def power_pollution():
'''
Input:
This function inputs data from local downloaded csv and xsl files.
Output:
The output data are in pandas dataframe format and do not requires
further process for plotting.
'''
state_p = power[np.logical_and(power['STATE'] != 'US-TOTAL',
power['STATE'] != 'US-Total')]
state_p = state_p[np.logical_and(power['STATE'] != 'DC',
power['STATE'] != 'HI')]
state_p = state_p[power['STATE'] != 'AK']
state_p = state_p[state_p['ENERGY SOURCE'] == 'Total']
state_p_f = state_p.groupby(
['YEAR', 'STATE'])['GENERATION (Megawatthours)'].sum().reset_index()
edata = hv.Dataset(data=state_p_f,
kdims=['YEAR', 'STATE', 'GENERATION (Megawatthours)'])
PM_data = pollution[
pollution['MeasureName'] ==
'Annual average ambient concentrations of PM 2.5 in micrograms per cubic meter, based on seasonal averages and daily measurement (monitor and modeled data)']
PM_data = PM_data[PM_data['StateName'] != 'District of Columbia']
PM_data = PM_data.replace({'StateName': us_state_abbrev})
PM_data_f = PM_data.groupby(['ReportYear',
'StateName'])['Value'].sum().reset_index()
PM_data_f = PM_data_f.rename(
index=str,
columns={'Value': 'Annual average ambient concentrations of PM 2.5'})
edata_PM = hv.Dataset(data=PM_data_f,
kdims=[
'ReportYear', 'StateName',
'Annual average ambient concentrations of PM 2.5'
])
return state_p, state_p_f, PM_data, PM_data_f
def update_hist(self):
hv.extension("matplotlib")
dcrop = (self.da_masked *
self.da_zone.sel(id=self.id_i)).isel(step=self.step)
dcrop.name = self.da.name
var_name = self.da.name
if self.levels:
hv_img = hv.Image(hv.Dataset(dcrop),
kdims=["longitude", "latitude"
]).opts(colorbar=True,
color_levels=self.levels,
cmap=self.colors)
html_map = hv.renderer("matplotlib").html(hv_img)
else:
hv_img = hv.Image(hv.Dataset(dcrop),
kdims=["longitude",
"latitude"]).opts(colorbar=True,
color_levels=30)
html_map = hv.renderer("matplotlib").html(hv_img)
# Si besoin de specifier le range : hv_img.redim.__getattribute__("range")(**{var_name:(self.vmin,self.vmax)}))
dstack = dcrop.stack(z=("latitude", "longitude")).reset_index("z")
dstack["z"] = range(len(dstack.z))
dstack.name = self.da.name
hv_dst = hv.Dataset(dstack)
k = histogram(hv_dst, dynamic=True, name="Test")
html = ''' <h4> Histogramme sur {} </h4> de {}'''.format(
self.hist_name, self.variable)
self.html2.value = html + hv.renderer("matplotlib").html(k) + html_map
def _update_filter(self):
print('update_filter:',self.select_file.value,self.ds.isel(time_slice=self.time_slice_deep_slider.value).amplitude.values.shape,self.filter_.shape)
if self.selection.selection_expr is not None:
hvds = hv.Dataset(
(
np.linspace(-0.5, 0.5, self.filter_.shape[1]),
np.linspace(-0.5, 0.5, self.filter_.shape[0]),
np.zeros(self.filter_.shape),
),
["x", "y"],
"val",
)
hvds = hv.Dataset(hvds.dframe())
hvds.data["val"].loc[
hvds.select(self.selection.selection_expr).data.index
] = 1
data = hvds["val"].reshape(self.filter_.shape).copy().T[::-1]
gauss_kernel = utils.scipy_gaussian_2D(int(self.filter_.shape[1]/40))
filter00 = signal.fftconvolve(data, gauss_kernel, mode="same")
filter00 = utils.normalise(filter00)
self.filter_ = self.filter_ + filter00
filter_ = hv.Image(self.filter_, group="filter")
return filter_
def show(ds):
if ds.data.trace.iloc[-1] == 0:
ds = hv.Dataset([[.01, 0, 0], [0, 0, .01]],
kdims=['x', 'sample'],
vdims=['y'])
else:
ds = hv.Dataset(ds.data.set_index(['trace', 'sample',
'variable']).value.unstack(),
