INNER CODE UNIT · Python
process_data
sstadick/perbase · paper/plot_benchmarks_comprehensive.py:24
def process_data(df):
df = df.copy()
df['tool'] = df['command'].apply(lambda x: x.split()[0])
df['mean_minutes'] = df['mean'] / 60 # Convert to minutes
return df
base_depth_df = process_data(base_depth_df)
mate_fix_df = process_data(mate_fix_df)
mate_fix_new_df = process_data(mate_fix_new_df)
# Get standard runtime data
perbase_std = base_depth_df[base_depth_df['tool'] == 'perbase']['mean_minutes'].values[0]
sambamba_std = base_depth_df[base_depth_df['tool'] == 'sambamba']['mean_minutes'].values[0]
# Get sambamba mate-fix runtime
sambamba_mf = mate_fix_new_df[mate_fix_new_df['command'].str.contains('sambamba')]['mean_minutes'].values[0]
# Extract mate-fix method data (excluding OLD version)