b7990885d8b26b9404fd9ce952b0b2f005019594,california_housing/feature_engineering.py,,,#,23

Before Change

//make a stratified split of the data
split = StratifiedShuffleSplit(n_splits=1, test_size=0.2, random_state=42)
for train_index, test_index in split.split(housing, housing["income_cat"]):
	train_set = housing.loc[train_index]
	test_set = housing.loc[test_index]

for set_ in (train_set, test_set):
	set_.drop("income_cat", axis=1, inplace=True)

gc.collect()

//////////
// plot data 

After Change

//example below
newport_ri = (41.49008, -71.312796)
cleveland_oh = (41.499498, -81.695391)
x = vincenty(newport_ri, cleveland_oh)
x //distance stored in km, see units on printing
print(x)
type(x.kilometers)

Instances