def api_activity_histogram(self,app_id,exp_uid,task):
"""
Description: returns the data to plot all API activity (for all algorithms) in a histogram with respect to time for any task in {getQuery,processAnswer,predict}
Expected input:
(string) task : must be in {'getQuery','processAnswer','predict'}
Expected output (in dict):
(dict) MPLD3 plot dictionary
"""
list_of_log_dict,didSucceed,message = self.ell.get_logs_with_filter(app_id+':APP-CALL',{'exp_uid':exp_uid,'task':task})
from datetime import datetime
from datetime import timedelta
start_date_str,didSucceed,message = self.db.get('experiments_admin',exp_uid,'start_date')
start_date = utils.str2datetime(start_date_str)
numerical_timestamps = [ ( utils.str2datetime(item['timestamp'])-start_date).total_seconds() for item in list_of_log_dict]
import matplotlib.pyplot as plt
import mpld3
fig, ax = plt.subplots(subplot_kw=dict(axisbg='#FFFFFF'),figsize=(12,1.5))
ax.hist(numerical_timestamps,int(1+4*numpy.sqrt(len(numerical_timestamps))),alpha=0.5,color='black')
ax.set_frame_on(False)
ax.get_xaxis().set_ticks([])
ax.get_yaxis().set_ticks([])
ax.get_yaxis().set_visible(False)
ax.set_xlim(0, max(numerical_timestamps))
plot_dict = mpld3.fig_to_dict(fig)
return plot_dict
def api_activity_histogram(self, app, butler):
"""
Description: returns the data to plot all API activity (for all algorithms) in a histogram with respect to time for any task in {getQuery,processAnswer,predict}
Expected output (in dict):
(dict) MPLD3 plot dictionary
"""
queries = butler.queries.get(pattern={'exp_uid': app.exp_uid})
#self.db.get_docs_with_filter(app_id+':queries',{'exp_uid':exp_uid})
start_date = utils.str2datetime(
butler.admin.get(uid=app.exp_uid)['start_date'])
numerical_timestamps = [
(utils.str2datetime(item['timestamp_query_generated']) -
start_date).total_seconds() for item in queries
]
fig, ax = plt.subplots(subplot_kw=dict(axisbg='#FFFFFF'),
figsize=(12, 1.5))
ax.hist(numerical_timestamps,
min(int(1 + 4 * numpy.sqrt(len(numerical_timestamps))), 300),
alpha=0.5,
color='black')
ax.set_frame_on(False)
ax.get_xaxis().set_ticks([])
ax.get_yaxis().set_ticks([])
ax.get_yaxis().set_visible(False)
ax.set_xlim(0, max(numerical_timestamps))
plot_dict = mpld3.fig_to_dict(fig)
plt.close()
return plot_dict
def api_activity_histogram(self, app, butler):
"""
Description: returns the data to plot all API activity (for all algorithms) in a histogram with respect to time for any task in {getQuery,processAnswer,predict}
Expected output (in dict):
(dict) MPLD3 plot dictionary
"""
queries = butler.queries.get(pattern={'exp_uid':app.exp_uid})
#self.db.get_docs_with_filter(app_id+':queries',{'exp_uid':exp_uid})
start_date = utils.str2datetime(butler.admin.get(uid=app.exp_uid)['start_date'])
numerical_timestamps = [(utils.str2datetime(item['timestamp_query_generated'])-start_date).total_seconds()
for item in queries]
fig, ax = plt.subplots(subplot_kw=dict(axisbg='#FFFFFF'),figsize=(12,1.5))
ax.hist(numerical_timestamps,min(int(1+4*numpy.sqrt(len(numerical_timestamps))),300),alpha=0.5,color='black')
ax.set_frame_on(False)
ax.get_xaxis().set_ticks([])
ax.get_yaxis().set_ticks([])
ax.get_yaxis().set_visible(False)
ax.set_xlim(0, max(numerical_timestamps))
plot_dict = mpld3.fig_to_dict(fig)
plt.close()
return plot_dict
def most_current_embedding(self, app_id, exp_uid, alg_label):
"""
Description: Returns embedding in the form of a list of dictionaries, which is conveneint for downstream applications
Expected input:
(string) alg_label : must be a valid alg_label contained in alg_list list of dicts
Expected output (in dict):
plot_type : 'scatter2d_noaxis'
(float) x_min : minimum x-value to display in viewing box
(float) x_max : maximum x-value to display in viewing box
(float) y_min : minimum y-value to display in viewing box
(float) y_max : maximum y-value to display in viewing box
(list of dicts with fields) data :
(int) index : index of target
(float) x : x-value of target
(float) y : y-value of target
"""
alg_list, didSucceed, message = self.db.get(app_id + ':experiments',
exp_uid, 'alg_list')
for algorithm in alg_list:
if algorithm['alg_label'] == alg_label:
alg_id = algorithm['alg_id']
alg_uid = algorithm['alg_uid']
list_of_log_dict, didSucceed, message = self.ell.get_logs_with_filter(
app_id + ':ALG-EVALUATION', {'alg_uid': alg_uid})
list_of_log_dict = sorted(
list_of_log_dict,
key=lambda item: utils.str2datetime(item['timestamp']))
item = list_of_log_dict[-1]
embedding = item['X2']
data = []
x_min = numpy.float('inf')
x_max = -numpy.float('inf')
y_min = numpy.float('inf')
y_max = -numpy.float('inf')
for idx, target in enumerate(embedding):
target_dict = {}
target_dict['index'] = idx
target_dict['x'] = target[0]
target_dict['y'] = target[1]
x_min = min(x_min, target[0])
x_max = max(x_max, target[0])
y_min = min(y_min, target[1])
y_max = max(y_max, target[1])
data.append(target_dict)
return_dict = {}
return_dict['x_min'] = x_min
return_dict['x_max'] = x_max
return_dict['y_min'] = y_min
return_dict['y_max'] = y_max
return_dict['data'] = data
return_dict['plot_type'] = 'scatter2d_noaxis'
return return_dict
def test_error_multiline_plot(self, app_id, exp_uid):
"""
Description: Returns multiline plot where there is a one-to-one mapping lines to
algorithms and each line indicates the error on the validation set with respect to number of reported answers
Expected input:
None
Expected output (in dict):
plot_type 'multi_line_plot'
(string) x_label : 'Number of answered triplets'
(float) x_min : 1
(float) x_max : maximum number of reported answers for any algorithm
(string) y_label : 'Error on hold-out set'
(float) y_min : 0.
