def summary_ccr(ht_ccr: hl.Table,
file_output: str,
ccr_pct_start: int = 0,
ccr_pct_end: int = 100,
ccr_pct_bins: int = 10,
cumulative_histogram: bool = False,
ccr_pct_cutoffs=None) -> None:
"""
Summarize Coding Constrain Region information (as histogram) per gene.
:param ht_ccr: CCR Hail table
:param file_output: File output path
:param ccr_pct_start: Start of histogram range.
:param ccr_pct_end: End of histogram range
:param ccr_pct_bins: Number of bins
:param cumulative_histogram: Generate a cumulative histogram (rather than to use bins)
:param ccr_pct_cutoffs: Cut-offs used to generate the cumulative histogram
:return: None
"""
if ccr_pct_cutoffs is None:
ccr_pct_cutoffs = [90, 95, 99]
if cumulative_histogram:
# generate cumulative counts histogram
summary_tb = (ht_ccr
.group_by('gene')
.aggregate(**{'ccr_above_' + str(ccr_pct_cutoffs[k]): agg.filter(ht_ccr.ccr_pct >=
ccr_pct_cutoffs[k], agg.count())
for k in range(0, len(ccr_pct_cutoffs))})
)
else:
summary_tb = (ht_ccr
.group_by('gene')
.aggregate(ccr_bins=agg.hist(ht_ccr.ccr_pct, ccr_pct_start, ccr_pct_end, ccr_pct_bins))
)
# get bin edges as list (expected n_bins + 1)
bin_edges = summary_tb.aggregate(agg.take(summary_tb.ccr_bins.bin_edges, 1))[0]
# unpack array structure and annotate as individual fields
summary_tb = (summary_tb
.annotate(**{'ccr_bin_' + str(bin_edges[k]) + '_' + str(bin_edges[k + 1]):
summary_tb.ccr_bins.bin_freq[k] for k in range(0, len(bin_edges) - 1)})
.flatten()
)
# drop fields
fields_to_drop = ['ccr_bins.bin_edges', 'ccr_bins.bin_freq']
summary_tb = (summary_tb
.drop(*fields_to_drop)
)
# Export summarized table
(summary_tb
.export(output=file_output)
)
def histogram(data, range=None, bins=50, legend=None, title=None):
"""Create a histogram.
Parameters
----------
data : :class:`.Struct` or :class:`.Float64Expression`
Sequence of data to plot.
range : Tuple[float]
Range of x values in the histogram.
bins : int
Number of bins in the histogram.
legend : str
Label of data on the x-axis.
title : str
Title of the histogram.
Returns
-------
:class:`bokeh.plotting.figure.Figure`
"""
if isinstance(data, Expression):
if data._indices.source is not None:
agg_f = data._aggregation_method()
if range is not None:
start = range[0]
end = range[1]
else:
finite_data = hail.bind(lambda x: hail.case().when(hail.is_finite(x), x).or_missing(), data)
start, end = agg_f((aggregators.min(finite_data),
aggregators.max(finite_data)))
if start is None and end is None:
raise ValueError(f"'data' contains no values that are defined and finite")
data = agg_f(aggregators.hist(data, start, end, bins))
else:
return ValueError('Invalid input')
p = figure(title=title, x_axis_label=legend, y_axis_label='Frequency', background_fill_color='#EEEEEE')
p.quad(
bottom=0, top=data.bin_freq,
left=data.bin_edges[:-1], right=data.bin_edges[1:],
legend=legend, line_color='black')
if data.n_larger > 0:
p.quad(
bottom=0, top=data.n_larger,
left=data.bin_edges[-1], right=(data.bin_edges[-1] + (data.bin_edges[1] - data.bin_edges[0])),
line_color='black', fill_color='green', legend='Outliers Above')
if data.n_smaller > 0:
p.quad(
bottom=0, top=data.n_smaller,
left=data.bin_edges[0] - (data.bin_edges[1] - data.bin_edges[0]), right=data.bin_edges[0],
line_color='black', fill_color='red', legend='Outliers Below')
return p
def cumulative_histogram(data, range=None, bins=50, legend=None, title=None, normalize=True, log=False):
"""Create a cumulative histogram.
Parameters
----------
data : :class:`.Struct` or :class:`.Float64Expression`
Sequence of data to plot.
range : Tuple[float]
Range of x values in the histogram.
bins : int
Number of bins in the histogram.
legend : str
Label of data on the x-axis.
title : str
Title of the histogram.
normalize: bool
Whether or not the cumulative data should be normalized.
log: bool
Whether or not the y-axis should be of type log.
