def displacement_plot(centered, limits=None, style=None):
u"""Draws nice displacement plots using ggplot2.
params:
centered (pd.DataFrame): needs cX, cY, Object, Frame columns, probably
produced by calling center() above
limits (real): Sets the limits of the scales to a square window showing
±limits on each axis.
style (Iterable): Collection of strings. Recognized values are 'theme-bw'
(which uses theme_bw instead of theme_seaborn) and 'no-terminal-dot'
(which does not label the end of tracks which terminate early).
Returns:
g (gg.ggplot): Plot object
"""
style = {} if style is None else style
centered['Object'] = centered['Object'].map(str)
centered = centered.sort(['Frame', 'Object'])
g = (gg.ggplot(centered, gg.aes(x='cX', y='cY', color='Object')) +
gg.geom_path(size=0.3))
g += gg.theme_bw() # if 'theme-bw' in style else gg.theme_seaborn()
if limits:
g = g + gg.ylim(-limits, limits) + gg.xlim(-limits, limits)
if 'no-terminal-dot' not in style:
max_frame = centered['Frame'].max()
endframe = centered.groupby('Object')['Frame'].max()
endframe = endframe[endframe != max_frame].reset_index()
endframe = endframe.merge(centered, on=['Object', 'Frame'])
# we should check if endframe is empty before adding it:
# https://github.com/yhat/ggplot/issues/425
if not endframe.empty:
g += gg.geom_point(data=endframe, color='black', size=1)
return g
def get_plot(X, ids, cluster_dct):
new_X = []
new_ids = []
for (i, nid) in enumerate(ids):
if nid in cluster_dct.keys():
new_X.append(X[i, :])
new_ids.append(nid)
X = np.array(new_X)
ids = np.array(new_ids)
print(X.shape, ids.shape)
feat_cols = ['pixel' + str(i) for i in range(X.shape[1])]
df = pd.DataFrame(X, columns=feat_cols)
n_sne = 480000
rndperm = ids
# print(len(rndperm), rndperm)
# rndperm_o = np.random.permutation(df.shape[0])
# time_start = time.time()
tsne = TSNE(n_components=2, verbose=1, perplexity=40, n_iter=300)
# tsne_results = tsne.fit_transform(df.loc[rndperm[:n_sne],feat_cols].values)
tsne_results = tsne.fit_transform(df.values)
df_tsne = df.copy()
df_tsne['x-tsne'] = tsne_results[:, 0]
df_tsne['y-tsne'] = tsne_results[:, 1]
# print(df_tsne)
print(max(tsne_results[:, 0]), min(tsne_results[:, 0]),
max(tsne_results[:, 1]), min(tsne_results[:, 1]))
kmeans = KMeans(n_clusters=10, random_state=0).fit(tsne_results)
# ids = ids[rndperm[:n_sne]]
# print(ids[0], cluster_dct[ids[0]])
labels = [cluster_dct[i] for i in ids]
y = np.array(labels)
print("y", y, y.shape)
# y = np.array(kmeans.labels_)
df_tsne['label'] = y
df_tsne['label'] = df_tsne['label'].apply(lambda i: str(i))
chart = ggplot( df_tsne, aes(x='x-tsne', y='y-tsne', color='label') ) \
+ geom_point(size=5,alpha=0.5) \
+ theme_bw()\
+ ggtitle("tSNE dimensions of steam graph embeddings")
# ggsave()
print(chart)
def _setup_ggplot(self):
try:
from ggplot import theme_bw
t = theme_bw()
for k, v in t.get_rcParams().iteritems():
mpl.rcParams[k] = v
def plot_post_hook():
for ax in self.figure.axes:
t.post_plot_callback(ax)
self._post_plot_hook = plot_post_hook
except ImportError:
pass
except AttributeError:
pass
def plotAlignmentStat(input, output):
"""plot Alignment summary using ggplot"""
