def make_figures():
# Make the ./plots/ dir if needed
elviz_utils.prepare_plot_dir(MAIN_DIR)
# Make figure 1:
make_heatmap_for_major_players(MAJOR_PLAYERS,
make_svg_too = MAKE_SVG_TOO)
# Make figure 2:
make_heatmap_for_particular_family_with_other(family='Methylophilaceae',
taxa_dict=METHYLOPHILACEAE,
make_svg_too = MAKE_SVG_TOO)
# Make figure 3:
make_heatmap_for_particular_family_with_other(family='Methylococcaceae',
taxa_dict=METHYLOCOCCACEAE,
make_svg_too = MAKE_SVG_TOO)
# Make figure 4:
# want a different kind of plot for Burkolderiales:
heatmap_burkolderiales(BURKOLDERIALES, make_svg_too = MAKE_SVG_TOO)
# Make figure 5:
make_heatmap_for_predators(PREDATORS, make_svg_too = MAKE_SVG_TOO)
def heatmap_from_taxa_dict(dataframe, taxa_dict,
title=False,
facet='rep', annotate=False,
summarise_other=True,
main_dir='./',
cap_facet_labels=True,
plot_dir='./plots/mixed_taxonomy/',
size_spec=False,
aspect_spec=False,
check_totals_sum_to_1=True,
svg=False):
"""
Make a plot using a taxa_dict.
The taxa_dict is used to make a summary dataframe using
aggregate_mixed_taxonomy(), and the reult is plotted.
:param dataframe: dataframe to source all data from
:param taxa_dict: a dictionary with taxonomic levels as keys and
names as values. E.g. {'Phylum':['Bacteroidetes'],
'Order':['Burkholderiales','Methylophilales', 'Methylococcales']}
:param facet: The rows to facet the subplots by. Defaults to replicates,
so weeks will be the columns.
:param annotate: print numerical values inside each square? (Makes big
plots *really* big; not recommended for default use.
:param main_dir: main dir to consider "home", so notebooks can be run in
remote directories.
:param summarise_other: include a bar for "other"? (Or just don't show)
:param plot_dir: path to save plots at, relative to main_dir
:param size_spec: manually specify the figure size (useful when default
is ugly)
:param aspect_spec: manually specify the figure asepct ratio (useful when
default is ugly
:return: saves and returns a seaborn heat map
"""
# Cherry pick out the rows for the specified taxa.
# If you give conflicting taxa as input, aggregate_mixed_taxonomy() will
# throw an error.
plot_data = aggregate_mixed_taxonomy(
dataframe=dataframe,
taxa_dict=taxa_dict,
main_dir=main_dir,
summarise_other=summarise_other,
check_totals_sum_to_1=check_totals_sum_to_1)
# store the maximum abundance level. We will need to tell all the
# sub-heat maps to use this same maximum so they aren't each on their
# own scale.
max_abundance = plot_data['abundance sum'].max()
# The data is seperated by these two variables.
# The one not used as the facet will be used as the columns in the
# subplot.
if facet == 'week':
cols_in_facet = 'rep'
else:
cols_in_facet = 'week'
print('plot_data.head()')
print(plot_data.head())
def pivot_so_columns_are_plotting_variable(dataframe, groupby):
return dataframe.pivot(index='taxonomic name',
columns=groupby,
values='abundance sum')
def facet_heatmap(data, groupby, xrotation, **kws):
"""
Used to fill the subplots with data.
:param data: dataframe to plot
:param groupby: column to group on
:param xrotation: degrees to rotate x labels by
:param kws: kewyord arguments for plotting
:return:
"""
