added assignment 5
This commit is contained in:
@@ -0,0 +1,341 @@
|
||||
raw manhattan rows: 96088
|
||||
raw brooklyn rows: 123813
|
||||
clean manhattan rows: 7294
|
||||
clean brooklyn rows: 42743
|
||||
Min. 1st Qu. Median Mean 3rd Qu. Max.
|
||||
1.005e+04 1.368e+06 4.000e+06 1.633e+07 9.575e+06 2.398e+09
|
||||
25% 50% 75% 90% 95% 99%
|
||||
1367750 4000000 9575000 22736850 50618132 266148692
|
||||
manhattan iqr upper bound: 21885875
|
||||
manhattan max sale price: 2397501899
|
||||
number of sale price outliers: 756
|
||||
sale_price gross_sqft land_sqft year_built res_units comm_units
|
||||
1.00000000 0.49144986 0.16392585 0.02117231 0.11589681 0.20912401
|
||||
total_units
|
||||
0.16618138
|
||||
|
||||
linear model (log price) metrics on manhattan:
|
||||
r2: 0.1867558 rmse: 1.689562 mae: 1.260938
|
||||
|
||||
random forest (log price) metrics on manhattan:
|
||||
r2: 0.6978428 rmse: 1.031439 mae: 0.661946
|
||||
|
||||
random forest (log price) metrics on brooklyn (trained on manhattan):
|
||||
r2: 0.2442946 rmse: 1.305062 mae: 1.084852
|
||||
|
||||
manhattan classification subset rows: 6792
|
||||
manhattan neighborhoods: 28
|
||||
|
||||
knn (manhattan) accuracy: 0.4774882 macro f1: 0.4174939
|
||||
|
||||
random forest classifier (manhattan) accuracy: 0.5841232 macro f1: 0.5328558
|
||||
[1] 28 28
|
||||
Reference
|
||||
Prediction ALPHABET CITY CHELSEA CHINATOWN CLINTON
|
||||
ALPHABET CITY 9 1 0 0
|
||||
CHELSEA 0 23 2 1
|
||||
CHINATOWN 0 0 10 0
|
||||
CLINTON 0 2 0 17
|
||||
EAST VILLAGE 2 2 2 0
|
||||
FASHION 0 4 0 0
|
||||
GRAMERCY 0 0 0 0
|
||||
GREENWICH VILLAGE-CENTRAL 0 2 1 0
|
||||
GREENWICH VILLAGE-WEST 1 3 0 1
|
||||
HARLEM-CENTRAL 3 4 3 5
|
||||
HARLEM-EAST 4 1 0 0
|
||||
HARLEM-UPPER 1 1 0 1
|
||||
KIPS BAY 0 2 0 0
|
||||
LOWER EAST SIDE 1 3 2 0
|
||||
MANHATTAN VALLEY 0 0 0 0
|
||||
MIDTOWN CBD 0 1 1 0
|
||||
MIDTOWN EAST 1 2 0 1
|
||||
MIDTOWN WEST 0 3 1 1
|
||||
MURRAY HILL 0 3 1 0
|
||||
SOHO 0 2 1 0
|
||||
TRIBECA 0 1 0 0
|
||||
UPPER EAST SIDE (59-79) 1 3 0 2
|
||||
UPPER EAST SIDE (79-96) 0 2 1 0
|
||||
