def interval(locus_table, interval_table, intervals, loci, boxplot = True):
qry = get_interval_query(intervals, loci, locus_table, interval_table)
frame = robjects.r('''data <- dbGetQuery(con, {})'''.format(qry))
# because we're sorting by interval, which is a factor, we need to
# explicitly re-sort the data by the first integer value
# of the interval. This is a bit cumbersome, because sorting
# in R is less than pleasant.
sort_string = '''data$interval <- factor(data$interval, {})'''.format(order_intervals(frame[1]))
robjects.r(sort_string)
gg_frame = ggplot2.ggplot(robjects.r('''data'''))
if boxplot:
plot = gg_frame + ggplot2.aes_string(x = 'interval', y = 'pi') + \
ggplot2.geom_boxplot(**{
'outlier.size':0,
'alpha':0.3
}
) + \
ggplot2.geom_jitter(ggplot2.aes_string(color = 'locus'), size = 3, \
alpha = 0.6, position=ggplot2.position_jitter(width=0.25)) + \
ggplot2.scale_y_continuous('phylogenetic informativeness') + \
ggplot2.scale_x_discrete('interval (years ago)')
else:
plot = gg_frame + ggplot2.aes_string(x = 'interval', y = 'pi',
fill='locus') + ggplot2.geom_bar() + \
ggplot2.facet_wrap(robjects.Formula('~ locus')) + \
ggplot2.opts(**{
'axis.text.x':ggplot2.theme_text(angle = -90, hjust = 0),
'legend.position':'none'
}) + \
ggplot2.scale_y_continuous('phylogenetic informativeness') + \
ggplot2.scale_x_discrete('interval (years ago)')
return plot
def plot(request):
r = robjects.r
ungram = Sentence.objects.filter(grammatical=False).exclude(
rating='N').values_list('similarity', flat=True)
gram = Sentence.objects.filter(grammatical=True).exclude(
rating='N').values_list('similarity', flat=True)
gram_r = robjects.FloatVector(gram)
ungram_r = robjects.FloatVector(ungram)
df = robjects.r["data.frame"]
gram_df = df(gram="GRAM", similarity=gram_r)
ungram_df = df(gram="UNGRAM", similarity=ungram_r)
rbind = r['rbind']
data = rbind(gram_df, ungram_df)
pp = ggplot2.ggplot(data) + \
ggplot2.aes_string(x="gram", y="similarity") + \
ggplot2.geom_boxplot()
grdevices = importr('grDevices')
grdevices.png(file="data.png", width=580, height=512)
pp.plot()
grdevices.dev_off()
image_data = open("data.png", "rb").read()
return HttpResponse(image_data, mimetype="image/png")
def plot(request):
r = robjects.r
ungram = Sentence.objects.filter(grammatical=False).exclude(rating='N').values_list('similarity', flat=True)
gram = Sentence.objects.filter(grammatical=True).exclude(rating='N').values_list('similarity', flat=True)
gram_r = robjects.FloatVector(gram)
ungram_r = robjects.FloatVector(ungram)
df = robjects.r["data.frame"]
gram_df = df(gram="GRAM", similarity=gram_r)
ungram_df = df(gram="UNGRAM", similarity=ungram_r)
rbind = r['rbind']
data = rbind(gram_df, ungram_df)
pp = ggplot2.ggplot(data) + \
ggplot2.aes_string(x="gram", y="similarity") + \
ggplot2.geom_boxplot()
grdevices = importr('grDevices')
grdevices.png(file="data.png", width=580, height=512)
pp.plot()
grdevices.dev_off()
image_data = open("data.png", "rb").read()
return HttpResponse(image_data, mimetype="image/png")
def makePlot(grdevices, plotName, samp_set1_vals, samp_set2_vals,
image_file_type):
samp_vector = ["set1" for i in range(len(samp_set1_vals))]
samp_vector.extend(["set2" for i in range(len(samp_set2_vals))])
dframe = robjects.DataFrame({
"sample":
robjects.StrVector(samp_vector),
"value":
robjects.FloatVector(samp_set1_vals + samp_set2_vals)
})
gp = ggplot2.ggplot(dframe)
pp = gp + \
ggplot2.aes_string(x="sample", y='value') + \
ggplot2.geom_boxplot() +\
ggplot2.geom_jitter() +\
