def t_histogram1d_impl(self, **kw: Any) -> None:
s = self.scheduler()
csv = CSVLoader(
get_dataset("bigfile"), index_col=False, header=None, scheduler=s
)
stirrer = Stirrer(update_column="_2", fixed_step_size=1000, scheduler=s, **kw)
stirrer.input[0] = csv.output.result
min_ = Min(scheduler=s)
min_.input[0] = stirrer.output.result
max_ = Max(scheduler=s)
max_.input[0] = stirrer.output.result
histogram1d = Histogram1D("_2", scheduler=s) # columns are called 1..30
histogram1d.input[0] = stirrer.output.result
histogram1d.input.min = min_.output.result
histogram1d.input.max = max_.output.result
# pr = Print(scheduler=s)
pr = Every(proc=self.terse, scheduler=s)
pr.input[0] = histogram1d.output.result
aio.run(s.start())
_ = histogram1d.trace_stats()
last = notNone(histogram1d.table.last()).to_dict()
h1 = last["array"]
bounds = (last["min"], last["max"])
tab = stirrer.table.loc[:, ["_2"]]
assert tab is not None
v = tab.to_array().reshape(-1)
h2, _ = np.histogram( # type: ignore
v, bins=histogram1d.params.bins, density=False, range=bounds
)
self.assertEqual(np.sum(h1), np.sum(h2))
self.assertListEqual(h1.tolist(), h2.tolist())
def _create_columns(self, columns: List[str], df: Any) -> None:
bins: int = cast(int, self.params.bins)
delta: float = cast(float, self.params.delta) # crude
inp = self.get_input_module("table")
minmod = self.get_input_module("min")
maxmod = self.get_input_module("max")
assert inp and minmod and maxmod
for column in columns:
logger.debug("Creating histogram1d %s", column)
dtype = df[column].dtype
if not np.issubdtype(dtype, numbers.Number):
# only create histograms for number columns
continue
histo = Histogram1D(
group=self.name,
column=column,
bins=bins,
delta=delta,
scheduler=self.scheduler,
)
histo.input.table = inp.output.result
histo.input.min = minmod.output.result
histo.input.max = maxmod.output.result
self.input.table = histo.output._trace # will become table.1 ...
self._histogram[column] = histo
def test_histogram1d1(self) -> None:
s = self.scheduler()
csv = CSVLoader(
get_dataset("bigfile"), index_col=False, header=None, scheduler=s
)
min_ = Min(scheduler=s)
min_.input[0] = csv.output.result
max_ = Max(scheduler=s)
max_.input[0] = csv.output.result
histogram1d = Histogram1D("_2", scheduler=s) # columns are called 1..30
histogram1d.input[0] = csv.output.result
histogram1d.input.min = min_.output.result
histogram1d.input.max = max_.output.result
pr = Every(proc=self.terse, scheduler=s)
pr.input[0] = histogram1d.output.result
aio.run(s.start())
_ = histogram1d.trace_stats()
last = notNone(histogram1d.table.last()).to_dict()
h1 = last["array"]
bounds = (last["min"], last["max"])
df = pd.read_csv(
get_dataset("bigfile"), header=None, usecols=[2] # type: ignore
)
v = df.to_numpy().reshape(-1)
h2, _ = np.histogram( # type: ignore
v, bins=histogram1d.params.bins, density=False, range=bounds
)
self.assertListEqual(h1.tolist(), h2.tolist())
def test_histogram1d(self) -> None:
s = self.scheduler()
csv = CSVLoader(
get_dataset("bigfile"), index_col=False, header=None, scheduler=s
)
min_ = Min(scheduler=s)
min_.input[0] = csv.output.result
max_ = Max(scheduler=s)
max_.input[0] = csv.output.result
histogram1d = Histogram1D("_2", scheduler=s) # columns are called 1..30
histogram1d.input[0] = csv.output.result
histogram1d.input.min = min_.output.result
histogram1d.input.max = max_.output.result
pr = Every(proc=self.terse, scheduler=s)
pr.input[0] = histogram1d.output.result
aio.run(s.start())
_ = histogram1d.trace_stats()
def refresh_info_hist_1d(hout: WidgetType, h1d_mod: Histogram1D, name: str,
tab: "TreeTab") -> None:
if (not tab.is_visible(name)) and h1d_mod.updated_once: # type: ignore
return
if not h1d_mod.table:
return
last = h1d_mod.table.last()
assert last
res = last.to_dict()
hist = res["array"]
min_ = res["min"]
max_ = res["max"]
bins_ = np.linspace(min_, max_, len(hist))
source = pd.DataFrame({
"xvals": bins_,
"nbins": range(len(hist)),
"level": hist
})
hout.children[1].update("data", remove="true", insert=source)
h1d_mod.updated_once = True # type: ignore
def test_histogram1d(self):
s = self.scheduler()
csv = CSVLoader(get_dataset('bigfile'),
index_col=False,
header=None,
scheduler=s)
min_ = Min(scheduler=s)
min_.input.table = csv.output.table
max_ = Max(scheduler=s)
max_.input.table = csv.output.table
histogram1d = Histogram1D('_2',
scheduler=s) # columns are called 1..30
histogram1d.input.table = csv.output.table
histogram1d.input.min = min_.output.table
histogram1d.input.max = max_.output.table
#pr = Print(scheduler=s)
pr = Every(proc=self.terse, scheduler=s)
pr.input.df = csv.output.table
s.start(tick_proc=lambda s, r: csv.is_terminated() and s.stop())
s.join()
s = histogram1d.trace_stats()
def _create_columns(self, columns, df):
bins = self.params.bins
delta = self.params.delta # crude
inp = self.get_input_module('table')
minmod = self.get_input_module('min')
maxmod = self.get_input_module('max')
for column in columns:
#if c==UPDATE_COLUMN:
# continue
logger.debug('Creating histogram1d %s', column)
dtype = df[column].dtype
if not np.issubdtype(dtype, numbers.Number):
# only create histograms for number columns
continue
histo = Histogram1D(group=self.name,
column=column,
bins=bins,
delta=delta,
scheduler=self.scheduler())
histo.input.table = inp.output.table
histo.input.min = minmod.output.table
histo.input.max = maxmod.output.table
self.input.table = histo.output._trace # will become table.1 ...
self._histogram[column] = histo