# pivot only supports one column for now.
# http://stackoverflow.com/questions/32805267/pandas-pivot-on-multiple-columns-gives-the-truth-value-of-a-dataframe-is-ambigu
facet_data = pivot_so_columns_are_plotting_variable(
dataframe=data, groupby=groupby)
# Pass kwargs to heatmap cmap used to be 'Blue'
sns.heatmap(facet_data, cmap="YlGnBu", **kws)
g.set_xticklabels(rotation=xrotation)
# todo: add a label at the bottom like "replicate" or "week"
# currently replicate is turned into facet_replicate but should just
# make a label that says replicate. Week
# Control plot aesthetics depending on facet option.
if facet == 'week':
xrotation = 0
num_rows = len(plot_data['taxonomic name'].unique())
size = 2 * 0.2*num_rows
aspect = 1
space_for_cbar = 0.85
x_axis_label = 'replicate'
else: # (facet = "rep")
xrotation = 90
# Calculate the size, aspect depending on the number of
# rows per subplot
num_rows = len(plot_data['taxonomic name'].unique())
size = 1 + 0.22*num_rows
aspect = 1.5 # aspect for each sub-plot, not a single tile
space_for_cbar = 0.85
if size_spec:
size = size_spec
if aspect_spec:
aspect = aspect_spec
print(plot_data.head())
if cap_facet_labels:
if facet == "rep":
row_var='$O_2$'
col_var = 'Week'
facet_var = "Replicate"
else:
print("not set up for facet != rep")
plot_data = capitalize_some_column_names(plot_data)
col_var
else:
facet_var = 'rep'
row_var = 'oxy'
col_var = 'week'
with sns.plotting_context(font_scale=8):
g = sns.FacetGrid(plot_data,
col=facet_var,
row=row_var,
size=size,
aspect=aspect,
margin_titles=True)
# Add axes for the colorbar. [left, bottom, width, height]
cbar_ax = g.fig.add_axes([.92, .3, .02, .4], title='fraction \n of reads')
g = g.map_dataframe(facet_heatmap,
cbar_ax=cbar_ax,
# NEED vmax = MAX ABUNDANCE or each plot will have
# its own color scale!
vmin=0, vmax=max_abundance,
annot=annotate,
groupby=col_var,
xrotation=xrotation)
g.set_axis_labels(col_var)
# add space for x label
g.fig.subplots_adjust(bottom=0.2)
# todo: add an x-label for each facet (I want only 1)
# g.set_axis_labels(['x label', 'ylabel'])
# g.fig.subplots_adjust(top=0.2)
# g.fig.text(0.5, 0.1, s='armadillo') #, *args, **kwargs)
# g.fig.xlabel('ardvark')
# Add space so the colorbar doesn't overlap th plot.
g.fig.subplots_adjust(right=space_for_cbar)
# todo: still not enough room for
# Order-Burkholderiales_Methylophilales_Methylococcales--
# Phylum-Bacteroidetes--rep.pdf
# Format the y strings in each subplot of the Seaborn grid.
# Don't put () on the function you are c
# Todo: make the 2nd argument a function
y_label_formatter(g, italics_unless_other)
supertitle = taxa_dict_to_descriptive_string(taxa_dict)
if title:
# TODO: they are currently being converted to LaTeX
# add a supertitle, you bet.
plt.subplots_adjust(top=0.80)
g.fig.suptitle(supertitle, size=16)
# Tight layout --> title and cbar overlap heat maps. Boo.
# NO: plt.tight_layout()
g.fig.subplots_adjust(wspace=.05, hspace=.05)
# prepare filename and save.
plot_dir = elviz_utils.prepare_plot_dir(plot_dir)
print("plot directory: {}".format(plot_dir))
filepath = plot_dir + supertitle
filepath += "--{}".format(facet)
if annotate:
filepath += "--annotated"
filepath += ".pdf"
print(filepath)
g.fig.savefig(filepath)
if svg:
g.fig.savefig(filepath.rstrip("pdf") + "svg")
return g
def heatmap_all_below(dataframe, taxa_dict, plot_dir, low_cutoff=0.001,
cap_facet_labels=True,
title=False, svg=False):
"""
Make a heatmap of all the taxa below the taxa specified in taxa_dict.
:param dataframe: dataframe of data to harvest excerpts from
:param taxa_dict: a dictionary with taxonomic levels as keys and
names as values. E.g. {'Order':['Burkholderiales']}
:param plot_dir: path to save plots to, relative to main_dir
:param main_dir: path to data source, etc.
:param low_cutoff: lowest abundance to include. A taxa must be above
this threshold in at least one sample to be included.