UPPER WEST SIDE (59-79) 1 1 0 1
|
||||
UPPER WEST SIDE (79-96) 1 3 0 0
|
||||
UPPER WEST SIDE (96-116) 0 1 0 1
|
||||
WASHINGTON HEIGHTS LOWER 0 0 0 0
|
||||
WASHINGTON HEIGHTS UPPER 0 0 0 1
|
||||
Reference
|
||||
Prediction EAST VILLAGE FASHION GRAMERCY
|
||||
ALPHABET CITY 2 0 0
|
||||
CHELSEA 1 1 0
|
||||
CHINATOWN 0 1 0
|
||||
CLINTON 1 0 0
|
||||
EAST VILLAGE 33 0 0
|
||||
FASHION 0 10 0
|
||||
GRAMERCY 1 0 29
|
||||
GREENWICH VILLAGE-CENTRAL 2 1 0
|
||||
GREENWICH VILLAGE-WEST 2 0 1
|
||||
HARLEM-CENTRAL 4 2 2
|
||||
HARLEM-EAST 0 2 0
|
||||
HARLEM-UPPER 0 0 0
|
||||
KIPS BAY 0 0 0
|
||||
LOWER EAST SIDE 0 1 0
|
||||
MANHATTAN VALLEY 0 0 1
|
||||
MIDTOWN CBD 0 3 2
|
||||
MIDTOWN EAST 0 1 0
|
||||
MIDTOWN WEST 0 2 0
|
||||
MURRAY HILL 0 2 0
|
||||
SOHO 0 0 0
|
||||
TRIBECA 1 1 0
|
||||
UPPER EAST SIDE (59-79) 1 0 1
|
||||
UPPER EAST SIDE (79-96) 0 0 0
|
||||
UPPER WEST SIDE (59-79) 0 1 0
|
||||
UPPER WEST SIDE (79-96) 2 0 2
|
||||
UPPER WEST SIDE (96-116) 1 0 0
|
||||
WASHINGTON HEIGHTS LOWER 1 0 0
|
||||
WASHINGTON HEIGHTS UPPER 0 0 0
|
||||
Reference
|
||||
Prediction GREENWICH VILLAGE-CENTRAL GREENWICH VILLAGE-WEST
|
||||
ALPHABET CITY 0 0
|
||||
CHELSEA 1 5
|
||||
CHINATOWN 1 1
|
||||
CLINTON 0 0
|
||||
EAST VILLAGE 3 1
|
||||
FASHION 0 0
|
||||
GRAMERCY 0 0
|
||||
GREENWICH VILLAGE-CENTRAL 14 3
|
||||
GREENWICH VILLAGE-WEST 5 42
|
||||
HARLEM-CENTRAL 1 4
|
||||
HARLEM-EAST 1 1
|
||||
HARLEM-UPPER 0 0
|
||||
KIPS BAY 0 1
|
||||
LOWER EAST SIDE 1 0
|
||||
MANHATTAN VALLEY 0 0
|
||||
MIDTOWN CBD 0 0
|
||||
MIDTOWN EAST 1 1
|
||||
MIDTOWN WEST 0 1
|
||||
MURRAY HILL 0 0
|
||||
SOHO 1 0
|
||||
TRIBECA 0 0
|
||||
UPPER EAST SIDE (59-79) 1 6
|
||||
UPPER EAST SIDE (79-96) 1 6
|
||||
UPPER WEST SIDE (59-79) 0 0
|
||||
UPPER WEST SIDE (79-96) 2 3
|
||||
UPPER WEST SIDE (96-116) 1 0
|
||||
WASHINGTON HEIGHTS LOWER 0 0
|
||||
WASHINGTON HEIGHTS UPPER 0 0
|
||||
Reference
|
||||
Prediction HARLEM-CENTRAL HARLEM-EAST HARLEM-UPPER KIPS BAY
|
||||
ALPHABET CITY 2 0 0 0
|
||||
CHELSEA 0 0 0 0
|
||||
CHINATOWN 2 0 0 0
|
||||
CLINTON 0 0 1 0
|
||||
EAST VILLAGE 0 0 0 0
