def production_envelope(self,
dataframe,
grid=None,
width=None,
height=None,
title=None,
points=None,
points_colors=None,
palette=None,
x_axis_label=None,
y_axis_label=None):
palette = self.get_option('palette') if palette is None else palette
width = self.get_option('width') if width is None else width
colors = self._palette(palette, len(dataframe.strain.unique()))
plot = aes(data=dataframe,
ymin="lb",
ymax="ub",
x="value",
color=scale_colour_manual(colors)) + geom_area()
if title:
plot += geom_tile(title)
if x_axis_label:
plot += scale_x_continuous(name=x_axis_label)
if y_axis_label:
plot += scale_y_continuous(name=y_axis_label)
return plot
def histogram(self, dataframe, bins=100, width=None, height=None, palette=None, title='Histogram', values=None,
groups=None, legend=True):
palette = self.__default_options__.get('palette', None) if palette is None else palette
return ggplot(dataframe, aes(x=values, fill=groups, color=groups)) + \
geom_histogram(alpha=0.6, breaks=bins, position="fill") + \
self._palette(palette) + \
ggtitle(title) + \
scale_y_continuous(name="Count (%s)" % values)
def signature_data_plot(sd):
import ggplot as gg
aes = gg.aes(x='set_exp', y='not_exp', color='pearson_r')
return gg.ggplot(aes, data=sd) \
+ gg.geom_point(size=15) \
+ gg.scale_color_gradient(low='yellow', high='red') \
+ gg.scale_x_log() + gg.scale_x_continuous(limits=(0.5, 10000)) \
+ gg.scale_y_log() + gg.scale_y_continuous(limits=(0.05, 10000))
def signature_data_plot(sd):
import ggplot as gg
aes = gg.aes(x='set_exp', y='not_exp', color='pearson_r')
return gg.ggplot(aes, data=sd) \
+ gg.geom_point(size=15) \
+ gg.scale_color_gradient(low='yellow', high='red') \
+ gg.scale_x_log() + gg.scale_x_continuous(limits=(0.5, 10000)) \
+ gg.scale_y_log() + gg.scale_y_continuous(limits=(0.05, 10000))
def scatter(self, dataframe, x=None, y=None, width=None, height=None, color=None, title='Scatter', xaxis_label=None,
yaxis_label=None):
color = self.__default_options__.get('palette', None) if color is None else color
width = self.__default_options__.get('width', None) if width is None else width
gg = ggplot(dataframe, aes(x, y)) + geom_point(color=color, alpha=0.6) + ggtitle(title)
if xaxis_label:
gg += scale_x_continuous(name=xaxis_label)
if yaxis_label:
gg += scale_y_continuous(name=xaxis_label)
return gg
def histogram(self,
dataframe,
bins=100,
width=None,
height=None,
palette=None,
title='Histogram',
values=None,
groups=None,
legend=True):
palette = self.__default_options__.get(
'palette', None) if palette is None else palette
return ggplot(dataframe, aes(x=values, fill=groups, color=groups)) + \
geom_histogram(alpha=0.6, breaks=bins, position="fill") + \
self._palette(palette) + \
ggtitle(title) + \
scale_y_continuous(name="Count (%s)" % values)
def _plot_and_save_local_ancestry(df, kmer, image_filename, num_chromosomes, id_vars, x_axis, y_scale):
print('saving plot as: {}'.format(image_filename))
var_name='chromosome'
local_ancestry_df_long = pd.melt(df, id_vars=id_vars, var_name=var_name, value_name='estimated_ancestry')
new_names = {}
for i in range(1, num_chromosomes + 1):
new_names['test_{}'.format(i)] = 2*i - 2 * y_scale
new_names['true_{}'.format(i)] = 2*i - 1 * y_scale
for key, value in new_names.items():
local_ancestry_df_long.replace(key, value, inplace=True)
plot = ggplot.ggplot(ggplot.aes(x=x_axis, y=var_name, color='estimated_ancestry'), data=local_ancestry_df_long) \
+ ggplot.geom_point() \
