Exemplo n.º 1
0
class FractionTaxaBarStack(Graph):
    """Comparing all fractions across all pools in a barstack"""
    short_name = 'fraction_taxa_barstack'

    def plot(self):
        self.frame = OrderedDict((('%s - %s' % (p,f), getattr(p.fractions, f).rdp.phyla)
                     for f in ('low', 'med', 'big') for p in self.parent.pools))
        self.frame = pandas.DataFrame(self.frame)
        self.frame = self.frame.fillna(0)
        self.frame = self.frame.transpose()
        self.frame = self.frame.apply(lambda x: 100*x/x.sum(), axis=1)
        # Sort the table by sum #
        sums = self.frame.sum()
        sums.sort(ascending=False)
        self.frame = self.frame.reindex_axis(sums.keys(), axis=1)
        # Plot #
        fig = pyplot.figure()
        axes = self.frame.plot(kind='bar', stacked=True, color=cool_colors)
        fig = pyplot.gcf()
        # Other #
        axes.set_title('Species relative abundances per fraction per pool')
        axes.set_ylabel('Relative abundances in percent')
        axes.xaxis.grid(False)
        axes.yaxis.grid(False)
        axes.set_ylim([0,100])
        # Put a legend below current axis
        axes.legend(loc='upper center', bbox_to_anchor=(0.5, -0.20), fancybox=True, shadow=True, ncol=5)
        # Save it #
        self.save_plot(fig, axes, width=24.0, height=14.0, bottom=0.30, top=0.97, left=0.04, right=0.98)
        self.frame.to_csv(self.csv_path)
        pyplot.close(fig)
Exemplo n.º 2
0
 def duplications_stats(self):
     result = OrderedDict()
     for g in self.genes:
         # Basic stats #
         result[g.name] = OrderedDict()
         result[g.name]['genome'] = g.genome.name
         result[g.name]['taxon'] = g.genome.info['taxon']
         result[g.name]['# of hits'] = len(g.raw_hits)
         result[g.name]['# of fresh hits'] = len(
             [h for h in g.hits if h['type'] == 'fresh'])
         result[g.name]['Is there a marine hit'] = len(
             [h for h in g.hits if h['type'] == 'marine'])
         result[g.name]['Is there a refseq hit'] = len(
             [h for h in g.hits if h['type'] == 'other'])
         # The hits not in this genome #
         fresh_outsiders = [
             h for h in g.hits
             if h['type'] == 'fresh' and h['genome'] is not g.genome
         ]
         result[g.name]['# of fresh hits not in genome'] = len(
             fresh_outsiders)
     # Make a dataframe #
     result = pandas.DataFrame.from_dict(result)
     result = result.transpose()
     return result
Exemplo n.º 3
0
 def duplications_stats(self):
     result = OrderedDict()
     for g in self.genes:
         # Basic stats #
         result[g.name] = OrderedDict()
         result[g.name]['genome']                = g.genome.name
         result[g.name]['taxon']                 = g.genome.info['taxon']
         result[g.name]['# of hits']             = len(g.raw_hits)
         result[g.name]['# of fresh hits']       = len([h for h in g.hits if h['type'] == 'fresh'])
         result[g.name]['Is there a marine hit'] = len([h for h in g.hits if h['type'] == 'marine'])
         result[g.name]['Is there a refseq hit'] = len([h for h in g.hits if h['type'] == 'other'])
         # The hits not in this genome #
         fresh_outsiders = [h for h in g.hits if h['type'] == 'fresh' and h['genome'] is not g.genome]
         result[g.name]['# of fresh hits not in genome'] = len(fresh_outsiders)
     # Make a dataframe #
     result = pandas.DataFrame.from_dict(result)
     result = result.transpose()
     return result
Exemplo n.º 4
0
class FractionTaxaBarStack(Graph):
    """Comparing all fractions across all pools in a barstack"""
    short_name = 'fraction_taxa_barstack'

    def plot(self):
        self.frame = OrderedDict(
            (('%s - %s' % (p, f), getattr(p.fractions, f).rdp.phyla)
             for f in ('low', 'med', 'big') for p in self.parent.pools))
        self.frame = pandas.DataFrame(self.frame)
        self.frame = self.frame.fillna(0)
        self.frame = self.frame.transpose()
        self.frame = self.frame.apply(lambda x: 100 * x / x.sum(), axis=1)
        # Sort the table by sum #
        sums = self.frame.sum()
        sums.sort(ascending=False)
        self.frame = self.frame.reindex_axis(sums.keys(), axis=1)
        # Plot #
        fig = pyplot.figure()
        axes = self.frame.plot(kind='bar', stacked=True, color=cool_colors)
        fig = pyplot.gcf()
        # Other #
        axes.set_title('Species relative abundances per fraction per pool')
        axes.set_ylabel('Relative abundances in percent')
        axes.xaxis.grid(False)
        axes.yaxis.grid(False)
        axes.set_ylim([0, 100])
        # Put a legend below current axis
        axes.legend(loc='upper center',
                    bbox_to_anchor=(0.5, -0.20),
                    fancybox=True,
                    shadow=True,
                    ncol=5)
        # Save it #
        self.save_plot(fig,
                       axes,
                       width=24.0,
                       height=14.0,
                       bottom=0.30,
                       top=0.97,
                       left=0.04,
                       right=0.98)
        self.frame.to_csv(self.csv_path)
        pyplot.close(fig)
Exemplo n.º 5
0
class FractionTaxaBarStack(Graph):
    short_name = 'fraction_taxa_barstack'
    bottom = 0.4
    top = 0.95
    left = 0.1
    right = 0.95
    formats = ('pdf', 'eps')