kdims=['x', 'sample'],
vdims=['y'])
return ds.to(hv.Path, kdims=['x', 'y'], vdims=[]).overlay()
def investigateOptimalAlgorithms(kmerId, kmerCount):
plot.setLibrary('bokeh')
plots = {}
params = {'n_components':N_PCA_COMPONENTS, 'random_state':42}
algos = (
('PCA', decomposition.PCA(**params)),
('LLE', manifold.LocallyLinearEmbedding(method='standard', **params)),
('LTSA', manifold.LocallyLinearEmbedding(method='ltsa', **params)),
('Hessian LLE', manifold.LocallyLinearEmbedding(method='hessian',
n_neighbors=10, **params)),
('Modified LLE', manifold.LocallyLinearEmbedding(method='modified',
**params)),
('tSNE', manifold.TSNE(**params)),
('Isomap', manifold.Isomap(n_components=N_PCA_COMPONENTS)),
('MDS', manifold.MDS(**params)),
('SE', manifold.SpectralEmbedding(**params)))
## Visualise data and manually determine which algorithm will be good
for i, (name, algo) in enumerate(algos, 1):
com = _getComponents(algo, kmerCount)
com = pd.DataFrame(com, columns=PCA_DATA_COL_NAMES)
kmerDf = pd.concat([kmerId, com], axis=1)
dataset = hv.Dataset(kmerDf, PCA_DATA_COL_NAMES)
scatter = dataset.to(hv.Scatter, PCA_DATA_COL_NAMES)
scatter.opts(opts.Scatter(size=10, show_legend=True))
plots[name] = scatter
plots = hv.HoloMap(plots, kdims='algo')
plots = plots.collate()
return plots
def distribution(df, feature, date, num_buck=10, date_freq='Q'):
"""
Строит график распределения признака во времени
Parameters
----------
df: Объект pandas.DataFrame
feature: Название признака числового или категориального
date: Наименование временной переменной
num_buck: Количество бакетов, если признак числовой
date_freq: Частота агрегации времени
"""
agg = df.pipe(make_bucket, feature, num_buck)\
.assign(obj_cnt=1)\
.groupby([pd.Grouper(key=date, freq=date_freq), 'bucket'])\
.agg({'obj_cnt': sum})\
.reset_index()\
.assign(obj_total=lambda x: (x.groupby([pd.Grouper(key=date,
freq=date_freq)])['obj_cnt'].transform('sum')))\
.assign(obj_rate=lambda x: x.obj_cnt / x.obj_total)\
.reset_index()\
.assign(objects_rate=lambda x:
x.groupby(date).apply(
lambda y: y.obj_rate.cumsum().to_frame())
.reset_index(drop=True))\
.assign(obj_rate_u=0, obj_rate_b=lambda x: x['obj_rate'])
data = hv.Dataset(agg,
kdims=['bucket', date],
vdims=['objects_rate', 'obj_rate_b', 'obj_rate_u'])
return data.to.spread(kdims=[date],
vdims=['objects_rate', 'obj_rate_b', 'obj_rate_u'],
group='Objects rate',
label=feature).overlay('bucket')
def __post_init__(self):
"""
:return:
"""
data = self.spectral_cube.data
self.ds = hv.Dataset((np.arange(data.shape[2]), np.arange(
data.shape[1]), np.arange(data.shape[0]), data),
[self.spectral_axis_name, 'x', 'y'], 'Cube')
# maybe PolyEdit as well
# polys = hv.Polygons([hv.Box(int(self.image_width / 2), int(self.image_height / 2), int(self.image_height / 2))])
# self.box_stream = streams.PolyEdit(source=polys)
polys = hv.Polygons([])
self.box_stream = streams.BoxEdit(source=polys)
hlines = hv.HoloMap({i: hv.VLine(i)
for i in range(data.shape[2])}, 'wavelengths')
dmap = hv.DynamicMap(self.roi_curves, streams=[self.box_stream])
im = self.ds.to(hv.Image, ['x', 'y'], dynamic=True)
self.layout = (im * polys + dmap * hlines).opts(
opts.Image(cmap=self.color_map,
width=self.image_width,
height=self.image_height),
opts.Curve(width=650, height=450, framewise=True),
opts.Polygons(fill_alpha=0.2, line_color='white'),
opts.VLine(color='black'))
def plot(self, category_name: str) -> hv.Layout:
"""Plot the titration curve as a function of pH.
