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

Before Change

housing["income_cat"].hist()

//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()

After Change

// passing data in for imputation and one hot encoding
//////////////////

city_lat_long = pd.read_csv("cal_cities_lat_long.csv")
city_pop_data = pd.read_csv("cal_populations_city.csv")
county_pop_data = pd.read_csv("cal_populations_county.csv")

Instances