ggplot2.theme_bw()
if image_file_type == "pdf":
grdevices.pdf(file=plotName)
else:
grdevices.png(file=plotName, width=512, height=512)
pp.plot()
grdevices.dev_off()
def render_plot(gp, args):
"""Render a plot using ggplot
:gp: A base ggplot2 object
:x: The x value expression
:y: The y value expression
:type: The type of plot to make
"""
args = util.Namespace(args)
import rpy2.robjects.lib.ggplot2 as ggplot2
pp = gp + ggplot2.aes_string(x=args.x,
y=args.y)
if args.type == 'points':
pp += ggplot2.geom_point()
elif args.type == 'lines':
pp += ggplot2.geom_line()
elif args.type == 'boxplot':
pp += ggplot2.geom_boxplot()
else:
raise Exception("{0} not implemented".format(args.type))
if args.facets is not None:
try:
pp += ggplot2.facet_grid(ro.Formula(args.facets))
except Exception:
pass
try:
pp.plot()
except Exception:
pass
def BoxPlot_One(self, metabolite):
#print(self.raw_data)
r('graphics.off()')
gp = ggplot2.ggplot(self.raw_data)
pp = gp + \
ggplot2.aes_string(x=self.metadata, y='`'+self.metabolite_dict[metabolite]+'`') + \
ggplot2.geom_boxplot()
pp.plot()
def boxPlot(self, dataframe, filename, x_parm, y_parm): grdevices.png(file=filename, width=512, height=512) data = ggplot2.ggplot(dataframe) aes = ggplot2.aes_string(x=x_parm,y=y_parm,) geom = ggplot2.geom_boxplot(alpha = 0.7,fill="aquamarine3") gg = data + aes + geom gg.plot() grdevices.dev_off()
def plot_coef(feat_mat_dir,
model_dir,
expt_names,
pref,
outfile=None,
height=120,
fsize=12):
for expt_idx, ex in enumerate(expt_names):
feat_mat_file = os.path.join(feat_mat_dir, ex + '_feat_mat.npz')
model_file = os.path.join(model_dir, pref + ex + '_model.pkl')
model = read_model(model_file)
(tmp_feat, tmp_y, tmp_feat_names,
tmp_gene_names) = read_feat_mat(feat_mat_file)
if expt_idx == 0:
feat_names = tmp_feat_names
clf_coef = model.clf_coef()
reg_coef = model.reg_coef()
else:
assert (all(f[0] == f[1] for f in zip(feat_names, tmp_feat_names)))
clf_coef = np.concatenate((clf_coef, model.clf_coef()), axis=1)
reg_coef = np.concatenate((reg_coef, model.reg_coef()), axis=1)
nexpt = expt_idx + 1
# Now clf_coef has one row per coefficient and one column per experiment.
# The reshape below will read the data row-first.
df = pd.DataFrame({
'feature': np.repeat(feat_names, nexpt),
'Classification': np.reshape(clf_coef, (clf_coef.size, )),
'Regression': np.reshape(reg_coef, (reg_coef.size, ))
})
df2 = pd.melt(df, id_vars='feature', var_name='fun')
r_df = com.convert_to_r_dataframe(df2)
gp = ggplot2.ggplot(r_df) + ggplot2.aes_string(x = 'factor(feature)', y = 'value') + \
ggplot2.facet_wrap('fun', scales = 'free_y') + \
ggplot2.geom_boxplot() + ggplot2.scale_y_continuous('Importance') + \
ggplot2.scale_x_discrete('') + ggplot2.theme_bw() + \
ggplot2.theme(**{'axis.text.x':ggplot2.element_text(size = fsize, angle = 65, vjust = 1, hjust = 1),
'axis.text.y':ggplot2.element_text(size = fsize),
'strip.text.x':ggplot2.element_text(size = fsize + 1)})
w = max(22 * nexpt, 80)
if outfile is None:
gp.plot()
else:
ro.r.ggsave(filename=outfile,
plot=gp,
width=w,
height=height,
unit='mm')
return df
def boxPlot(self, dataframe, filename, x_parm, y_parm):
grdevices.png(file=filename, width=512, height=512)
data = ggplot2.ggplot(dataframe)
aes = ggplot2.aes_string(
x=x_parm,
y=y_parm,
)
geom = ggplot2.geom_boxplot(alpha=0.7, fill="aquamarine3")
gg = data + aes + geom
gg.plot()
grdevices.dev_off()
def plot_cv_r2(pandas_df, outfile, fsize = 10, height = 120, max_width = 50, xlab = 'Parameters'):
