Python Table.is_empty方法代码示例

# 需要导入模块: from biom import Table [as 别名]
# 或者: from biom.Table import is_empty [as 别名]
def beta_phylogenetic(table: biom.Table, phylogeny: skbio.TreeNode,
                      metric: str, n_jobs: int=1)-> skbio.DistanceMatrix:
    if metric not in phylogenetic_metrics():
        raise ValueError("Unknown phylogenetic metric: %s" % metric)
    if table.is_empty():
        raise ValueError("The provided table object is empty")
    if n_jobs != 1 and metric == 'weighted_unifrac':
        raise ValueError("Weighted UniFrac is not parallelizable")

    counts = table.matrix_data.toarray().astype(int).T
    sample_ids = table.ids(axis='sample')
    feature_ids = table.ids(axis='observation')

    try:
        results = skbio.diversity.beta_diversity(
            metric=metric,
            counts=counts,
            ids=sample_ids,
            otu_ids=feature_ids,
            tree=phylogeny,
            pairwise_func=sklearn.metrics.pairwise_distances,
            n_jobs=n_jobs
        )
    except skbio.tree.MissingNodeError as e:
        message = str(e).replace('otu_ids', 'feature_ids')
        message = message.replace('tree', 'phylogeny')
        raise skbio.tree.MissingNodeError(message)

    return results

# 需要导入模块: from biom import Table [as 别名]
# 或者: from biom.Table import is_empty [as 别名]
def beta(table: biom.Table, metric: str,
         pseudocount: int=1, n_jobs: int=1)-> skbio.DistanceMatrix:

    if not (metric in non_phylogenetic_metrics()):
        raise ValueError("Unknown metric: %s" % metric)

    counts = table.matrix_data.toarray().T

    def aitchison(x, y, **kwds):
        return euclidean(clr(x), clr(y))

    if metric == 'aitchison':
        counts += pseudocount
        metric = aitchison

    if table.is_empty():
        raise ValueError("The provided table object is empty")

    sample_ids = table.ids(axis='sample')

    return skbio.diversity.beta_diversity(
        metric=metric,
        counts=counts,
        ids=sample_ids,
        validate=True,
        pairwise_func=sklearn.metrics.pairwise_distances,
        n_jobs=n_jobs
    )

# 需要导入模块: from biom import Table [as 别名]
# 或者: from biom.Table import is_empty [as 别名]
def group(table: biom.Table, axis: str,
          metadata: qiime2.CategoricalMetadataColumn, mode: str) -> biom.Table:
    if table.is_empty():
        raise ValueError("Cannot group an empty table.")

    if axis == 'feature':
        biom_axis = 'observation'
    else:
        biom_axis = axis

    metadata = _munge_metadata_column(metadata, table.ids(axis=biom_axis),
                                      axis)

    grouped_table = table.collapse(
        lambda axis_id, _: metadata.get_value(axis_id),
        collapse_f=_mode_lookup[mode],
        axis=biom_axis,
        norm=False,
        include_collapsed_metadata=False)
    # Reorder axis by first unique appearance of each group value in metadata
    # (makes it stable for identity mappings and easier to test)
    # TODO use CategoricalMetadataColumn API for retrieving categories/groups,
    # when the API exists.
    series = metadata.to_series()
    return grouped_table.sort_order(series.unique(), axis=biom_axis)

# 需要导入模块: from biom import Table [as 别名]
# 或者: from biom.Table import is_empty [as 别名]
def rarefy(table: biom.Table, sampling_depth: int) -> biom.Table:
    table = table.subsample(sampling_depth, axis='sample', by_id=False)

    if table.is_empty():
        raise ValueError('The rarefied table contains no samples or features. '
                         'Verify your table is valid and that you provided a '
                         'shallow enough sampling depth.')

    return table

# 需要导入模块: from biom import Table [as 别名]
# 或者: from biom.Table import is_empty [as 别名]
def alpha(table: biom.Table, metric: str) -> pd.Series:
    if metric not in non_phylogenetic_metrics():
        raise ValueError("Unknown metric: %s" % metric)
    if table.is_empty():
        raise ValueError("The provided table object is empty")

    counts = table.matrix_data.toarray().astype(int).T
    sample_ids = table.ids(axis='sample')

    result = skbio.diversity.alpha_diversity(metric=metric, counts=counts,
                                             ids=sample_ids)
    result.name = metric
    return result