+ ggplot.scale_y_continuous(labels=list(new_names.keys()), breaks=list(new_names.values())) \
+ ggplot.scale_color_manual(values=['#FF0000', '#0000FF', '#73008C']) \
+ ggplot.theme(plot_margin={'top':0.7, 'bottom':0.3}) ### TODO: this should depend on scale
plot.save(image_filename)
def scatter(self,
dataframe,
x=None,
y=None,
width=None,
height=None,
color=None,
title='Scatter',
xaxis_label=None,
yaxis_label=None,
label=None):
color = self.__default_options__.get('palette',
None) if color is None else color
width = self.__default_options__.get('width',
None) if width is None else width
gg = ggplot(dataframe, aes(x, y)) + geom_point(
color=color, alpha=0.6) + ggtitle(title)
if xaxis_label:
gg += scale_x_continuous(name=xaxis_label)
if yaxis_label:
gg += scale_y_continuous(name=xaxis_label)
return gg
p += ggtitle("sarimax coefficient magnitude distribution")
p += facet_wrap("feature", ncol=3, scales="free")
p += labs(x=" ", y=" ")
# visuals
t = theme_gray()
t._rcParams['font.size'] = 10
t._rcParams['font.family'] = 'monospace'
p += t
p.save("arima_1/" + "histogram.png")
# boxplot
p = ggplot(aes(x='variable', y='value'), data=master_df)
p += geom_boxplot()
p += scale_y_continuous(limits=(-25, 25))
p += ggtitle("sarimax coefficient magnitudes")
p += facet_wrap("feature", ncol=3)
p += labs(x=" ", y=" ")
# visuals
t = theme_gray()
t._rcParams['font.size'] = 10
t._rcParams['font.family'] = 'monospace'
p += t
p.save("arima_1/" + "boxplot.png")
for feature in [
"home_goal", "away_goal", "home_yellow", "away_yellow", "home_red",
"away_red"
# Generate new dataframe with analyses performed per window
if options.graphics == True:
print "Analysing by "+ str(windowsize) +"sliding windows and generating plots"
windowed_df = pd.DataFrame({'window':sorted(list(set(vcfdf['window']))),
'MaxMinor':windowMax(sorted(list(set(vcfdf['window'])))),
'Pi':windowPi(sorted(list(set(vcfdf['window']))))})
# Now try and plot graph
p_MaxMinor = gg.ggplot(gg.aes('window', 'MaxMinor'),data=windowed_df) +gg.geom_point() +gg.theme_bw() +gg.labs(x="Genome Position (bp; windowsize="+ str(windowsize) +")", y="Minor Variant Frequency (%)") +gg.ggtitle(vcfoutput + "\n Valid Minor Variant Sites :" + str(len(minorvar)))
# Plot Nucleotide Diversity (Pi) along genome
p_pi =gg.ggplot(gg.aes('window', 'Pi'),data=windowed_df) +gg.geom_point() +gg.theme_bw() +gg.labs(x="Genome Position (bp; windowsize="+ str(windowsize) +")", y="Mean nucleotide diversity (" + u"\u03c0" +")") +gg.scale_y_continuous(expand=(0,0),limits=(0, windowed_df['Pi'].max(axis=0)+0.001)) +gg.ggtitle(vcfoutput + "\n Genome-wide Mean Nucleotide Diversity (" +u"\u03c0"+ ") :" +str(round(gw_Pi,6)))
#p_pi
# Facetted plot (still not sorted y axes labels yet)
windowed_df_melt = pd.melt(windowed_df, id_vars=['window'])
p_combi = gg.ggplot(gg.aes('window', 'value',colour='variable'),data=windowed_df_melt)
p_combi = p_combi + gg.geom_point(colour='variable') + gg.facet_grid('variable',scales='free_y')+gg.theme_bw() +gg.labs(x="Genome Position (bp; windowsize="+ str(windowsize) +")")
# Print graphs to .png
p_combi.save(vcfinput + ".MinorVar_combo.png")
p_MaxMinor.save(vcfinput + ".MinorVar.png")
p_pi.save(vcfinput + ".Pi-diversity.png")
def new_plot_ancestry_with_correct_results(test, true, y_scale=0.5, image_filename=None):
columns_to_ignore = ['POS', 'ID', 'REF', 'ALT', 'QUAL', 'FILTER', 'INFO', 'FORMAT'] ### we want only 'POS' and ancestry columns
ancestry_cols = list(filter(lambda x: x not in columns_to_ignore, test.columns))
merged = pd.DataFrame(test['POS'])
