Exploratory data analysis checklist for tabular ML projects

                  import pandas as pd

df = pd.read_parquet('churn_training.parquet')

print('shape:', df.shape)
print('target balance:', df['churned'].value_counts(normalize=True).round(3))
print('missing ratio:')
print(df.isna().mean().sort_values(ascending=False).head(15))

numeric = df.select_dtypes(include=['number'])
print('top correlations with target:')
correlations = numeric.corr(numeric_only=True)['churned'].sort_values(key=abs, ascending=False)
print(correlations.head(10))

high_cardinality = df.nunique().sort_values(ascending=False)
print('high-cardinality features:')
print(high_cardinality.head(10))