# 需要导入模块: from biom import Table [as 别名]
# 或者: from biom.Table import is_empty [as 别名]
def beta(table: biom.Table, metric: str, n_jobs: int=1)-> skbio.DistanceMatrix:
    if metric not in non_phylogenetic_metrics():
        raise ValueError("Unknown metric: %s" % metric)
    if table.is_empty():
        raise ValueError("The provided table object is empty")

    counts = table.matrix_data.toarray().astype(int).T
    sample_ids = table.ids(axis='sample')

    return skbio.diversity.beta_diversity(
        metric=metric,
        counts=counts,
        ids=sample_ids,
        pairwise_func=sklearn.metrics.pairwise_distances,
        n_jobs=n_jobs
    )

# 需要导入模块: from biom import Table [as 别名]
# 或者: from biom.Table import is_empty [as 别名]
def beta(table: biom.Table, metric: str,
         pseudocount: int = 1, n_jobs: int = 1) -> skbio.DistanceMatrix:

    if not (metric in non_phylogenetic_metrics()):
        raise ValueError("Unknown metric: %s" % metric)

    counts = table.matrix_data.toarray().T

    def aitchison(x, y, **kwds):
        return euclidean(clr(x), clr(y))

    def canberra_adkins(x, y, **kwds):
        if (x < 0).any() or (y < 0).any():
            raise ValueError("Canberra-Adkins is only defined over positive "
                             "values.")

        nz = ((x > 0) | (y > 0))
        x_ = x[nz]
        y_ = y[nz]
        nnz = nz.sum()

        return (1. / nnz) * np.sum(np.abs(x_ - y_) / (x_ + y_))

    if metric == 'aitchison':
        counts += pseudocount
        metric = aitchison
    elif metric == 'canberra_adkins':
        metric = canberra_adkins

    if table.is_empty():
        raise ValueError("The provided table object is empty")

    sample_ids = table.ids(axis='sample')

    return skbio.diversity.beta_diversity(
        metric=metric,
        counts=counts,
        ids=sample_ids,
        validate=True,
        pairwise_func=sklearn.metrics.pairwise_distances,
        n_jobs=n_jobs
    )

# 需要导入模块: from biom import Table [as 别名]
# 或者: from biom.Table import is_empty [as 别名]
def alpha_phylogenetic(table: biom.Table, phylogeny: skbio.TreeNode,
                       metric: str) -> pd.Series:
    if metric not in phylogenetic_metrics():
        raise ValueError("Unknown phylogenetic metric: %s" % metric)
    if table.is_empty():
        raise ValueError("The provided table object is empty")

    counts = table.matrix_data.toarray().astype(int).T
    sample_ids = table.ids(axis='sample')
    feature_ids = table.ids(axis='observation')

    try:
        result = skbio.diversity.alpha_diversity(metric=metric,
                                                 counts=counts,
                                                 ids=sample_ids,
                                                 otu_ids=feature_ids,
                                                 tree=phylogeny)
    except skbio.tree.MissingNodeError as e:
        message = str(e).replace('otu_ids', 'feature_ids')
        message = message.replace('tree', 'phylogeny')
        raise skbio.tree.MissingNodeError(message)

    result.name = metric
    return result

# 需要导入模块: from biom import Table [as 别名]
# 或者: from biom.Table import is_empty [as 别名]
def alpha_rarefaction(output_dir: str, table: biom.Table, max_depth: int,
                      phylogeny: skbio.TreeNode = None, metrics: set = None,
                      metadata: qiime2.Metadata = None, min_depth: int = 1,
                      steps: int = 10, iterations: int = 10) -> None:

    if metrics is None:
        metrics = {'observed_otus', 'shannon'}
        if phylogeny is not None:
            metrics.add('faith_pd')
    elif not metrics:
        raise ValueError('`metrics` was given an empty set.')
    else:
        phylo_overlap = phylogenetic_metrics() & metrics
        if phylo_overlap and phylogeny is None:
            raise ValueError('Phylogenetic metric %s was requested but '
                             'phylogeny was not provided.' % phylo_overlap)

    if max_depth <= min_depth:
        raise ValueError('Provided max_depth of %d must be greater than '
                         'provided min_depth of %d.' % (max_depth, min_depth))
    possible_steps = max_depth - min_depth
    if possible_steps < steps:
        raise ValueError('Provided number of steps (%d) is greater than the '
                         'steps possible between min_depth and '
                         'max_depth (%d).' % (steps, possible_steps))
    if table.is_empty():
        raise ValueError('Provided table is empty.')
    max_frequency = max(table.sum(axis='sample'))
    if max_frequency < max_depth:
        raise ValueError('Provided max_depth of %d is greater than '
                         'the maximum sample total frequency of the '
                         'feature_table (%d).' % (max_depth, max_frequency))

    if metadata is None:
        columns, filtered_columns = set(), set()
    else:
        # Filter metadata to only include sample IDs present in the feature
        # table. Also ensures every feature table sample ID is present in the
        # metadata.
        metadata = metadata.filter_ids(table.ids(axis='sample'))