:return:
"""
# TODO: this function has a lot of commonality with heatmap_from_taxa_dict
# and could/should be factored.
# grab the data for that taxa:
# for now assume just 1 key and 1 value.
taxa_level = list(taxa_dict.keys())[0]
taxa_name = list(taxa_dict.values())[0][0]
dataframe = dataframe[dataframe[taxa_level] == taxa_name]
print(dataframe.head())
# Columns to form a concatenated label from:
label_cols = taxonomy_levels_below(taxa_level=taxa_level)
print('label_cols: {}'.format(label_cols))
# change nan cells to 'unknown'
dataframe.fillna('unknown', inplace=True)
# make a summary string representing the taxonomy for everything below
def label_building_lambda(f, column_value_list, taxa_name):
"""
Returns a lambda function to make row labels from.
:param f: function to make a lambda out of.
:param columns: column names to pass to function f in the lambda
:return: function
"""
# * means unpack the list you get from the list comprehension
print("columns passed: {}".format(column_value_list))
print("Use those in {}".format(f))
# Passing a list into label_from_taxa_colnames().
# Doing a list comprehension on columns.
# Note that (row[col] for col in columns)) is a generator .
# building something like label_from_taxa_colnames()
return lambda row: f([row[col] for col in column_value_list],
taxa_name)
# e.g. makes:
# my_function([Comamonadaceae, Curvibacter]) from a row of a dataframe
# and the specification that columns = ['Family', 'Genus']
# TODO: use the taxa_dict to get the columns to use!
# make a name_string per row. It's something like
# "Comamonadaceae, Curvibacter" or "other"
dataframe['name_string'] = dataframe.apply(
label_building_lambda(f=label_from_taxa_colnames,
column_value_list=label_cols,
taxa_name=taxa_name),
axis=1)
print("dataframe.head() for name_string:")
print(dataframe.head())
# reduce to only name_string rows with at least one abundance > the
# threshold set by low_cutoff to we don't have a zillion rows:
# todo: allow high to change?
dataframe = \
abundance_utils.filter_by_abundance(data=dataframe,
abundance_column='fraction of '
'reads',
high=1,
low=low_cutoff,
taxonomy_column='name_string')
# Plot as usual, using the stuff developed above.
# todo: factor some of this??
def pivot_so_columns_are_plotting_variable(dataframe, groupby):
return dataframe.pivot(index='name_string',
columns=groupby,
values='fraction of reads')
def facet_heatmap(data, groupby, xrotation, **kws):
"""
Used to fill the subplots with data.
:param data: dataframe to plot
:param groupby: column to group on
:param xrotation:
:param kws:
:return:
"""
# pivot only supports one column for now.
# http://stackoverflow.com/questions/32805267/pandas-pivot-on-multiple-columns-gives-the-truth-value-of-a-dataframe-is-ambigu
facet_data = pivot_so_columns_are_plotting_variable(
dataframe=data, groupby=groupby)
# Pass kwargs to heatmap cmap.
sns.heatmap(facet_data, cmap="YlGnBu", **kws)
g.set_xticklabels(rotation=xrotation)
# set some plotting parameters
xrotation = 90
# Calculate the size, aspect depending on the number of
# rows per subplot
num_rows = len(dataframe['name_string'].unique())
size = 1 + 0.22*num_rows
aspect = 1.5 # a
if cap_facet_labels:
dataframe = capitalize_some_column_names(dataframe)
facet_var = "Replicate"
row_var='$O_2$'
col_var = "Week"
else:
facet_var = 'rep'
row_var = 'oxy'
col_var = 'week'
# todo: this doesn't seem to be changing the font size. Probably isn't
# for other plotting calls either!
with sns.plotting_context(font_scale=40):
g = sns.FacetGrid(dataframe,
col=facet_var,
row=row_var,
size=size,
aspect=aspect,
margin_titles=True)
g.set_axis_labels(col_var)
# Add axes for the colorbar. [left, bottom, width, height]
cbar_ax = g.fig.add_axes([.94, .3, .02, .4], title='fraction \n of reads')
