.plugins.sparql.processor.SPARQLResult): SPARQL query results 
+        results (rdflib.plugins.sparql.processor.SPARQLResult): SPARQL query results
                                                                 from rdflib.
-    
+
     Returns:
         pd.DataFrame: DataFrame where each row represents a query result and columns
                      correspond to SPARQL variables.
@@ -67,16 +67,16 @@ def sparql_result_to_dataframe(results):
 def apply_custom_filters(data: pd.DataFrame) -> pd.DataFrame:
     """
     Filter provenance data to include only first-order linear elements.
-    
+
     Filters rows where element_degree = 1 and element_order = 1, then removes
     these filtering columns from the result.
-    
+
     Args:
-        data (pd.DataFrame): Input DataFrame containing element_degree and 
+        data (pd.DataFrame): Input DataFrame containing element_degree and
                             element_order columns.
-    
+
     Returns:
-        pd.DataFrame: Filtered DataFrame with element_degree and element_order 
+        pd.DataFrame: Filtered DataFrame with element_degree and element_order
                      columns removed and index reset.
     """
     filtered_df = data[(data["element_degree"] == 1) & (data["element_order"] == 1)]
@@ -89,16 +89,16 @@ def apply_custom_filters(data: pd.DataFrame) -> pd.DataFrame:
 def summary_file_to_dataframe(summary_path, parameters, metrics):
     """
     Load benchmark data from a summary.json file into a DataFrame.
-    
+
     Handles both dictionary-style parameter/metric values (with 'value' key) and
     direct scalar values. Converts parameter names from underscore to hyphen format
     for JSON lookup.
-    
+
     Args:
         summary_path (str): Path to the summary.json file.
         parameters (list): List of parameter names to extract.
         metrics (list): List of metric names to extract.
-    
+
     Returns:
         pd.DataFrame: DataFrame with columns for each parameter and metric.
     """
@@ -134,20 +134,20 @@ def summary_file_to_dataframe(summary_path, parameters, metrics):
 def compare_dataframes(df1: pd.DataFrame, df2: pd.DataFrame):
     """
     Compare two DataFrames for identical content regardless of row order.
-    
+
     Sorts both DataFrames by all columns, then checks for equality. If differences
     are found, prints rows that appear in one DataFrame but not the other.
-    
+
     Args:
         df1 (pd.DataFrame): First DataFrame to compare.
         df2 (pd.DataFrame): Second DataFrame to compare.
-    
+
     Returns:
         bool: True if DataFrames contain identical data, False otherwise.
-    
+
     Raises:
         ValueError: If the DataFrames have different columns.
-    
+
     Prints:
         Rows that are present in one DataFrame but missing in the other,
         when differences are detected.
@@ -186,23 +186,23 @@ def compare_dataframes(df1: pd.DataFrame, df2: pd.DataFrame):
 def load_and_query_graph(analyzer, parameters, metrics, tools):
     """
     Load the RO-Crate graph and execute a SPARQL query to extract provenance data.
-    
+
     Args:
         analyzer (ProvenanceAnalyzer): Initialized analyzer instance.
         parameters (list): List of parameter names to query.
         metrics (list): List of metric names to query.
         tools (list): List of tool names to filter by.
-    
+
     Returns:
         pd.DataFrame: DataFrame containing the query results.
-    
+
     Raises:
         AssertionError: If the query returns no data.
     """
     graph = analyzer.load_graph_from_file()
     query = analyzer.build_dynamic_query(parameters, metrics, tools)
     results = analyzer.run_query_on_graph(graph, query)
-    
+
     provenance_df = sparql_result_to_dataframe(results)
     assert len(provenance_df), "No data found for the provenance query."
 