df = pd.read_csv(input, thousands=",")
# replace % with '' and convert the type to float
#df.replace('%', '', regex=True)
print df.dtypes
# convert to numeric
#df1=df.apply(pd.to_numeric, args=('coerce',))
# Get certain rows
print df
df = df.iloc[[2, 4, 5], ]
#df = df.ix[['Uniquely mapped reads %', 'Number of reads mapped to multiple loci %', 'Reads unmapped: too short %']]
dfm = pd.melt(df,
id_vars=['category'],
var_name='sampleName',
value_name='Value')
print dfm
#from ggplot import *
#import pandas as pd
#df = pd.DataFrame({"x":[1,2,3,4], "y":[1,3,4,2]})
#ggplot(aes(x="x", weight="y"), df) + geom_bar()
#ggplot(diamonds, aes(x='price', fill='cut')) + geom_histogram() + theme_bw() + scale_color_brewer(type='qual')
from ggplot import ggplot, geom_bar, aes, theme_bw, ggtitle, coord_flip, geom_histogram #,scale_y_continuous,coord_flip
p = ggplot(dfm, aes(x='sampleName', weight='Value',
fill='category')) + geom_bar() + theme_bw() + ggtitle(
"Alignment Summary stats") + coord_flip(
) # + scale_y_continuous(labels='comma
#p = ggplot(dfm, aes(x='sampleName', weight='Value', fill='category')) + geom_bar(position = "stack", stat='identity') + theme_bw() + ggtitle("Alignment Summary stats") + coord_flip()# + scale_y_continuous(labels='comma') + coord_flip()
#p = ggplot(df, aes(x = "category", y = "value", fill = "variable")) + \
#geom_bar(stat="bar", labels=df["category"].tolist()) + \
#theme(axis_text_x = element_text(angle=90))
dirname, filename = os.path.split(output)
print dirname
print filename
p.save(output)
#ggsave(plot=p, filename=filename, path=dirname)
return
#total-based
dftmp = df[['n_sub']+brks[:5]].melt(id_vars=['n_sub'],value_vars=brks[:5], var_name = 'stat',value_name = 'value')
dftmp['method']=['(Total-Expected Total)/Expected Total']*dftmp['n_sub'].size
df_stacked = dftmp
#enhancement-based
dftmp = df[['n_sub']+brks[5:10]].melt(id_vars=['n_sub'],value_vars=brks[5:10], var_name = 'stat',value_name = 'value')
dftmp['method']=['(Enhanc-Expected Enhanc)/Expected Enhanc']*dftmp['n_sub'].size
df_stacked = df_stacked.append(dftmp)
#enhancements + full sample background
dftmp = df[['n_sub']+brks[10:]].melt(id_vars=['n_sub'],value_vars=brks[10:], var_name = 'stat',value_name = 'value')
dftmp['method']=['(Enhanc+Expected Backgr-Expected Total)/Expected Total']*dftmp['n_sub'].size
df_stacked = df_stacked.append(dftmp)
df_stacked['percentile']=['{0}th%'.format(a[1:3]) for a in df_stacked['stat']]
#plots
#compare all 3
plt1 = gg.ggplot(df_stacked, gg.aes(x='n_sub',y='value',color='percentile'))+gg.geom_line()+gg.xlab('N drives')+gg.ylab('Bias (%)')+gg.theme_bw()+gg.scale_color_manual(values=colors)+gg.geom_hline(y=[-25,25],linetype="dashed",color="gray")+gg.geom_vline(x=[10,15],linetype="dashed",color="gray")+gg.facet_wrap('method')+gg.ggtitle('Bias comparison {0}'.format(title))
plt1.save(filename = r'..\charts\drivebias_laqn_{0}.png'.format(species), width=None, height=None, dpi=300)
#plot total alone for presenation