g = g.map_dataframe(facet_heatmap,
cbar_ax=cbar_ax, vmin=0,
# MUST SET VMAX or all of the subplots will be on
# their own color scale and you might not know it.
vmax=dataframe['fraction of reads'].max(),
annot=False,
groupby=col_var,
xrotation=90)
# modify labels
# Todo: make the 2nd argument a function
y_label_formatter(g, italics_unless_other)
# add space for x label
g.fig.subplots_adjust(bottom=0.2)
# room for colorbar (cbar)
g.fig.subplots_adjust(right=0.85)
# add a supertitle, you bet.
supertitle_base = taxa_dict_to_descriptive_string(taxa_dict)
if title:
plt.subplots_adjust(top=0.80)
supertitle = \
supertitle_base + '. Min fraction of reads cutoff = {}'.format(
low_cutoff)
g.fig.suptitle(supertitle, size=15)
# Also summarise # of taxa rows being grouped together.
# prepare filename and save.
plot_dir = elviz_utils.prepare_plot_dir(plot_dir)
filepath = plot_dir + supertitle_base
filepath += "--min_{}".format(low_cutoff)
filepath += "--{}".format('x-week')
filepath += ".pdf"
print(filepath)
g.fig.savefig(filepath)
if svg:
g.fig.savefig(filepath.rstrip("pdf") + "svg")
return g
def plot_heatmap_genus(dataframe, high, low, oxy, rep, plot_dir):
"""
Make a heatmap at Genus, using oganisms withing the specified abundance
cutoffs.
:param dataframe: dataframe to pass
:param high: highest abundance to include genera for
:param low: lowes abundance to include genera for
:param oxy: oxygen tension, "Low" or "High"
:param rep: replicate (1-4)
:param plot_dir: directory to save plots in.
:return:
"""
# get rid of oxygen levels and replicates if specified.
if oxy is not 'all':
print("keep only {} oxygen samples".format(oxy))
dataframe = dataframe[dataframe['oxy'] == oxy]
if rep is not 'all':
print("keep only replicate levels:", rep)
dataframe = dataframe[dataframe['rep'].isin(rep)]
dataframe = abundance_utils.filter_by_abundance(
data=dataframe,
abundance_column='fraction of reads',
high=high, low=low)
dataframe['facet_replicate'] = 'replicate ' + dataframe['rep'].astype(str)
# make height of the plot a function of the number of rows (Genera):
num_data_rows = len(dataframe['Genus'].unique())
plot_size = 2 + num_data_rows / 7
plot_aspect = 2
if num_data_rows > 6:
plot_aspect = .85
if num_data_rows > 9:
plot_aspect = .65
if num_data_rows > 9:
plot_aspect = .6
def facet_heatmap(data, **kws):
"""
Used to fill the subplots with data.
:param data:
:param kws:
:return:
"""
facet_data = data.pivot(index='Genus', columns='week',
values='fraction of reads')
# Pass kwargs to heatmap cmap used to be 'Blue'
sns.heatmap(facet_data, cmap="YlGnBu", **kws)
with sns.plotting_context(font_scale=7):
g = sns.FacetGrid(dataframe, col='facet_replicate',
margin_titles=True,
size=plot_size, aspect=plot_aspect)
g.set_xticklabels(rotation=90)
# Create a colorbar axes
cbar_ax = g.fig.add_axes([.94, .3, .02, .4], title='fraction \n of reads')
g = g.map_dataframe(facet_heatmap,
cbar_ax=cbar_ax, vmin=0,
# specify vmax = max abundance seen or each will
# have its own scale (and you might not know it!)
vmax=dataframe['fraction of reads'].max(),
)
g.set_titles(col_template="{col_name}", fontweight='bold', fontsize=18)
g.set_axis_labels('week')
# Add space so the colorbar doesn't overlap the plot
g.fig.subplots_adjust(right=.9)
# add a supertitle, you bet.
plt.subplots_adjust(top=0.80)
supertitle = str(low) + ' < fraction of reads < ' + str(
high) + ', {} oxygen'.format(oxy)
g.fig.suptitle(supertitle, size=18)
# write a filename and save.
filename = oxy + "_oxygen--{0}_to_{1}_abundance".format(low, high)
print('filename:', filename)
plot_dir = elviz_utils.prepare_plot_dir(plot_dir)
# save figure
g.savefig(plot_dir + filename + '.pdf')