更改数据帧列类型的简单方法,但对错误使用默认值?

选项1

pd.to_numeric(a, 'coerce').fillna(0).astype(int)

b = pd.to_numeric(a, 'coerce')
b.mask(b.isnull(), 0).astype(int)

选项3

def try_int(x):
    try:
        return int(x)
    except:
        return 0

a.apply(try_int)

选项4

b = np.empty(a.shape, dtype=int)

i = np.core.defchararray.isdigit(a.values.astype(str))

b[i] = a[i].astype(int)
b[~i] = 0

pd.Series(b, a.index)

所有产品

0    0
1    1
2    5
3    1
4    0
5    3
6    0
7    2
dtype: int64

代码如下

def pir1(a):
    return pd.to_numeric(a, 'coerce').fillna(0).astype(int)

def pir2(a):
    b = pd.to_numeric(a, 'coerce')
    return b.mask(b.isnull(), 0).astype(int)

def try_int(x):
    try:
        return int(x)
    except:
        return 0

def pir3(a):
    return a.apply(try_int)

def pir4(a):
    b = np.empty(a.shape, dtype=int)

    i = np.core.defchararray.isdigit(a.values.astype(str))

    b[i] = a[i].astype(int)
    b[~i] = 0
    return pd.Series(b, a.index)


def alt1(a):
    return pd.to_numeric(a.where(a.str.isnumeric(), 0))

results = pd.DataFrame(
    index=[1, 3, 10, 30, 100, 300, 1000, 3000, 10000],
    columns='pir1 pir2 pir3 pir4 alt1'.split()
)

for i in results.index:
    c = pd.concat([a] * i, ignore_index=True)
    for j in results.columns:
        stmt = '{}(c)'.format(j)
        setp = 'from __main__ import c, {}'.format(j)
        results.set_value(i, j, timeit(stmt, setp, number=10))

results.plot(logx=True, logy=True)

a.where(a.str.isnumeric(),0).astype(int)

输出:

0    0
1    1
2    5
3    1
4    0
5    3
6    0
7    2
dtype: int64