"""Makes boxplots of cross-validation results for different parameter settings"""
ncv = len(set(list(pandas_df['title'])))
r_df = com.convert_to_r_dataframe(pandas_df)
gp = ggplot2.ggplot(r_df) + ggplot2.aes_string(x = 'factor(title)', y = 'r2') + \
ggplot2.geom_boxplot() + ggplot2.scale_y_continuous('R-squared') + \
ggplot2.scale_x_discrete(xlab) + ggplot2.theme_bw() + \
ggplot2.theme(**{'axis.text.x':ggplot2.element_text(size = fsize, angle = 65, vjust = 1, hjust = 1),
'axis.text.y':ggplot2.element_text(size = fsize)})
w = max(5 * ncv, max_width)
ro.r.ggsave(filename = outfile, plot = gp, width = w, height = height, unit = 'mm')
def runBoruta():
base.load("Rcode/zscores.RData")
base.source('Z:/Cristina/MassNonmass/codeProject/codeBase/trainClassifier/Rcode/borutaRelevance.R')
outputBoruta = globalenv['findRelevant'](globalenv['massallfeatures'], globalenv['nonmassallfeatures'])
# generate boxplot comparison of relevant mass features vs. the same non-mass feature
plotgp = ggplot2.ggplot(outputBoruta.rx2("masszscore_selected")) + \
ggplot2.aes_string(x='MorN', y='zscores', fill = 'factor(MorN)') + \
ggplot2.geom_boxplot() + \
ggplot2.opts(title = "Comparison of Z-scores for Mass confirmed features", y="Z-scores")
plotgp.plot()
return
def makeDistanceBox( alldata, figurename, feature="distance") :
alldata["distance"] = alldata.het + alldata.hom
r_dataframe = com.convert_to_r_dataframe(alldata)
p = ggplot2.ggplot(r_dataframe) + \
ggplot2.aes_string(x="factor(continent)", y=feature) + \
ggplot2.geom_boxplot() + \
ggplot2.ggtitle("Distance from Reference by Continent") + \
ggplot2.theme(**mytheme) #+ \
#ggplot2.theme(**{'axis.text.x': ggplot2.element_text(angle = 45)}) + \
#ggplot2.facet_grid( robjects.Formula('RVIS_type ~ .') )
grdevices.png(figurename)
p.plot()
grdevices.dev_off()
def plot_summary(barcodes_obs, barcode_table, directory, expt_id):
barcodes, counts, matches = get_vectors(barcodes_obs, barcode_table)
df = DataFrame({'barcode': barcodes, 'count': counts, 'matched': matches})
p = ggplot2.ggplot(df) + \
ggplot2.aes_string(x='factor(matched)', y='count / 1000000') + \
ggplot2.geom_boxplot(outlier_size = 0) + \
ggplot2.geom_jitter() + \
ggplot2.ggtitle(label = expt_id) + \
ggplot2.ggplot2.xlab(label = "") + \
ggplot2.scale_y_continuous(name = "Count\n(million reads)")
filename = "{0}/{1}.png".format(directory, expt_id)
grdevices.png(filename=filename, width=4, height=5, unit='in', res=300)
p.plot()
grdevices.dev_off()
def direct_taxon_abundance_box_plot(data, plot_file_path, title, xlabel, ylabel):
grdevices.pdf(file=plot_file_path)
gp = ggplot2.ggplot(data)
pp = gp \
+ ggplot2.aes_string(x='genotype', y='abundance') \
+ ggplot2.geom_boxplot() \
+ ggplot2.ggtitle(title) \
+ ggplot2.labs(x=xlabel, y=ylabel) \
+ ggplot2.geom_jitter(position=ggplot2.position_jitter(w=0.1)) \
+ ggplot2.geom_point()
pp.plot()
grdevices.dev_off()
def ridge_cv_plot(val_err, lam_range):
"""
Source: http://rpy.sourceforge.net/rpy2/doc-2.3/html/graphics.html
"""
base = importr('base')
df = pd.DataFrame(val_err, columns = lam_range)
df = pd.melt(df)
df_r = com.convert_to_r_dataframe(df)
# Create boxplot
gp = ggplot2.ggplot(df_r)
pp = gp + \
ggplot2.aes_string(x='factor(variable)', y='value') + \
ggplot2.geom_boxplot() + \
ggplot2.ggtitle("Validation Error by Lambda")
pp.plot()
return
def plot_summary(barcodes_obs, barcode_table, directory, expt_id):
barcodes, counts, matches = get_vectors(barcodes_obs, barcode_table)
df = DataFrame({'barcode': barcodes,