|
||||
FASHION 0 0 0 0
|
||||
GRAMERCY 0 0 0 0
|
||||
GREENWICH VILLAGE-CENTRAL 0 0 0 0
|
||||
GREENWICH VILLAGE-WEST 0 0 2 0
|
||||
HARLEM-CENTRAL 158 15 21 0
|
||||
HARLEM-EAST 9 35 2 0
|
||||
HARLEM-UPPER 9 2 19 0
|
||||
KIPS BAY 2 0 1 27
|
||||
LOWER EAST SIDE 3 0 0 0
|
||||
MANHATTAN VALLEY 1 4 0 0
|
||||
MIDTOWN CBD 0 0 0 0
|
||||
MIDTOWN EAST 2 0 0 2
|
||||
MIDTOWN WEST 2 0 0 0
|
||||
MURRAY HILL 2 1 0 0
|
||||
SOHO 1 1 0 0
|
||||
TRIBECA 0 0 0 0
|
||||
UPPER EAST SIDE (59-79) 2 0 1 0
|
||||
UPPER EAST SIDE (79-96) 2 4 0 1
|
||||
UPPER WEST SIDE (59-79) 0 0 0 0
|
||||
UPPER WEST SIDE (79-96) 0 0 0 0
|
||||
UPPER WEST SIDE (96-116) 0 0 4 0
|
||||
WASHINGTON HEIGHTS LOWER 7 3 1 0
|
||||
WASHINGTON HEIGHTS UPPER 1 1 1 0
|
||||
Reference
|
||||
Prediction LOWER EAST SIDE MANHATTAN VALLEY MIDTOWN CBD
|
||||
ALPHABET CITY 0 0 0
|
||||
CHELSEA 4 0 0
|
||||
CHINATOWN 0 1 0
|
||||
CLINTON 0 0 0
|
||||
EAST VILLAGE 3 0 0
|
||||
FASHION 2 0 1
|
||||
GRAMERCY 0 1 0
|
||||
GREENWICH VILLAGE-CENTRAL 0 0 0
|
||||
GREENWICH VILLAGE-WEST 1 0 0
|
||||
HARLEM-CENTRAL 4 7 2
|
||||
HARLEM-EAST 1 0 0
|
||||
HARLEM-UPPER 0 0 0
|
||||
KIPS BAY 0 0 0
|
||||
LOWER EAST SIDE 47 2 0
|
||||
MANHATTAN VALLEY 0 11 0
|
||||
MIDTOWN CBD 0 0 12
|
||||
MIDTOWN EAST 0 0 3
|
||||
MIDTOWN WEST 0 2 1
|
||||
MURRAY HILL 2 0 0
|
||||
SOHO 0 0 1
|
||||
TRIBECA 0 0 0
|
||||
UPPER EAST SIDE (59-79) 1 0 2
|
||||
UPPER EAST SIDE (79-96) 1 1 1
|
||||
UPPER WEST SIDE (59-79) 0 0 2
|
||||
UPPER WEST SIDE (79-96) 0 0 1
|
||||
UPPER WEST SIDE (96-116) 0 1 0
|
||||
WASHINGTON HEIGHTS LOWER 0 1 0
|
||||
WASHINGTON HEIGHTS UPPER 0 1 0
|
||||
Reference
|
||||
Prediction MIDTOWN EAST MIDTOWN WEST MURRAY HILL SOHO TRIBECA
|
||||
ALPHABET CITY 0 0 1 1 0
|
||||
CHELSEA 3 1 2 1 0
|
||||
CHINATOWN 0 1 2 0 0
|
||||
CLINTON 0 0 1 2 0
|
||||
EAST VILLAGE 1 0 0 2 0
|
||||
FASHION 0 3 3 1 0
|
||||
GRAMERCY 1 0 0 0 1
|
||||
GREENWICH VILLAGE-CENTRAL 0 1 0 3 1
|
||||
GREENWICH VILLAGE-WEST 1 0 1 3 1
|
||||
HARLEM-CENTRAL 4 5 5 0 0
|
||||
HARLEM-EAST 0 0 1 0 0
|
||||
HARLEM-UPPER 0 1 2 0 0
|
||||