(float) y_max : maximum duration value achieved by any algorithm
(list of dicts with fields) data :
(list of strings) t : list of timestamp strings
(list of floats) x : integers ranging from 1 to maximum number of elements in y (or t)
(list of floats) y : list of durations
(string) legend_label : alg_label
"""
# get list of algorithms associated with project
alg_list, didSucceed, message = self.db.get(app_id + ':experiments',
exp_uid, 'alg_list')
x_min = numpy.float('inf')
x_max = -numpy.float('inf')
y_min = numpy.float('inf')
y_max = -numpy.float('inf')
list_of_alg_dicts = []
for algorithm in alg_list:
alg_id = algorithm['alg_id']
alg_uid = algorithm['alg_uid']
alg_label = algorithm['alg_label']
list_of_log_dict, didSucceed, message = self.ell.get_logs_with_filter(
app_id + ':ALG-EVALUATION', {'alg_uid': alg_uid})
list_of_log_dict = sorted(
list_of_log_dict,
key=lambda item: utils.str2datetime(item['timestamp']))
x = []
y = []
t = []
for item in list_of_log_dict:
x.append(item['num_reported_answers'])
_y = float(item['error'])
y.append(_y)
t.append(str(item['timestamp'])[:-3])
if _y > 0.:
y_min = min(y_min, _y)
alg_dict = {}
alg_dict['legend_label'] = alg_label
alg_dict['x'] = x
alg_dict['y'] = y
alg_dict['t'] = t
try:
x_min = min(x_min, min(x))
x_max = max(x_max, max(x))
y_max = max(y_max, max(y))
except:
pass
list_of_alg_dicts.append(alg_dict)
return_dict = {}
return_dict['data'] = list_of_alg_dicts
return_dict['plot_type'] = 'multi_line_plot'
return_dict['x_label'] = 'Number of answered triplets'
return_dict['x_min'] = x_min
return_dict['x_max'] = x_max
return_dict['y_label'] = 'Error on hold-out set'
return_dict['y_min'] = y_min
return_dict['y_max'] = y_max
return return_dict
def compute_duration_detailed_stacked_area_plot(self,app_id,exp_uid,task,alg_label,detailedDB=False):
"""
Description: Returns stacked area plot for a particular algorithm and task where the durations
are broken down into compute,db_set,db_get (for cpu, database_set, database_get)
Expected input:
(string) task : must be in {'getQuery','processAnswer','predict'}
(string) alg_label : must be a valid alg_label contained in alg_list list of dicts
Expected output (in dict):
(dict) MPLD3 plot dictionary
"""
alg_list,didSucceed,message = self.db.get(app_id+':experiments',exp_uid,'alg_list')
for algorithm in alg_list:
if algorithm['alg_label'] == alg_label:
alg_id = algorithm['alg_id']
alg_uid = algorithm['alg_uid']
list_of_log_dict,didSucceed,message = self.ell.get_logs_with_filter(app_id+':ALG-DURATION',{'alg_uid':alg_uid,'task':task})
list_of_log_dict = sorted(list_of_log_dict, key=lambda item: utils.str2datetime(item['timestamp']) )
y = []
for item in list_of_log_dict:
y.append( item.get('app_duration',0.) + item.get('duration_enqueued',0.) )
y = numpy.array(y)
num_items = len(list_of_log_dict)
multiplier = min(num_items,MAX_SAMPLES_PER_PLOT)
incr_inds = [ k*num_items/multiplier for k in range(multiplier)]
max_inds = list(numpy.argsort(-y)[0:multiplier])
final_inds = sorted(set(incr_inds + max_inds))
x = []
t = []
enqueued = []
admin = []
dbOverhead = []
dbGet = []
dbSet = []
compute = []
max_y_value = 0.
min_y_value = float('inf')
for idx in final_inds:
item = list_of_log_dict[idx]
x.append(idx+1)
t.append(str(item.get('timestamp','')))
_alg_duration = item.get('duration',0.)
_alg_duration_dbGet = item.get('duration_dbGet',0.)
_alg_duration_dbSet = item.get('duration_dbSet',0.)
_duration_enqueued = item.get('duration_enqueued',0.)
_app_duration = item.get('app_duration',0.)
if (_app_duration+_duration_enqueued) > max_y_value:
max_y_value = _app_duration + _duration_enqueued
if (_app_duration+_duration_enqueued) < min_y_value:
min_y_value = _app_duration + _duration_enqueued
enqueued.append(_duration_enqueued)
admin.append(_app_duration-_alg_duration)
dbSet.append(_alg_duration_dbSet)
dbGet.append(_alg_duration_dbGet)
compute.append( _alg_duration - _alg_duration_dbSet - _alg_duration_dbGet )
try:
min_x = min(x)
max_x = max(x)
except:
min_x = 0.
max_x = 0.
import matplotlib.pyplot as plt
import mpld3
fig, ax = plt.subplots(subplot_kw=dict(axisbg='#EEEEEE'))
stack_coll = ax.stackplot(x,compute,dbGet,dbSet,admin,enqueued, alpha=.5)
ax.set_xlabel('API Call')
ax.set_ylabel('Duration (s)')
ax.set_xlim([min_x,max_x])
ax.set_ylim([0.,max_y_value])
ax.grid(color='white', linestyle='solid')
ax.set_title(alg_label+' - '+task, size=14)
proxy_rects = [plt.Rectangle((0, 0), 1, 1, alpha=.5,fc=pc.get_facecolor()[0]) for pc in stack_coll]
legend = ax.legend(proxy_rects, ['compute','dbGet','dbSet','admin','enqueued'],loc=2,ncol=3,mode="expand")
for label in legend.get_texts():
label.set_fontsize('small')
plot_dict = mpld3.fig_to_dict(fig)
return plot_dict
def compute_duration_detailed_stacked_area_plot(self, app_id, exp_uid, task, alg_label, detailedDB=False):
"""
Description: Returns stacked area plot for a particular algorithm and task where the durations
are broken down into compute,db_set,db_get (for cpu, database_set, database_get)
Expected input:
(string) task : must be in {'getQuery','processAnswer','predict'}
(string) alg_label : must be a valid alg_label contained in alg_list list of dicts
Expected output (in dict):
plot_type 'stacked_area_plot'
(string) x_label : 'API Call'
(float) x_min : 1
(float) x_max : length of datastream
(string) y_label : 'Duration (s)'
(float) y_min : 0.
(float) y_max : maximum duration value achieved sum of all layers
(list of strings) t : list of timestamp strings
(list of floats) x : integers ranging from 1 x_max
(list of dicts with fields) data :
(list of floats) y : list of durations
(string) legend_label : area_label in {'compute','db_set','db_get'}
"""
alg_list, didSucceed, message = self.db.get(app_id + ":experiments", exp_uid, "alg_list")
for algorithm in alg_list:
if algorithm["alg_label"] == alg_label:
alg_id = algorithm["alg_id"]
alg_uid = algorithm["alg_uid"]
list_of_log_dict, didSucceed, message = self.ell.get_logs_with_filter(
app_id + ":ALG-DURATION", {"alg_uid": alg_uid, "task": task}
)
list_of_log_dict = sorted(list_of_log_dict, key=lambda item: utils.str2datetime(item["timestamp"]))
x = []
t = []
enqueued = []
admin = []
dbOverhead = []
dbGet = []
dbSet = []
compute = []
max_y_value = 0.0
min_y_value = float("inf")
k = 0
for item in list_of_log_dict:
k += 1
x.append(k)
t.append(str(item.get("timestamp", "")))
_alg_duration = item.get("duration", 0.0)
_alg_duration_dbGet = item.get("duration_dbGet", 0.0)
_alg_duration_dbSet = item.get("duration_dbSet", 0.0)
_duration_enqueued = item.get("duration_enqueued", 0.0)
_app_duration = item.get("app_duration", 0.0)
if (_app_duration + _duration_enqueued) > max_y_value:
max_y_value = _app_duration + _duration_enqueued
if (_app_duration + _duration_enqueued) < min_y_value:
min_y_value = _app_duration + _duration_enqueued
enqueued.append(_duration_enqueued)
admin.append(_app_duration - _alg_duration)
dbSet.append(_alg_duration_dbSet)
dbGet.append(_alg_duration_dbGet)
compute.append(_alg_duration - _alg_duration_dbSet - _alg_duration_dbGet)
list_of_dicts = []
duration_dict = {}
duration_dict["legend_label"] = "compute"
duration_dict["y"] = compute
list_of_dicts.append(duration_dict)
duration_dict = {}
duration_dict["legend_label"] = "db:get"
duration_dict["y"] = dbGet
list_of_dicts.append(duration_dict)
duration_dict = {}
duration_dict["legend_label"] = "db:set"
duration_dict["y"] = dbSet
list_of_dicts.append(duration_dict)
duration_dict = {}
duration_dict["legend_label"] = "admin"
duration_dict["y"] = admin
list_of_dicts.append(duration_dict)
duration_dict = {}
duration_dict["legend_label"] = "enqueued"
duration_dict["y"] = enqueued
list_of_dicts.append(duration_dict)
return_dict = {}
return_dict["x"] = x
return_dict["t"] = t
return_dict["data"] = list_of_dicts
return_dict["plot_type"] = "stacked_area_plot"
return_dict["x_label"] = "API Call"
try:
return_dict["x_min"] = min(x)
return_dict["x_max"] = max(x)
return_dict["y_min"] = min_y_value
return_dict["y_max"] = max_y_value
except:
return_dict["x_min"] = 0.0
return_dict["x_max"] = 0.0
return_dict["y_min"] = 0.0
return_dict["y_max"] = 0.0
return_dict["y_label"] = "Duration (s)"
return return_dict
def compute_duration_detailed_stacked_area_plot(self,app_id,exp_uid,task,alg_label,detailedDB=False):
"""
Description: Returns stacked area plot for a particular algorithm and task where the durations
are broken down into compute,db_set,db_get (for cpu, database_set, database_get)
Expected input:
(string) task : must be in {'getQuery','reportAnswer','predict'}
(string) alg_label : must be a valid alg_label contained in alg_list list of dicts
Expected output (in dict):
plot_type 'stacked_area_plot'
(string) x_label : 'API Call'
(float) x_min : 1
(float) x_max : length of datastream
(string) y_label : 'Duration (s)'
(float) y_min : 0.