for col_name in ancestry_cols:
if col_name not in true:
raise KeyError('true ancestry dataframe is missing ancestry for id: {}'.format(col_name))
merged[col_name+'_test'] = test[col_name]
merged[col_name+'_true'] = true[col_name]
melted = pd.melt(merged, id_vars=['POS'], var_name='chromosome', value_name='ancestry')
# the above takes merged from something like this:
###
### columns: POS sample1_test sample1_true sample2_test sample2_true
### 111 pop1 pop1 pop2 pop1
### 124 pop1 pop1 pop2 pop1
###
# to this: (spaces between rows added for clarity)
###
### columns: POS chromosome ancestry
# 111 sample1_test pop1
# 124 sample1_test pop1
#
# 111 sample1_true pop1
# 124 sample1_true pop1
#
# 111 sample2_test pop2
# 124 sample2_test pop2
#
# 111 sample2_true pop1
# 124 sample2_true pop1
spacing = {}
for i, col_name in enumerate(ancestry_cols):
spacing[col_name+'_test'] = 2*i - 2 * y_scale
spacing[col_name+'_true'] = 2*i - 1 * y_scale
# taks above example to something like:
###
### columns: POS chromosome ancestry
# 111 0 pop1
# 124 0 pop1
#
# 111 1 pop1
# 124 1 pop1
#
# 111 2 pop2
# 124 2 pop2
#
# 111 3 pop1
# 124 3 pop1
for col_name, spacing_val in spacing.items():
melted.replace(col_name, spacing_val, inplace=True)
plot = ggplot.ggplot(ggplot.aes(x='POS', y='chromosome', color='ancestry'), data=melted) \
+ ggplot.geom_point() \
+ ggplot.scale_y_continuous(labels=list(spacing.keys()), breaks=list(spacing.values())) \
+ ggplot.scale_color_manual(values=['#FF0000', '#0000FF', '#73008C']) \
+ ggplot.theme(plot_margin={'top':0.7, 'bottom':0.3}) ### TODO: this should depend on scale
if image_filename is not None:
plot.save(image_filename)
else:
plot.show()
def firms_dynamics_plot(decision):
data = pd.read_csv(os.path.join(
parameters.OUTPUT_PATH,
"temp_general_firms_pop_%s_decision_%s_time_%s.txt" %
(parameters.pop_redutor, decision, parameters.final_Time)),
sep=",",
header=None,
decimal=",").astype(float)
# renaming the collunms names
data.columns = [
'time', 'total_firms', 'average_output', 'average_age', 'average_size',
'new_firms', 'exit_firms', 'max_size', 'total_effort', 'average_effort'
]
#logical test to control the process of burn the initial
if parameters.time_to_cut_plots > 0:
data = data.loc[(
data['time']).astype(int) >= parameters.time_to_cut_plots, :]
# variable to add in the plot title
title_pop_val = float(parameters.pop_redutor) * 100
# create a list of a years to plot
list_of_years_division = list(
range(int(data['time'].min()), int(data['time'].max()),
12)) + [data['time'].max() + 1]
list_of_years = [int(i / 12) for i in list_of_years_division]
# graph paramter variables
dpi_var_plot = 700
width_var_plot = 15
height_var_plot = 10
###############################################################################################################
# plotting AGENTS UTILITY
# Total firms
plot_data = gg.ggplot(data, gg.aes('time', 'total_firms')) + gg.geom_line() + gg.scale_y_continuous(breaks=11) + \
gg.scale_x_discrete(breaks=list_of_years_division, labels=list_of_years) +\
gg.ggtitle('Total firms') + gg.xlab('Years') + gg.ylab('Total of Firms')+ gg.theme_bw()
# logical test for presence of plot, if is TRUE is deleted before save the new one
if os.path.isfile(
os.path.join(
parameters.OUTPUT_PATH,
('temp_general_total_firms_%s_%s_%s.png' %
(decision, title_pop_val, parameters.final_Time)))) is True:
os.remove(
os.path.join(parameters.OUTPUT_PATH,
('temp_general_total_firms_%s_%s_%s.png' %
