Overview
There were {{ interviews|length }} total interviews. The number of interviews with exceptions was {{ num_exceptions }}.
The models used were: {{ models_used }}.
For documentation on dealing with exceptions on Expected Parrot,
see here.
Exceptions by Type
Exception Type |
Number |
{% for exception_type, exceptions in exceptions_by_type.items() %}
{{ exception_type }} |
{{ exceptions }} |
{% endfor %}
Exceptions by Model
Model |
Number |
{% for model, exceptions in exceptions_by_model.items() %}
{{ model }} |
{{ exceptions }} |
{% endfor %}
Exceptions by Question Name
Question Name |
Number of Exceptions |
{% for question_name, exception_count in exceptions_by_question_name.items() %}
{{ question_name }} |
{{ exception_count }} |
{% endfor %}
{% for index, interview in interviews.items() %}
{% if interview.exceptions != {} %}
Interview: {{ index }}
Failing questions
{% endif %}
{% for question, exceptions in interview.exceptions.items() %}
question_name: {{ question }}
Question
{{ interview.survey._get_question_by_name(question).html() }}
Scenario
{{ interview.scenario._repr_html_() }}
Agent
{{ interview.agent._repr_html_() }}
Model
{{ interview.model._repr_html_() }}
Exception details
{% for exception_message in exceptions %}
Exception: {{ exception_message.exception }}
Time: {{ exception_message.time }}
Traceback:
{{ exception_message.traceback }}
{% endfor %}
{% endfor %}
{% endfor %}
Performance Plot
{{ performance_plot_html }}