'count': counts,
'matched': matches})
p = ggplot2.ggplot(df) + \
ggplot2.aes_string(x='factor(matched)', y='count / 1000000') + \
ggplot2.geom_boxplot(outlier_size = 0) + \
ggplot2.geom_jitter() + \
ggplot2.ggtitle(label = expt_id) + \
ggplot2.ggplot2.xlab(label = "") + \
ggplot2.scale_y_continuous(name = "Count\n(million reads)")
filename = "{0}/{1}.png".format(directory, expt_id)
grdevices.png(filename=filename, width=4, height=5, unit='in', res=300)
p.plot()
grdevices.dev_off()
def BoxPlot_All(self):
#print(self.metabolite_list)
r('graphics.off()')
plots = []
for i in range(1, len(self.metabolite_list) + 1):
if i % 4 == 0 and i > 0:
grDevices.X11()
gridExtra.grid_arrange(*plots, nrow=2, ncol=2)
plots = []
gp = ggplot2.ggplot(self.raw_data)
plots.append(gp + \
ggplot2.aes_string(x=self.metadata, y='`'+str(i)+'`') + \
ggplot2.geom_boxplot())
grDevices.X11()
gridExtra.grid_arrange(*plots, nrow=2, ncol=2)
def plot_thresh_distr(motif_names, thresh, out_dir, width = 350):
"""Creates boxplots of the thresholds used with each feature."""
df = pd.DataFrame({'motif':motif_names, 'thresh':thresh})
df = df[df['thresh'] > 1]
df.to_csv(os.path.join(out_dir, 'count_thresh.txt'), sep = '\t', index = False)
fsize = 10
r_df = com.convert_to_r_dataframe(df)
gp = ggplot2.ggplot(r_df) + ggplot2.aes_string(x = 'factor(motif)', y = 'thresh') + \
ggplot2.geom_boxplot() + ggplot2.scale_y_continuous('Threshold counts', limits = ro.IntVector([0, 70])) + \
ggplot2.scale_x_discrete('') + ggplot2.theme_bw() + ggplot2.coord_flip() + \
ggplot2.theme(**{'axis.text.x':ggplot2.element_text(size = fsize),
'axis.text.y':ggplot2.element_text(size = fsize, hjust = 1),
'strip.text.x':ggplot2.element_text(size = fsize + 1)})
for ext in ['.pdf', '.png']:
ro.r.ggsave(filename = os.path.join(out_dir, 'count_thresh_bar' + ext),
plot = gp, width = width, height = 300, unit = 'mm')
def plot_cv_r2(pandas_df,
outfile,
fsize=10,
height=120,
max_width=50,
xlab='Parameters'):
"""Makes boxplots of cross-validation results for different parameter settings"""
ncv = len(set(list(pandas_df['title'])))
r_df = com.convert_to_r_dataframe(pandas_df)
gp = ggplot2.ggplot(r_df) + ggplot2.aes_string(x = 'factor(title)', y = 'r2') + \
ggplot2.geom_boxplot() + ggplot2.scale_y_continuous('R-squared') + \
ggplot2.scale_x_discrete(xlab) + ggplot2.theme_bw() + \
ggplot2.theme(**{'axis.text.x':ggplot2.element_text(size = fsize, angle = 65, vjust = 1, hjust = 1),
'axis.text.y':ggplot2.element_text(size = fsize)})
w = max(5 * ncv, max_width)
ro.r.ggsave(filename=outfile, plot=gp, width=w, height=height, unit='mm')
def compare_mean_boxplot(locus_table, interval_table, intervals, loci, names, rows):
frame = get_r_data_by_top(locus_table, interval_table, intervals, names,
rows)
if len(intervals) > 1:
sort_string = '''data$interval <- factor(data$interval, {})'''.format(order_intervals(frame[1]))
robjects.r(sort_string)
gg_frame = ggplot2.ggplot(robjects.r('''data'''))
plot = gg_frame + ggplot2.aes_string(x = 'interval', y = 'pi') + \
ggplot2.geom_boxplot(ggplot2.aes_string(fill = 'factor(db)'), **{
'outlier.size':3,
'outlier.colour':'#767676',
'outlier.alpha':0.3,
'alpha':0.6
}
) + \
ggplot2.scale_y_continuous('mean phylogenetic informativeness') + \
ggplot2.scale_x_discrete('interval (years ago)') + \
ggplot2.scale_fill_brewer("database", palette='Blues')
return plot
def plot_thresh_distr(motif_names, thresh, out_dir, width=350):
"""Creates boxplots of the thresholds used with each feature."""