Parameters
----------
category
"""
category_data: Optional[np.ndarray] = None
if category_name == 'population':
category_data = self.populations
elif category_name == 'free_energy':
category_data = self.free_energies
else:
raise ValueError(
"Pick population or free_energy as category names.")
data_series = dict(pH=self.ph_values)
state_vars = []
for s, state in enumerate(category_data):
if self._state_ids is None:
state_var = "{}".format(s + 1)
else:
state_var = self._state_ids[s]
data_series[state_var] = state
state_vars.append(state_var)
df = pd.DataFrame.from_dict(data_series)
df_pop = df.melt(id_vars=["pH"],
value_vars=state_vars,
var_name="State",
value_name=category_name)
ds_pop = hv.Dataset(df_pop, vdims=category_name)
return ds_pop.to(hv.Curve, 'pH', groupby='State').overlay()
def covid_viewer_v2(ds):
'''
covid viewer, for actives_vs_beds
'''
opts.defaults(
opts.Curve(tools=['hover'], width=800, height = 600, ylabel='')
)
logtog = pn.widgets.Toggle(name='Log (Y-axis)', button_type='default', value=False)
xlim=(np.datetime64('2020-03-01'), np.datetime64('2020-03-25'))
hv_ds = hv.Dataset(ds, ['date', 'place'], ['active_per_beds'])
avb = hv_ds.to(hv.Curve, 'date', 'active_per_beds').overlay('place').opts(
legend_position='top_left', shared_axes=True,
ylim=(0, 0.13),
xlim=xlim, title='Severe Cases per Open Hospital Bed')
avb_log = hv_ds.to(hv.Curve, 'date', 'active_per_beds').overlay('place').opts(
legend_position='top_left', shared_axes=True, logy=True,
ylim=(1e-6, 10),
xlim=xlim, title='Severe Cases per Open Hospital Bed (Log Scale)')
max_line = hv.HLine(1).opts( opts.HLine(color='red', line_width=6),
opts.Points(color='#D3D3D3'))
# layout = (avb_log)
# layout.opts(
# opts.Curve(width=400, height=300, framewise=True))
# pn_layout = pn.pane.HoloViews(layout)
# return pn.Row(logtog, pn_layout)
return avb
def GenDepth(sonar_data, chan_id, regen_cache=False):
normalized_channel = NormalizeChannel(sonar_data,
chan_id,
regen_cache=regen_cache)
hv_ds = holoviews.Dataset(normalized_channel)
img = hv_ds.to(holoviews.Image, kdims=["frame_index", "depth"])
img = img.opts(cmap='viridis', logz=False)
img = img.opts(tools=['hover', 'crosshair'])
channel = sonar_data.sel(channel=chan_id)
depth_data = holoviews.Table((channel.frame_index, channel.water_depth),
'frame_index', 'depth')
depth_curve = holoviews.Curve(depth_data)
depth_curve = depth_curve.opts(line_width=0.5, color='red',
alpha=0.5) #, line_dash='dashed')
depth_curve = depth_curve.opts(tools=['hover', 'crosshair'])
depth_curve = depth_curve.opts(active_tools=['box_zoom'])
