{% set ns = namespace(tests=summary.total_evaluations, passed=0, failed=0) %} {% for r in summary.results %} {% set p = namespace(pass=false, fail=false) %} {% if r.result and r.result.scores %} {% for s in r.result.scores %} {% if s.passed is true %} {% set p.pass = true %} {% elif s.passed is false and p.pass is not true %} {% set p.fail = true %} {% endif %} {% endfor %} {% endif %} {% if p.pass %}{% set ns.passed = ns.passed + 1 %}{% elif p.fail %}{% set ns.failed = ns.failed + 1 %}{% endif %} {% endfor %}
Tests: {{ summary.total_evaluations }} {% for chip in score_chips %} {% if chip.type == 'ratio' %} {% set klass = 'bg-yellow-100 text-yellow-800' %} {% if chip.passed == chip.total %}{% set klass = 'bg-green-100 text-green-800' %}{% elif chip.passed == 0 and chip.total > 0 %}{% set klass = 'bg-red-100 text-red-800' %}{% endif %} {{ chip.key }}: {{ chip.passed }}/{{ chip.total }} {% elif chip.type == 'avg' %} {{ chip.key }}: {{ chip.avg | round(2) }} {% endif %} {% endfor %} {% if summary.average_latency > 0 %} Avg: {{ summary.average_latency | round(2) }}s {% endif %}
{% for r in summary.results %} {% set row_id = loop.index0 %} {% endfor %}
Function Dataset Labels Input Output Reference Error Scores Latency
{{ r.function }} {{ r.dataset }} {% if r.labels %} {% for la in r.labels %} {{ la }} {% endfor %} {% endif %} {{ r.result.input }} {{ r.result.output }} {% if r.result.reference is not none %} {{ r.result.reference }} {% else %} {% endif %} {% if r.result.error %} {{ r.result.error }} {% else %} {% endif %} {% if r.result.scores %} {% set max_show = 3 %}
{% for s in r.result.scores %} {% if loop.index0 < max_show %} {% set badge = 'bg-slate-100 text-slate-700' %} {% if s.passed is true %} {% set badge = 'bg-green-100 text-green-800' %} {% elif s.passed is false %} {% set badge = 'bg-red-100 text-red-800' %} {% endif %} {% if s.value is not none %} {{ s.key }}: {{ (s.value is number) and (s.value | round(2)) or s.value }} {% else %} {{ s.key }} {% endif %} {% endif %} {% endfor %} {% if r.result.scores | length > max_show %} +{{ r.result.scores | length - max_show }} {% endif %}
{% else %} {% endif %}
{% if r.result.latency is not none %} {% set latency = r.result.latency %} {% set label = latency | round(2) %} {% if latency <= 0.5 %} {{ label }}s {% elif latency <= 1.5 %} {{ label }}s {% else %} {{ label }}s {% endif %} {% else %} {% endif %}