(float) y_max : maximum duration value achieved sum of all layers
(list of strings) t : list of timestamp strings
(list of floats) x : integers ranging from 1 x_max
(list of dicts with fields) data :
(list of floats) y : list of durations
(string) legend_label : area_label in {'compute','db_set','db_get'}
"""
alg_list,didSucceed,message = self.db.get(app_id+':experiments',exp_uid,'alg_list')
for algorithm in alg_list:
if algorithm['alg_label'] == alg_label:
alg_id = algorithm['alg_id']
alg_uid = algorithm['alg_uid']
list_of_log_dict,didSucceed,message = self.ell.get_logs_with_filter(app_id+':ALG-DURATION',{'alg_uid':alg_uid,'task':task})
list_of_log_dict = sorted(list_of_log_dict, key=lambda item: utils.str2datetime(item['timestamp']) )
x = []
t = []
enqueued = []
admin = []
dbOverhead = []
dbGet = []
dbSet = []
compute = []
max_y_value = 0.
min_y_value = float('inf')
k = 0
for item in list_of_log_dict:
k += 1
x.append(k)
t.append(str(item.get('timestamp','')))
_alg_duration = item.get('duration',0.)
_alg_duration_dbGet = item.get('duration_dbGet',0.)
_alg_duration_dbSet = item.get('duration_dbSet',0.)
_duration_enqueued = item.get('duration_enqueued',0.)
_app_duration = item.get('app_duration',0.)
if (_app_duration+_duration_enqueued) > max_y_value:
max_y_value = _app_duration + _duration_enqueued
if (_app_duration+_duration_enqueued) < min_y_value:
min_y_value = _app_duration + _duration_enqueued
enqueued.append(_duration_enqueued)
admin.append(_app_duration-_alg_duration)
dbSet.append(_alg_duration_dbSet)
dbGet.append(_alg_duration_dbGet)
compute.append( _alg_duration - _alg_duration_dbSet - _alg_duration_dbGet )
list_of_dicts = []
duration_dict = {}
duration_dict['legend_label'] = 'compute'
duration_dict['y'] = compute
list_of_dicts.append(duration_dict)
duration_dict = {}
duration_dict['legend_label'] = 'db:get'
duration_dict['y'] = dbGet
list_of_dicts.append(duration_dict)
duration_dict = {}
duration_dict['legend_label'] = 'db:set'
duration_dict['y'] = dbSet
list_of_dicts.append(duration_dict)
duration_dict = {}
duration_dict['legend_label'] = 'admin'
duration_dict['y'] = admin
list_of_dicts.append(duration_dict)
duration_dict = {}
duration_dict['legend_label'] = 'enqueued'
duration_dict['y'] = enqueued
list_of_dicts.append(duration_dict)
return_dict = {}
return_dict['x'] = x
return_dict['t'] = t
return_dict['data'] = list_of_dicts
return_dict['plot_type'] = 'stacked_area_plot'
return_dict['x_label'] = 'API Call'
try:
return_dict['x_min'] = min(x)
return_dict['x_max'] = max(x)
return_dict['y_min'] = min_y_value
return_dict['y_max'] = max_y_value
except:
return_dict['x_min'] = 0.
return_dict['x_max'] = 0.
return_dict['y_min'] = 0.
return_dict['y_max'] = 0.
return_dict['y_label'] = 'Duration (s)'
return return_dict
def compute_duration_multiline_plot(self,app_id,exp_uid,task):
"""
Description: Returns multiline plot where there is a one-to-one mapping lines to
algorithms and each line indicates the durations to complete the task (wrt to the api call)
Expected input:
(string) task : must be in {'getQuery','processAnswer','predict'}
Expected output (in dict):
(dict) MPLD3 plot dictionary
"""
alg_list,didSucceed,message = self.db.get(app_id+':experiments',exp_uid,'alg_list')
x_min = numpy.float('inf')
x_max = -numpy.float('inf')
y_min = numpy.float('inf')
y_max = -numpy.float('inf')
list_of_alg_dicts = []
for algorithm in alg_list:
alg_id = algorithm['alg_id']
alg_uid = algorithm['alg_uid']
alg_label = algorithm['alg_label']
list_of_log_dict,didSucceed,message = self.ell.get_logs_with_filter(app_id+':ALG-DURATION',{'alg_uid':alg_uid,'task':task})
list_of_log_dict = sorted(list_of_log_dict, key=lambda item: utils.str2datetime(item['timestamp']) )
x = []
y = []
t = []
k=0
for item in list_of_log_dict:
k+=1
x.append(k)
y.append( item.get('app_duration',0.) + item.get('duration_enqueued',0.) )
t.append(str(item['timestamp'])[:-3])
x = numpy.array(x)
y = numpy.array(y)
t = numpy.array(t)
num_items = len(list_of_log_dict)
multiplier = min(num_items,MAX_SAMPLES_PER_PLOT)
incr_inds = [ k*num_items/multiplier for k in range(multiplier)]
max_inds = list(numpy.argsort(-y)[0:multiplier])
final_inds = sorted(set(incr_inds + max_inds))
x = list(x[final_inds])
y = list(y[final_inds])
t = list(t[final_inds])
alg_dict = {}
alg_dict['legend_label'] = alg_label
alg_dict['x'] = x
alg_dict['y'] = y
alg_dict['t'] = t
try:
x_min = min(x_min,min(x))
x_max = max(x_max,max(x))
y_min = min(y_min,min(y))
y_max = max(y_max,max(y))
except:
pass
list_of_alg_dicts.append(alg_dict)
return_dict = {}
return_dict['data'] = list_of_alg_dicts
return_dict['plot_type'] = 'multi_line_plot'
return_dict['x_label'] = 'API Call'
return_dict['x_min'] = x_min
return_dict['x_max'] = x_max
return_dict['y_label'] = 'Duration (s)'
return_dict['y_min'] = y_min
return_dict['y_max'] = y_max
import matplotlib.pyplot as plt
import mpld3
fig, ax = plt.subplots(subplot_kw=dict(axisbg='#EEEEEE'))
for alg_dict in list_of_alg_dicts:
ax.plot(alg_dict['x'],alg_dict['y'],label=alg_dict['legend_label'])
ax.set_xlabel('API Call')
ax.set_ylabel('Duration (s)')
ax.set_xlim([x_min,x_max])
ax.set_ylim([y_min,y_max])
ax.grid(color='white', linestyle='solid')
ax.set_title(task, size=14)
legend = ax.legend(loc=2,ncol=3,mode="expand")
for label in legend.get_texts():
label.set_fontsize('small')
plot_dict = mpld3.fig_to_dict(fig)
return plot_dict
def compute_duration_detailed_stacked_area_plot(self,
app_id,
exp_uid,
task,
alg_label,
detailedDB=False):
"""
Description: Returns stacked area plot for a particular algorithm and task where the durations
are broken down into compute,db_set,db_get (for cpu, database_set, database_get)
Expected input:
(string) task : must be in {'getQuery','processAnswer','predict'}
(string) alg_label : must be a valid alg_label contained in alg_list list of dicts
Expected output (in dict):
plot_type 'stacked_area_plot'
(string) x_label : 'API Call'
(float) x_min : 1
(float) x_max : length of datastream
(string) y_label : 'Duration (s)'
(float) y_min : 0.