@@ -214,18 +214,18 @@ def validate_provenance_data(
 ):
     """
     Validate provenance query results against ground truth data from summary.json files.
-    
+
     For each tool, loads the corresponding summary.json file and compares its data
     against the filtered provenance query results for that tool.
-    
+
     Args:
         provenance_df (pd.DataFrame): DataFrame containing all provenance query results.
         parameters (list): List of parameter names used in the comparison.
         metrics (list): List of metric names used in the comparison.
         tools (list): List of tool names to validate.
-        provenance_folderpath (str): Base path to the provenance folder containing 
+        provenance_folderpath (str): Base path to the provenance folder containing
                                      summary.json files.
-    
+
     Raises:
         AssertionError: If data mismatch is found between summary.json and provenance
                        data for any tool.
@@ -252,14 +252,14 @@ def validate_provenance_data(
 def plot_results(analyzer, final_df, output_file):
     """
     Generate a visualization plot of the provenance results.
-    
+
     Creates a scatter/line plot showing the relationship between element size
     and maximum von Mises stress, grouped by tool name.
-    
+
     Args:
         analyzer (ProvenanceAnalyzer): Initialized analyzer instance.
         final_df (pd.DataFrame): DataFrame containing filtered data to plot.
-                                Expected columns: element_size, max_von_mises_stress_nodes, 
+                                Expected columns: element_size, max_von_mises_stress_nodes,
                                 tool_name (in that order).
         output_file (str): Path where the plot image will be saved.
     """
@@ -278,15 +278,15 @@ def plot_results(analyzer, final_df, output_file):
 def run(args, parameters, metrics, tools):
     """
     Execute the complete provenance analysis workflow.
-    
+
     Performs the following steps:
     1. Initialize the ProvenanceAnalyzer
     2. Validate the RO-Crate metadata structure
     3. Load and query the provenance graph
     4. Validate query results against summary.json ground truth data
     5. Apply custom filters to the data
     6. Generate visualization plot
-    
+
     Args:
         args (argparse.Namespace): Parsed command-line arguments.
         parameters (list): List of parameter names to extract.
@@ -297,7 +297,7 @@ def run(args, parameters, metrics, tools):
         provenance_folderpath=args.provenance_folderpath,
         provenance_filename=args.provenance_filename,
     )
-    
+
     analyzer.validate_provevance()
 
     provenance_df = load_and_query_graph(analyzer, parameters, metrics, tools)
@@ -314,7 +314,7 @@ def run(args, parameters, metrics, tools):
 def main():
     """
     Main entry point for the provenance analysis script.
-    
+
     Parses command-line arguments, defines the parameters and metrics to extract,
     retrieves tool names from the workflow configuration, and executes the analysis
     workflow.
@@ -329,4 +329,4 @@ def main():
 
 
 if __name__ == "__main__":
-    main()
+    main()

benchmarks/linear-elastic-plate-with-hole/provenance.py

@@ -6,12 +6,13 @@
 import re
 from rocrate_validator import services, models
 
+
 class ProvenanceAnalyzer:
     """
     A class to analyze, validate, and visualize provenance data from RO-Crate metadata files.
 
-    This class loads RO-Crate JSON-LD files, builds dynamic SPARQL queries to extract 
-    workflow metadata about methods, parameters, and metrics, and provides visualization 
+    This class loads RO-Crate JSON-LD files, builds dynamic SPARQL queries to extract
+    workflow metadata about methods, parameters, and metrics, and provides visualization
     capabilities. It also validates RO-Crate files against the RO-Crate 1.1 profile.
 
     Attributes:
@@ -61,13 +62,13 @@ def load_graph_from_file(self) -> Graph:
     def sanitize_variable_name(self, name: str) -> str:
         """
         Convert a string into a valid SPARQL variable name.
-        
+
         Replaces invalid characters with underscores and ensures the variable
         name doesn't start with a digit.
-        
+
         Args:
             name (str): The original string to convert.
-            
+
         Returns:
             str: A sanitized variable name safe for use in SPARQL queries.
         """
@@ -80,20 +81,20 @@ def sanitize_variable_name(self, name: str) -> str:
 
     def build_dynamic_query(self, parameters, metrics, tools=None, named_graph=None):
         """
-        Generate a dynamic SPARQL query to extract m4i:Method instances with specified 
+        Generate a dynamic SPARQL query to extract m4i:Method instances with specified
         parameters and metrics.
-        
+
         The query extracts methods along with their associated parameters (via m4i:hasParameter),
         metrics (via m4i:investigates), and the tools that implement them (via ssn:implementedBy).
-        
+
         Args:
             parameters (list): List of parameter names to query (matched via rdfs:label).
             metrics (list): List of metric names to query (matched via rdfs:label).
-            tools (list, optional): List of tool name substrings to filter results. 
+            tools (list, optional): List of tool name substrings to filter results.
                                    Case-insensitive matching. Defaults to None.
-            named_graph (str, optional): URI of a named graph to query within. 
+            named_graph (str, optional): URI of a named graph to query within.
                                         If None, queries the default graph. Defaults to None.
-        
+
         Returns:
             str: A complete SPARQL query string ready to execute.
         """
@@ -171,7 +172,7 @@ def run_query_on_graph(
             query (str): The SPARQL query string to execute.
 