(decision, title_pop_val, parameters.final_Time))))
# saving the plot
gg.ggsave(plot_data,
os.path.join(parameters.OUTPUT_PATH,
('temp_general_total_firms_%s_%s_%s.png' %
(decision, title_pop_val, parameters.final_Time))),
width=width_var_plot,
height=height_var_plot,
units="in")
# Average of output
plot_data = gg.ggplot(data, gg.aes('time', 'average_output')) + gg.geom_line() + gg.scale_y_continuous(breaks=11) + \
gg.scale_x_discrete(breaks=list_of_years_division, labels=list_of_years)\
+gg.ggtitle('Average of output') + gg.xlab('Years') + gg.ylab('Units')+ gg.theme_bw()
# logical test for presence of plot, if is TRUE is deleted before save the new one
if os.path.isfile(
os.path.join(
parameters.OUTPUT_PATH,
('temp_general_average_output_%s_%s_%s.png' %
(decision, title_pop_val, parameters.final_Time)))) is True:
os.remove(
os.path.join(parameters.OUTPUT_PATH,
('temp_general_average_output_%s_%s_%s.png' %
(decision, title_pop_val, parameters.final_Time))))
# saving the plot
gg.ggsave(plot_data,
os.path.join(parameters.OUTPUT_PATH,
('temp_general_average_output_%s_%s_%s.png' %
(decision, title_pop_val, parameters.final_Time))),
width=width_var_plot,
height=height_var_plot,
units="in")
# Average of age
plot_data = gg.ggplot(data, gg.aes('time', 'average_age')) + gg.geom_line() + gg.scale_y_continuous(breaks=11) + \
gg.scale_x_discrete(breaks=list_of_years_division, labels=list_of_years)\
+gg.ggtitle('Average of age of firms') + gg.xlab('Years') + gg.ylab('Age of Firms')+ gg.theme_bw()
# logical test for presence of plot, if is TRUE is deleted before save the new one
if os.path.isfile(
os.path.join(
parameters.OUTPUT_PATH,
('temp_general_average_age_%s_%s_%s.png' %
(decision, title_pop_val, parameters.final_Time)))) is True:
os.remove(
os.path.join(parameters.OUTPUT_PATH,
('temp_general_average_age_%s_%s_%s.png' %
(decision, title_pop_val, parameters.final_Time))))
# saving the plot
gg.ggsave(plot_data,
os.path.join(parameters.OUTPUT_PATH,
('temp_general_average_age_%s_%s_%s.png' %
(decision, title_pop_val, parameters.final_Time))),
width=width_var_plot,
height=height_var_plot,
units="in")
# Average of size
plot_data = gg.ggplot(data, gg.aes('time', 'average_size')) + gg.geom_line() + gg.scale_y_continuous(breaks=11) + \
gg.scale_x_discrete(breaks=list_of_years_division, labels=list_of_years)\
+gg.ggtitle('Average of size of firms') + gg.xlab('Years') + gg.ylab('Units')+ gg.theme_bw()
# logical test for presence of plot, if is TRUE is deleted before save the new one
if os.path.isfile(
os.path.join(
parameters.OUTPUT_PATH,
('temp_general_average_size_%s_%s_%s.png' %
(decision, title_pop_val, parameters.final_Time)))) is True:
os.remove(
os.path.join(parameters.OUTPUT_PATH,
('temp_general_average_size_%s_%s_%s.png' %
(decision, title_pop_val, parameters.final_Time))))
# saving the plot
gg.ggsave(plot_data,
os.path.join(parameters.OUTPUT_PATH,
('temp_general_average_size_%s_%s_%s.png' %
(decision, title_pop_val, parameters.final_Time))),
width=width_var_plot,
height=height_var_plot,
units="in")
# number of new firms
plot_data = gg.ggplot(data, gg.aes('time', 'new_firms')) + gg.geom_line() + gg.scale_y_continuous(breaks=11) + \
gg.scale_x_discrete(breaks=list_of_years_division, labels=list_of_years)\
+gg.ggtitle('Number of new firms') + gg.xlab('Years') + gg.ylab('Units')+ gg.theme_bw()
# logical test for presence of plot, if is TRUE is deleted before save the new one
if os.path.isfile(
os.path.join(
parameters.OUTPUT_PATH,
