def biplot(output_dir: str,
biplot: skbio.OrdinationResults,
sample_metadata: qiime2.Metadata,
feature_metadata: qiime2.Metadata = None,
ignore_missing_samples: bool = False,
invert: bool = False,
number_of_features: int = 5) -> None:
if invert:
biplot.samples, biplot.features = biplot.features, biplot.samples
sample_metadata, feature_metadata = feature_metadata, sample_metadata
# select the top N most important features based on the vector's magnitude
feats = biplot.features.copy()
origin = np.zeros_like(feats.columns)
feats['importance'] = feats.apply(euclidean, axis=1, args=(origin, ))
feats.sort_values('importance', inplace=True, ascending=False)
feats.drop(['importance'], inplace=True, axis=1)
biplot.features = feats[:number_of_features].copy()
generic_plot(output_dir,
master=biplot,
other_pcoa=None,
ignore_missing_samples=ignore_missing_samples,
metadata=sample_metadata,
feature_metadata=feature_metadata,
plot_name='biplot')
def procrustes_analysis(
reference: OrdinationResults,
other: OrdinationResults,
dimensions: int = 5,
permutations: int = 999
) -> (OrdinationResults, OrdinationResults, pd.DataFrame):
if reference.samples.shape != other.samples.shape:
raise ValueError('The matrices cannot be fitted unless they have the '
'same dimensions')
if reference.samples.shape[1] < dimensions:
raise ValueError('Cannot fit fewer dimensions than available')
# fail if there are any elements in the symmetric difference
diff = reference.samples.index.symmetric_difference(other.samples.index)
if not diff.empty:
raise ValueError('The ordinations represent two different sets of '
'samples')
# make the matrices be comparable
other.samples = other.samples.reindex(index=reference.samples.index)
mtx1, mtx2, m2 = procrustes(reference.samples.values[:, :dimensions],
other.samples.values[:, :dimensions])
axes = reference.samples.columns[:dimensions]
samples1 = pd.DataFrame(data=mtx1,
index=reference.samples.index.copy(),
columns=axes.copy())
samples2 = pd.DataFrame(data=mtx2,
index=reference.samples.index.copy(),
columns=axes.copy())
info = _procrustes_monte_carlo(reference.samples.values[:, :dimensions],
other.samples.values[:, :dimensions], m2,
permutations)
out1 = OrdinationResults(short_method_name=reference.short_method_name,
long_method_name=reference.long_method_name,
eigvals=reference.eigvals[:dimensions].copy(),
samples=samples1,
features=reference.features,
biplot_scores=reference.biplot_scores,
sample_constraints=reference.sample_constraints,
proportion_explained=reference.
proportion_explained[:dimensions].copy())
out2 = OrdinationResults(
short_method_name=other.short_method_name,
long_method_name=other.long_method_name,
eigvals=other.eigvals[:dimensions].copy(),
samples=samples2,
features=other.features,
biplot_scores=other.biplot_scores,
sample_constraints=other.sample_constraints,
proportion_explained=other.proportion_explained[:dimensions].copy())
return out1, out2, info
def procrustes_analysis(reference: OrdinationResults, other: OrdinationResults,
dimensions: int=5) -> (OrdinationResults,
OrdinationResults):
if reference.samples.shape != other.samples.shape:
raise ValueError('The matrices cannot be fitted unless they have the '
'same dimensions')
if reference.samples.shape[1] < dimensions:
raise ValueError('Cannot fit fewer dimensions than available')
# fail if there are any elements in the symmetric difference
if not (reference.samples.index ^ other.samples.index).empty:
raise ValueError('The ordinations represent two different sets of '
'samples')
# make the matrices be comparable
other.samples = other.samples.reindex(index=reference.samples.index)
mtx1, mtx2, _ = procrustes(reference.samples.values[:, :dimensions],
other.samples.values[:, :dimensions])
axes = reference.samples.columns[:dimensions]
samples1 = pd.DataFrame(data=mtx1,
index=reference.samples.index.copy(),
columns=axes.copy())
samples2 = pd.DataFrame(data=mtx2,
index=reference.samples.index.copy(),
columns=axes.copy())
out1 = OrdinationResults(
short_method_name=reference.short_method_name,
long_method_name=reference.long_method_name,
eigvals=reference.eigvals[:dimensions].copy(),
samples=samples1,
features=reference.features,
biplot_scores=reference.biplot_scores,
sample_constraints=reference.sample_constraints,
proportion_explained=reference.proportion_explained[:dimensions]
.copy())
out2 = OrdinationResults(
short_method_name=other.short_method_name,
long_method_name=other.long_method_name,
eigvals=other.eigvals[:dimensions].copy(),
samples=samples2,
features=other.features,
biplot_scores=other.biplot_scores,
sample_constraints=other.sample_constraints,
proportion_explained=other.proportion_explained[:dimensions]
.copy())
return out1, out2
def scatterplot(df, x=None, y=None, z=None, remote=True):
"""Create an Emperor scatter plot from a Pandas DataFrame
Parameters
----------
df : pd.DataFrame
Pandas DataFrame with the data to display, this includes both
*metadata* and *coordinates* to position the samples in a 3D space.
x, y, z : str, optional
Column names in `df`, to use as first (``x``), second (``y``) and third
(``z``) axes in the visualization. If these are not specified, axes
are chosen according to the variance (in decremental order).
remote : bool, optional
Whether the JavaScript resources should be loaded locally or from
GitHub. Defaults to ``True``.
Returns
-------
emperor.core.Emperor
Emperor object with the numerical data as the `ordination` attribute
and the entire DataFrame as the `mf` attribute.
Raises
------
ValueError
If `df` is not a PandasDataFrame
If `x`, `y` or `z` are missing from `df` or if they are not numeric
columns.
If after removing rows with missing data there are fewer than 3
samples.
Notes
-----
If a row has missing data, that data point will be removed from the
visualization.
See Also
--------
emperor.core.Emperor
"""
if not isinstance(df, pd.DataFrame):
raise ValueError("The argument is not a Pandas DataFrame")
for col in [z, y, x]:
if col is None:
continue
if col not in df.columns:
raise ValueError("'%s' is not a column in the DataFrame" % col)
if not np.issubdtype(df[col].dtype, np.number):
raise ValueError("'%s' is not a numeric column" % col)
# remove NAs
samples = df.select_dtypes(include=[np.number]).copy()
samples.dropna(axis=0, how='any', inplace=True)
if len(samples.columns) < 3:
raise ValueError("Not enough data to plot")
# sort columns by variance
variance = samples.var().sort_values(ascending=False)
samples = samples[variance.index]
# re-order x, y and z
ordered = samples.columns.tolist()
for col in [z, y, x]:
if col is not None:
ordered.remove(col)
ordered = [col] + ordered
samples = samples[ordered]
# match up the metadata and coordinates
df = df.loc[samples.index]
ores = OrdinationResults(short_method_name='',
long_method_name='',
eigvals=np.zeros_like(samples.columns),
samples=samples,
proportion_explained=variance)
df.index.name = '#SampleID'
# HACK: scale the position of the samples to fit better within the screen
ores.samples = ores.samples / ores.samples.max(axis=0)
return Emperor(ores,
df,
dimensions=len(ores.samples.columns),
remote=remote)
