File size: 1,227 Bytes
d7f258e | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 | """Ejemplo de uso de EDA Express descargado del Hub.
pip install huggingface_hub pandas numpy tabulate requests
python example.py
"""
import sys
import pandas as pd
from huggingface_hub import snapshot_download
path = snapshot_download("aitziberluis/eda-express")
sys.path.insert(0, path)
from eda import alerts, profiler, report # noqa: E402
# El repo incluye el dataset del Titanic como ejemplo.
df = pd.read_csv(f"{path}/datasets/titanic.csv")
print("=== Visión general ===")
for k, v in profiler.overview(df).items():
print(f" {k}: {v}")
print("\n=== Alertas ===")
for a in alerts.run_all_checks(df, target="survived"):
print(f" [{a['nivel'].upper()}] {a['columna']}: {a['mensaje']}")
print("\n=== Eta² respecto a 'survived' ===")
print(profiler.eta_squared_table(df, "survived").to_string(index=False))
pca = profiler.pca_summary(df)
if pca:
v = pca["varianza_explicada"]
print(f"\n=== PCA === PC1 {v[0]:.0%} + PC2 {v[1]:.0%} de la varianza")
md = report.build_report(df, "titanic", alerts.run_all_checks(df, "survived"), "survived")
with open("informe_titanic.md", "w", encoding="utf-8") as f:
f.write(md)
print(f"\nInforme guardado: informe_titanic.md ({len(md)} caracteres)")
|