Returns
-------
:class:`bokeh.plotting.figure.Figure`
"""
if isinstance(data, Expression):
if data._indices.source is not None:
agg_f = data._aggregation_method()
if range is not None:
start = range[0]
end = range[1]
else:
start, end = agg_f((aggregators.min(data), aggregators.max(data)))
data = agg_f(aggregators.hist(data, start, end, bins))
else:
return ValueError('Invalid input')
cumulative_data = np.cumsum(data.bin_freq) + data.n_smaller
np.append(cumulative_data, [cumulative_data[-1] + data.n_larger])
num_data_points = max(cumulative_data)
if normalize:
cumulative_data = cumulative_data / num_data_points
if title is not None:
title = f'{title} ({num_data_points:,} data points)'
if log:
p = figure(title=title, x_axis_label=legend, y_axis_label='Frequency',
background_fill_color='#EEEEEE', y_axis_type='log')
else:
p = figure(title=title, x_axis_label=legend, y_axis_label='Frequency', background_fill_color='#EEEEEE')
p.line(data.bin_edges[:-1], cumulative_data, line_color='#036564', line_width=3)
return p
def cumulative_histogram(data, range=None, bins=50, legend=None, title=None, normalize=True, log=False):
"""Create a cumulative histogram.
Parameters
----------
data : :class:`.Struct` or :class:`.Float64Expression`
Sequence of data to plot.
range : Tuple[float]
Range of x values in the histogram.
bins : int
Number of bins in the histogram.
legend : str
Label of data on the x-axis.
title : str
Title of the histogram.
normalize: bool
Whether or not the cumulative data should be normalized.
log: bool
Whether or not the y-axis should be of type log.
Returns
-------
:class:`bokeh.plotting.figure.Figure`
"""
if isinstance(data, Expression):
if data._indices.source is not None:
agg_f = data._aggregation_method()
if range is not None:
start = range[0]
end = range[1]
else:
start, end = agg_f((aggregators.min(data), aggregators.max(data)))
data = agg_f(aggregators.hist(data, start, end, bins))
else:
return ValueError('Invalid input')
cumulative_data = np.cumsum(data.bin_freq) + data.n_smaller
np.append(cumulative_data, [cumulative_data[-1] + data.n_larger])
num_data_points = max(cumulative_data)
if normalize:
cumulative_data = cumulative_data / num_data_points
if title is not None:
title = f'{title} ({num_data_points:,} data points)'
if log:
p = figure(title=title, x_axis_label=legend, y_axis_label='Frequency',
background_fill_color='#EEEEEE', y_axis_type='log')
else:
p = figure(title=title, x_axis_label=legend, y_axis_label='Frequency', background_fill_color='#EEEEEE')
p.line(data.bin_edges[:-1], cumulative_data, line_color='#036564', line_width=3)
return p
def histogram(data, range=None, bins=50, legend=None, title=None, log=False, interactive=False):
"""Create a histogram.
Notes
-----
`data` can be a :class:`.Float64Expression`, or the result of the :func:`.agg.hist`
or :func:`.agg.approx_cdf` aggregators.
Parameters
----------
data : :class:`.Struct` or :class:`.Float64Expression`
Sequence of data to plot.
range : Tuple[float]
Range of x values in the histogram.
bins : int
Number of bins in the histogram.
legend : str
Label of data on the x-axis.
title : str
Title of the histogram.
log : bool
Plot the log10 of the bin counts.
Returns
-------
:class:`bokeh.plotting.figure.Figure`
"""
if isinstance(data, Expression):
if data._indices.source is not None:
if interactive:
raise ValueError("'interactive' flag can only be used on data from 'approx_cdf'.")
agg_f = data._aggregation_method()
if range is not None:
start = range[0]
end = range[1]
else:
finite_data = hail.bind(lambda x: hail.case().when(hail.is_finite(x), x).or_missing(), data)
start, end = agg_f((aggregators.min(finite_data),
aggregators.max(finite_data)))
if start is None and end is None:
raise ValueError(f"'data' contains no values that are defined and finite")
data = agg_f(aggregators.hist(data, start, end, bins))
else:
return ValueError('Invalid input')
elif 'values' in data:
cdf = data
hist, edges = np.histogram(cdf.values, bins=bins, weights=np.diff(cdf.ranks), density=True)
data = Struct(bin_freq=hist, bin_edges=edges, n_larger=0, n_smaller=0)
if log:
data.bin_freq = [log10(x) for x in data.bin_freq]
data.n_larger = log10(data.n_larger)
data.n_smaller = log10(data.n_smaller)
y_axis_label = 'log10 Frequency'
else:
y_axis_label = 'Frequency'
x_span = data.bin_edges[-1] - data.bin_edges[0]
x_start = data.bin_edges[0] - .05 * x_span
x_end = data.bin_edges[-1] + .05 * x_span
p = figure(
title=title,
x_axis_label=legend,
y_axis_label=y_axis_label,
background_fill_color='#EEEEEE',
x_range=(x_start, x_end))
q = p.quad(
bottom=0, top=data.bin_freq,
left=data.bin_edges[:-1], right=data.bin_edges[1:],
legend=legend, line_color='black')
if data.n_larger > 0:
p.quad(
bottom=0, top=data.n_larger,
left=data.bin_edges[-1], right=(data.bin_edges[-1] + (data.bin_edges[1] - data.bin_edges[0])),
line_color='black', fill_color='green', legend='Outliers Above')
if data.n_smaller > 0:
p.quad(
bottom=0, top=data.n_smaller,
left=data.bin_edges[0] - (data.bin_edges[1] - data.bin_edges[0]), right=data.bin_edges[0],
line_color='black', fill_color='red', legend='Outliers Below')
if interactive:
def mk_interact(handle):
def update(bins=bins, phase=0):
if phase > 0 and phase < 1:
bins = bins + 1
delta = (cdf.values[-1] - cdf.values[0]) / bins
edges = np.linspace(cdf.values[0] - (1 - phase) * delta, cdf.values[-1] + phase * delta, bins)
else:
edges = np.linspace(cdf.values[0], cdf.values[-1], bins)
hist, edges = np.histogram(cdf.values, bins=edges, weights=np.diff(cdf.ranks), density=True)
new_data = {'top': hist, 'left': edges[:-1], 'right': edges[1:], 'bottom': np.full(len(hist), 0)}
q.data_source.data = new_data
bokeh.io.push_notebook(handle)
from ipywidgets import interact
interact(update, bins=(0, 5*bins), phase=(0, 1, .01))
return p, mk_interact
else:
return p
def histogram(data, range=None, bins=50, legend=None, title=None, log=False, interactive=False):
"""Create a histogram.
