Data Profile Report

Comprehensive Dataset Analysis

Dataset Overview

Summary
{{ profile.overview.num_Row }}
Total Observations
{{ profile.overview.num_Columns }}
Variables
{{ profile.overview.duplicated_rows }}
Duplicate Rows
{% if profile.overview.duplicate_percentage is defined %}
{{ "%.2f"|format(profile.overview.duplicate_percentage) }}%
Duplicate Percentage
{% endif %}
{{ "%.2f"|format(profile.overview.missing_percentage) }}%
Missing Value %
{% if profile.overview.duplicate_indices and profile.overview.duplicate_indices|length > 0 %}
Duplicate Details
Duplicate Indices {{ profile.overview.duplicate_indices | join(", ") }}
{% if profile.overview.duplicate_samples and profile.overview.duplicate_samples|length > 0 %}
Duplicate Samples
{% for sample in profile.overview.duplicate_samples %} 
{{ sample | tojson(indent=2) }}
{% endfor %}
{% endif %} {% endif %} {% if profile.overview.alerts and profile.overview.alerts|length > 0 %}
Dataset Alerts
{% for alert in profile.overview.alerts %}
{{ alert.alert_type | replace('_', ' ') | upper }}
{{ alert.message }}
{% endfor %}
{% endif %}
🔍
    {% for var_name in profile.variables.keys() %}
  • {{ var_name }}
    • {% endfor %}
{% for var_name, details in profile.variables.items() %}

Variable: {{ var_name }}

Statistical Summary
{% for stat_key, stat_value in details.items() %} {% if stat_key not in ['plot', 'plot_bar', 'plot_base64', 'plot_bar_base64', 'plot_data', 'plot_bar_data', 'plot_type', 'plot_bar_type', 'value_counts', 'value_counts_top_10', 'alerts', 'value_counts_top_5', 'value_counts_top_n', 'word_frequencies', 'outlier_indices'] %} {% endif %} {% endfor %}
{{ stat_key | replace('_', ' ') | title }} {% if stat_value is number and stat_value is not integer %}{{ "%.3f"|format(stat_value) }}{% else %}{{ stat_value }}{% endif %}
{% if details.value_counts or details.value_counts_top_10 or details.value_counts_top_5 or details.value_counts_top_n %}
Value Distribution
{% set counts = details.value_counts or details.value_counts_top_10 or details.value_counts_top_5 or details.value_counts_top_n %} {% for value, count in counts.items() %} {% endfor %}
{{ value }} {{ count }}
{% endif %} {% if details.alerts and details.alerts|length > 0 %}
Variable Alerts
{% for alert in details.alerts %}
{{ alert.alert_type | replace('_', ' ') | upper }}
{{ alert.message }}
{% endfor %}
{% endif %} {% if details.plot %} {% if details.word_frequencies %}
Word Cloud
{% if details.plot.type == 'plotly' %}
{% else %} Word cloud for {{ var_name }} {% endif %} {% if details.plot_bar %}
Value Distribution (Bar Chart)
{% if details.plot_bar.type == 'plotly' %}
{% else %} Bar chart for {{ var_name }} {% endif %} {% endif %} {% else %}
Distribution Plot
{% if details.plot.type == 'plotly' %}
{% else %} Distribution plot for {{ var_name }} {% endif %} {% endif %} {% endif %}
{% endfor %}

Data Quality Alerts

Issues
{% set has_alerts = false %} {% set alerts_found = [] %} {% for var_name, details in profile.variables.items() %} {% if details.alerts and details.alerts|length > 0 %} {% set _ = alerts_found.append(1) %}

Variable: {{ var_name }}

{% for alert in details.alerts %} {% if alert.alert_type and alert.message %}
{{ alert.alert_type | replace('_', ' ') | upper }}
{{ alert.message }}
{% endif %} {% endfor %}
{% endif %} {% endfor %} {% if alerts_found|length == 0 %}

No data quality issues detected.

{% endif %}

Correlation Analysis

Relationships
{% if profile.Correlations_Plots and profile.Correlations_Plots.keys() | length > 0 %}
{% for corr_name in profile.Correlations_Plots.keys() %} {% endfor %}
{% for corr_name, plot_data in profile.Correlations_Plots.items() %}
{% if plot_data is mapping and plot_data.type == 'plotly' %}
{% else %} Correlation plot for {{ corr_name }} {% endif %}
{% endfor %}
{% else %}

No correlation plots were generated.

{% endif %}

Data Sample

Preview
{% if profile.Sample_data %}
{{ profile.Sample_data.Head | safe }}
{{ profile.Sample_data.Tail | safe }}
{% endif %}