def create_basic_report_data_dict(umbral,target,main_metric,feature_selection_method,penalize_falses,lista_variables_descartadas,ruta_logo):
report_data = {glod.get_title_key(): "Overview With Execution Information",
glod.get_logo_key():ruta_logo,
glod.get_umbral_key(): str(umbral),
glod.get_main_metric_key(): str(main_metric),
glod.get_feature_selection_key(): str(feature_selection_method),
glod.get_penalization_name(): str(penalize_falses),
glod.get_objective_target_key(): target,
glod.get_variables_key():{glod.get_deleted_by_user_key():lista_variables_descartadas},
glod.get_general_info_execution_key():''
}
return report_data
def create_report_data_dict(evento,umbral,target,lista_variables_descartadas,ruta_logo):
report_data = {glod.get_objective_target_key(): target,
glod.get_event_key():evento,
glod.get_logo_key():ruta_logo,
glod.get_report_general_info_key():{glod.get_report_generic_target_key():{},
glod.get_variables_key():{glod.get_deleted_by_user_key():lista_variables_descartadas,glod.get_empty_or_constant_key():[],glod.get_score_relevant_key():[]},
glod.get_training_division_key():{},
glod.get_test_division_key():{},
},
glod.get_umbral_key(): str(umbral),
glod.get_warning_key(): ''
}
return report_data
def create_report_data_dict(evento, umbral, target, lista_variables_descartadas, ruta_logo):
'''This funcion allows to create the structure for the report data dictionary
for the current event'''
report_data = {glod.get_objective_target_key(): target,
glod.get_event_key():evento,
glod.get_logo_key():ruta_logo,
glod.get_report_general_info_key():{glod.get_report_generic_target_key():{},
glod.get_variables_key():{glod.get_deleted_by_user_key():lista_variables_descartadas, glod.get_empty_or_constant_key():[], glod.get_score_relevant_key():[]},
glod.get_training_division_key():{},
glod.get_test_division_key():{},
},
glod.get_umbral_key(): str(umbral),
glod.get_warning_key(): glod.get_empty_string()
}
return report_data
def create_basic_report_data_dict(basic_parameters, lista_variables_descartadas, ruta_logo):
'''This funcion allows to create the structure for the report data dictionary'''
umbral = basic_parameters[0]
target = basic_parameters[1]
main_metric = basic_parameters[2]
feature_selection_method = basic_parameters[3]
penalize_falses = basic_parameters[4]
report_data = {glod.get_title_key(): "Overview With Execution Information",
glod.get_logo_key():ruta_logo,
glod.get_umbral_key(): str(umbral),
glod.get_main_metric_key(): str(main_metric),
glod.get_feature_selection_key(): str(feature_selection_method),
glod.get_penalization_name(): str(penalize_falses),
glod.get_objective_target_key(): target,
glod.get_variables_key():{glod.get_deleted_by_user_key():\
lista_variables_descartadas},
glod.get_general_info_execution_key():glod.get_empty_string()
}
return report_data
def create_report_current_model(report_dict,lista_modelos,ruta_relativa_datos_auxiliares,ruta_directorio_informes,enco):
env = Environment(loader=FileSystemLoader('.'))