        # Drop metadata columns that aren't categorical, or consist solely of
        # missing values.
        pre_filtered_cols = set(metadata.columns)
        metadata = metadata.filter_columns(column_type='categorical',
                                           drop_all_missing=True)
        filtered_columns = pre_filtered_cols - set(metadata.columns)

        metadata_df = metadata.to_dataframe()
        if metadata_df.empty or len(metadata.columns) == 0:
            raise ValueError("All metadata filtered after dropping columns "
                             "that contained non-categorical data.")
        metadata_df.columns = pd.MultiIndex.from_tuples(
            [(c, '') for c in metadata_df.columns])
        columns = metadata_df.columns.get_level_values(0)

    data = _compute_rarefaction_data(table, min_depth, max_depth,
                                     steps, iterations, phylogeny, metrics)

    filenames = []
    for m, data in data.items():
        metric_name = quote(m)
        filename = '%s.csv' % metric_name

        if metadata is None:
            n_df = _compute_summary(data, 'sample-id')
            jsonp_filename = '%s.jsonp' % metric_name
            _alpha_rarefaction_jsonp(output_dir, jsonp_filename, metric_name,
                                     n_df, '')
            filenames.append(jsonp_filename)
        else:
            merged = data.join(metadata_df, how='left')
            for column in columns:
                column_name = quote(column)
                reindexed_df, counts = _reindex_with_metadata(column,
                                                              columns,
                                                              merged)
                c_df = _compute_summary(reindexed_df, column, counts=counts)
                jsonp_filename = "%s-%s.jsonp" % (metric_name, column_name)
                _alpha_rarefaction_jsonp(output_dir, jsonp_filename,
                                         metric_name, c_df, column)
                filenames.append(jsonp_filename)

        with open(os.path.join(output_dir, filename), 'w') as fh:
            data.columns = ['depth-%d_iter-%d' % (t[0], t[1])
                            for t in data.columns.values]
            if metadata is not None:
                data = data.join(metadata.to_dataframe(), how='left')
            data.to_csv(fh, index_label=['sample-id'])

    index = os.path.join(TEMPLATES, 'alpha_rarefaction_assets', 'index.html')
    q2templates.render(index, output_dir,
                       context={'metrics': list(metrics),
                                'filenames': [quote(f) for f in filenames],
                                'columns': list(columns),
                                'steps': steps,
                                'filtered_columns': sorted(filtered_columns)})

    shutil.copytree(os.path.join(TEMPLATES, 'alpha_rarefaction_assets',
                                 'dist'),
#.........这里部分代码省略.........

# 需要导入模块: from biom import Table [as 别名]
# 或者: from biom.Table import is_empty [as 别名]
def beta_rarefaction(output_dir: str, table: biom.Table, metric: str,
                     clustering_method: str, metadata: qiime2.Metadata,
                     sampling_depth: int, iterations: int=10,
                     phylogeny: skbio.TreeNode=None,
                     correlation_method: str='spearman',
                     color_scheme: str='BrBG') -> None:
    if metric in phylogenetic_metrics():
        if phylogeny is None:
            raise ValueError("A phylogenetic metric (%s) was requested, "
                             "but a phylogenetic tree was not provided. "
                             "Phylogeny must be provided when using a "
                             "phylogenetic diversity metric." % metric)
        beta_func = functools.partial(beta_phylogenetic, phylogeny=phylogeny)
    else:
        beta_func = beta

    if table.is_empty():
        raise ValueError("Input feature table is empty.")

    # Filter metadata to only include sample IDs present in the feature table.
    # Also ensures every feature table sample ID is present in the metadata.
    metadata = metadata.filter_ids(table.ids(axis='sample'))

    distance_matrices = _get_multiple_rarefaction(
        beta_func, metric, iterations, table, sampling_depth)
    primary = distance_matrices[0]
    support = distance_matrices[1:]

    heatmap_fig, similarity_df = _make_heatmap(
        distance_matrices, metric, correlation_method, color_scheme)
    heatmap_fig.savefig(os.path.join(output_dir, 'heatmap.svg'))
    similarity_df.to_csv(
        os.path.join(output_dir, 'rarefaction-iteration-correlation.tsv'),
        sep='\t')

    tree = _cluster_samples(primary, support, clustering_method)
    tree.write(os.path.join(output_dir,
                            'sample-clustering-%s.tre' % clustering_method))

    emperor = _jackknifed_emperor(primary, support, metadata)
    emperor_dir = os.path.join(output_dir, 'emperor')
    emperor.copy_support_files(emperor_dir)
    with open(os.path.join(emperor_dir, 'index.html'), 'w') as fh:
        fh.write(emperor.make_emperor(standalone=True))

    templates = list(map(
        lambda page: os.path.join(TEMPLATES, 'beta_rarefaction_assets', page),
        ['index.html', 'heatmap.html', 'tree.html', 'emperor.html']))

    context = {
        'metric': metric,
        'clustering_method': clustering_method,
        'tabs': [{'url': 'emperor.html',
                  'title': 'PCoA'},
                 {'url': 'heatmap.html',
                  'title': 'Heatmap'},
                 {'url': 'tree.html',
                  'title': 'Clustering'}]
    }

    q2templates.render(templates, output_dir, context=context)

