import numpy as np
for problem, problem_group in benchmark_data_merged.groupby("FilePath"):
problem_group = problem_group.loc[problem_group["AlgorithmShort"].apply(
lambda x: x not in ["MultiSURF*", "FixedReliefFPercent20", "FixedReliefFPercent30",
"FixedReliefFPercent38.2",
"ReliefF-NN10", "ReliefF-NN100", "ReliefF-NN200"])]
After Change
csv.field_size_limit(sys.maxsize)
benchmark_data_merged = pd.read_csv("benchmark-parsed-merged-analyzed.tsv.gz", sep="\t", engine="python")
benchmark_data_merged.sort_values(["FilePath", "Algorithm"], inplace=True)
solved_cols = [x for x in benchmark_data_merged.columns.values if "Solved" in x]
for problem, problem_group in benchmark_data_merged.groupby("FilePath"):