plt2 = gg.ggplot(df_stacked[df_stacked['method']=='(Total-Expected Total)/Expected Total'], gg.aes(x='n_sub',y='value',color='percentile'))+gg.geom_line()+gg.xlab('N drives')+gg.ylab('Bias (%)')+gg.ylim(-100,100)+gg.scale_color_manual(values=colors)+gg.geom_hline(y=[-25,25],linetype="dashed",color="gray")+gg.geom_vline(x=[10,15],linetype="dashed",color="gray")+gg.ggtitle('Bias comparison {0}'.format(title))
t = gg.theme_bw()
t._rcParams['font.size']=16
plt2 = plt2+t
plt2.save(filename = r'..\charts\drivebias_laqn_{0}_total.png'.format(species), width=None, height=None, dpi=300)
#plot enhancement alone for presenation
plt3 = gg.ggplot(df_stacked[df_stacked['method']=='(Enhanc+Expected Backgr-Expected Total)/Expected Total'], gg.aes(x='n_sub',y='value',color='percentile'))+gg.geom_line()+gg.xlab('N drives')+gg.ylab('Bias (%)')+gg.ylim(-100,100)+gg.scale_color_manual(values=colors)+gg.geom_hline(y=[-25,25],linetype="dashed",color="gray")+gg.geom_vline(x=[10,15],linetype="dashed",color="gray")+gg.ggtitle('Bias comparison {0}'.format(title))
t = gg.theme_bw()
t._rcParams['font.size']=16
plt3 = plt3+t
plt3.save(filename = r'..\charts\drivebias_laqn_{0}_enhanc.png'.format(species), width=None, height=None, dpi=300)
)
group by pod_id_location
""")
qry_job = bqclient.query(qry_str, location='EU', job_config=job_config)
#save result as dataframe
df = qry_job.to_dataframe()
df_long = df.melt(id_vars=['pod_str', 'pod_idx'],
value_vars=['p05', 'p25', 'med', 'p75', 'p95'],
var_name='yparam',
value_name='value')
#plots
#plt1 = gg.ggplot(df, gg.aes(x='date_UTC',y='no2_ppb'))+gg.geom_line()+gg.xlab('Time')+gg.ylab('NO2 (ppb)')+gg.theme_bw()+gg.facet_wrap('pod_id_location',scales='free_y')
#plt1.save(filename = r'.\charts\ulezpodts.png', width=None, height=None, dpi=200)
plt2 = gg.ggplot(df_long, gg.aes(
x='pod_str', y='value', color='yparam')) + gg.geom_point() + gg.xlab(
'pod') + gg.ylab('NO2 (as % of median)') + gg.theme_bw() + gg.theme(
figure_size=(12, 6)) + gg.scale_x_discrete()
plt2.save(filename=r'.\charts\ulezpodvar.png', width=10, height=6, dpi=200)
#repeat for mobile data using segid instead of podid where N = 10 and N = 40
#repeat for stationary data at mobile times
qry_str = ("""
with cte0 as (
--all data, ULEZ pods with 6000 hrs
select date_UTC, a.pod_id_location, no2_ppb
from AQMesh.NO2_scaled_hightimeres_ppb_20180901_20190630 a
join AQMesh.NO2_site_metadata_v2_1_20180901_20190630 b
on a.pod_id_location=b.pod_id_location
where ULEZ = true and no2_ppb <> -999
and a.pod_id_location in
--limit to pods with at least 6000 hours
(vcfdf['TestBias']=='Pass') &
(vcfdf['CHROM']==reference) ]['Pi']))
return testwindows
# 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")
import sys
from pandas.plotting import register_matplotlib_converters
register_matplotlib_converters()
species = 'no2'
df = pd.read_csv(r'.\charts\background_data_melted.csv',
index_col='idx',
dtype={
'timestamp': 'str',
'vidperiod': 'str',
'type': 'str',
'param': 'str',
'value': 'float64'
})
print(df[:10])
df['timestamp'] = pd.to_datetime(df['timestamp'], format="%Y-%m-%d %H:%M:%S")
#plots
plt1 = gg.ggplot(df, gg.aes(
x='timestamp', y='value', color='type')) + gg.geom_line() + gg.xlab(
'Time') + gg.ylab('Concentration') + gg.theme_bw() + gg.ylim(
0, 100) + gg.facet_wrap('vidperiod', scales='free') + gg.ggtitle(