(float) y_max : maximum duration value achieved sum of all layers
(list of strings) t : list of timestamp strings
(list of floats) x : integers ranging from 1 x_max
(list of dicts with fields) data :
(list of floats) y : list of durations
(string) legend_label : area_label in {'compute','db_set','db_get'}
"""
alg_list, didSucceed, message = self.db.get(app_id + ':experiments',
exp_uid, 'alg_list')
for algorithm in alg_list:
if algorithm['alg_label'] == alg_label:
alg_id = algorithm['alg_id']
alg_uid = algorithm['alg_uid']
list_of_log_dict, didSucceed, message = self.ell.get_logs_with_filter(
app_id + ':ALG-DURATION', {
'alg_uid': alg_uid,
'task': task
})
list_of_log_dict = sorted(
list_of_log_dict,
key=lambda item: utils.str2datetime(item['timestamp']))
x = []
t = []
enqueued = []
admin = []
dbOverhead = []
dbGet = []
dbSet = []
compute = []
max_y_value = 0.
min_y_value = float('inf')
k = 0
for item in list_of_log_dict:
k += 1
x.append(k)
t.append(str(item.get('timestamp', '')))
_alg_duration = item.get('duration', 0.)
_alg_duration_dbGet = item.get('duration_dbGet', 0.)
_alg_duration_dbSet = item.get('duration_dbSet', 0.)
_duration_enqueued = item.get('duration_enqueued', 0.)
_app_duration = item.get('app_duration', 0.)
if (_app_duration + _duration_enqueued) > max_y_value:
max_y_value = _app_duration + _duration_enqueued
if (_app_duration + _duration_enqueued) < min_y_value:
min_y_value = _app_duration + _duration_enqueued
enqueued.append(_duration_enqueued)
admin.append(_app_duration - _alg_duration)
dbSet.append(_alg_duration_dbSet)
dbGet.append(_alg_duration_dbGet)
compute.append(_alg_duration - _alg_duration_dbSet -
_alg_duration_dbGet)
list_of_dicts = []
duration_dict = {}
duration_dict['legend_label'] = 'compute'
duration_dict['y'] = compute
list_of_dicts.append(duration_dict)
duration_dict = {}
duration_dict['legend_label'] = 'db:get'
duration_dict['y'] = dbGet
list_of_dicts.append(duration_dict)
duration_dict = {}
duration_dict['legend_label'] = 'db:set'
duration_dict['y'] = dbSet
list_of_dicts.append(duration_dict)
duration_dict = {}
duration_dict['legend_label'] = 'admin'
duration_dict['y'] = admin
list_of_dicts.append(duration_dict)
duration_dict = {}
duration_dict['legend_label'] = 'enqueued'
duration_dict['y'] = enqueued
list_of_dicts.append(duration_dict)
return_dict = {}
return_dict['x'] = x
return_dict['t'] = t
return_dict['data'] = list_of_dicts
return_dict['plot_type'] = 'stacked_area_plot'
return_dict['x_label'] = 'API Call'
try:
return_dict['x_min'] = min(x)
return_dict['x_max'] = max(x)
return_dict['y_min'] = min_y_value
return_dict['y_max'] = max_y_value
except:
return_dict['x_min'] = 0.
return_dict['x_max'] = 0.
return_dict['y_min'] = 0.
return_dict['y_max'] = 0.
return_dict['y_label'] = 'Duration (s)'
return return_dict
def test_error_multiline_plot(self, app, butler):
"""
Description: Returns multiline plot where there is a one-to-one mapping lines to
algorithms and each line indicates the error on the validation set with respect to number of reported answers
Expected input:
None
Expected output (in dict):
(dict) MPLD3 plot dictionary
"""
# get list of algorithms associated with project
args = butler.experiment.get(key='args')
test_alg_label = args['alg_list'][0]['test_alg_label']
test_S = butler.queries.get(pattern={
'exp_uid': app.exp_uid,
'alg_label': test_alg_label
})
x_min = numpy.float('inf')
x_max = -numpy.float('inf')
y_min = numpy.float('inf')
y_max = -numpy.float('inf')
list_of_alg_dicts = []
for algorithm in args['alg_list']:
alg_label = algorithm['alg_label']
list_of_log_dict, didSucceed, message = butler.ell.get_logs_with_filter(
app.app_id + ':ALG-EVALUATION', {
'exp_uid': app.exp_uid,
'alg_label': alg_label
})
list_of_log_dict = sorted(
list_of_log_dict,
key=lambda item: utils.str2datetime(item['timestamp']))
x = []
y = []
for item in list_of_log_dict:
num_reported_answers = item['num_reported_answers']
Xd = item['X']
err = 0.5
if len(test_S) > 0:
# compute error rate
number_correct = 0.