KIPS BAY 0 0 0 0 0
|
||||
LOWER EAST SIDE 0 2 1 2 1
|
||||
MANHATTAN VALLEY 0 0 0 1 0
|
||||
MIDTOWN CBD 0 6 0 1 0
|
||||
MIDTOWN EAST 24 1 1 0 0
|
||||
MIDTOWN WEST 0 177 0 2 0
|
||||
MURRAY HILL 3 0 16 1 0
|
||||
SOHO 1 1 1 16 1
|
||||
TRIBECA 0 3 0 0 36
|
||||
UPPER EAST SIDE (59-79) 1 0 2 2 2
|
||||
UPPER EAST SIDE (79-96) 3 2 2 1 1
|
||||
UPPER WEST SIDE (59-79) 2 0 0 0 0
|
||||
UPPER WEST SIDE (79-96) 3 0 2 0 2
|
||||
UPPER WEST SIDE (96-116) 1 0 0 0 0
|
||||
WASHINGTON HEIGHTS LOWER 0 0 0 0 0
|
||||
WASHINGTON HEIGHTS UPPER 0 0 0 0 0
|
||||
Reference
|
||||
Prediction UPPER EAST SIDE (59-79) UPPER EAST SIDE (79-96)
|
||||
ALPHABET CITY 0 0
|
||||
CHELSEA 1 3
|
||||
CHINATOWN 1 4
|
||||
CLINTON 1 1
|
||||
EAST VILLAGE 2 1
|
||||
FASHION 2 1
|
||||
GRAMERCY 0 0
|
||||
GREENWICH VILLAGE-CENTRAL 0 0
|
||||
GREENWICH VILLAGE-WEST 2 7
|
||||
HARLEM-CENTRAL 6 5
|
||||
HARLEM-EAST 0 0
|
||||
HARLEM-UPPER 1 2
|
||||
KIPS BAY 0 0
|
||||
LOWER EAST SIDE 1 1
|
||||
MANHATTAN VALLEY 0 0
|
||||
MIDTOWN CBD 2 2
|
||||
MIDTOWN EAST 4 2
|
||||
MIDTOWN WEST 1 0
|
||||
MURRAY HILL 0 1
|
||||
SOHO 2 2
|
||||
TRIBECA 1 0
|
||||
UPPER EAST SIDE (59-79) 47 14
|
||||
UPPER EAST SIDE (79-96) 20 53
|
||||
UPPER WEST SIDE (59-79) 2 1
|
||||
UPPER WEST SIDE (79-96) 3 2
|
||||
UPPER WEST SIDE (96-116) 0 3
|
||||
WASHINGTON HEIGHTS LOWER 1 0
|
||||
WASHINGTON HEIGHTS UPPER 0 1
|
||||
Reference
|
||||
Prediction UPPER WEST SIDE (59-79) UPPER WEST SIDE (79-96)
|
||||
ALPHABET CITY 1 1
|
||||
CHELSEA 0 2
|
||||
CHINATOWN 0 0
|
||||
CLINTON 0 1
|
||||
EAST VILLAGE 1 1
|
||||
FASHION 0 0
|
||||
GRAMERCY 0 0
|
||||
GREENWICH VILLAGE-CENTRAL 1 1
|
||||
GREENWICH VILLAGE-WEST 0 1
|
||||
HARLEM-CENTRAL 4 3
|
||||
HARLEM-EAST 1 1
|
||||
HARLEM-UPPER 0 1
|
||||
KIPS BAY 0 0
|
||||
LOWER EAST SIDE 0 0
|
||||
MANHATTAN VALLEY 0 2
|
||||
MIDTOWN CBD 0 0
|
||||
MIDTOWN EAST 0 0
|
||||
MIDTOWN WEST 3 1
|
||||
MURRAY HILL 0 0
|
||||
SOHO 0 0
|
||||
TRIBECA 1 1
|
||||
UPPER EAST SIDE (59-79) 4 2
|
||||
UPPER EAST SIDE (79-96) 4 8
|
||||
UPPER WEST SIDE (59-79) 46 2
|
||||
UPPER WEST SIDE (79-96) 7 31
