python中cut_python – 熊猫如何使用pd.cut()

test['range'] = pd.cut(test.days, [0,30,60], include_lowest=True)

print (test)

days range

0 0 (-0.001, 30.0]

1 31 (30.0, 60.0]

2 45 (30.0, 60.0]

看到差异：

test = pd.DataFrame({'days': [0,20,30,31,45,60]})

test['range1'] = pd.cut(test.days, [0,30,60], include_lowest=True)

#30 value is in [30, 60) group

test['range2'] = pd.cut(test.days, [0,30,60], right=False)

#30 value is in (0, 30] group

test['range3'] = pd.cut(test.days, [0,30,60])

print (test)

days range1 range2 range3

0 0 (-0.001, 30.0] [0, 30) NaN

1 20 (-0.001, 30.0] [0, 30) (0, 30]

2 30 (-0.001, 30.0] [30, 60) (0, 30]

3 31 (30.0, 60.0] [30, 60) (30, 60]

4 45 (30.0, 60.0] [30, 60) (30, 60]

5 60 (30.0, 60.0] NaN (30, 60]

arr = np.array([0,30,60])

test['range1'] = arr.searchsorted(test.days)

test['range2'] = arr.searchsorted(test.days, side='right') - 1

print (test)

days range1 range2

0 0 0 0

1 20 1 0

2 30 1 1

3 31 2 1

4 45 2 1

5 60 2 2