'Regional background comparison {0}'.format(species))
#+gg.theme(axis_text_x=gg.element_text(angle=20))
plt1.save(filename=r'.\charts\background_{0}_ggtest_{1}.png'.format(
species,
dt.datetime.today().strftime('%Y%b%d')),
width=None,
height=None,
dpi=300)
for x in repeatedKnnResults],
columns = ['p',
'k',
'cvAccuracy',
'testAccuracy'])
ggdata = pandas.concat(
[DataFrame({'log10(p)' : log10(knnResultsSimplified.p),
'k' : knnResultsSimplified.k.apply(int),
'type' : 'cv',
'Accuracy' : knnResultsSimplified.cvAccuracy}),
DataFrame({'log10(p)' : log10(knnResultsSimplified.p),
'k' : knnResultsSimplified.k.apply(int),
'type' : 'test',
'Accuracy' : knnResultsSimplified.testAccuracy})],
axis = 0
)
ggobj = ggplot.ggplot(
data = ggdata,
aesthetics = ggplot.aes(x='log10(p)', y='Accuracy',
color='type', group='type', linetype='type')
)
ggobj += ggplot.theme_bw()
# ggobj += ggplot.scale_x_log()
ggobj += ggplot.geom_point(alpha=0.6)
ggobj += ggplot.stat_smooth()
ggobj += ggplot.facet_wrap('k')
print(ggobj)
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)
df_along = df_a.melt(id_vars=['site_str', 'n_passes'],
value_vars=['p05', 'p25', 'p50', 'p75', 'p95'],
var_name='yparam',
value_name='value')
print(c['name'])
#print(df_a)
#plots
#split percentiles into different charts, all sites
#plt1 = gg.ggplot(df_along, gg.aes(x='n_passes',y='value',color='site_str'))+gg.geom_point()+gg.xlab('N drives')+gg.ylab('Bias (%)')+gg.theme_bw()+gg.xlim(0,100)+gg.facet_wrap('yparam',scales='free_y')
#plt1.save(filename = r'..\charts\bias_{0}.png'.format(c['name']), width=None, height=None, dpi=200)
#n_segments
plt2 = gg.ggplot(
df_a, gg.aes(x='n_passes', y='n_segments', color='site_str')
) + gg.geom_line() + gg.xlab('n, number drive periods') + gg.ylab(
'Sample size (number of drive patterns)') + gg.theme_bw() + gg.xlim(
0, 35) + gg.ylim(0, 2000)
plt2.save(filename=r'..\charts\n_segments_{0}_{1}.png'.format(
c['name'], dtstamp),
width=None,
height=None,
dpi=200)
#combine percentiles, split sites
plt3 = gg.ggplot(
df_along, gg.aes(x='n_passes', y='value', color='yparam')
) + gg.geom_line() + gg.xlab('n, number of drive periods') + gg.ylab(
'Sample error (%)') + gg.theme_bw() + gg.xlim(0, 35) + gg.ylim(
-100, 100) + gg.geom_hline(
y=25, linetype="dashed", color="gray") + gg.geom_hline(
y=-25, linetype="dashed", color="gray") + gg.geom_vline(
x=[10, 15], linetype="dashed",
for x in repeatedKnnResults],
columns = ['p',
'k',
'cvAccuracy',
'testAccuracy'])
ggdata = pandas.concat(
[DataFrame({'log10(p)' : log10(knnResultsSimplified.p),
'k' : knnResultsSimplified.k.apply(int),
'type' : 'cv',
'Accuracy' : knnResultsSimplified.cvAccuracy}),
DataFrame({'log10(p)' : log10(knnResultsSimplified.p),
'k' : knnResultsSimplified.k.apply(int),
'type' : 'test',
'Accuracy' : knnResultsSimplified.testAccuracy})],
axis = 0
)
ggobj = ggplot.ggplot(
data = ggdata,
aesthetics = ggplot.aes(x='log10(p)', y='Accuracy',
color='type', group='type', linetype='type')
)
ggobj += ggplot.theme_bw()
# ggobj += ggplot.scale_x_log()
ggobj += ggplot.geom_point(alpha=0.6)
ggobj += ggplot.stat_smooth()
ggobj += ggplot.facet_wrap('k')
print ggobj
