用一些虚拟数据来看这个。基于@MRocklin 的答案(并在我的特定用例之后进行更多建模),假设您的向量实际上是整数列表而不是浮点数,并且列表存储为字符串。我们获取序列,对其进行转换,并将其存储在一个 zarr 数组文件中。
# create dummy data
vectors = [ np.random.randint(low=0,high=100,size=300).tolist() for _ in range(1000) ]
df = pd.DataFrame()
df['vector'] = vectors
df['vector'] = df['vector'].map(lambda x:f"{x}")
df['foo'] = 'bar'
ddf = dd.from_pandas( df, npartitions=100 )
# transform series data to numpy array
def convert_series_to_array( series ): # make this as fast as you can
series_ = [ast.literal_eval( i ) for i in series]
return np.stack(series_, axis=0)
L = ddf['vector'].to_delayed()
L = [delayed(convert_series_to_array)(x) for x in L]
arrays = [da.from_delayed(x, shape=(np.nan, 300), dtype=np.int64) for x in L]
x = da.concatenate(arrays, axis=0)
# store result into a zarr array
x.compute_chunk_sizes().to_zarr( 'toy_dataset.zarr', '/home/user/Documents/', overwrite=True )