ruta_plantilla_temporal = os.path.join(ruta_relativa_datos_auxiliares,'temp_html.html')
if(lista_modelos == []): #if process not completed
template = env.get_template(ruta_relativa_datos_auxiliares + '/' + 'incomplete_event_report_template.html') #usamos la plantilla de informes incompletos
template_vars = {glod.get_title_key(): "Incomplete Execution Report",
glod.get_logo_key(): encode_image(report_dict[glod.get_logo_key()].replace('\'','')),
glod.get_report_generic_target_key(): report_dict[glod.get_objective_target_key()],
glod.get_event_key(): report_dict[glod.get_event_key()],
glod.get_info_key(): " " + report_dict['Warning_info']
}
#html
with codecs.open(ruta_plantilla_temporal,'w',encoding=enco) as output_file:
output_file.write(template.render(template_vars))
#pdf
with codecs.open(ruta_plantilla_temporal, 'r') as html_leido:
pdf_resultante=os.path.join(ruta_directorio_informes,"report_"+report_dict[glod.get_event_key()]+"_incomplete.pdf")
with open(pdf_resultante, "wb") as incomplete_rep:
pisa.CreatePDF(html_leido.read(),incomplete_rep)
logging.getLogger("xhtml2pdf").addHandler(PisaNullHandler())
else:
lista_pares_modelo_indice = auxf.order_models_by_score_and_time(report_dict,lista_modelos)
template = env.get_template(ruta_relativa_datos_auxiliares + '/' +'report_template.html') #using standard template
for modelo in lista_modelos:
if(modelo in report_dict):
observations_targets="<p><strong>Target distribution of observations</strong></br>"
for ob_target in auxf.natsorted(report_dict[glod.get_report_general_info_key()][glod.get_report_generic_target_key()].keys()):
observations_targets+=" "+ "With target " + str(ob_target) + " :"+ str(report_dict[glod.get_report_general_info_key()][glod.get_report_generic_target_key()][ob_target]) + "</br>"
observations_targets+="</p>"
variables_summary="<p><strong>Summary of variables</strong></br>"
discarded_for_event = report_dict[glod.get_report_general_info_key()][glod.get_variables_key()][glod.get_user_discarded_key()]
variables_summary+="<br><i><u>Deleted by the user at the begining:</i></u></br>"
for deleted_var in report_dict[glod.get_report_general_info_key()][glod.get_variables_key()][glod.get_deleted_by_user_key()]:
variable_dis=''
if deleted_var in discarded_for_event:
variable_dis = "<strong>" + deleted_var + "</strong>"
else:
variable_dis = deleted_var
variables_summary+=" "+ variable_dis + "</br>"
variables_summary+=" <i>*variables in bold were specified by the user to be discarded specifically for this event<i></br>"
variables_summary+="</br>"
variables_summary+="<br><i><u>Deleted in execution time(Empty or Constant):</i></u></br>"
for emp_con_var in report_dict[glod.get_report_general_info_key()][glod.get_variables_key()][glod.get_empty_or_constant_key()]:
variables_summary+=" "+ emp_con_var + "</br>"
variables_summary+="</br>"
variables_summary+="<br><i><u>Requested for the event by the user:</i></u></br>"
for req_var in report_dict[glod.get_report_general_info_key()][glod.get_variables_key()][glod.get_user_requested_key()]:
variables_summary+=" "+ req_var + "</br>"
variables_summary+="</br>"
variables_summary+="<br><i><u>Used during the process:</i></u></br>"
diccionario_relevantes_mif = report_dict[glod.get_report_general_info_key()][glod.get_variables_key()][glod.get_score_relevant_key()]
sorted_relevant_vars = sorted(diccionario_relevantes_mif.items(), key=operator.itemgetter(1), reverse=True)
for relevant_var in sorted_relevant_vars:
rel_variable= relevant_var[0]
rel_variable = "<strong>" + rel_variable +' '+ str(diccionario_relevantes_mif[rel_variable]) +"</strong>"
variables_summary+=" "+ rel_variable + "</br>"
