from sklearn.datasets import fetch_openml
import pandas as pd
import numpy as np
import statsmodels.formula.api as smf
import statsmodels.api as sm

X, y = fetch_openml("titanic", version=1, as_frame=True, return_X_y=True)
type(X)

X.info()

y.dtype

y.attrs

y.values

y

y.index

y.empty

X.columns

y.name

y.flags

y.astype

y.rank

y.type

y.astype

type(y)

df = pd.merge(X, y, right_index = True, left_index = True)
print(df)

df.info()

df.index

formula = 'survived ~ age + pclass'
model = smf.glm(formula = formula, data=df, family=sm.families.Binomial())
result=model.fit()
print(result.summary())