for query in test_S:
if 'q' in query:
i, j, k = query['q']
score = numpy.dot(Xd[j], Xd[j]) - 2 * numpy.dot(
Xd[j], Xd[k]) + 2 * numpy.dot(
Xd[i], Xd[k]) - numpy.dot(Xd[i], Xd[i])
if score > 0:
number_correct += 1.0
accuracy = number_correct / len(test_S)
err = 1.0 - accuracy
x.append(num_reported_answers)
y.append(err)
alg_dict = {'legend_label': alg_label, 'x': x, 'y': y}
try:
x_min = min(x_min, min(x))
x_max = max(x_max, max(x))
y_min = min(y_min, min(y))
y_max = max(y_max, max(y))
except:
pass
list_of_alg_dicts.append(alg_dict)
import matplotlib.pyplot as plt
import mpld3
fig, ax = plt.subplots(subplot_kw=dict(axisbg='#EEEEEE'))
for alg_dict in list_of_alg_dicts:
ax.plot(alg_dict['x'],
alg_dict['y'],
label=alg_dict['legend_label'])
ax.set_xlabel('Number of answered triplets')
ax.set_ylabel('Error on hold-out set')
ax.set_xlim([x_min, x_max])
ax.set_ylim([y_min, y_max])
ax.grid(color='white', linestyle='solid')
ax.set_title('Triplet Test Error', size=14)
legend = ax.legend(loc=2, ncol=3, mode="expand")
for label in legend.get_texts():
label.set_fontsize('small')
plot_dict = mpld3.fig_to_dict(fig)
plt.close()
return plot_dict
def test_error_multiline_plot(self,app_id,exp_uid):
"""
Description: Returns multiline plot where there is a one-to-one mapping lines to
algorithms and each line indicates the error on the validation set with respect to number of reported answers
Expected input:
None
Expected output (in dict):
mpld3 plot object
"""
# get list of algorithms associated with project
alg_list,didSucceed,message = self.db.get(app_id+':experiments',exp_uid,'alg_list')
x_min = numpy.float('inf')
x_max = -numpy.float('inf')
y_min = numpy.float('inf')
y_max = -numpy.float('inf')
list_of_alg_dicts = []
for algorithm in alg_list:
alg_id = algorithm['alg_id']
alg_uid = algorithm['alg_uid']
alg_label = algorithm['alg_label']
list_of_log_dict,didSucceed,message = self.ell.get_logs_with_filter(app_id+':ALG-EVALUATION',{'alg_uid':alg_uid})
list_of_log_dict = sorted(list_of_log_dict, key=lambda item: utils.str2datetime(item['timestamp']) )
x = []
y = []
for item in list_of_log_dict:
num_reported_answers = item['num_reported_answers']
err = item['error']
x.append(num_reported_answers)
y.append(err)
alg_dict = {}
alg_dict['legend_label'] = alg_label
alg_dict['x'] = x
alg_dict['y'] = y
try:
x_min = min(x_min,min(x))
x_max = max(x_max,max(x))
y_min = min(y_min,min(y))
y_max = max(y_max,max(y))
except:
pass
list_of_alg_dicts.append(alg_dict)
import matplotlib.pyplot as plt
import mpld3
fig, ax = plt.subplots(subplot_kw=dict(axisbg='#EEEEEE'))
for alg_dict in list_of_alg_dicts:
ax.plot(alg_dict['x'],alg_dict['y'],label=alg_dict['legend_label'])
ax.set_xlabel('Number of answered triplets')
ax.set_ylabel('Error on hold-out set')
ax.set_xlim([x_min,x_max])
ax.set_ylim([y_min,y_max])
ax.grid(color='white', linestyle='solid')
ax.set_title('Triplet Test Error', size=14)
legend = ax.legend(loc=2,ncol=3,mode="expand")
for label in legend.get_texts():
label.set_fontsize('small')
plot_dict = mpld3.fig_to_dict(fig)
return plot_dict
def compute_duration_multiline_plot(self, app_id, exp_uid, task):
"""
Description: Returns multiline plot where there is a one-to-one mapping lines to
algorithms and each line indicates the durations to complete the task (wrt to the api call)
Expected input:
(string) task : must be in {'getQuery','processAnswer','predict'}
Expected output (in dict):
plot_type 'multi_line_plot'
(string) x_label : 'API Call'
(float) x_min : 1
(float) x_max : maximum number of reported answers for any algorithm
(string) y_label : 'Duration (s)'
(float) y_min : 0.
(float) y_max : maximum duration value achieved by any algorithm
(list of dicts with fields) data :
(list of strings) t : list of timestamp strings
(list of floats) x : integers ranging from 1 to maximum number of elements in y (or t)
(list of floats) y : list of durations
(string) legend_label : alg_label
"""
alg_list, didSucceed, message = self.db.get(app_id + ':experiments',
exp_uid, 'alg_list')
x_min = numpy.float('inf')
x_max = -numpy.float('inf')
y_min = numpy.float('inf')
y_max = -numpy.float('inf')
list_of_alg_dicts = []
for algorithm in alg_list:
alg_id = algorithm['alg_id']
alg_uid = algorithm['alg_uid']
alg_label = algorithm['alg_label']
list_of_log_dict, didSucceed, message = self.ell.get_logs_with_filter(
app_id + ':ALG-DURATION', {
'alg_uid': alg_uid,
'task': task
})
list_of_log_dict = sorted(
list_of_log_dict,
key=lambda item: utils.str2datetime(item['timestamp']))
x = []
y = []
t = []
k = 0
for item in list_of_log_dict:
k += 1
x.append(k)
y.append(
item.get('app_duration', 0.) +
item.get('duration_enqueued', 0.))
t.append(str(item['timestamp'])[:-3])
alg_dict = {}
alg_dict['legend_label'] = alg_label
alg_dict['x'] = x
alg_dict['y'] = y
alg_dict['t'] = t
try:
x_min = min(x_min, min(x))
x_max = max(x_max, max(x))
y_min = min(y_min, min(y))
y_max = max(y_max, max(y))
except:
pass
list_of_alg_dicts.append(alg_dict)
return_dict = {}
return_dict['data'] = list_of_alg_dicts
return_dict['plot_type'] = 'multi_line_plot'
return_dict['x_label'] = 'API Call'
return_dict['x_min'] = x_min
return_dict['x_max'] = x_max
return_dict['y_label'] = 'Duration (s)'
return_dict['y_min'] = y_min
return_dict['y_max'] = y_max
return return_dict
def test_error_multiline_plot(self, app, butler):
"""
Description: Returns multiline plot where there is a one-to-one mapping lines to
algorithms and each line indicates the error on the validation set with respect to number of reported answers
Expected input:
None
Expected output (in dict):
(dict) MPLD3 plot dictionary
"""
# get list of algorithms associated with project
args = butler.experiment.get(key='args')
test_alg_label = args['alg_list'][0]['test_alg_label']
test_S = butler.queries.get(pattern={'exp_uid':app.exp_uid, 'alg_label':test_alg_label})
x_min = numpy.float('inf')
x_max = -numpy.float('inf')
y_min = numpy.float('inf')
y_max = -numpy.float('inf')
list_of_alg_dicts = []
for algorithm in args['alg_list']:
alg_label = algorithm['alg_label']
list_of_log_dict,didSucceed,message = butler.ell.get_logs_with_filter(app.app_id+':ALG-EVALUATION',{'exp_uid':app.exp_uid, 'alg_label':alg_label})
list_of_log_dict = sorted(list_of_log_dict, key=lambda item: utils.str2datetime(item['timestamp']) )
x = []
y = []
for item in list_of_log_dict:
num_reported_answers = item['num_reported_answers']
Xd = item['X']
err = 0.5
if len(test_S)>0:
# compute error rate
number_correct = 0.
