A quick way to split a column into multiple rows in Pandas

Question

I have the following data frame:

import pandas as pd
df = pd.DataFrame({ 'gene':["foo",
                            "bar // lal",
                            "qux",
                            "woz"], 'cell1':[5,9,1,7], 'cell2':[12,90,13,87]})
df = df[["gene","cell1","cell2"]]
df

It looks like this:

Out[6]:
         gene  cell1  cell2
0         foo      5     12
1  bar // lal      9     90
2         qux      1     13
3         woz      7     87

What I want to do is split the “gene” column so it looks like this:

         gene  cell1  cell2
         foo      5     12
         bar      9     90
         lal      9     90
         qux      1     13
         woz      7     87

My current approach is this:

import pandas as pd
import timeit

def create():
    df = pd.DataFrame({ 'gene':["foo",
                            "bar // lal",
                            "qux",
                            "woz"], 'cell1':[5,9,1,7], 'cell2':[12,90,13,87]})
    df = df[["gene","cell1","cell2"]]

    s = df["gene"].str.split(' // ').apply(pd.Series,1).stack()
    s.index = s.index.droplevel(-1)
    s.name = "Genes"
    del df["gene"]
    df.join(s)


if __name__ == '__main__':
    print(timeit.timeit("create()", setup="from __main__ import create", number=100))
    # 0.608163118362

It is very slow. In fact, I have about 40 thousand lines for checking and the process.

What is the quick implementation of this?

Answer 1

TBH I think we need a quick built-in way to normalize such elements. Although, since I’m already too in the know, I know that there is one, and I just don’t know this. :-) In the meantime, I used the following methods:

def create(n):
    df = pd.DataFrame({ 'gene':["foo",
                                "bar // lal",
                                "qux",
                                "woz"], 
                        'cell1':[5,9,1,7], 'cell2':[12,90,13,87]})
    df = df[["gene","cell1","cell2"]]
    df = pd.concat([df]*n)
    df = df.reset_index(drop=True)
    return df

def orig(df):
    s = df["gene"].str.split(' // ').apply(pd.Series,1).stack()
    s.index = s.index.droplevel(-1)
    s.name = "Genes"
    del df["gene"]
    return df.join(s)

def faster(df):
    s = df["gene"].str.split(' // ', expand=True).stack()
    i = s.index.get_level_values(0)
    df2 = df.loc[i].copy()
    df2["gene"] = s.values
    return df2

which gives me

>>> df = create(1)
>>> df
         gene  cell1  cell2
0         foo      5     12
1  bar // lal      9     90
2         qux      1     13
3         woz      7     87
>>> %time orig(df.copy())
CPU times: user 12 ms, sys: 0 ns, total: 12 ms
Wall time: 10.2 ms
   cell1  cell2 Genes
0      5     12   foo
1      9     90   bar
1      9     90   lal
2      1     13   qux
3      7     87   woz
>>> %time faster(df.copy())
CPU times: user 16 ms, sys: 0 ns, total: 16 ms
Wall time: 12.4 ms
  gene  cell1  cell2
0  foo      5     12
1  bar      9     90
1  lal      9     90
2  qux      1     13
3  woz      7     87

for comparable speeds at low sizes and

>>> df = create(10000)
>>> %timeit z = orig(df.copy())
1 loops, best of 3: 14.2 s per loop
>>> %timeit z = faster(df.copy())
1 loops, best of 3: 231 ms per loop

60- . , , df.copy() , , orig .