for relevant_var in report_dict[glod.get_report_general_info_key()][glod.get_variables_key()][glod.get_used_in_process()]:
if (relevant_var not in diccionario_relevantes_mif) :
variables_summary+=" "+ relevant_var + "</br>"
variables_summary+=" <i>*variables in bold were used to train the models<i></br>"
variables_summary+="</p>"
#Information about the model
accuracy = "</br></br> <strong>Accuracy: "+ str(float(round(report_dict[modelo][glod.get_accuracy_parameter_name()],5)))+"</strong>"
ranking = get_string_with_ranking_of_models(lista_pares_modelo_indice,modelo)
model_info = "<p><strong>Parameters used to configure the model</strong></br>"
for param in report_dict[modelo][glod.get_parameters_key()]:
model_info+= " <i>"+ param + "</i>: " + str(report_dict[modelo][glod.get_parameters_key()][param]) + "</br>"
model_info+="</p>"
time_info = "<p><strong>Time elapsed</strong></br>"
tiempo_seleccion_parametros = report_dict[modelo][glod.get_time_parameters_key()][glod.get_time_sel_finish_key()] - report_dict[modelo][glod.get_time_parameters_key()][glod.get_time_sel_init_key()]
tiempo_entrenamiento = report_dict[modelo][glod.get_time_parameters_key()][glod.get_time_train_finish_key()] - report_dict[modelo][glod.get_time_parameters_key()][glod.get_time_train_init_key()]
time_info+=" "+ "Parameters selection time: "+ str(tiempo_seleccion_parametros) + "</br>"
time_info+=" "+ "Training time: "+ str(tiempo_entrenamiento) + "</br>"
time_info+="</p>"
total_train = 0.0
vector_of_targets = []
vector_of_values_by_target = []
vector_of_percentages_by_target = []
train_distribution_info ="<p></br><strong>Training Data Distribution</strong></br>"
for train_target in auxf.natsorted(report_dict[glod.get_report_general_info_key()][glod.get_training_division_key()].keys()):
train_distribution_info+=" "+ "With target " + str(train_target) + " :"+ str(report_dict[glod.get_report_general_info_key()][glod.get_training_division_key()][train_target]) + "</br>"
vector_of_targets.append(train_target)
vector_of_values_by_target.append(float(report_dict[glod.get_report_general_info_key()][glod.get_training_division_key()][train_target]))
total_train+=float(report_dict[glod.get_report_general_info_key()][glod.get_training_division_key()][train_target])
train_distribution_info+="</p>"
#getting null train accuracy
null_train_accuracy = 0.0
for indice_t in range(len(vector_of_values_by_target)):
vector_of_percentages_by_target.append(round(vector_of_values_by_target[indice_t]/total_train,4))
null_train_accuracy = max(vector_of_percentages_by_target)
total_test = 0.0
vector_of_targets = []
vector_of_values_by_target = []
vector_of_percentages_by_target = []
test_distribution_info ="<p><strong>Test Data Distribution</strong></br>"
for test_target in auxf.natsorted(report_dict[glod.get_report_general_info_key()][glod.get_test_division_key()].keys()):
test_distribution_info+=" "+ "With target " + str(test_target) + " :"+ str(report_dict[glod.get_report_general_info_key()][glod.get_test_division_key()][test_target]) + "</br>"
vector_of_targets.append(test_target)
vector_of_values_by_target.append(float(report_dict[glod.get_report_general_info_key()][glod.get_test_division_key()][test_target]))
total_test+=float(report_dict[glod.get_report_general_info_key()][glod.get_test_division_key()][test_target])
test_distribution_info+="</p>"
null_test_accuracy = 0.0
for indice_t in range(len(vector_of_values_by_target)):
vector_of_percentages_by_target.append(round(vector_of_values_by_target[indice_t]/total_test,4))
null_test_accuracy = max(vector_of_percentages_by_target)
event = report_dict[glod.get_event_key()]
