最佳方法
better_dfs_min = data_frames(index=range_indexes(min_size=better_df_minsize),
columns=[column("Chromosome", chromosomes_small),
column("Start", elements=small_lengths),
column("End", elements=small_lengths),
column("Strand", strands)])
@st.composite()
def dfs_min(draw):
df = draw(better_dfs_min)
df.loc[:, "End"] += df.Start
return df
@given(df=dfs_min())
def test_me(df):
print(df)
assert 0
首次尝试:
from hypothesis.extra.pandas import columns, data_frames, column
import hypothesis.strategies as st
def mysort(tp):
key = [-1, tp[1], tp[2], int(1e10)]
return [x for _, x in sorted(zip(key, tp))]
positions = st.integers(min_value=0, max_value=int(1e7))
strands = st.sampled_from("+ -".split())
chromosomes = st.sampled_from(elements=["chr{}".format(str(e)) for e in list(range(23)) + "X Y M".split()])
data_frames(columns=columns(["Chromosome", "Start", "End", "Strand"], dtype=int), rows=st.tuples(chromosomes, positions, positions, strands).map(mysort)).example()
结果:
Chromosome Start End Strand
0 chr13 5660600 6171569 -
1 chrY 3987154 5435816 +
2 chr11 4659655 4956997 +
3 chr14 239357 8566407 +
4 chr3 3200488 9337489 +
5 chr8 304886 1078020 +
必须有更好的方法来做这件事,而不是实现你自己的分类…我的排序依赖于开始和结束的整数介于0和int(1e10)-1之间,这让人觉得恶心。