for query in test_S:
if 'q' in query:
i, j, k = query['q']
score = numpy.dot(Xd[j],Xd[j]) -2*numpy.dot(Xd[j],Xd[k]) + 2*numpy.dot(Xd[i],Xd[k]) - numpy.dot(Xd[i],Xd[i])
if score > 0:
number_correct += 1.0
accuracy = number_correct/len(test_S)
err = 1.0-accuracy
x.append(num_reported_answers)
y.append(err)
alg_dict = {'legend_label':alg_label, 'x':x,'y':y}
try:
x_min = min(x_min,min(x))
x_max = max(x_max,max(x))
y_min = min(y_min,min(y))
y_max = max(y_max,max(y))
except:
pass
list_of_alg_dicts.append(alg_dict)
import matplotlib.pyplot as plt
import mpld3
fig, ax = plt.subplots(subplot_kw=dict(axisbg='#EEEEEE'))
for alg_dict in list_of_alg_dicts:
ax.plot(alg_dict['x'],alg_dict['y'],label=alg_dict['legend_label'])
ax.set_xlabel('Number of answered triplets')
ax.set_ylabel('Error on hold-out set')
ax.set_xlim([x_min,x_max])
ax.set_ylim([y_min,y_max])
ax.grid(color='white', linestyle='solid')
ax.set_title('Triplet Test Error', size=14)
legend = ax.legend(loc=2,ncol=3,mode="expand")
for label in legend.get_texts():
label.set_fontsize('small')
plot_dict = mpld3.fig_to_dict(fig)
plt.close()
return plot_dict
def test_error_multiline_plot(self,app_id,exp_uid):
"""
Description: Returns multiline plot where there is a one-to-one mapping lines to
algorithms and each line indicates the error on the validation set with respect to number of reported answers
Expected input:
None
Expected output (in dict):
plot_type 'multi_line_plot'
(string) x_label : 'Number of answered triplets'
(float) x_min : 1
(float) x_max : maximum number of reported answers for any algorithm
(string) y_label : 'Error on hold-out set'
(float) y_min : 0.
(float) y_max : maximum duration value achieved by any algorithm
(list of dicts with fields) data :
(list of strings) t : list of timestamp strings
(list of floats) x : integers ranging from 1 to maximum number of elements in y (or t)
(list of floats) y : list of durations
(string) legend_label : alg_label
"""
# get list of algorithms associated with project
alg_list,didSucceed,message = self.db.get(app_id+':experiments',exp_uid,'alg_list')
x_min = numpy.float('inf')
x_max = -numpy.float('inf')
y_min = numpy.float('inf')
y_max = -numpy.float('inf')
list_of_alg_dicts = []
for algorithm in alg_list:
alg_id = algorithm['alg_id']
alg_uid = algorithm['alg_uid']
alg_label = algorithm['alg_label']
list_of_log_dict,didSucceed,message = self.ell.get_logs_with_filter(app_id+':ALG-EVALUATION',{'alg_uid':alg_uid})
list_of_log_dict = sorted(list_of_log_dict, key=lambda item: utils.str2datetime(item['timestamp']) )
x = []
y = []
t = []
for item in list_of_log_dict:
x.append(item['num_reported_answers'])
_y = float(item['error'])
y.append(_y)
t.append(str(item['timestamp'])[:-3])
if _y >0.:
y_min = min(y_min,_y)
alg_dict = {}
alg_dict['legend_label'] = alg_label
alg_dict['x'] = x
alg_dict['y'] = y
alg_dict['t'] = t
try:
x_min = min(x_min,min(x))
x_max = max(x_max,max(x))
y_max = max(y_max,max(y))
except:
pass
list_of_alg_dicts.append(alg_dict)
return_dict = {}
return_dict['data'] = list_of_alg_dicts
return_dict['plot_type'] = 'multi_line_plot'
return_dict['x_label'] = 'Number of answered triplets'
return_dict['x_min'] = x_min
return_dict['x_max'] = x_max
return_dict['y_label'] = 'Error on hold-out set'
return_dict['y_min'] = y_min
return_dict['y_max'] = y_max
return return_dict
def most_current_embedding(self,app_id,exp_uid,alg_label):
"""
Description: Returns embedding in the form of a list of dictionaries, which is conveneint for downstream applications
Expected input:
(string) alg_label : must be a valid alg_label contained in alg_list list of dicts
Expected output (in dict):
plot_type : 'scatter2d_noaxis'
(float) x_min : minimum x-value to display in viewing box
(float) x_max : maximum x-value to display in viewing box
(float) y_min : minimum y-value to display in viewing box
(float) y_max : maximum y-value to display in viewing box
(list of dicts with fields) data :
(int) index : index of target
(float) x : x-value of target
(float) y : y-value of target
"""
alg_list,didSucceed,message = self.db.get(app_id+':experiments',exp_uid,'alg_list')
for algorithm in alg_list:
if algorithm['alg_label'] == alg_label:
alg_id = algorithm['alg_id']
alg_uid = algorithm['alg_uid']
list_of_log_dict,didSucceed,message = self.ell.get_logs_with_filter(app_id+':ALG-EVALUATION',{'alg_uid':alg_uid})
list_of_log_dict = sorted(list_of_log_dict, key=lambda item: utils.str2datetime(item['timestamp']) )
item = list_of_log_dict[-1]
embedding = item['X2']
data = []
x_min = numpy.float('inf')
x_max = -numpy.float('inf')
y_min = numpy.float('inf')
y_max = -numpy.float('inf')
for idx,target in enumerate(embedding):
target_dict = {}
target_dict['index'] = idx
target_dict['x'] = target[0]
target_dict['y'] = target[1]
x_min = min(x_min,target[0])
x_max = max(x_max,target[0])
y_min = min(y_min,target[1])
y_max = max(y_max,target[1])
data.append(target_dict)
return_dict = {}
return_dict['x_min'] = x_min
return_dict['x_max'] = x_max
return_dict['y_min'] = y_min
return_dict['y_max'] = y_max
return_dict['data'] = data
return_dict['plot_type'] = 'scatter2d_noaxis'
return return_dict
def test_error_multiline_plot(self,app, butler):
"""
Description: Returns multiline plot where there is a one-to-one mapping lines to
algorithms and each line indicates the error on the validation set with respect to number of reported answers
Expected input:
None
Expected output (in dict):
(dict) MPLD3 plot dictionary
"""
args = butler.experiment.get(key='args')
alg_list = args['alg_list']
test_alg_label = alg_list[0]['test_alg_label']
test_queries, didSucceed, message = butler.db.get_docs_with_filter(app.app_id+':queries',{'exp_uid':app.exp_uid, 'alg_label':test_alg_label})
test_S = [(query['target_index'], query['target_label'])
for query in test_queries
if 'target_index' in query.keys()]
targets = butler.targets.get_targetset(app.exp_uid)
targets = sorted(targets,key=lambda x: x['target_id'])
target_features = []
for target_index in range(len(targets)):
target_vec = targets[target_index]['meta']['features']
target_vec.append(1.)
target_features.append(target_vec)
x_min = numpy.float('inf')
x_max = -numpy.float('inf')
y_min = numpy.float('inf')
y_max = -numpy.float('inf')
list_of_alg_dicts = []
for algorithm in alg_list:
alg_label = algorithm['alg_label']
list_of_log_dict,didSucceed,message = self.ell.get_logs_with_filter(app.app_id+':ALG-EVALUATION',{'exp_uid':app.exp_uid, 'alg_label':alg_label})
list_of_log_dict = sorted(list_of_log_dict, key=lambda item: utils.str2datetime(item['timestamp']) )
x = []
y = []
for item in list_of_log_dict:
num_reported_answers = item['num_reported_answers']
weights = item['weights']
err = 0.
