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

Before Change

	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

city_coords = {}

for dat in city_lat_long.iterrows():
    row = dat[1]
    if row["Name"] not in city_pop_data["City"].values:   
        continue           
    else: 
        city_coords[row["Name"]] = (float(row["Latitude"]), float(row["Longitude"]))


//clean pop
//fill in the missing 1980s values with avg rate of change
//make a dictonary of cities lat/long pass in a tuple of lat/longs
//for a given point and do the comparison

//two functions
/Ǘ. take two lat long tuples as input
	//return the distance between the two
    //vincenty(tuple1, tuple2)


//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

Instances