How to find regression parameters

Working off the transform_regression example, can you please show me how to find the coef array when you pass parms=True as an argument?

import altair as alt
import pandas as pd
import numpy as np

np.random.seed(42)
x = np.linspace(0, 10)
y = x - 5 + np.random.randn(len(x))

df = pd.DataFrame({'x': x, 'y': y})
chart = alt.Chart(df).mark_point().encode(
    x='x',
    y='y'
)

b  = chart.transform_regression('x', 'y', params=True).mark_line()
chart +  b

[jakevdp]

From above:

Install it with:

pip install git+https://github.com/altair-viz/altair-transform.git

[jakevdp]

Transforms are computed in the frontend, so the results are generally not directly available in Python.

The altair_transform package has some experimental support for extracting them, however.

Install it with:

pip install git+https://github.com/altair-viz/altair-transform.git

And then extract the parameters this way:

import altair_transform
print(altair_transform.extract_data(b))
#                                        coef  rSquared
# 0  [-4.935556907797029, 0.9420166005081777]  0.903174