for q in test_S:
estimated_label = numpy.sign(numpy.dot( numpy.array(target_features[q[0]]), numpy.array(weights) ))
err += estimated_label*q[1]<0. #do the labels agree or not
m = float(len(test_S))
err = err/m
x.append(num_reported_answers)
y.append(err)
x = numpy.argsort(x)
x = [x[i] for i in x]
y = [y[i] for i in x]
alg_dict = {}
alg_dict['legend_label'] = alg_label
alg_dict['x'] = x
alg_dict['y'] = y
try:
x_min = min(x_min,min(x))
x_max = max(x_max,max(x))
y_min = min(y_min,min(y))
y_max = max(y_max,max(y))
except:
pass
list_of_alg_dicts.append(alg_dict)
import matplotlib.pyplot as plt
import mpld3
fig, ax = plt.subplots(subplot_kw=dict(axisbg='#EEEEEE'))
for alg_dict in list_of_alg_dicts:
ax.plot(alg_dict['x'],alg_dict['y'],label=alg_dict['legend_label'])
ax.set_xlabel('Number of answered queries')
ax.set_ylabel('Error on hold-out set')
ax.set_xlim([x_min,x_max])
ax.set_ylim([y_min,y_max])
ax.grid(color='white', linestyle='solid')
ax.set_title('Test Error', size=14)
legend = ax.legend(loc=2,ncol=3,mode="expand")
for label in legend.get_texts():
label.set_fontsize('small')
plot_dict = mpld3.fig_to_dict(fig)
plt.close()
return plot_dict
def compute_duration_multiline_plot(self, app_id, exp_uid, task):
"""
Description: Returns multiline plot where there is a one-to-one mapping lines to
algorithms and each line indicates the durations to complete the task (wrt to the api call)
Expected input:
(string) task : must be in {'getQuery','processAnswer','predict'}
Expected output (in dict):
plot_type 'multi_line_plot'
(string) x_label : 'API Call'
(float) x_min : 1
(float) x_max : maximum number of reported answers for any algorithm
(string) y_label : 'Duration (s)'
(float) y_min : 0.
(float) y_max : maximum duration value achieved by any algorithm
(list of dicts with fields) data :
(list of strings) t : list of timestamp strings
(list of floats) x : integers ranging from 1 to maximum number of elements in y (or t)
(list of floats) y : list of durations
(string) legend_label : alg_label
"""
alg_list, didSucceed, message = self.db.get(app_id + ":experiments", exp_uid, "alg_list")
x_min = numpy.float("inf")
x_max = -numpy.float("inf")
y_min = numpy.float("inf")
y_max = -numpy.float("inf")
list_of_alg_dicts = []
for algorithm in alg_list:
alg_id = algorithm["alg_id"]
alg_uid = algorithm["alg_uid"]
alg_label = algorithm["alg_label"]
list_of_log_dict, didSucceed, message = self.ell.get_logs_with_filter(
app_id + ":ALG-DURATION", {"alg_uid": alg_uid, "task": task}
)
list_of_log_dict = sorted(list_of_log_dict, key=lambda item: utils.str2datetime(item["timestamp"]))
x = []
y = []
t = []
k = 0
for item in list_of_log_dict:
k += 1
x.append(k)
y.append(item.get("app_duration", 0.0) + item.get("duration_enqueued", 0.0))
t.append(str(item["timestamp"])[:-3])
alg_dict = {}
alg_dict["legend_label"] = alg_label
alg_dict["x"] = x
alg_dict["y"] = y
alg_dict["t"] = t
try:
x_min = min(x_min, min(x))
x_max = max(x_max, max(x))
y_min = min(y_min, min(y))
y_max = max(y_max, max(y))
except:
pass
list_of_alg_dicts.append(alg_dict)
return_dict = {}
return_dict["data"] = list_of_alg_dicts
return_dict["plot_type"] = "multi_line_plot"
return_dict["x_label"] = "API Call"
return_dict["x_min"] = x_min
return_dict["x_max"] = x_max
return_dict["y_label"] = "Duration (s)"
return_dict["y_min"] = y_min
return_dict["y_max"] = y_max
return return_dict
def test_error_multiline_plot(self, app, butler):
"""
Description: Returns multiline plot where there is a one-to-one mapping lines to
algorithms and each line indicates the error on the validation set with respect to number of reported answers
Expected input:
None
Expected output (in dict):
(dict) MPLD3 plot dictionary
"""
args = butler.experiment.get(key='args')
alg_list = args['alg_list']
test_alg_label = alg_list[0]['test_alg_label']
test_queries, didSucceed, message = butler.db.get_docs_with_filter(
app.app_id + ':queries', {
'exp_uid': app.exp_uid,
'alg_label': test_alg_label
})
test_S = [(query['target_index'], query['target_label'])
for query in test_queries if 'target_index' in query.keys()]
targets = butler.targets.get_targetset(app.exp_uid)
targets = sorted(targets, key=lambda x: x['target_id'])
target_features = []
for target_index in range(len(targets)):
target_vec = targets[target_index]['meta']['features']
target_vec.append(1.)
target_features.append(target_vec)
x_min = numpy.float('inf')
x_max = -numpy.float('inf')
y_min = numpy.float('inf')
y_max = -numpy.float('inf')
list_of_alg_dicts = []
for algorithm in alg_list:
alg_label = algorithm['alg_label']
list_of_log_dict, didSucceed, message = self.ell.get_logs_with_filter(
app.app_id + ':ALG-EVALUATION', {
'exp_uid': app.exp_uid,
'alg_label': alg_label
})
list_of_log_dict = sorted(
list_of_log_dict,
key=lambda item: utils.str2datetime(item['timestamp']))
x = []
y = []
for item in list_of_log_dict:
num_reported_answers = item['num_reported_answers']
weights = item['weights']
err = 0.
for q in test_S:
estimated_label = numpy.sign(
numpy.dot(numpy.array(target_features[q[0]]),
numpy.array(weights)))
err += estimated_label * q[
1] < 0. #do the labels agree or not
m = float(len(test_S))
err = err / m
x.append(num_reported_answers)
y.append(err)
x = numpy.argsort(x)
x = [x[i] for i in x]
y = [y[i] for i in x]
alg_dict = {}
alg_dict['legend_label'] = alg_label
alg_dict['x'] = x
alg_dict['y'] = y
try:
x_min = min(x_min, min(x))
x_max = max(x_max, max(x))
y_min = min(y_min, min(y))
y_max = max(y_max, max(y))
except:
pass
list_of_alg_dicts.append(alg_dict)
import matplotlib.pyplot as plt
import mpld3
fig, ax = plt.subplots(subplot_kw=dict(axisbg='#EEEEEE'))
for alg_dict in list_of_alg_dicts:
ax.plot(alg_dict['x'],
alg_dict['y'],
label=alg_dict['legend_label'])
ax.set_xlabel('Number of answered queries')
ax.set_ylabel('Error on hold-out set')
ax.set_xlim([x_min, x_max])
ax.set_ylim([y_min, y_max])
ax.grid(color='white', linestyle='solid')
ax.set_title('Test Error', size=14)
legend = ax.legend(loc=2, ncol=3, mode="expand")
for label in legend.get_texts():
label.set_fontsize('small')
plot_dict = mpld3.fig_to_dict(fig)
plt.close()
return plot_dict
def test_error_multiline_plot(self,app_id,exp_uid):
"""
Description: Returns multiline plot where there is a one-to-one mapping lines to
algorithms and each line indicates the error on the validation set with respect to number of reported answers
Expected input:
None
Expected output (in dict):
(dict) MPLD3 plot dictionary
"""
# get list of algorithms associated with project
alg_list,didSucceed,message = self.db.get(app_id+':experiments',exp_uid,'alg_list')
for algorithm in alg_list:
test_alg_label = algorithm['test_alg_label']
predict_id = 'get_queries'
params = {'alg_label':test_alg_label}
predict_args_dict = {'predict_id':predict_id,'params':params}
predict_args_json = json.dumps(predict_args_dict)
next_app = utils.get_app(app_id)
args_out_json,didSucceed,message = next_app.predict(exp_uid, predict_args_json, self.db, self.ell)
predict_args_dict = json.loads(args_out_json)
test_S = predict_args_dict['args']['queries']
x_min = numpy.float('inf')
x_max = -numpy.float('inf')
y_min = numpy.float('inf')
y_max = -numpy.float('inf')
list_of_alg_dicts = []
for algorithm in alg_list:
alg_id = algorithm['alg_id']
alg_uid = algorithm['alg_uid']
alg_label = algorithm['alg_label']
list_of_log_dict,didSucceed,message = self.ell.get_logs_with_filter(app_id+':ALG-EVALUATION',{'alg_uid':alg_uid})
list_of_log_dict = sorted(list_of_log_dict, key=lambda item: utils.str2datetime(item['timestamp']) )
x = []
y = []
for item in list_of_log_dict:
num_reported_answers = item['num_reported_answers']
Xd = item['Xd']
err = 0.5
if len(test_S)>0:
# compute error rate
number_correct = 0.