('temp_general_number_of_new_firms_%s_%s_%s.png' %
(decision, title_pop_val, parameters.final_Time)))) is True:
os.remove(
os.path.join(parameters.OUTPUT_PATH,
('temp_general_number_of_new_firms_%s_%s_%s.png' %
(decision, title_pop_val, parameters.final_Time))))
# saving the plot
gg.ggsave(plot_data,
os.path.join(parameters.OUTPUT_PATH,
('temp_general_number_of_new_firms_%s_%s_%s.png' %
(decision, title_pop_val, parameters.final_Time))),
width=width_var_plot,
height=height_var_plot,
units="in")
# Number of firms out
plot_data = gg.ggplot(data, gg.aes('time', 'exit_firms')) + gg.geom_line() + gg.scale_y_continuous(breaks=11) + \
gg.scale_x_discrete(breaks=list_of_years_division, labels=list_of_years)\
+gg.ggtitle('Number of firms out') + gg.xlab('Years') + gg.ylab('Units')+ gg.theme_bw()
# logical test for presence of plot, if is TRUE is deleted before save the new one
if os.path.isfile(
os.path.join(
parameters.OUTPUT_PATH,
('temp_general_number_of_firms_out_%s_%s_%s.png' %
(decision, title_pop_val, parameters.final_Time)))) is True:
os.remove(
os.path.join(parameters.OUTPUT_PATH,
('temp_general_number_of_firms_out_%s_%s_%s.png' %
(decision, title_pop_val, parameters.final_Time))))
# saving the plot
gg.ggsave(plot_data,
os.path.join(parameters.OUTPUT_PATH,
('temp_general_number_of_firms_out_%s_%s_%s.png' %
(decision, title_pop_val, parameters.final_Time))),
width=width_var_plot,
height=height_var_plot,
units="in")
# Average and max size of firms
dat_merged = pd.concat([
data.iloc[:, data.columns == 'average_effort'],
data.iloc[:, data.columns == 'total_effort']
],
axis=1)
plot_data = dat_merged.plot(
title='Average and maximum effort of employees')
plot_data.set_xlabel('Years')
plot_data.set_ylabel('Values units of effort')
plot_data.legend(loc='center left', bbox_to_anchor=(1, 0.5))
plot_data.set_xticks(list_of_years_division)
plot_data.set_xticklabels(list_of_years)
plot_data.set_axis_bgcolor('w')
fig = plot_data.get_figure()
fig.set_size_inches(width_var_plot, height_var_plot)
# logical test for presence of plot, if is TRUE is deleted before save the new one
if os.path.isfile(
os.path.join(
parameters.OUTPUT_PATH,
('temp_average_and_maximum_effort_of_firms_out_%s_%s_%s.png' %
(decision, title_pop_val, parameters.final_Time)))) is True:
os.remove(
os.path.join(
parameters.OUTPUT_PATH,
('temp_average_and_maximum_effort_of_firms_out_%s_%s_%s.png' %
(decision, title_pop_val, parameters.final_Time))))
# saving the plot
fig.savefig(os.path.join(
parameters.OUTPUT_PATH,
('temp_average_and_maximum_effort_of_firms_out_%s_%s_%s.png' %
(decision, title_pop_val, parameters.final_Time))),
dpi=dpi_var_plot)
dat_merged = pd.concat([
data.iloc[:, data.columns == 'average_size'],
data.iloc[:, data.columns == 'max_size']
],
axis=1)
plot_data = dat_merged.plot(title='Average and maximum size firms')
plot_data.set_xlabel('Years')
plot_data.set_ylabel('Number of employees')
plot_data.legend(loc='center left', bbox_to_anchor=(1, 0.5))
plot_data.set_xticks(list_of_years_division)
plot_data.set_xticklabels(list_of_years)
plot_data.set_axis_bgcolor('w')
fig = plot_data.get_figure()
fig.set_size_inches(width_var_plot, height_var_plot)
# logical test for presence of plot, if is TRUE is deleted before save the new one
if os.path.isfile(
os.path.join(
parameters.OUTPUT_PATH,
('temp_average_size_and_maximum_of_firms_out_%s_%s_%s.png' %
(decision, title_pop_val, parameters.final_Time)))) is True:
os.remove(
os.path.join(
parameters.OUTPUT_PATH,