# @todo We should consider using the native height instead of 1024 as we will see more detail.
#y_size = len(normalized_channel.depth)
x_size = 1024
y_size = 768
rasterized_img = holoviews.operation.datashader.rasterize(img,
width=x_size,
height=y_size,
precompute=True)
rasterized_img = rasterized_img.opts(invert_yaxis=True)
graph = holoviews.Overlay([rasterized_img, depth_curve])
graph = graph.collate()
return graph
def select_tg(data_dir, tgs, index):
# https://github.com/holoviz/hvplot/issues/180
hover = HoverTool(
tooltips=[("Time", "@Time{%F}"), ("Elevation", "@Elevation")],
formatters={"@Time":
"datetime"}, # use 'datetime' formatter for '@date' field
)
if not index:
name = ""
df = pd.DataFrame({"Time": [], "Elevation": []})
df = df.hvplot("Time",
"Elevation",
color="green",
width=833,
height=250,
padding=0.1)
else:
name = tgs.data.iloc[index[0]].Name
df = get_station_dataframe(data_dir, name)
dataset = hv.Dataset(df)
curve = hv.Curve(dataset, kdims=["Time"], vdims=["Elevation"])
curve = curve.opts(color="green",
width=833,
height=350,
padding=0.1,
framewise=True,
xformatter=DTF,
title=name,
tools=[hover])
return curve
def _flow_to_sankey(self, match, flow):
nodes = []
node_mapping = collections.defaultdict(dict)
spans = {'s': match.doc_span, 't': match.query}
def token(name, i):
idx = node_mapping[name]
k = idx.get(i)
if k is not None:
return k
idx[i] = len(nodes)
nodes.append(' %s [%d] ' % (spans[name][i].text, i))
return idx[i]
edges = [(token('t', t), token('s', s), f)
for t, s, f in flow_edges(flow, self._cutoff)]
if len(edges) < 1:
logging.warning("no edges found")
n = max(len(set(x[0] for x in edges)), len(set(x[1] for x in edges)))
nodes = hv.Dataset(enumerate(nodes), 'index', 'label')
return hv.Sankey((edges, nodes)).opts(width=self._width,
height=n * self._height_per_node,
labels='label',
label_position='inner',
cmap=self._cmap,
node_padding=self._node_padding,
show_values=False)
def investigateOptimalAlgorithms(kmerId, kmerPca):
plot.setLibrary('bokeh')
pca = kmerPca.loc[:, PCA_DATA_COL_NAMES]
plots = {}
algos = (
('Elliptic', EllipticEnvelope()),
('SVM', OneClassSVM()),
('Forest', IsolationForest()),
('Local', LocalOutlierFactor()))
## Visualise data and manually determine which algorithm will be good
for i, (name, algo) in enumerate(algos, 1):
labels = _getLabels(algo, pca)
labels = pd.DataFrame(labels, columns=[OLABEL_COL_NAME])
kmerDf = pd.concat([kmerId, pca, labels], axis=1)
dataset = hv.Dataset(kmerDf, PCA_DATA_COL_NAMES)
scatter = dataset.to(hv.Scatter, PCA_DATA_COL_NAMES, groupby=OLABEL_COL_NAME).overlay()
scatter.opts(opts.Scatter(size=10, show_legend=True))
plots[name] = scatter
plots = hv.HoloMap(plots, kdims='algo')
plots = plots.collate()
return plots
def test_split_flights_raises_AttributeError():
"""This occurs when the input dataframe lacks the time_position column."""
df_in = pd.DataFrame({"latitude": [51.509865], "longitude": [-0.118092]})
df = exp_hdf5.transform_coords(df_in)
dataset = hv.Dataset(df)
with pytest.raises(AttributeError):
exp_hdf5.split_flights(dataset)
def make_sankey_data(data, year_range, number):
'''this function generate the data for the slank chart given
the year and value thresholds'''
# select year range
data_y = year_range_sum(data=data, year_range=(1990, 2016))
# select data over a particular value
data_values = data_y[data_y['value'] > number].reset_index(
drop=True).dropna()
data_values['value'] = np.round(data_values['value'] / 1000)
data_values['value'] = data_values['value'].astype('int')
# this function generates the nodes dataset based on to and from variables
data, nodes = gen_nodes(data=data_values)
data.dropna(inplace=True)
nodes.dropna(inplace=True)
# add in unique identifiers from 0 to len(nodes)
data_edges = add_ids(data=data, nodes=nodes)
# define the edges (connection of the data)
edges = zip_edges(data_edges)
# place nodes in holoviews dataset for plotting
nodes_plot = hv.Dataset(enumerate(nodes['country_name']), 'index', 'label')
# return edges and nodes to plot
return edges, nodes_plot
def slider(self,
data,
kdims=['z', 'x', 'y'],
vdims=['v'],
flat=['x', 'y'],
slider='z',
invert_yaxis=False,
sub_sample=4):
'''Test for interactive display 3D grid with slider.
