Rename evaluation scripts and output files for consistency and clarity across code and performance evaluation

Author: voltjia

compare_code_metrics.py evaluate_code.pycompare_code_metrics.py renamed to evaluate_code.py

@@ -3,7 +3,7 @@
 import matplotlib.pyplot as plt
 import pandas as pd
 
-from compare_code_metrics import _BACKSLASH_CHAR
+from evaluate_code import _BACKSLASH_CHAR
 from run_experiments import ALL_MAX_NEW_TOKENS, BACKENDS
 
 if __name__ == "__main__":

compare_performance_metrics.py evaluate_performance.pycompare_performance_metrics.py renamed to evaluate_performance.py

@@ -118,8 +118,8 @@ def _benchmark_ops(ops, *args, **kwargs):
     for command in radon_commands:
         subprocess.run(command, check=True)
 
-    with open("code_metrics.tex", "w") as f:
-        subprocess.run(("python", "compare_code_metrics.py"), stdout=f, check=True)
+    with open("code_evaluation.tex", "w") as f:
+        subprocess.run(("python", "evaluate_code.py"), stdout=f, check=True)
 
     dtype = torch.float16
     device = "cuda"
@@ -183,7 +183,5 @@ def _benchmark_ops(ops, *args, **kwargs):
                     check=True,
                 )
 
-    with open("performance_metrics.tex", "w") as f:
-        subprocess.run(
-            ("python", "compare_performance_metrics.py"), stdout=f, check=True
-        )
+    with open("performance_evaluation.tex", "w") as f:
+        subprocess.run(("python", "evaluate_performance.py"), stdout=f, check=True)