('temp_average_size_and_maximum_of_firms_out_%s_%s_%s.png' %
(decision, title_pop_val, parameters.final_Time))))
# saving the plot
fig.savefig(os.path.join(
parameters.OUTPUT_PATH,
('temp_average_size_and_maximum_of_firms_out_%s_%s_%s.png' %
(decision, title_pop_val, parameters.final_Time))),
dpi=dpi_var_plot)
def plot_vol(dates, x, cp, my_domain):
# -------------------- Prepare for Plotting -------------------------- #
# Prepare DataFrame objects for graphing
#Add a column for the label to show in the legend in the graph
#Need to reshape it, from (124,) to (124,1) for exmple, so that it
#will concatenate. This gives a df with [date, vol_data, 'Volume']
v = ['Volume' for i in xrange(x.shape[0])]
#df_domain = np.concatenate((x, v), axis=1)
ndf_vol = np.transpose(np.array([dates, x, v]))
df_vol = pd.DataFrame(ndf_vol, columns=['Date', 'Volume', 'Data'])
#Create pre-allocated lists for plotting means and cp
xmin_list = [0 for i in xrange(len(cp))] #hold lft pt of vol_mean
xmax_list = [0 for i in xrange(len(cp))] #hold rt pt of vol_mean
yint_list = [0 for i in xrange(len(cp))] #holds vol_means
cp_date_list = [0 for i in xrange(len(cp))] #holds date for cp
cp_value_list = [0 for i in xrange(len(cp))] #holds cp value
ref_idx = 0 #used to keep track of vol_means
#collect list data for plotting
for i in xrange(len(cp)):
cp_idx = cp[i][0] - 1 #-1 b/c 1-indexed (includes cp itself)
xmin_list[i] = dates[ref_idx].toordinal() #convert to match ggplot
xmax_list[i] = dates[cp_idx].toordinal() #convert to match ggplot
yint_list[i] = cp[i][2] #use value from_mean for vol_mean
cp_date_list[i] = dates[cp_idx] #date of cp
#cp_value_list[i] = x[cp_idx] #value of cp
cp_value_list[i] = cp[i][2]
ref_idx = cp_idx + 1 #+1 b/c moving to next point
#Reform lists into a data frame and attach to df_domains. The first two
#lists can be created together since they are both numeric, but if I try
#to create all three together all types will be downgraded to strings.
#np.concatenate avoids this conversion. The transpose is needed to take
#an item from each to form a single row.
cp_lbl = ['Change Point' for i in xrange(len(yint_list))]
#Need to create a dummy entry to put 'Volume Mean' into legend
cp_date_list.append(dates[0])
yint_list.append(x[0])
cp_lbl.append('Volume Mean')
ndf_cp = np.transpose(np.array([cp_date_list, yint_list, cp_lbl]))
yint_list.pop(-1)
cp_date_list.pop(-1)
df_cp = pd.DataFrame(ndf_cp, columns=['Date', 'Volume', 'Data'])
df_plot = pd.concat((df_vol, df_cp), axis=0)
#Need to create a dummy entry to put 'Volume Mean' into legend
#dummy = np.array([dates[0], x[0], 'Volume Mean']).reshape(1,-1)
#df_cp = np.concatenate( (df_cp, dummy), axis=0) #add to bottom df_cp
#df_domain = np.concatenate( (df_domain, df_cp), axis=0 ) #add df_domains
#convert final array into a pd.DataFrame for printing and plotting
#df_domain = pd.DataFrame(df_domain, columns=['Date','Volume','Data'])
#df_domain.to_html(open('out.html','w'))
#os.system('sudo cp out.html /usr/local/www/analytics/rwing')
margin = 0.10 * (np.max(x) - np.min(x))
p = ggplot.ggplot(aes(x='Date', y='Volume', color='Data'), data=df_plot) + \
ggplot.geom_line(color='blue',size=2) + \
ggplot.geom_point(x=xmax_list, y=cp_value_list, color='black', \
shape='D', size=50) + \
ggplot.geom_hline(xmin=xmin_list, \
xmax=xmax_list, \
yintercept=yint_list, color="red", size=3) + \
ggplot.scale_x_date(labels = date_format("%Y-%m-%d"), breaks="1 week") + \
ggplot.scale_colour_manual(values = ["black", "blue", "red"]) + \