'''
import holoviews as hv
hv.extension('bokeh', logo=False)
data = self._user_to_array(data)
ds = hv.Dataset((np.arange(
np.shape(data)[2]), np.linspace(
0., 1.,
np.shape(data)[1]), np.linspace(0., 1.,
np.shape(data)[0]), data),
kdims=kdims,
vdims=vdims)
return ds.to(hv.Image, flat).redim(slider).options(
colorbar=True, invert_yaxis=invert_yaxis).hist()
def evaluate(*args, **kwargs):
ds = hv.Dataset(self._obj)
obj = self._transform.apply(ds, keep_index=True, compute=False)
if self._plot:
return Interactive._fig
else:
return obj
def investigateOptimalAlgorithms(kmerId, kmerPca):
plot.setLibrary('bokeh')
pca = kmerPca.loc[:, PCA_DATA_COL_NAMES]
plots = {}
algos = (('KMeans', cluster.KMeans()), ('Affinity',
cluster.AffinityPropagation()),
('MeanShift',
cluster.MeanShift()), ('Spectral', cluster.SpectralClustering()),
('Agglomerative',
cluster.AgglomerativeClustering(linkage='average')),
('Agglomerative',
cluster.AgglomerativeClustering(linkage='ward')),
('DBSCAN', cluster.DBSCAN()), ('Gaussian', GaussianMixture()))
## Visualise data and manually determine which algorithm will be good
for i, (name, algo) in enumerate(algos, 1):
labels = _getLabels(algo, pca)
labels = pd.DataFrame(labels, columns=[CLABEL_COL_NAME])
kmerDf = pd.concat([kmerId, pca, labels], axis=1)
dataset = hv.Dataset(kmerDf, PCA_DATA_COL_NAMES)
scatter = dataset.to(hv.Scatter,
PCA_DATA_COL_NAMES,
groupby=CLABEL_COL_NAME).overlay()
scatter.opts(opts.Scatter(size=10, show_legend=True))
plots[name] = scatter
plots = hv.HoloMap(plots, kdims='algo')
plots = plots.collate()
return plots
def __init__(self,
obj,
transform=None,
plot=False,
depth=0,
loc='top_left',
center=False,
dmap=False,
inherit_kwargs={},
**kwargs):
self._obj = obj
self._method = None
if transform is None:
import xarray as xr
if isinstance(obj, xr.DataArray):
self._transform = hv.dim(obj.name)
else:
self._transform = hv.dim('*')
else:
self._transform = transform
self._plot = plot
self._depth = depth
self._loc = loc
self._center = center
self._dmap = dmap
self._inherit_kwargs = inherit_kwargs
self._kwargs = kwargs
ds = hv.Dataset(self._obj)
self._current = self._transform.apply(ds,
keep_index=True,
compute=False)
def make_spatio_temporal_vel_curve_obj(spatio_temporal_vel_data_tab_df):
kdims = [('starttime', 'Date'), ('station', 'Station')]
vdims = [("e_max", "Velocity Changes (%)")]
emax_avg_ds = hv.Dataset(spatio_temporal_vel_data_tab_df, kdims, vdims)
spatio_temporal_vel_curve_obj = emax_avg_ds.to(hv.Curve, "starttime",
"e_max")
return (spatio_temporal_vel_curve_obj)
def pmt_map(t_0, t_1, array='top', **kwargs):
# Compute the PMT pattern (fast)
ps = points[(t_0 <= points['time']) & (points['time'] < t_1)]
areas = np.bincount(ps['channel'],
weights=ps['area'],
minlength=len(pmt_locs))
# Which PMTs should we include?
pmt_mask = pmt_locs['array'] == array
d = pmt_locs[pmt_mask].copy()
d['area'] = areas[pmt_mask]
# Convert to holoviews points
d = hv.Dataset(d,
kdims=[
hv.Dimension('x',
unit='cm',
range=(-tpc_r * f, tpc_r * f)),
hv.Dimension('y',
unit='cm',
range=(-tpc_r * f, tpc_r * f)),
hv.Dimension('i', label='PMT number'),
hv.Dimension('area', label='Area', unit='PE')
])
return d.to(hv.Points,
vdims=['area', 'i'],
group='PMTPattern',
label=array.capitalize(),
**kwargs).opts(plot=dict(color_index=2,
tools=['hover'],
show_grid=False),
style=dict(size=17, cmap='magma'))
def _get_linked_plots(backend: str = "plotly") -> Tuple:
"""Returns a tuple (scatter, hist) of linked plots
Args:
backend (str, optional): "plotly" or "bokeh". Defaults to "plotly".