df = pd.DataFrame({'motif': motif_names, 'thresh': thresh})
df = df[df['thresh'] > 1]
df.to_csv(os.path.join(out_dir, 'count_thresh.txt'), sep='\t', index=False)
fsize = 10
r_df = com.convert_to_r_dataframe(df)
gp = ggplot2.ggplot(r_df) + ggplot2.aes_string(x = 'factor(motif)', y = 'thresh') + \
ggplot2.geom_boxplot() + ggplot2.scale_y_continuous('Threshold counts', limits = ro.IntVector([0, 70])) + \
ggplot2.scale_x_discrete('') + ggplot2.theme_bw() + ggplot2.coord_flip() + \
ggplot2.theme(**{'axis.text.x':ggplot2.element_text(size = fsize),
'axis.text.y':ggplot2.element_text(size = fsize, hjust = 1),
'strip.text.x':ggplot2.element_text(size = fsize + 1)})
for ext in ['.pdf', '.png']:
ro.r.ggsave(filename=os.path.join(out_dir, 'count_thresh_bar' + ext),
plot=gp,
width=width,
height=300,
unit='mm')
def plot_coef(feat_mat_dir, model_dir, expt_names, pref, outfile = None, height = 120, fsize = 12):
for expt_idx, ex in enumerate(expt_names):
feat_mat_file = os.path.join(feat_mat_dir, ex + '_feat_mat.npz')
model_file = os.path.join(model_dir, pref + ex + '_model.pkl')
model = read_model(model_file)
(tmp_feat, tmp_y, tmp_feat_names, tmp_gene_names) = read_feat_mat(feat_mat_file)
if expt_idx == 0:
feat_names = tmp_feat_names
clf_coef = model.clf_coef()
reg_coef = model.reg_coef()
else:
assert(all(f[0] == f[1] for f in zip(feat_names, tmp_feat_names)))
clf_coef = np.concatenate((clf_coef, model.clf_coef()), axis = 1)
reg_coef = np.concatenate((reg_coef, model.reg_coef()), axis = 1)
nexpt = expt_idx + 1
# Now clf_coef has one row per coefficient and one column per experiment.
# The reshape below will read the data row-first.
df = pd.DataFrame({'feature':np.repeat(feat_names, nexpt),
'Classification':np.reshape(clf_coef, (clf_coef.size,)),
'Regression':np.reshape(reg_coef, (reg_coef.size,))})
df2 = pd.melt(df, id_vars = 'feature', var_name = 'fun')
r_df = com.convert_to_r_dataframe(df2)
gp = ggplot2.ggplot(r_df) + ggplot2.aes_string(x = 'factor(feature)', y = 'value') + \
ggplot2.facet_wrap('fun', scales = 'free_y') + \
ggplot2.geom_boxplot() + ggplot2.scale_y_continuous('Importance') + \
ggplot2.scale_x_discrete('') + ggplot2.theme_bw() + \
ggplot2.theme(**{'axis.text.x':ggplot2.element_text(size = fsize, angle = 65, vjust = 1, hjust = 1),
'axis.text.y':ggplot2.element_text(size = fsize),
'strip.text.x':ggplot2.element_text(size = fsize + 1)})
w = max(22 * nexpt, 80)
if outfile is None:
gp.plot()
else:
ro.r.ggsave(filename = outfile, plot = gp, width = w, height = height, unit = 'mm')
return df
def makePlot(grdevices, plotName, samp_set1_vals, samp_set2_vals,
image_file_type):
samp_vector = ["set1" for i in range(len(samp_set1_vals))]
samp_vector.extend(["set2" for i in range(len(samp_set2_vals))])
dframe = robjects.DataFrame({"sample":robjects.StrVector(samp_vector),
"value":robjects.FloatVector(samp_set1_vals + samp_set2_vals)})
gp = ggplot2.ggplot(dframe)
pp = gp + \