|
||||
UPPER WEST SIDE (96-116) 1 0
|
||||
WASHINGTON HEIGHTS LOWER 0 0
|
||||
WASHINGTON HEIGHTS UPPER 0 1
|
||||
Reference
|
||||
Prediction UPPER WEST SIDE (96-116) WASHINGTON HEIGHTS LOWER
|
||||
ALPHABET CITY 0 0
|
||||
CHELSEA 1 0
|
||||
CHINATOWN 0 0
|
||||
CLINTON 0 0
|
||||
EAST VILLAGE 0 0
|
||||
FASHION 0 0
|
||||
GRAMERCY 0 0
|
||||
GREENWICH VILLAGE-CENTRAL 1 0
|
||||
GREENWICH VILLAGE-WEST 0 0
|
||||
HARLEM-CENTRAL 6 18
|
||||
HARLEM-EAST 1 1
|
||||
HARLEM-UPPER 1 5
|
||||
KIPS BAY 1 0
|
||||
LOWER EAST SIDE 1 1
|
||||
MANHATTAN VALLEY 0 0
|
||||
MIDTOWN CBD 0 0
|
||||
MIDTOWN EAST 0 0
|
||||
MIDTOWN WEST 0 0
|
||||
MURRAY HILL 0 0
|
||||
SOHO 0 0
|
||||
TRIBECA 1 0
|
||||
UPPER EAST SIDE (59-79) 1 0
|
||||
UPPER EAST SIDE (79-96) 2 1
|
||||
UPPER WEST SIDE (59-79) 1 0
|
||||
UPPER WEST SIDE (79-96) 2 0
|
||||
UPPER WEST SIDE (96-116) 16 0
|
||||
WASHINGTON HEIGHTS LOWER 0 23
|
||||
WASHINGTON HEIGHTS UPPER 1 2
|
||||
Reference
|
||||
Prediction WASHINGTON HEIGHTS UPPER
|
||||
ALPHABET CITY 0
|
||||
CHELSEA 0
|
||||
CHINATOWN 0
|
||||
CLINTON 0
|
||||
EAST VILLAGE 0
|
||||
FASHION 0
|
||||
GRAMERCY 0
|
||||
GREENWICH VILLAGE-CENTRAL 0
|
||||
GREENWICH VILLAGE-WEST 0
|
||||
HARLEM-CENTRAL 7
|
||||
HARLEM-EAST 3
|
||||
HARLEM-UPPER 4
|
||||
KIPS BAY 0
|
||||
LOWER EAST SIDE 0
|
||||
MANHATTAN VALLEY 0
|
||||
MIDTOWN CBD 0
|
||||
MIDTOWN EAST 0
|
||||
MIDTOWN WEST 0
|
||||
MURRAY HILL 0
|
||||
SOHO 1
|
||||
TRIBECA 0
|
||||
UPPER EAST SIDE (59-79) 0
|
||||
UPPER EAST SIDE (79-96) 0
|
||||
UPPER WEST SIDE (59-79) 0
|
||||
UPPER WEST SIDE (79-96) 1
|
||||
UPPER WEST SIDE (96-116) 0
|
||||
WASHINGTON HEIGHTS LOWER 7
|
||||
WASHINGTON HEIGHTS UPPER 5
|
||||
|
||||
multinomial logistic regression (manhattan) accuracy: 0.2517773 macro f1: 0.2957543
|
||||
|
||||
brooklyn classification subset rows: 42533
|
||||
brooklyn neighborhoods: 56
|
||||
|
||||
contingency table dimensions (knn): 56 28
|
||||
contingency table dimensions (random forest): 56 28
|
||||
contingency table dimensions (logit): 56 28
|
||||
Reference in New Issue
Block a user