import pandas as pd
from pycaret.datasets import get_data
from pandas_profiling import ProfileReport
# Record version of key libraries
from importlib.metadata import version
print('pandas-profiling==%s' % version('pandas-profiling'))
pandas-profiling==3.0.0
# Select a pre-packaged data for testing
df = get_data('diabetes', verbose=True)
| Number of times pregnant | Plasma glucose concentration a 2 hours in an oral glucose tolerance test | Diastolic blood pressure (mm Hg) | Triceps skin fold thickness (mm) | 2-Hour serum insulin (mu U/ml) | Body mass index (weight in kg/(height in m)^2) | Diabetes pedigree function | Age (years) | Class variable | |
|---|---|---|---|---|---|---|---|---|---|
| 0 | 6 | 148 | 72 | 35 | 0 | 33.6 | 0.627 | 50 | 1 |
| 1 | 1 | 85 | 66 | 29 | 0 | 26.6 | 0.351 | 31 | 0 |
| 2 | 8 | 183 | 64 | 0 | 0 | 23.3 | 0.672 | 32 | 1 |
| 3 | 1 | 89 | 66 | 23 | 94 | 28.1 | 0.167 | 21 | 0 |
| 4 | 0 | 137 | 40 | 35 | 168 | 43.1 | 2.288 | 33 | 1 |
# Generate details EDA report on data - including uni/paired variables distribution, correlation and missing values
# NOTE - use minimal=True when the data is big in size
# NOTE - use explorativ=True when data contains text, image or file
# NOTE - use sensitive=True to assume no duplicates in data?
profile = ProfileReport(df, title="Pandas Profiling Report - Diabetes")
# Display report in Jupyter notebook
profile.to_notebook_iframe() # will be included in notebook
# profile.to_widgets() # only available interactively
# Save report to an HTML file
profile.to_file("pandas_profiling_report.html")