ggplot2.aes_string(x="sample", y='value') + \
ggplot2.geom_boxplot() +\
ggplot2.geom_jitter() +\
ggplot2.theme_bw()
if image_file_type == "pdf":
grdevices.pdf(file=plotName)
else:
grdevices.png(file=plotName, width=512, height=512)
pp.plot()
grdevices.dev_off()
pp.plot(vp=vp)
#-- ggplot2geomhexbin-end
grdevices.dev_off()
grdevices.png('../../_static/graphics_ggplot2geomboxplot.png',
width=612,
height=612,
antialias="subpixel",
type="cairo")
#-- ggplot2geomboxplot-begin
gp = ggplot2.ggplot(mtcars)
pp = gp + \
ggplot2.aes_string(x='factor(cyl)', y='mpg') + \
ggplot2.geom_boxplot()
pp.plot()
#-- ggplot2geomboxplot-end
grdevices.dev_off()
#-- ggplot2geomhistogram-begin
gp = ggplot2.ggplot(mtcars)
pp = gp + \
ggplot2.aes_string(x='wt') + \
ggplot2.geom_histogram()
#pp.plot()
#-- ggplot2geomhistogram-end
pp.plot(vp = vp)
#-- ggplot2geomhexbin-end
grdevices.dev_off()
grdevices.png('../../_static/graphics_ggplot2geomboxplot.png',
width = 612, height = 612, antialias="subpixel", type="cairo")
#-- ggplot2geomboxplot-begin
gp = ggplot2.ggplot(mtcars)
pp = gp + \
ggplot2.aes_string(x='factor(cyl)', y='mpg') + \
ggplot2.geom_boxplot()
pp.plot()
#-- ggplot2geomboxplot-end
grdevices.dev_off()
#-- ggplot2geomhistogram-begin
gp = ggplot2.ggplot(mtcars)
pp = gp + \
ggplot2.aes_string(x='wt') + \
ggplot2.geom_histogram()
#pp.plot()
#-- ggplot2geomhistogram-end
def plot(self, fn, x='x', y='y', col=None, group=None, w=1100, h=800, size=2, smooth=True, point=True, jitter=False, boxplot=False, boxplot2=False, title=False, flip=False, se=False, density=False, line=False):
df=self.df
#import math, datetime
grdevices = importr('grDevices')
if not title:
title=fn.split("/")[-1]
grdevices.png(file=fn, width=w, height=h)
gp = ggplot2.ggplot(df)
pp = gp
if col and group:
pp+=ggplot2.aes_string(x=x, y=y,col=col,group=group)
elif col:
pp+=ggplot2.aes_string(x=x, y=y,col=col)
elif group:
pp+=ggplot2.aes_string(x=x, y=y,group=group)
else:
pp+=ggplot2.aes_string(x=x, y=y)
if boxplot:
if col:
pp+=ggplot2.geom_boxplot(ggplot2.aes_string(fill=col),color='blue')
else:
pp+=ggplot2.geom_boxplot(color='blue')
if point:
if jitter:
if col:
pp+=ggplot2.geom_point(ggplot2.aes_string(fill=col,col=col),size=size,position='jitter')
else:
pp+=ggplot2.geom_point(size=size,position='jitter')
else:
if col:
pp+=ggplot2.geom_point(ggplot2.aes_string(fill=col,col=col),size=size)
else:
pp+=ggplot2.geom_point(size=size)
if boxplot2:
if col:
pp+=ggplot2.geom_boxplot(ggplot2.aes_string(fill=col),color='blue',outlier_colour="NA")
else:
pp+=ggplot2.geom_boxplot(color='blue')
if smooth:
if smooth=='lm':
if col:
pp+=ggplot2.stat_smooth(ggplot2.aes_string(col=col),size=1,method='lm',se=se)
else:
pp+=ggplot2.stat_smooth(col='blue',size=1,method='lm',se=se)
else:
if col:
pp+=ggplot2.stat_smooth(ggplot2.aes_string(col=col),size=1,se=se)
else:
pp+=ggplot2.stat_smooth(col='blue',size=1,se=se)
if density:
pp+=ggplot2.geom_density(ggplot2.aes_string(x=x,y='..count..'))