for q in test_S:
i,j,k = q
score = numpy.dot(Xd[j],Xd[j]) -2*numpy.dot(Xd[j],Xd[k]) + 2*numpy.dot(Xd[i],Xd[k]) - numpy.dot(Xd[i],Xd[i])
if score > 0:
number_correct += 1.0
accuracy = number_correct/len(test_S)
err = 1.0-accuracy
x.append(num_reported_answers)
y.append(err)
alg_dict = {}
alg_dict['legend_label'] = alg_label
alg_dict['x'] = x
alg_dict['y'] = y
try:
x_min = min(x_min,min(x))
x_max = max(x_max,max(x))
y_min = min(y_min,min(y))
y_max = max(y_max,max(y))
except:
pass
list_of_alg_dicts.append(alg_dict)
import matplotlib.pyplot as plt
import mpld3
fig, ax = plt.subplots(subplot_kw=dict(axisbg='#EEEEEE'))
for alg_dict in list_of_alg_dicts:
ax.plot(alg_dict['x'],alg_dict['y'],label=alg_dict['legend_label'])
ax.set_xlabel('Number of answered triplets')
ax.set_ylabel('Error on hold-out set')
ax.set_xlim([x_min,x_max])
ax.set_ylim([y_min,y_max])
ax.grid(color='white', linestyle='solid')
ax.set_title('Triplet Test Error', size=14)
legend = ax.legend(loc=2,ncol=3,mode="expand")
for label in legend.get_texts():
label.set_fontsize('small')
plot_dict = mpld3.fig_to_dict(fig)
return plot_dict
def test_error_multiline_plot(self, app_id, exp_uid):
"""
Description: Returns multiline plot where there is a one-to-one mapping lines to
algorithms and each line indicates the error on the validation set with respect to number of reported answers
Expected input:
None
Expected output (in dict):
mpld3 plot object
"""
# get list of algorithms associated with project
alg_list, didSucceed, message = self.db.get(app_id + ':experiments',
exp_uid, 'alg_list')
x_min = numpy.float('inf')
x_max = -numpy.float('inf')
y_min = numpy.float('inf')
y_max = -numpy.float('inf')
list_of_alg_dicts = []
for algorithm in alg_list:
alg_id = algorithm['alg_id']
alg_uid = algorithm['alg_uid']
alg_label = algorithm['alg_label']
list_of_log_dict, didSucceed, message = self.ell.get_logs_with_filter(
app_id + ':ALG-EVALUATION', {'alg_uid': alg_uid})
list_of_log_dict = sorted(
list_of_log_dict,
key=lambda item: utils.str2datetime(item['timestamp']))
x = []
y = []
for item in list_of_log_dict:
num_reported_answers = item['num_reported_answers']
err = item['error']
x.append(num_reported_answers)
y.append(err)
alg_dict = {}
alg_dict['legend_label'] = alg_label
alg_dict['x'] = x
alg_dict['y'] = y
try:
x_min = min(x_min, min(x))
x_max = max(x_max, max(x))
y_min = min(y_min, min(y))
y_max = max(y_max, max(y))
except:
pass
list_of_alg_dicts.append(alg_dict)
import matplotlib.pyplot as plt
import mpld3
fig, ax = plt.subplots(subplot_kw=dict(axisbg='#EEEEEE'))
for alg_dict in list_of_alg_dicts:
ax.plot(alg_dict['x'],
alg_dict['y'],
label=alg_dict['legend_label'])
ax.set_xlabel('Number of answered triplets')
ax.set_ylabel('Error on hold-out set')
ax.set_xlim([x_min, x_max])
ax.set_ylim([y_min, y_max])
ax.grid(color='white', linestyle='solid')
ax.set_title('Triplet Test Error', size=14)
legend = ax.legend(loc=2, ncol=3, mode="expand")
for label in legend.get_texts():
label.set_fontsize('small')
plot_dict = mpld3.fig_to_dict(fig)
return plot_dict
def compute_duration_multiline_plot(self,app_id,exp_uid,task):
"""
Description: Returns multiline plot where there is a one-to-one mapping lines to
algorithms and each line indicates the durations to complete the task (wrt to the api call)
Expected input:
(string) task : must be in {'getQuery','reportAnswer','predict'}
Expected output (in dict):
plot_type 'multi_line_plot'
(string) x_label : 'API Call'
(float) x_min : 1
(float) x_max : maximum number of reported answers for any algorithm
(string) y_label : 'Duration (s)'
(float) y_min : 0.
(float) y_max : maximum duration value achieved by any algorithm
(list of dicts with fields) data :
(list of strings) t : list of timestamp strings
(list of floats) x : integers ranging from 1 to maximum number of elements in y (or t)
(list of floats) y : list of durations
(string) legend_label : alg_label
"""
alg_list,didSucceed,message = self.db.get(app_id+':experiments',exp_uid,'alg_list')
x_min = numpy.float('inf')
x_max = -numpy.float('inf')
y_min = numpy.float('inf')
y_max = -numpy.float('inf')
list_of_alg_dicts = []
for algorithm in alg_list:
alg_id = algorithm['alg_id']
alg_uid = algorithm['alg_uid']
alg_label = algorithm['alg_label']
list_of_log_dict,didSucceed,message = self.ell.get_logs_with_filter(app_id+':ALG-DURATION',{'alg_uid':alg_uid,'task':task})
list_of_log_dict = sorted(list_of_log_dict, key=lambda item: utils.str2datetime(item['timestamp']) )
x = []
y = []
t = []
k=0
for item in list_of_log_dict:
k+=1
x.append(k)
y.append( item.get('app_duration',0.) + item.get('duration_enqueued',0.) )
t.append(str(item['timestamp'])[:-3])
alg_dict = {}
alg_dict['legend_label'] = alg_label
alg_dict['x'] = x
alg_dict['y'] = y
alg_dict['t'] = t
try:
x_min = min(x_min,min(x))
x_max = max(x_max,max(x))
y_min = min(y_min,min(y))
y_max = max(y_max,max(y))
except:
pass
list_of_alg_dicts.append(alg_dict)
return_dict = {}
return_dict['data'] = list_of_alg_dicts
return_dict['plot_type'] = 'multi_line_plot'
return_dict['x_label'] = 'API Call'
return_dict['x_min'] = x_min
return_dict['x_max'] = x_max
return_dict['y_label'] = 'Duration (s)'
return_dict['y_min'] = y_min
return_dict['y_max'] = y_max
return return_dict