Notes
-----
`data` can be a :class:`.Float64Expression`, or the result of the :func:`.agg.hist`
or :func:`.agg.approx_cdf` aggregators.
Parameters
----------
data : :class:`.Struct` or :class:`.Float64Expression`
Sequence of data to plot.
range : Tuple[float]
Range of x values in the histogram.
bins : int
Number of bins in the histogram.
legend : str
Label of data on the x-axis.
title : str
Title of the histogram.
log : bool
Plot the log10 of the bin counts.
Returns
-------
:class:`bokeh.plotting.figure.Figure`
"""
if isinstance(data, Expression):
if data._indices.source is not None:
if interactive:
raise ValueError("'interactive' flag can only be used on data from 'approx_cdf'.")
agg_f = data._aggregation_method()
if range is not None:
start = range[0]
end = range[1]
else:
finite_data = hail.bind(lambda x: hail.case().when(hail.is_finite(x), x).or_missing(), data)
start, end = agg_f((aggregators.min(finite_data),
aggregators.max(finite_data)))
if start is None and end is None:
raise ValueError(f"'data' contains no values that are defined and finite")
data = agg_f(aggregators.hist(data, start, end, bins))
else:
return ValueError('Invalid input')
elif 'values' in data:
cdf = data
hist, edges = np.histogram(cdf.values, bins=bins, weights=np.diff(cdf.ranks), density=True)
data = Struct(bin_freq=hist, bin_edges=edges, n_larger=0, n_smaller=0)
if log:
data.bin_freq = [log10(x) for x in data.bin_freq]
data.n_larger = log10(data.n_larger)
data.n_smaller = log10(data.n_smaller)
y_axis_label = 'log10 Frequency'
else:
y_axis_label = 'Frequency'
x_span = data.bin_edges[-1] - data.bin_edges[0]
x_start = data.bin_edges[0] - .05 * x_span
x_end = data.bin_edges[-1] + .05 * x_span
p = figure(
title=title,
x_axis_label=legend,
y_axis_label=y_axis_label,
background_fill_color='#EEEEEE',
x_range=(x_start, x_end))
q = p.quad(
bottom=0, top=data.bin_freq,
left=data.bin_edges[:-1], right=data.bin_edges[1:],
legend=legend, line_color='black')
if data.n_larger > 0:
p.quad(
bottom=0, top=data.n_larger,
left=data.bin_edges[-1], right=(data.bin_edges[-1] + (data.bin_edges[1] - data.bin_edges[0])),
line_color='black', fill_color='green', legend='Outliers Above')
if data.n_smaller > 0:
p.quad(
bottom=0, top=data.n_smaller,
left=data.bin_edges[0] - (data.bin_edges[1] - data.bin_edges[0]), right=data.bin_edges[0],
line_color='black', fill_color='red', legend='Outliers Below')
if interactive:
def mk_interact(handle):
def update(bins=bins, phase=0):
if phase > 0 and phase < 1:
bins = bins + 1
delta = (cdf.values[-1] - cdf.values[0]) / bins
edges = np.linspace(cdf.values[0] - (1 - phase) * delta, cdf.values[-1] + phase * delta, bins)
else:
edges = np.linspace(cdf.values[0], cdf.values[-1], bins)
hist, edges = np.histogram(cdf.values, bins=edges, weights=np.diff(cdf.ranks), density=True)
new_data = {'top': hist, 'left': edges[:-1], 'right': edges[1:], 'bottom': np.full(len(hist), 0)}
q.data_source.data = new_data
bokeh.io.push_notebook(handle)
from ipywidgets import interact
interact(update, bins=(0, 5*bins), phase=(0, 1, .01))
return p, mk_interact
else:
return p