if line:
pp+=ggplot2.geom_line(position='jitter')
pp+=ggplot2.opts(**{'title' : title, 'axis.text.x': ggplot2.theme_text(size=24), 'axis.text.y': ggplot2.theme_text(size=24,hjust=1)} )
#pp+=ggplot2.scale_colour_brewer(palette="Set1")
pp+=ggplot2.scale_colour_hue()
if flip:
pp+=ggplot2.coord_flip()
pp.plot()
grdevices.dev_off()
print ">> saved: "+fn
# print str(a)
try:
if dsumFC.has_key(drug):
dsumFC[drug]['Fold_Change'].append(math.log10(float(val)))
dsumY[drug]['Year'].append(yr)
else:
dsumFC[drug]= {'Fold_Change': [math.log10(float(val)),]}
dsumY[drug]= {'Year': [yr,]}
except:
print "FAILURE: dsumFC="+str(dsumFC)+"\n\ndsumY="+str(dsumY)
sys.exit()
drugs = dsumFC.keys()
for x in drugs:
od = rlc.OrdDict([('Fold_Change',robjects.FloatVector(dsumFC[x]['Fold_Change'])),('Year',robjects.FactorVector(dsumY[x]['Year'])),('Drug',robjects.FactorVector(x))])
grdevices.pdf(file="drugs.pdf",width=7,height=7)
dataf = robjects.DataFrame(od)
gp3 = ggplot2.ggplot(dataf)
pp3 = gp3 + ggplot2.scale_fill_brewer(palette='BrBG',name="Year")+ ggplot2.aes_string(x='Year',y='Fold_Change',fill='factor(Year)') + ggplot2.geom_boxplot() + ggplot2.opts(title = x+" Yearly Trend")
# pp3 = gp3 + ggplot2.scale_colour_hue(h=base.c(180,270),name="Year")+ ggplot2.aes_string(x='Year',y='Fold_Change',fill='factor(Year)') + ggplot2.geom_boxplot() + ggplot2.opts(title = x+" Yearly Trend")
#+ ggplot2.scale_y_log10()
pp3.plot()
grdevices.dev_off()
f.close()
print "\nfinished\n"
def rest():
df = q1_median_q3_rep_wide
pops = ["pdc", "dc-cd11b", "dc-cd8a"]
stats_l = []
for stat, (popa, popb) in product(["Q1", "median", "Q3"],
product(pops, pops)):
print(stat, popa, popb)
popa = "hsc"
popb = "pdc"
stat = "median"
mw_u, pvalue = scipy.stats.mannwhitneyu(
[0.8, 0.81, 0.79],
[0.4, 0.39, 0.41],
# df.query("Population == @popa")[stat].to_numpy(),
# df.query("Population == @popb")[stat].to_numpy(),
use_continuity=True,
alternative="two-sided",
)
pvalue
stats_l.append([stat, popa, popb, mw_u, pvalue])
stats_df = pd.DataFrame(stats_l).set_axis(
["stat", "popA", "popB", "U", "pvalue"], axis=1)
kruskal_format_means = pd.pivot(
q1_median_q3_rep_wide.query("Population in @pops"),
index="Population",
columns="Replicate",
values="mean",
)
import scikit_posthocs
stat, p_value = scipy.stats.kruskal(
*[kruskal_format_means.loc[pop].to_numpy() for pop in pops], )
dunn_res_df = scikit_posthocs.posthoc_dunn(
kruskal_format_means.to_numpy(),
p_adjust='fdr_bh',
sort=True,
)
stat, pvalue = scipy.stats.f_oneway(
*[kruskal_format_means.loc[pop].to_numpy() for pop in pops], )
import statsmodels
df = kruskal_format_means.stack().reset_index()
kruskal_format_means
res = statsmodels.stats.multicomp.pairwise_tukeyhsd(
df[0], df['Population'].to_numpy(), alpha=0.05)
res.pvalues
res.summary()
# wilcox.test(c(0.8, 0.79, 0.81), c(0.4, 0.39, 0.41), paired=F, exact=F)
plot_pops = ["pdc", "dc-cd8a", "dc-cd11b"]
results_dir = "/icgc/dkfzlsdf/analysis/hs_ontogeny/notebook-data/gNs4xcMJscaLLwlt"
point_plot_quartiles_png = results_dir + "/point-plot-quartiles.png"
q1_median_q3_rep_wide
ggplot_data = (
q1_median_q3_rep_long.query("Population in @plot_pops").sort_values(
"value",
ascending=False,
).groupby(["Population", "stat"]).apply(
