[IMP] cleans up code and removes all unused or unimportant files

SAP · Aug 30, 2024 · aa8d2fe · aa8d2fe
1 parent b56718c
commit aa8d2fe
Show file tree

Hide file tree

Showing 8 changed files with 9 additions and 340 deletions.
diff --git a/prospector/evaluation/analyse.py b/prospector/evaluation/analyse.py
@@ -80,7 +80,7 @@ def analyse_prospector_reports(filename: str, selected_cves: str):
     # Keep track of the CVEs where there is no report file
     reports_not_found = []
 
-    #### Data to insert into table
+    # Data to insert into table
     if BATCH in ["regular", "old_code"]:
         results = {
             "high": [],
@@ -620,7 +620,7 @@ def generate_checkmarks_table(input_dataset: str, selected_cves):
 
         rule_checks = {rule: "" for rule in all_rules}
         for r in matched_rules:
-            rule_checks[r] = "\checkmark"
+            rule_checks[r] = "\checkmark" # noqa: W605
 
         row.extend([rule_checks[r] for r in all_rules])
         row.extend([str(overall_exectime), str(llm_exectime)])
@@ -785,9 +785,7 @@ def generate_sankey_diagram(file1: str, file2: str, file3: str):
         height=800,
     )
 
-    output_file = (
-        ANALYSIS_RESULTS_PATH + f"sankey-{file1}-{file2}-{file3}.png"
-    )
+    output_file = ANALYSIS_RESULTS_PATH + f"sankey-{file1}-{file2}-{file3}.png"
     # Save as PNG
     write_image(fig, output_file)
     print(f"Sankey diagram saved to {output_file}")
diff --git a/prospector/evaluation/analyse_statistics.py b/prospector/evaluation/analyse_statistics.py
@@ -63,16 +63,6 @@ def analyse_statistics(filename: str):  # noqa: C901
     avg_cc_time = sum(cc_times) / len(cc_times)
     avg_total_cc_time = sum(total_cc_times) / len(total_cc_times)
 
-    # How many commits was the commit classification rule applied to?
-    for itm in dataset:
-        filepath = PROSPECTOR_REPORTS_PATH_HOST + filename + f"/{itm[0]}.json"
-        try:
-            cc_num_commits = _get_cc_num_commits(filepath)
-            break
-
-        except FileNotFoundError:
-            continue
-
     execution_data = {
         "timestamp": datetime.now().strftime("%H:%M:%S"),
         "total_files_found": len(repo_times),

diff --git a/prospector/evaluation/compare.py b/prospector/evaluation/compare.py
@@ -91,7 +91,7 @@ def main():
     file = "evaluation/data/input/d63.csv"
     dataset = load_dataset(file)
 
-    ## Things to measure
+    # Things to measure
     counterpart_exists = []
     missing_in_directory1 = []
     missing_in_directory2 = []

diff --git a/prospector/evaluation/compare_reports.py b/prospector/evaluation/compare_reports.py
diff --git a/prospector/evaluation/create_jobs.py b/prospector/evaluation/create_jobs.py
diff --git a/prospector/evaluation/dispatch_jobs.py b/prospector/evaluation/dispatch_jobs.py
@@ -101,7 +101,7 @@ def _run_prospector_and_generate_report(
         logger.error(f"prospector() crashed at {cve_id}: {e}")
         raise e
 
-    logger.info(f"prospector() returned. Generating report now.")
+    logger.info("prospector() returned. Generating report now.")
 
     try:
         generate_report(

diff --git a/prospector/evaluation/extract_errors.py b/prospector/evaluation/extract_errors.py