tabaudit report

{{ summary.path }} · generated {{ generated_at }} · v{{ version }}

Data health

{% for sev, n in counts %}{% if n %}{{ sev }} {{ n }}{% endif %}{% endfor %} {% if not findings %}No issues found{% endif %}

Shape: {{ "{:,}".format(summary.n_rows) }} rows × {{ summary.n_cols }} columns ({{ summary.memory_mb }} MB)
Columns: {% for k, v in summary.dtypes.items() %}{{ v }} {{ k }}{{ ", " if not loop.last }}{% endfor %}
Target: {% if summary.target %}{{ summary.target }} → {{ summary.task }}{% if summary.n_classes %} ({{ summary.n_classes }} classes){% endif %}{% else %}none{% endif %}
Test set: {{ summary.test_path }} ({{ "{:,}".format(summary.n_test_rows) }} rows)

{% for f in findings %}

{% if f.columns %}

{% for c in f.columns[:30] %}{{ c }}{% endfor %}{% if f.columns|length > 30 %}+{{ f.columns|length - 30 }} more{% endif %}

{% endif %} {% if f.recommendation %}

→ {{ f.recommendation }}

{% endif %} {% if f.evidence.top_suspects %} {% for r in f.evidence.top_suspects[:15] %} {% endfor %}

row	given label	suggested label	P(given)	P(suggested)
{{ r.row }}	{{ r.given_label }}	{{ r.suggested_label }}	{{ "%.2f" \| format(r.confidence_in_given) }}	{{ "%.2f" \| format(r.confidence_in_suggested) }}

{% endif %}

{% endfor %}

{% for c in checks %} {% endfor %}

check	status	findings	time
`{{ c.name }}`	{% if c.status == "ok" %}✓ ok{% else %}✗ {{ c.status }} {{ c.note }}{% endif %}	{{ c.n_findings }}	{{ "%.2f" \| format(c.duration_s) }}s