    def plot(self):
        # Make Frame #
        self.frame = OrderedDict(
            (('%s - %s' % (p, f), getattr(p.fractions, f).rdp.phyla)
             for f in ('low', 'med', 'big') for p in self.parent.pools))
        self.frame = pandas.DataFrame(self.frame)
        self.frame = self.frame.fillna(0)
        # Rename #
        new_names = {
            u"run001-pool01 - low": "2-step PCR low",
            u"run001-pool02 - low": "2-step PCR low",
            u"run001-pool03 - low": "2-step PCR low",
            u"run001-pool04 - low": "1-step PCR low",
            u"run002-pool01 - low": "New chem low",
            u"run001-pool01 - med": "2-step PCR med",
            u"run001-pool02 - med": "2-step PCR med",
            u"run001-pool03 - med": "2-step PCR med",
            u"run001-pool04 - med": "1-step PCR med",
            u"run002-pool01 - med": "New chem med",
            u"run001-pool01 - big": "2-step PCR high",
            u"run001-pool02 - big": "2-step PCR high",
            u"run001-pool03 - big": "2-step PCR high",
            u"run001-pool04 - big": "1-step PCR high",
            u"run002-pool01 - big": "New chem high",
        }
        self.frame.rename(columns=new_names, inplace=True)
        self.frame = self.frame.transpose()
        # Group low abundant into 'others' #
        low_abundance = self.frame.sum() < 30000
        other_count = self.frame.loc[:, low_abundance].sum(axis=1)
        self.frame = self.frame.loc[:, ~low_abundance]
        self.frame['Others'] = other_count
        # Normalize #
        self.frame = self.frame.apply(lambda x: 100 * x / x.sum(), axis=1)
        # Sort the table by sum #
        sums = self.frame.sum()
        sums.sort(ascending=False)
        self.frame = self.frame.reindex_axis(sums.keys(), axis=1)
        # Plot #
        fig = pyplot.figure()
        axes = self.frame.plot(kind='bar', stacked=True, color=cool_colors)
        fig = pyplot.gcf()
        # Other #
        axes.set_ylabel('Relative abundances in percent')
        axes.xaxis.grid(False)
        axes.yaxis.grid(False)
        axes.set_ylim([0, 100])
        # Put a legend below current axis
        axes.legend(loc='upper center',
                    bbox_to_anchor=(0.5, -0.40),
                    fancybox=True,
                    shadow=True,
                    ncol=5,
                    prop={'size': 10})
        # Font size #
        axes.tick_params(axis='x', which='major', labelsize=11)
        # Save it #
        self.save_plot(fig, axes)
        self.frame.to_csv(self.csv_path)
        pyplot.close(fig)
Exemplo n.º 6
0
class FractionTaxaBarStack(Graph):
    """This is figure 3 of the paper"""

    short_name = 'fraction_taxa_barstack'
    bottom = 0.4
    top = 0.95
    left = 0.1
    right = 0.95
    formats = ('pdf', 'eps')

    def plot(self):
        # Make Frame #
        self.frame = OrderedDict((('%s - %s' % (p,f), getattr(p.fractions, f).rdp.phyla)
                     for f in ('low', 'med', 'big') for p in self.parent.pools))
        self.frame = pandas.DataFrame(self.frame)
        self.frame = self.frame.fillna(0)
        # Rename #
        new_names = {
            u"run001-pool01 - low": "2-step PCR low",
            u"run001-pool02 - low": "2-step PCR low",
            u"run001-pool03 - low": "2-step PCR low",
            u"run001-pool04 - low": "1-step PCR low",
            u"run002-pool01 - low": "New chem low",
            u"run001-pool01 - med": "2-step PCR med",
            u"run001-pool02 - med": "2-step PCR med",
            u"run001-pool03 - med": "2-step PCR med",
            u"run001-pool04 - med": "1-step PCR med",
            u"run002-pool01 - med": "New chem med",
            u"run001-pool01 - big": "2-step PCR high",
            u"run001-pool02 - big": "2-step PCR high",
            u"run001-pool03 - big": "2-step PCR high",
            u"run001-pool04 - big": "1-step PCR high",
            u"run002-pool01 - big": "New chem high",
        }
        self.frame.rename(columns=new_names, inplace=True)
        self.frame = self.frame.transpose()
        # Group low abundant into 'others' #
        low_abundance = self.frame.sum() < 30000
        other_count = self.frame.loc[:, low_abundance].sum(axis=1)
        self.frame = self.frame.loc[:, ~low_abundance]
        self.frame['Others'] = other_count
        # Normalize #
        self.frame = self.frame.apply(lambda x: 100*x/x.sum(), axis=1)
        # Sort the table by sum #
        sums = self.frame.sum()
        sums.sort(ascending=False)
        self.frame = self.frame.reindex_axis(sums.keys(), axis=1)
        # Plot #
        fig = pyplot.figure()
        axes = self.frame.plot(kind='bar', stacked=True, color=cool_colors)
        fig = pyplot.gcf()
        # Other #
        axes.set_ylabel('Relative abundances in percent')
        axes.xaxis.grid(False)
        axes.yaxis.grid(False)
        axes.set_ylim([0,100])
        # Put a legend below current axis
        axes.legend(loc='upper center', bbox_to_anchor=(0.5, -0.40), fancybox=True, shadow=True, ncol=5, prop={'size':10})
        # Font size #
        axes.tick_params(axis='x', which='major', labelsize=11)
        # Save it #
        self.save_plot(fig, axes)
        self.frame.to_csv(self.csv_path)
        pyplot.close(fig)