         Returns:
-            rdflib.plugins.sparql.processor.SPARQLResult: The query results object 
+            rdflib.plugins.sparql.processor.SPARQLResult: The query results object
                                                           from rdflib.
         """
         return graph.query(query)
@@ -190,7 +191,7 @@ def plot_provenance_graph(
     ):
         """
         Generates a scatter/line plot from the extracted provenance data.
-        
+
         The plot displays data points grouped by a specified column, with each group
         shown as a separate line series. The x-axis uses a logarithmic scale.
 
@@ -202,9 +203,9 @@ def plot_provenance_graph(
             y_axis_index (int or str): Index or key for the y-axis values in each row.
             group_by_index (int or str): Index or key for the grouping variable (used for legend).
             title (str): Title of the plot.
-            output_file (str, optional): Path where the plot will be saved as an image. 
+            output_file (str, optional): Path where the plot will be saved as an image.
                                         If None, displays the plot. Defaults to None.
-            figsize (Tuple[int, int], optional): Figure dimensions (width, height). 
+            figsize (Tuple[int, int], optional): Figure dimensions (width, height).
                                                 Defaults to (12, 5).
         """
 
@@ -244,36 +245,32 @@ def plot_provenance_graph(
         else:
             plt.show()
 
-
-    def validate_provevance(self): 
+    def validate_provevance(self):
         """
         Validates the RO-Crate against the RO-Crate 1.1 profile.
-        
+
         Uses the rocrate-validator library to check if the RO-Crate metadata
         conforms to the RO-Crate 1.1 specification with required severity level.
-        
+
         Raises:
             AssertionError: If the RO-Crate has validation issues, with details
                            about each issue's severity and message.
-        
+
         Prints:
             Success message if the RO-Crate is valid.
         """
         settings = services.ValidationSettings(
             rocrate_uri=self.provenance_folderpath,
-            profile_identifier='ro-crate-1.1',
+            profile_identifier="ro-crate-1.1",
             requirement_severity=models.Severity.REQUIRED,
         )
 
         result = services.validate(settings)
 
-        assert not result.has_issues(), (
-            "RO-Crate is invalid!\n" +
-            "\n".join(
-                f"Detected issue of severity {issue.severity.name} with check "
-                f'"{issue.check.identifier}": {issue.message}'
-                for issue in result.get_issues()
-            )
+        assert not result.has_issues(), "RO-Crate is invalid!\n" + "\n".join(
+            f"Detected issue of severity {issue.severity.name} with check "
+            f'"{issue.check.identifier}": {issue.message}'
+            for issue in result.get_issues()
         )
 
-        print("RO-Crate is valid!")
+        print("RO-Crate is valid!")

benchmarks/linear-elastic-plate-with-hole/upload_provenance.py

@@ -30,8 +30,9 @@ def parse_args():
 
 def run(args):
     rohub.settings.SLEEP_TIME = 10
-    
+
     USE_DEVELOPMENT_VERSION = True
+    
     if USE_DEVELOPMENT_VERSION:
         rohub.settings.API_URL = "https://rohub2020-rohub.apps.paas-dev.psnc.pl/api/"
         rohub.settings.KEYCLOAK_CLIENT_ID = "rohub2020-cli"
@@ -42,7 +43,7 @@ def run(args):
         )
 
     rohub.login(args.username, args.password)
-    
+
     my_ros = rohub.list_my_ros()
 
     try:
@@ -81,14 +82,17 @@ def run(args):
     ANNOTATION_PREDICATE = "http://w3id.org/nfdi4ing/metadata4ing#investigates"
     ANNOTATION_OBJECT = "https://github.com/BAMresearch/NFDI4IngModelValidationPlatform/tree/main/benchmarks/linear-elastic-plate-with-hole"
 
-    if (uuid != ""):
+    if uuid != "":
         _RO = rohub.ros_load(uuid)
-        annotation_json = [{"property": ANNOTATION_PREDICATE, "value": ANNOTATION_OBJECT}]
+        annotation_json = [
+            {"property": ANNOTATION_PREDICATE, "value": ANNOTATION_OBJECT}
+        ]
         add_annotations_result = _RO.add_annotations(
             body_specification_json=annotation_json
         )
         print(add_annotations_result)
 
+
 def main():
     args = parse_args()
     run(args)