numba module for speed up.On big datasets (500k >) pd.cut can be quite slow for binning data.
I wrote my own function in numba with just in time compilation, which is roughly 16x faster:
from numba import njit
@njit
def cut(arr):
bins = np.empty(arr.shape[0])
for idx, x in enumerate(arr):
if (x >= 0) & (x < 1):
bins[idx] = 1
elif (x >= 1) & (x < 5):
bins[idx] = 2
elif (x >= 5) & (x < 10):
bins[idx] = 3
elif (x >= 10) & (x < 25):
bins[idx] = 4
elif (x >= 25) & (x < 50):
bins[idx] = 5
elif (x >= 50) & (x < 100):
bins[idx] = 6
else:
bins[idx] = 7
return bins
cut(df['percentage'].to_numpy())
# array([5., 5., 7., 5.])
Optional: you can also map it to bins as strings:
a = cut(df['percentage'].to_numpy())
conversion_dict = {1: 'bin1',
2: 'bin2',
3: 'bin3',
4: 'bin4',
5: 'bin5',
6: 'bin6',
7: 'bin7'}
bins = list(map(conversion_dict.get, a))
# ['bin5', 'bin5', 'bin7', 'bin5']
Speed comparison:
# create dataframe of 8 million rows for testing
dfbig = pd.concat([df]*2000000, ignore_index=True)
dfbig.shape
# (8000000, 1)
%%timeit
cut(dfbig['percentage'].to_numpy())
# 38 ms ± 616 µs per loop (mean ± std. dev. of 7 runs, 10 loops each)
%%timeit
bins = [0, 1, 5, 10, 25, 50, 100]
labels = [1,2,3,4,5,6]
pd.cut(dfbig['percentage'], bins=bins, labels=labels)
# 215 ms ± 9.76 ms per loop (mean ± std. dev. of 7 runs, 10 loops each)