Returns:
[Tuple]: Returns a tuple (scatter, hist) of linked plots
"""
dataset = hv.Dataset(IRIS_DATASET)
scatter = hv.Scatter(dataset,
kdims=["sepal_length"],
vdims=["sepal_width"])
hist = hv.operation.histogram(dataset,
dimension="petal_width",
normed=False)
# pylint: disable=no-value-for-parameter
selection_linker = hv.selection.link_selections.instance()
scatter = selection_linker(scatter).opts(
opts.Scatter(**OPTS["all"]["scatter"], **OPTS[backend]["scatter"]))
hist = selection_linker(hist).opts(
opts.Histogram(**OPTS["all"]["hist"], **OPTS[backend]["hist"]))
return scatter, hist
def create_hv_dataset(df, stats, percentile=(1, 99)):
_idNames = ("patch", "tract", "filter")
_kdims = ("ra", "dec", "psfMag")
_flags = [c for c in df.columns if df[c].dtype == np.dtype("bool")]
kdims = []
vdims = []
for c in df.columns:
if c in _kdims or c in _idNames or c in _flags:
if c in ("ra", "dec", "psfMag"):
cmin, cmax = stats[c]["min"].min(), stats[c]["max"].max()
c = hv.Dimension(c, range=(cmin, cmax))
elif c in ("filter", "patch", "tract"):
cvalues = list(df[c].unique())
c = hv.Dimension(c, values=cvalues)
elif df[c].dtype.kind == "b":
c = hv.Dimension(c, values=[True, False])
kdims.append(c)
else:
if percentile is not None:
p0, p1 = percentile
if c in stats.columns and f"{p0}%" in stats.index and f"{p1}%" in stats.index:
cmin, cmax = stats[c][f"{p0}%"].min(), stats[c][f"{p1}%"].max()
else:
print("percentiles not found in stats, computing")
darray = df[c].values
cmin, cmax = (np.percentile(darray, p0), np.percentile(darray, p1))
else:
cmin, cmax = stats[c]["min"].min(), stats[c]["max"].max()
c = hv.Dimension(c, range=(cmin, cmax))
vdims.append(c)
return hv.Dataset(df, kdims=kdims, vdims=vdims)
def generate_chord_diagram(responses_count, thr_count=5):
# generate dataframes as required for the plotting function
plot_data = responses_count.loc[responses_count['count'] > 0,
['index', 'target', 'count']]
plot_data.columns = ['source', 'target', 'value']
plot_data.index = np.arange(len(plot_data))
nodes = responses_count.loc[responses_count['count']>0, ['index', 'screen_name', 'party']].\
drop_duplicates().set_index('index').sort_index(level=0)
nodes = hv.Dataset(nodes, 'index')
nodes.data.head()
# generate colormap for single accounts according to party affiliations
person_party_cmap = dict(
zip(responses_count['index'],
responses_count['party'].apply(lambda row: party_cmap[row])))
# generate plot
chord = hv.Chord((plot_data, nodes)).select(value=(thr_count, None))
chord.opts(
hv_opts.Chord(cmap=party_cmap,
edge_cmap=person_party_cmap,
edge_color=hv_dim('source'),
labels='screen_name',
node_color=hv_dim('party'),
edge_hover_line_color='cyan',
node_hover_fill_color='cyan',
height=700,
width=700))
return chord
def modify_doc(doc, mytabs):
start, end = 1, 20
samples_count = 5
slider = Slider(start=start, end=end, value=start, step=1, title="Counts")
select = Select(title="Count", value="aux", options=["box", "pack", "image", "user"])
renderer = hv.renderer('bokeh')##.instance(mode='server')
hv.extension('bokeh')
hv.output(size=200)
links = pd.DataFrame(data['links'])
print(links.head(3))
nodes = hv.Dataset(pd.DataFrame(data['nodes']), 'index')
chord = hv.Chord((links, nodes)).select(value=(samples_count, None))
chord.opts(opts.Chord(cmap='Category20', edge_cmap='Category20', edge_color=dim('source').str(), labels='name', node_color=dim('index').str()))
# Create HoloViews plot and attach the document
hvplot = renderer.get_plot(chord, doc)
def slider_update(attrname, old, new):
# Notify the HoloViews stream of the slider update
print ("update received")
samples_count = new
links = pd.DataFrame(data['links'])
print(links.head(3))
nodes = hv.Dataset(pd.DataFrame(data['nodes']), 'index')
