I have a pandas dataframe
in which one column of text strings contains comma-separated values. I want to split each CSV field and create a new row per entry (as
My version of the solution to add to this collection! :-)
# Original problem
from pandas import DataFrame
import numpy as np
a = DataFrame([{'var1': 'a,b,c', 'var2': 1},
{'var1': 'd,e,f', 'var2': 2}])
b = DataFrame([{'var1': 'a', 'var2': 1},
{'var1': 'b', 'var2': 1},
{'var1': 'c', 'var2': 1},
{'var1': 'd', 'var2': 2},
{'var1': 'e', 'var2': 2},
{'var1': 'f', 'var2': 2}])
### My solution
import pandas as pd
import functools
def expand_on_cols(df, fuse_cols, delim=","):
def expand_on_col(df, fuse_col):
col_order = df.columns
df_expanded = pd.DataFrame(
df.set_index([x for x in df.columns if x != fuse_col])[fuse_col]
.apply(lambda x: x.split(delim))
.explode()
).reset_index()
return df_expanded[col_order]
all_expanded = functools.reduce(expand_on_col, fuse_cols, df)
return all_expanded
assert(b.equals(expand_on_cols(a, ["var1"], delim=",")))