def main():
in_fname = sys.argv[1]
out_fname = sys.argv[2]
try:
columns = int( sys.argv[3] ) - 1, int( sys.argv[4] ) - 1
except:
stop_err( "Columns not specified, your query does not contain a column of numerical data." )
title = sys.argv[5]
xlab = sys.argv[6]
ylab = sys.argv[7]
matrix = []
skipped_lines = 0
first_invalid_line = 0
invalid_value = ''
invalid_column = 0
i = 0
for i, line in enumerate( file( in_fname ) ):
valid = True
line = line.rstrip( '\r\n' )
if line and not line.startswith( '#' ):
row = []
fields = line.split( "\t" )
for column in columns:
try:
val = fields[column]
if val.lower() == "na":
row.append( float( "nan" ) )
else:
row.append( float( fields[column] ) )
except:
valid = False
skipped_lines += 1
if not first_invalid_line:
first_invalid_line = i + 1
try:
invalid_value = fields[column]
except:
invalid_value = ''
invalid_column = column + 1
break
else:
valid = False
skipped_lines += 1
if not first_invalid_line:
first_invalid_line = i+1
if valid:
matrix.append( row )
if skipped_lines < i:
try:
r.pdf( out_fname, 8, 8 )
r.plot( array(matrix), type="p", main=title, xlab=xlab, ylab=ylab, col="blue", pch=19 )
r['dev.off']()
except Exception, exc:
stop_err( "%s" %str( exc ) )
def plotIDR(output_file, input_prefixes):
'''create IDR plots.
This code is taken from the R script
batch-consistency-plot.r
within the IDR package.
'''
dirname = os.path.dirname(__file__)
R.source(os.path.join(dirname, "WrapperIDR.r"))
R('''df.txt = 10''')
R('''uri.list <- list()
uri.list.match <- list()
ez.list <- list()
legend.txt <- c()
em.output.list <- list()
uri.output.list <- list()''')
npair = len(input_prefixes)
for x, input_prefix in enumerate(input_prefixes):
R.load(input_prefix + "-uri.sav")
R.load(input_prefix + "-em.sav")
i = x + 1
R('''uri.output.list[[%(i)i]] <- uri.output;
em.output.list[[%(i)i]] <- em.output;
# reverse =T for error rate;''' % locals())
R('''
ez.list[[%(i)i]] <- get.ez.tt.all(em.output, uri.output.list[[%(i)i]]$data12.enrich$merge1,
uri.output.list[[%(i)i]]$data12.enrich$merge2);'''
% locals())
R('''
# URI for all peaks
uri.list[[%(i)i]] <- uri.output$uri.n;
# URI for matched peaks
uri.match <- get.uri.matched(em.output$data.pruned, df=df.txt);
uri.list.match[[%(i)i]] <- uri.match$uri.n;
''' % locals())
legend = "%(i)i = %(input_prefix)s" % locals()
R('''
legend.txt[%(i)i] <- '%(legend)s';
''' % locals())
R.pdf(output_file)
R('''par(mfcol=c(2,3), mar=c(5,6,4,2)+0.1)''')
R('''plot.uri.group(uri.list, NULL, file.name=NULL, c(1:%(npair)i), title.txt="all peaks");
plot.uri.group(uri.list.match, NULL, file.name=NULL, c(1:%(npair)i), title.txt="matched peaks");
plot.ez.group(ez.list, plot.dir=NULL, file.name=NULL, legend.txt=c(1:%(npair)i), y.lim=c(0, 0.6));
plot(0, 1, type="n", xlim=c(0,1), ylim=c(0,1), xlab="", ylab="", xaxt="n", yaxt="n");
legend(0, 1, legend.txt, cex=0.6);''' % locals())
R["dev.off"]()
def plotIDR( output_file, input_prefixes ):
'''create IDR plots.
This code is taken from the R script
batch-consistency-plot.r
within the IDR package.
'''
dirname = os.path.dirname(__file__)
R.source(os.path.join( dirname, "WrapperIDR.r"))
R('''df.txt = 10''')
R('''uri.list <- list()
uri.list.match <- list()
ez.list <- list()
legend.txt <- c()
em.output.list <- list()
uri.output.list <- list()''')
npair = len(input_prefixes)
for x, input_prefix in enumerate(input_prefixes):
R.load( input_prefix + "-uri.sav" )
R.load( input_prefix + "-em.sav" )
i = x + 1
R( '''uri.output.list[[%(i)i]] <- uri.output;
em.output.list[[%(i)i]] <- em.output;
# reverse =T for error rate;''' % locals())
R('''
ez.list[[%(i)i]] <- get.ez.tt.all(em.output, uri.output.list[[%(i)i]]$data12.enrich$merge1,
uri.output.list[[%(i)i]]$data12.enrich$merge2);''' % locals())
R('''
# URI for all peaks
uri.list[[%(i)i]] <- uri.output$uri.n;
# URI for matched peaks
uri.match <- get.uri.matched(em.output$data.pruned, df=df.txt);
uri.list.match[[%(i)i]] <- uri.match$uri.n;
''' % locals() )
legend = "%(i)i = %(input_prefix)s" % locals()
R('''
legend.txt[%(i)i] <- '%(legend)s';
'''% locals())
R.pdf( output_file )
R('''par(mfcol=c(2,3), mar=c(5,6,4,2)+0.1)''')
R('''plot.uri.group(uri.list, NULL, file.name=NULL, c(1:%(npair)i), title.txt="all peaks");
plot.uri.group(uri.list.match, NULL, file.name=NULL, c(1:%(npair)i), title.txt="matched peaks");
plot.ez.group(ez.list, plot.dir=NULL, file.name=NULL, legend.txt=c(1:%(npair)i), y.lim=c(0, 0.6));