ggplot.scale_y_continuous(labels='comma') + \
ggplot.ylim(low=np.min(x)-margin/4.0, high=np.max(x)+margin) + \
ggplot.xlab("Week (Marked on Mondays)") + \
ggplot.ylab("Message Vol") + \
ggplot.ggtitle("%s\nMessage Volume by Week" % my_domain) + \
ggplot.theme_seaborn()
return p
def main():
parser = argparse.ArgumentParser(description="Draws displacement plots.",
formatter_class=argparse.ArgumentDefaultsHelpFormatter)
parser.add_argument('--limits', type=int, help="Maximum extent of the axes")
parser.add_argument('--no-plots', action='store_true', help="Don't save plots")
parser.add_argument('--summary', help='Save summary stats by file')
parser.add_argument('--imagetype', '-i', default='png', help="Extension to use for plots")
parser.add_argument('--pixels-per-micron', '--pixels', '-p', default=1.51, type=float,
help="Pixels per µm (length scale of tracked images)")
parser.add_argument('--minutes-per-frame', '--minutes', '-m', default=10, type=float,
help="Minutes between each frame of the tracked images")
parser.add_argument('--plot-titles', type=argparse.FileType('r'),
help="CSV file with filename and title columns")
parser.add_argument('--style', action='append', default=[],
choices=['theme-bw', 'no-terminal-dot'],
help='Change style options for the plot.')
parser.add_argument('--tick-breaks', '--ticks', '-t', nargs=3, type=int,
metavar=('start', 'end', 'step'),
help="Beginning and end tick breaks on displacement plots")
parser.add_argument('--plot-text', type=int, default=8,
help='Plot text size (pt)')
parser.add_argument('--plot-height', type=float, default=1.81,
help='Plot height (in)')
parser.add_argument('--plot-width', type=float, default=2.5,
help='Plot width (in)')
parser.add_argument('infile', nargs='+', help="File(s) to process.")
args = parser.parse_args()
style = {argument: True for argument in args.style}
plot_titles = pd.read_csv(args.plot_titles, index_col="filename") if args.plot_titles else None
all_dfs = []
for filename in args.infile:
# there has to be a better pattern for this
try:
df = read_mtrackj_mdf(filename)
except ValueError:
try:
df = read_mtrack2(filename)
except Exception:
df = read_manual_track(filename)
centered = center(df)
centered.to_csv(filename + '.centered')
if not args.no_plots:
g = displacement_plot(centered, limits=args.limits, style=style)
g += gg.theme(axis_text=gg.element_text(size=args.plot_text))
g += gg.labs(x='px', y='px')
if args.tick_breaks:
g += gg.scale_x_continuous(breaks=range(*args.tick_breaks))
g += gg.scale_y_continuous(breaks=range(*args.tick_breaks))
if plot_titles is not None and filename in plot_titles.index:
g += gg.labs(title=plot_titles.ix[filename, 'title'])
g.save('{}.{}'.format(filename, args.imagetype),
width=args.plot_width, height=args.plot_height)
centered['filename'] = filename
all_dfs.append(centered)
mega_df = pd.concat(all_dfs, ignore_index=True)
stats_for = lambda x: stats(x, length_scale=args.pixels_per_micron,
time_scale=args.minutes_per_frame)
obj_stats = (mega_df.groupby('filename', sort=False)
.apply(stats_for)
.reset_index())
summary_by_file = obj_stats.groupby('filename').apply(summary)
if args.summary:
summary_by_file.to_csv(args.summary, index=False)
print("# Produced by {} at {}".format(' '.join(sys.argv), time.ctime()))
print("# {} pixels per micron, {} minutes per frame".
format(args.pixels_per_micron, args.minutes_per_frame))
print("# distance units are microns; velocity units are microns/hour")
obj_stats.to_csv(sys.stdout, index=False)