def histogram(
arr: da.Array,
bins: Optional[int] = None,
return_edges: bool = True,
range: Optional[Tuple[int, int]] = None, # pylint: disable=redefined-builtin
dtype: Optional[DTypeDef] = None,
) -> Tuple[da.Array, ...]:
"""Calculate "histogram" for both numerical and categorical."""
if len(arr.shape) != 1:
raise ValueError("Histogram only supports 1-d array.")
if is_dtype(detect_dtype(arr, dtype), Continuous()):
if range is not None:
minimum, maximum = range
else:
minimum, maximum = arr.min(axis=0), arr.max(axis=0)
if bins is None:
raise ValueError(
"num_bins cannot be None if calculating numerical histograms.")
counts, edges = da.histogram(arr, bins, range=[minimum, maximum])
centers = (edges[:-1] + edges[1:]) / 2
if not return_edges:
return counts, centers
return counts, centers, edges
elif is_dtype(detect_dtype(arr, dtype), Nominal()):
# Dask array's unique is way slower than the values_counts on Series
# See https://github.com/dask/dask/issues/2851
# centers, counts = da.unique(arr, return_counts=True)
srs = dd.from_dask_array(arr)
value_counts = srs.value_counts()
counts = value_counts.to_dask_array()
centers = value_counts.index.to_dask_array()
return (counts, centers)
else:
raise ValueError(f"Unsupported dtype {arr.dtype}")
def calc_hist_kde(
data: da.Array, bins: int,
bandwidth: float) -> Tuple[pd.DataFrame, np.ndarray, np.ndarray]:
"""
Calculate a density histogram and its corresponding kernel density
estimate over a given series. The kernel is guassian.
Parameters
----------
data: da.Array
one numerical column over which to compute the histogram and kde
bins : int
number of bins to use in the histogram
bandwidth: float
bandwidth for the kde
Returns
-------
Tuple[pd.DataFrame, np.ndarray, np.ndarray]
The histogram in a dataframe, range of points for the kde,
and the kde calculated at the specified points
"""
minv, maxv = dask.compute(data.min(), data.max())
hist_arr, bins_arr = da.histogram(data,
range=[minv, maxv],
bins=bins,
density=True)
hist_arr = hist_arr.compute()
intervals = _format_bin_intervals(bins_arr)
hist_df = pd.DataFrame({
"intervals": intervals,
"left": bins_arr[:-1],
"right": bins_arr[1:],
"freq": hist_arr,
})
pts_rng = np.linspace(minv, maxv, 1000)
pdf = gaussian_kde(data.compute(), bw_method=bandwidth)(pts_rng)
return hist_df, pts_rng, pdf