import dask.dataframe as dd
import pandas as pd
# prepare data
data = {
'name': ['Eason', 'Jay', 'JJ', 'Alice', 'yaya'],
'id': [1000, 1001, 1002, 1003, 1004],
'x': [1.9897712, -98.432490, -0.258545, 0.012345, 0.146248],
'y': [1.9897347, -98.902596, -0.254255, 0.012345, 0.145124]
}
# create dask dataframe
df = dd.from_pandas(pd.DataFrame(data), npartitions=1)
def split_x(x):
int_part = x.astype(int)
decimal_part = x - int_part
return pd.DataFrame({'x_int': int_part, 'x_decimal': decimal_part})
df[['int_part', 'decimal_part']] = df['x'].map_partitions(split_x)
df = df.compute()
df
分离float类型整数和小数位
于 2023-08-31 10:02:53 首次发布