plot(0, 1, type="n", xlim=c(0,1), ylim=c(0,1), xlab="", ylab="", xaxt="n", yaxt="n");
legend(0, 1, legend.txt, cex=0.6);''' % locals())
R["dev.off"]()
def run(self):
# open(self.outpaths(final=False)["visualization"], "w")
edges = load_edges(self.options)
cluster = edges.loc[edges["cluster"] == self.cluster]
# breakpoints = get_cluster_breakpoints(self.options, self.cluster)
from rpy2.robjects import r
r.pdf(self.outpaths(final=False)["visualization"])
for sample, dataset in sorted(self.options.iter_10xdatasets()):
graphing.plot_frags(cluster, self.options, sample, dataset)
for i, row in cluster.iterrows():
plot_triangles(row, self.options)
# print "::", breakpoints
# graphing.visualize_frag_cluster(breakpoints, self.options)
r["dev.off"]()
def visualize_frags(outdir, graphs, options):
from rpy2.robjects import r
utilities.ensure_dir(outdir)
for i, graph in enumerate(graphs):
r.pdf(os.path.join(outdir, "fragments.cluster_{}.pdf".format(i)))
for component in networkx.connected_components(graph):
subgraph = graph.subgraph(component)
ends = [node for node,degree in subgraph.degree_iter() if degree==1]
breakends = [node for node in list(networkx.shortest_simple_paths(subgraph, ends[0], ends[1]))[0]]
# breakends = [breakend_from_label(node) for node in breakends]
breakends = breakends[:-1:2] + breakends[-1:]
# print ")"*100, breakends
for sample, dataset in sorted(options.iter_10xdatasets()):
plot_frags(breakends, options, sample, dataset)
# plot_frags(breakpoints, options, sample, dataset)
r["dev.off"]()
def val(self):
""" Estimate value functions with b-splines and compare """
new_data = pd.DataFrame({'OverallRank': np.linspace(1, 194, 1000)})
fit_a = self.spline_est(self.policy_a['value'], new_data)
fit_b = self.spline_est(self.policy_b['value'], new_data)
r.pdf(os.path.join(os.path.dirname(self.out_dir), 'value.pdf'))
r.plot(new_data['OverallRank'], fit_a, type='l', xlab='Rank_M',
ylab='V(Rank)')
r.lines(new_data['OverallRank'], fit_b, col='red')
r.points(self.policy_a['value']['OverallRank'],
self.policy_a['value']['val'],
col='black')
r.points(self.policy_b['value']['OverallRank'],
self.policy_b['value']['val'],
col='red')
r.legend('topright', np.array(['No Info', 'Info']),
lty=np.array([1, 1]), col=np.array(['black', 'red']))
r('dev.off()')
diff = np.array(fit_b) - np.array(fit_a)
r.pdf(os.path.join(os.path.dirname(self.out_dir), 'value_diff.pdf'))
r.plot(new_data['OverallRank'], diff, type='l', xlab='Rank',
ylab='V(Rank|info=1) - V(Rank|info=0)')
r.abline(h=0, lty=2)
r('dev.off()')
diff = (np.array(fit_b) - np.array(fit_a)) / np.array(fit_a)
r.pdf(os.path.join(os.path.dirname(self.out_dir),
'value_percent_diff.pdf'))
r.plot(new_data['OverallRank'], diff, type='l', xlab='Rank',
ylab='(V(Rank|info=1) - V(Rank|info=0)) / V(Rank|info=0)')
r.abline(h=0, lty=2)
r('dev.off()')
data_path = dirname(dirname(__file__))
data_path = join(data_path, 'data', 'lawData.csv')
data = pd.read_csv(data_path)
new_data = deepcopy(data.loc[data['year'] == 2013, 'OverallRank'])
#new_data = np.concatenate((
# new_data, np.zeros(lc.N_SCHOOLS - len(new_data))
#))
new_data = pd.DataFrame({'OverallRank': np.array(new_data)})
fit_a = self.spline_est(self.policy_a['value'], new_data)
fit_b = self.spline_est(self.policy_b['value'], new_data)
diff = np.sum(np.array(fit_b) - np.array(fit_a))
pdiff = diff / np.sum(fit_a)
print(" - Change in Producer Surplus: {0}".format(diff))
print(" - Percent change in Producer Surplus: {0}".format(pdiff))
return diff
#r.barplot(py2ri(qc_df.num_reads))
# r.plot(py2ri(qc_df))
if __name__ == "__main__":
print "Plotting"
from rpy2.robjects.lib import ggplot2
from rpy2.robjects import r
from rpy2.robjects.packages import importr
scales = importr('scales')
iris = r('iris')
r.pdf("/home/yarden/jaen/Musashi/rtest.pdf")
iris_py = pandas.read_csv("/home/yarden/iris.csv")
iris_py = iris_py.rename(columns={"Name": "Species"})
corrs = []
from scipy.stats import spearmanr
for species in set(iris_py.Species):
entries = iris_py[iris_py["Species"] == species]
c = spearmanr(entries["SepalLength"], entries["SepalWidth"])
print "c: ", c
# compute r.cor(x, y) and divide up by Species
# Assume we get a vector of length Species saying what the
# correlation is for each Species' Petal Length/Width
p = ggplot2.ggplot(iris) + \
ggplot2.geom_point(ggplot2.aes_string(x="Sepal.Length", y="Sepal.Width")) + \