chord = hv.Chord((links, nodes)).select(value=(samples_count, None))
chord.opts(opts.Chord(cmap='Category20', edge_cmap='Category20', edge_color=dim('source').str(), labels='name', node_color=dim('index').str()))
# Create HoloViews plot and attach the document
hvplot = renderer.get_plot(chord, doc)
tab3 = Panel(child=row(slider, hvplot.state), title="Chord Plot")
mytabs.append(tab3)
views = Tabs(tabs = mytabs)
layout=row(views)
doc.add_root(layout)
return doc
slider.on_change('value', slider_update)
def select_update(attrname, old, new):
# Notify the HoloViews stream of the slider update
print ("update received. Old: {} New: {}".format(old, new))
select.on_change('value', select_update)
# Combine the holoviews plot and widgets in a layout
tab3 = Panel(child=row(slider, hvplot.state), title="Chord Plot")
mytabs.append(tab3)
views = Tabs(tabs = mytabs)
layout=row(views)
doc.add_root(layout)
return doc
def hist(self):
ds = hv.Dataset(self.data.to_frame())
plot_opts = dict(self._plot_opts)
plot_opts['invert_axes'] = self.kwds.get('orientation') == 'horizontal'
opts = dict(plot=plot_opts,
style=dict(alpha=self.kwds.get('alpha', 1)))
return hv.operation.histogram(ds,
dimension=self.data.name).opts(**opts)
def parallel_coordinates(data,
class_column,
cols=None,
alpha=0.5,
width=600,
height=300,
var_name='variable',
value_name='value',
**kwds):
"""
Parallel coordinates plotting.
Parameters
----------
frame: DataFrame
class_column: str
Column name containing class names
cols: list, optional
A list of column names to use
alpha: float, optional
The transparency of the lines
Returns
-------
obj : HoloViews object
The HoloViews representation of the plot.
See Also
--------
pandas.plotting.parallel_coordinates : matplotlib version of this routine
"""
# Transform the dataframe to be used in Vega-Lite
if cols is not None:
data = data[list(cols) + [class_column]]
cols = data.columns
df = data.reset_index()
index = (set(df.columns) - set(cols)).pop()
assert index in df.columns
df = df.melt([index, class_column],
var_name=var_name,
value_name=value_name)
labelled = [] if var_name == 'variable' else ['x']
if value_name != 'value':
labelled.append('y')
options = {
'Curve':
dict(kwds, labelled=labelled, alpha=alpha, width=width, height=height),
'Overlay':
dict(legend_limit=5000)
}
colors = _hv.plotting.util.process_cmap('Category10', categorical=True)
dataset = _hv.Dataset(df)
groups = dataset.to(_hv.Curve, var_name, value_name).overlay(index).items()
return _hv.Overlay([
curve.relabel(k).options('Curve', color=c)
for c, (k, v) in zip(colors, groups) for curve in v
]).options(options)
def random_allocation_cb(n_samples):
all_weights, ret_arr, vol_arr, sharpe_arr = random_allocation(
stocks.values, stocks.shift(1).values, num_ports=n_samples)
vdims = [
*('%s Weight' % c for c in stocks.columns), 'Return', 'Volatility',
'Sharpe Ratio'
]
return hv.Dataset((*all_weights.T, ret_arr, vol_arr, sharpe_arr),
vdims=vdims)
def scatter(library, kmerPca):
## Create plots
d = hv.Dataset(kmerPca, ml.PCA_DATA_COL_NAMES)
s = d.to(hv.Scatter, ml.PCA_DATA_COL_NAMES, groupby='class').overlay()
## Style plots
options = _getOptions(library)
s.opts(options)
return s
def hv_imshow_stack(X,cmap = 'gray',scale=.8,title='dataset',timelabel = 'frame'):
import holoviews as hv
hv.extension('bokeh')
d = X.shape
if len(d) == 4:
ds = hv.Dataset((np.arange(d[3]), np.arange(d[2]), np.arange(d[1]),np.arange(d[0]),
X),
['h','w', 'ch', timelabel], title)
elif len(d) == 3:
ds = hv.Dataset((np.arange(d[2]), np.arange(d[1]),np.arange(d[0]),
X),
['h','w', timelabel], title)
else:
print('imshow_stack only works for 3d and 4d stacks.')
return None
im = ds.to(hv.Image, ['h', 'w'],dynamic=True)
im.opts(cmap=cmap,width=int(d[-1]*scale),height=int(d[-2]*scale))
return im