lambda df: df.assign(group_order=np.arange(1, df.shape[0] + 1))))
g = (gg.ggplot(ggplot_data) + gg.aes_string(
x="Population", y="value", group="group_order", color="stat") +
gg.geom_point(position=gg.position_dodge(width=0.5), size=1) +
mh_rpy2_styling.gg_paper_theme + gg.labs(y='Methylation (%)', x=''))
a = 3
rpy2_utils.image_png2(g, (ut.cm(6), ut.cm(6)))
ut.save_and_display(
g,
png_path=point_plot_quartiles_png,
# additional_formats=tuple(),
height=ut.cm(6),
width=ut.cm(6),
)
q1_median_q3_rep_wide
g = (
gg.ggplot(
q1_median_q3_rep_wide.query("Population in @plot_pops").assign(
sample=lambda df: df["Population"].astype(str) + df[
"Replicate"].astype(str))) + gg.geom_boxplot(
gg.aes_string(
x="Population",
fill="Population",
group="sample",
lower="Q1",
upper="Q3",
middle="median",
ymin="min1",
ymax="max99",
# position=gg.position_dodge(width=0.5),
),
stat="identity",
)
# + mh_rpy2_styling.gg_paper_theme
+ gg.theme(axis_text_x=gg.element_text(angle=90, hjust=1)) +
gg.scale_fill_brewer(guide=False))
a = 3
ut.save_and_display(
g,
png_path=point_plot_quartiles_png,
additional_formats=tuple(),
height=ut.cm(6),
width=ut.cm(7),
)
# image_png2(g, (ut.cm(12), ut.cm(12)))
beta_values.loc[:, ("hsc", "1")]
def plot(self,
fn,
x='x',
y='y',
col=None,
group=None,
w=1100,
h=800,
size=2,
smooth=True,
point=True,
jitter=False,
boxplot=False,
boxplot2=False,
title=False,
flip=False,
se=False,
density=False,
line=False):
df = self.df
#import math, datetime
grdevices = importr('grDevices')
if not title:
title = fn.split("/")[-1]
grdevices.png(file=fn, width=w, height=h)
gp = ggplot2.ggplot(df)
pp = gp
if col and group:
pp += ggplot2.aes_string(x=x, y=y, col=col, group=group)
elif col:
pp += ggplot2.aes_string(x=x, y=y, col=col)
elif group:
pp += ggplot2.aes_string(x=x, y=y, group=group)
else:
pp += ggplot2.aes_string(x=x, y=y)
if boxplot:
if col:
pp += ggplot2.geom_boxplot(ggplot2.aes_string(fill=col),
color='blue')
else:
pp += ggplot2.geom_boxplot(color='blue')
if point:
if jitter:
if col:
pp += ggplot2.geom_point(ggplot2.aes_string(fill=col,
col=col),
size=size,
position='jitter')
else:
pp += ggplot2.geom_point(size=size, position='jitter')
else:
if col:
pp += ggplot2.geom_point(ggplot2.aes_string(fill=col,
col=col),
size=size)
else:
pp += ggplot2.geom_point(size=size)
if boxplot2:
if col:
pp += ggplot2.geom_boxplot(ggplot2.aes_string(fill=col),
color='blue',
outlier_colour="NA")
else:
pp += ggplot2.geom_boxplot(color='blue')
if smooth:
if smooth == 'lm':
if col:
pp += ggplot2.stat_smooth(ggplot2.aes_string(col=col),
size=1,
method='lm',
se=se)
else:
pp += ggplot2.stat_smooth(col='blue',
size=1,
method='lm',
se=se)
else:
if col:
pp += ggplot2.stat_smooth(ggplot2.aes_string(col=col),
size=1,
se=se)
else:
pp += ggplot2.stat_smooth(col='blue', size=1, se=se)
if density:
pp += ggplot2.geom_density(ggplot2.aes_string(x=x, y='..count..'))
if line:
pp += ggplot2.geom_line(position='jitter')
pp += ggplot2.opts(
**{
'title': title,
'axis.text.x': ggplot2.theme_text(size=24),
'axis.text.y': ggplot2.theme_text(size=24, hjust=1)
})
#pp+=ggplot2.scale_colour_brewer(palette="Set1")
pp += ggplot2.scale_colour_hue()
if flip:
pp += ggplot2.coord_flip()
pp.plot()
grdevices.dev_off()
print ">> saved: " + fn
