3ab0e54a3ce88c7018a34192461dd47e5867d357,atlas/tables.py,,col_split,#Any#Any#Any#,48
Before Change
indexes = list()
new_values = list()
df = df.dropna(subset=[column])
for i, presplit in enumerate(df[column].astype(str)):
for value in presplit.split(sep):
indexes.append(i)
new_values.append(value)
new_df = df.iloc[indexes, :].copy()
new_df[column] = new_values
return new_df
After Change
col_series = []
for c in cols:
col_series.append(df[c].str.split(sep, expand=True).stack().str.strip().reset_index(level=1, drop=True))
temp_df = pd.concat(col_series, axis=1, keys=cols)
return df.drop(cols, axis=1).join(temp_df).reset_index(drop=True)
def get_split_cols(df, values):
In pattern: SUPERPATTERN
Frequency: 3
Non-data size: 6
Instances
Project Name: metagenome-atlas/atlas
Commit Name: 3ab0e54a3ce88c7018a34192461dd47e5867d357
Time: 2017-01-28
Author: joe.brown@pnnl.gov
File Name: atlas/tables.py
Class Name:
Method Name: col_split
Project Name: etal/cnvkit
Commit Name: ec576f6724639d899e39664558c2cf0ddd052449
Time: 2015-11-18
Author: eric.talevich@gmail.com
File Name: cnvlib/export.py
Class Name:
Method Name: fmt_cdt
Project Name: dpressel/mead-baseline
Commit Name: 78eba7b3f82b8420deac3cd28318dbfead0f9b9e
Time: 2018-10-30
Author: dpressel@gmail.com
File Name: python/baseline/dy/seq2seq/model.py
Class Name: Seq2SeqModel
Method Name: decode