template_vars = {glod.get_title_key(): "Execution Report",
glod.get_logo_key():encode_image(report_dict[glod.get_logo_key()].replace('\'','')),
glod.get_model_key(): modelo,
glod.get_report_generic_target_key(): report_dict[glod.get_objective_target_key()],
glod.get_event_key(): event,
glod.get_accuracy_parameter_name(): str(accuracy)+"<br> <strong>Null train acc: "+ str(null_train_accuracy)+"</strong>"+"<br> <strong>Null test acc: "+ str(null_test_accuracy)+ "</strong></p>",
glod.get_models_ranking_key(): ranking,
glod.get_observations_targets_key(): observations_targets,
glod.get_variables_summary_key(): variables_summary,
glod.get_models_info_key(): model_info,
glod.get_time_info_key(): time_info,
glod.get_train_distribution_info_key(): train_distribution_info,
glod.get_test_distribution_info_key(): test_distribution_info
}
template_vars[glod.get_metrics_info_key()] =""
for metric in report_dict[modelo][glod.get_metrics_micro_avg_key()]:
template_vars[glod.get_metrics_info_key()] +="<p>"+"<strong>"+metric+"</strong>: " + report_dict[modelo][glod.get_metrics_micro_avg_key()][metric] +"</br>"
template_vars[glod.get_metrics_info_key()] +="</p>"
if glod.get_model_parameters_plot_name() in report_dict[modelo]:
template_vars[glod.get_image_parameters_accuracy_key()] = encode_image(report_dict[modelo][glod.get_model_parameters_plot_name()].replace('\'',''))
if glod.get_confussion_matrix_train_path_key() in report_dict[modelo]:
template_vars[glod.get_conf_train_img_key()] = encode_image(report_dict[modelo][glod.get_confussion_matrix_train_path_key()].replace('\'',''))
if glod.get_confussion_matrix_test_path_key() in report_dict[modelo]:
template_vars[glod.get_conf_test_img_key()] = encode_image(report_dict[modelo][glod.get_confussion_matrix_test_path_key()].replace('\'',''))
if(glod.get_learning_curve_key() in report_dict[modelo]):
template_vars[glod.get_learning_curve_key()] = encode_image(report_dict[modelo][glod.get_learning_curve_key()].replace('\'',''))
metrics_by_label = "<table width='100%' border='1' cellspacing='0' cellpadding='5'>"
keys = ''
for elemento in auxf.natsorted(report_dict[modelo][glod.get_metrics_key()].keys()):
if(keys == ''):
keys = report_dict[modelo][glod.get_metrics_key()][elemento].keys()
metrics_by_label+="<tr><td align='center' class='black'>"+ glod.get_report_generic_target_key() +"</td>"
for cabecera in keys:
metrics_by_label+="<td align='center' class='black'>" + cabecera +"</td>"
metrics_by_label += "</tr>"
metrics_by_label+= "<tr><td>" + elemento.replace('target_','') + "</td>"
for key in keys:
metrics_by_label += "<td>"+str(report_dict[modelo][glod.get_metrics_key()][elemento][key])+"</td>"
metrics_by_label+= "</tr>"
metrics_by_label+="</table>"
template_vars[glod.get_metrics_by_label_key()] = metrics_by_label
#generamos el html
with codecs.open(ruta_plantilla_temporal,'w',encoding=enco) as output_file:
output_file.write(template.render(template_vars))
#generamos el pdf
with codecs.open(ruta_plantilla_temporal, mode='r',encoding=enco) as read_html:
pdf_resultante=os.path.join(ruta_directorio_informes,modelo + "_report_for_"+ event +".pdf")
with open(pdf_resultante, mode='wb') as pdf_gen:
pisa.CreatePDF(read_html.read(),pdf_gen)
logging.getLogger("xhtml2pdf").addHandler(PisaNullHandler())
if(os.path.exists(ruta_plantilla_temporal)):
os.remove(ruta_plantilla_temporal)
def create_report_current_execution(report_dict,lista_eventos,lista_variables_usuario,lista_listas_variables_descartadas,lista_aprendizajes,lista_modelos, diccionario_aprendizajes, ruta_relativa_datos_auxiliares, ruta_directorio_resultados,enco):
env = Environment(loader=FileSystemLoader('.'))
