使用 dataframe 中的数据将随机数添加到 dask dataframe 以设置限制

Question

I would like to add random numbers to a dask dataframe that uses a column intensity of the original dataframe to set the limits of the random numbers for each row. The code works with pandas and numpy.random , but not with dask and dask.array .

import dask.array as da
import dask.dataframe as dd
from dask.distributed import Client
client = Client()

fns = [list-of-filenames]

df = dd.read_parquet(fns)

# dataframe has a column called intensity of type float
# and no missing values

df['separation_dimension_1'] = da.random.uniform(size=N, low=-noise_level/df.intensity, high=noise_level/df.intensity)

The error is:

ValueError: shape mismatch: objects cannot be broadcast to a single shape.  Mismatch is between arg 0 with shape (0,) and arg 1 with shape (33276691,).

Seems the syntax of numpy.random.uniform is a bit different than dask_array.random.uniform?

Full traceback

Cell In[21], line 7
      5 df['mz_'] = df.mz * 1000000000
      6 df['rt_'] = df.scan_time*10
----> 7 df['separation_dimension_1'] = da.random.uniform(size=N, low=-noise_level/df.intensity, high=noise_level/df.intensity)
      8 #df['separation_dimension_2'] = da.random.uniform(size=N, low=-noise_level/df.intensity, high=noise_level/df.intensity)
      9 #df['separation_dimension_3'] = da.random.uniform(size=N, low=-noise_level/df.intensity, high=noise_level/df.intensity)
     11 df = df[df.intensity > 1e5][['rt_', 'mz_', 'logint']]

File ~/miniconda3/envs/dask/lib/python3.9/site-packages/dask/array/random.py:465, in _make_api.<locals>.wrapper(*args, **kwargs)
    462 if backend not in _cached_random_states:
    463     # Cache the default RandomState object for this backend
    464     _cached_random_states[backend] = RandomState()
--> 465 return getattr(
    466     _cached_random_states[backend],
    467     attr,
    468 )(*args, **kwargs)

File ~/miniconda3/envs/dask/lib/python3.9/site-packages/dask/array/random.py:423, in RandomState.uniform(self, low, high, size, chunks, **kwargs)
    421 @derived_from(np.random.RandomState, skipblocks=1)
    422 def uniform(self, low=0.0, high=1.0, size=None, chunks="auto", **kwargs):
--> 423     return self._wrap("uniform", low, high, size=size, chunks=chunks, **kwargs)

File ~/miniconda3/envs/dask/lib/python3.9/site-packages/dask/array/random.py:170, in RandomState._wrap(self, funcname, size, chunks, extra_chunks, *args, **kwargs)
    165                 kwrg[k] = (getitem, lookup[k], slc)
    166     vals.append(
    167         (_apply_random, self._RandomState, funcname, seed, size, arg, kwrg)
    168     )
--> 170 meta = _apply_random(
    171     self._RandomState,
    172     funcname,
    173     seed,
    174     (0,) * len(size),
    175     small_args,
    176     small_kwargs,
    177 )
    179 dsk.update(dict(zip(keys, vals)))
    181 graph = HighLevelGraph.from_collections(name, dsk, dependencies=dependencies)

File ~/miniconda3/envs/dask/lib/python3.9/site-packages/dask/array/random.py:453, in _apply_random(RandomState, funcname, state_data, size, args, kwargs)
    451 state = RandomState(state_data)
    452 func = getattr(state, funcname)
--> 453 return func(*args, size=size, **kwargs)

File mtrand.pyx:1134, in numpy.random.mtrand.RandomState.uniform()

File _common.pyx:600, in numpy.random._common.cont()

File _common.pyx:517, in numpy.random._common.cont_broadcast_2()

File __init__.pxd:741, in numpy.PyArray_MultiIterNew3()

ValueError: shape mismatch: objects cannot be broadcast to a single shape.  Mismatch is between arg 0 with shape (0,) and arg 1 with shape (6249365,).

Answer 1

As is often the case, you will be able to do this using map_partitions, which applies the operation you are after on each component real pandas dataframe

def op(df):
    df['separation_dimension_1'] = np.random.uniform(size=N, low=-noise_level/df.intensity, high=noise_level/df.intensity)
    return df

df2 = df.map_partitions(op)