# 需要导入模块: from biom import Table [as 别名]
# 或者: from biom.Table import is_empty [as 别名]
def alpha_rarefaction(output_dir: str, table: biom.Table, max_depth: int,
                      phylogeny: skbio.TreeNode=None, metrics: set=None,
                      metadata: qiime2.Metadata=None, min_depth: int=1,
                      steps: int=10, iterations: int=10) -> None:

    if metrics is None:
        metrics = {'observed_otus', 'shannon'}
        if phylogeny is not None:
            metrics.add('faith_pd')
    elif not metrics:
        raise ValueError('`metrics` was given an empty set.')
    else:
        phylo_overlap = phylogenetic_metrics() & metrics
        if phylo_overlap and phylogeny is None:
            raise ValueError('Phylogenetic metric %s was requested but '
                             'phylogeny was not provided.' % phylo_overlap)

    if max_depth <= min_depth:
        raise ValueError('Provided max_depth of %d must be greater than '
                         'provided min_depth of %d.' % (max_depth, min_depth))
    possible_steps = max_depth - min_depth
    if possible_steps < steps:
        raise ValueError('Provided number of steps (%d) is greater than the '
                         'steps possible between min_depth and '
                         'max_depth (%d).' % (steps, possible_steps))
    if table.is_empty():
        raise ValueError('Provided table is empty.')
    max_frequency = max(table.sum(axis='sample'))
    if max_frequency < max_depth:
        raise ValueError('Provided max_depth of %d is greater than '
                         'the maximum sample total frequency of the '
                         'feature_table (%d).' % (max_depth, max_frequency))
    if metadata is not None:
        metadata_ids = metadata.ids()
        table_ids = set(table.ids(axis='sample'))
        if not table_ids.issubset(metadata_ids):
            raise ValueError('Missing samples in metadata: %r' %
                             table_ids.difference(metadata_ids))

    filenames, categories, empty_columns = [], [], []
    data = _compute_rarefaction_data(table, min_depth, max_depth,
                                     steps, iterations, phylogeny, metrics)
    for m, data in data.items():
        metric_name = quote(m)
        filename = '%s.csv' % metric_name

        if metadata is None:
            n_df = _compute_summary(data, 'sample-id')
            jsonp_filename = '%s.jsonp' % metric_name
            _alpha_rarefaction_jsonp(output_dir, jsonp_filename, metric_name,
                                     n_df, '')
            filenames.append(jsonp_filename)
        else:
            metadata_df = metadata.to_dataframe()
            metadata_df = metadata_df.loc[data.index]

            all_columns = metadata_df.columns
            metadata_df.dropna(axis='columns', how='all', inplace=True)
            empty_columns = set(all_columns) - set(metadata_df.columns)

            metadata_df.columns = pd.MultiIndex.from_tuples(
                [(c, '') for c in metadata_df.columns])
            merged = data.join(metadata_df, how='left')
            categories = metadata_df.columns.get_level_values(0)
            for category in categories:
                category_name = quote(category)
                reindexed_df, counts = _reindex_with_metadata(category,
                                                              categories,
                                                              merged)
                c_df = _compute_summary(reindexed_df, category, counts=counts)
                jsonp_filename = "%s-%s.jsonp" % (metric_name, category_name)
                _alpha_rarefaction_jsonp(output_dir, jsonp_filename,
                                         metric_name, c_df, category_name)
                filenames.append(jsonp_filename)

        with open(os.path.join(output_dir, filename), 'w') as fh:
            data.columns = ['depth-%d_iter-%d' % (t[0], t[1])
                            for t in data.columns.values]
            if metadata is not None:
                data = data.join(metadata.to_dataframe(), how='left')
            data.to_csv(fh, index_label=['sample-id'])

    index = os.path.join(TEMPLATES, 'alpha_rarefaction_assets', 'index.html')
    q2templates.render(index, output_dir,
                       context={'metrics': list(metrics),
                                'filenames': filenames,
                                'categories': list(categories),
                                'empty_columns': sorted(empty_columns)})

    shutil.copytree(os.path.join(TEMPLATES, 'alpha_rarefaction_assets',
                                 'dist'),
                    os.path.join(output_dir, 'dist'))