ruta_plantilla_temporal = os.path.join(ruta_relativa_datos_auxiliares,'temp_html.html')
template = env.get_template(ruta_relativa_datos_auxiliares + '/' + 'general_execution_template.html')
template_vars = {glod.get_title_key(): report_dict[glod.get_title_key()],
glod.get_logo_key():encode_image(report_dict[glod.get_logo_key()].replace('\'','')),
glod.get_general_info_execution_key():''
}
#General parameters (target,umbral,variables_descartadas)
target = report_dict[glod.get_objective_target_key()]
umbral = report_dict[glod.get_umbral_key()]
main_metric = report_dict[glod.get_main_metric_key()]
feature_selection_method = report_dict[glod.get_feature_selection_key()]
penalize_falses = report_dict[glod.get_penalization_name()]
lista_variables_descartadas = report_dict[glod.get_variables_key()][glod.get_deleted_by_user_key()]
tabulacion = " "
informacion= "<h3>Common Parameters </h3></p>"
informacion+= tabulacion+tabulacion + "<i>Objective Target: </i>" + target + "</br></br>"
informacion+=tabulacion+tabulacion + "<i>Percentil for Scoring Function: </i>" + umbral + "</br></br>"
informacion+=tabulacion+tabulacion + "<i>Main metric: </i>" + main_metric + "</br></br>"
informacion+=tabulacion+tabulacion + "<i>Feature selection method: </i>" + feature_selection_method + "</br></br>"
informacion+=tabulacion+tabulacion + "<i>Penalize falses: </i>" + penalize_falses + "</br></br>"
informacion+=tabulacion+tabulacion + "<i>Common Discarded Variables:</i></br>"
for variable_descartada in lista_variables_descartadas:
informacion+=tabulacion+tabulacion+tabulacion + variable_descartada + "</br>"
if(lista_variables_descartadas == []):
informacion+=tabulacion+"No variables were selected to be discarded</br>"
informacion+="</p>"
informacion+= "<h3>Events to be processed: </h3><p>"
for indice in range(len(lista_eventos)):
informacion+=tabulacion+"<strong>"+ lista_eventos[indice] + "</strong></br>"
informacion+=tabulacion+tabulacion+"<i>Important features for the user:</i> </br>"
if(lista_variables_usuario[indice]):
for variable in lista_variables_usuario[indice]:
informacion+=tabulacion+tabulacion+tabulacion+variable + "</br>"
else:
informacion+=tabulacion+tabulacion+tabulacion+"No important features were specified</br>"
informacion+="</br>"
informacion+=tabulacion+tabulacion+"<i>Discarded variables by the user:</i> </br>"
if(lista_listas_variables_descartadas[indice]):
for variable in lista_listas_variables_descartadas[indice]:
informacion+=tabulacion+tabulacion+tabulacion+variable + "</br>"
else:
informacion+=tabulacion+tabulacion+tabulacion+"No variables were discarded</br>"
informacion+="</br>"
informacion += tabulacion+tabulacion+"<i>Learnings to be applied: </i></br>"
aprendizaje = lista_aprendizajes[indice]
modelos = lista_modelos[indice]
if aprendizaje == glod.get_all_learning_modes_name():#looping supervised models
informacion += tabulacion+tabulacion+tabulacion+"<u>" +\
str(diccionario_aprendizajes[1]) + "</u>:</br>"
modelos_sup = modelos[0]
for modelo_act in modelos_sup:
informacion += tabulacion+tabulacion+tabulacion+tabulacion + modelo_act + "</br>"
informacion += "</br>"
informacion += tabulacion+tabulacion+tabulacion+"<u>" +\
str(diccionario_aprendizajes[2]) + "</u>:</br>"
modelos_unsup = modelos[1]
for modelo_act in modelos_unsup:
informacion += tabulacion+tabulacion+tabulacion+tabulacion + modelo_act + "</br>"
informacion += "</br>"
else:
informacion += tabulacion+tabulacion+tabulacion+"<u>"+aprendizaje + "</u>:</br>"
for modelo_act in modelos:
informacion += tabulacion+tabulacion+tabulacion+tabulacion + modelo_act + "</br>"
informacion += "</p>"
template_vars[glod.get_general_info_execution_key()] = informacion
with codecs.open(ruta_plantilla_temporal,'w',encoding=enco) as output_file:
output_file.write(template.render(template_vars))
with codecs.open(ruta_plantilla_temporal, 'r') as html_leido:
pdf_resultante=os.path.join(ruta_directorio_resultados,"General_execution_report_"+ target +".pdf")
with open(pdf_resultante, "wb") as gen_report:
pisa.CreatePDF(html_leido.read(),gen_report)
logging.getLogger("xhtml2pdf").addHandler(PisaNullHandler())
if(os.path.exists(ruta_plantilla_temporal)):
os.remove(ruta_plantilla_temporal)