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

    if row["Name"] not in city_pop_data["City"].values:   
        continue           
    else: 
        city_coords[row["Name"]] = (float(row["Latitude"]), float(row["Longitude"]))


//clean pop

Instances