sivakornchong
commited on
Commit
•
b9ed1ac
1
Parent(s):
ca08c8e
Enter new model (using XGBoost pipeline instead)
Browse files- .gitignore +2 -1
- data/RPI_dict.csv +30 -0
- finalized_model.sav +0 -3
- main.py +33 -30
- main_old.py +96 -0
- test.ipynb +428 -0
.gitignore
CHANGED
@@ -1,3 +1,4 @@
|
|
1 |
__pycache__
|
2 |
model/
|
3 |
-
*sav
|
|
|
|
1 |
__pycache__
|
2 |
model/
|
3 |
+
*sav
|
4 |
+
.ipynb_checkpoints
|
data/RPI_dict.csv
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
2Q2024,184
|
2 |
+
1Q2024,182
|
3 |
+
4Q2023,180.2
|
4 |
+
3Q2023,178.5
|
5 |
+
2Q2023,176.2
|
6 |
+
1Q2023,173.6
|
7 |
+
4Q2022,171.9
|
8 |
+
3Q2022,168.1
|
9 |
+
2Q2022,163.9
|
10 |
+
1Q2022,159.5
|
11 |
+
4Q2021,155.7
|
12 |
+
3Q2021,150.6
|
13 |
+
2Q2021,146.4
|
14 |
+
1Q2021,142.2
|
15 |
+
4Q2020,138.1
|
16 |
+
3Q2020,133.9
|
17 |
+
2Q2020,131.9
|
18 |
+
1Q2020,131.5
|
19 |
+
4Q2019,131.5
|
20 |
+
3Q2019,130.9
|
21 |
+
2Q2019,130.8
|
22 |
+
1Q2019,131.0
|
23 |
+
4Q2018,131.4
|
24 |
+
3Q2018,131.6
|
25 |
+
2Q2018,131.7
|
26 |
+
1Q2018,131.6
|
27 |
+
4Q2017,132.6
|
28 |
+
3Q2017,132.8
|
29 |
+
2Q2017,133.7
|
30 |
+
1Q2017,133.9
|
finalized_model.sav
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:1fcee802bc380de56e88aee0b2fee8a6586391ee036fa11f9e16eba6d21ffa6f
|
3 |
-
size 813445176
|
|
|
|
|
|
|
|
main.py
CHANGED
@@ -4,24 +4,21 @@ from misc import nearest_mrt
|
|
4 |
import pickle
|
5 |
import os
|
6 |
import pandas as pd
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
|
11 |
def main_fn(Postal_,age_,town_,storey_,room_):
|
12 |
-
|
13 |
-
filename = '
|
14 |
-
|
15 |
-
if os.path.exists("./finalized_model.sav"):
|
16 |
model = pickle.load(open(filename, 'rb'))
|
17 |
print('loaded model')
|
18 |
else:
|
19 |
print('failed loading model')
|
20 |
|
21 |
-
#extract feature names
|
22 |
-
feature_names = model.
|
23 |
input = [0]*len(feature_names)
|
24 |
-
# print(feature_names)
|
25 |
|
26 |
#Set up mrt_list
|
27 |
mrt_name = []
|
@@ -33,16 +30,17 @@ def main_fn(Postal_,age_,town_,storey_,room_):
|
|
33 |
loc = tuple([float(i) for i in item['location']])
|
34 |
mrt_loc.append(loc)
|
35 |
|
36 |
-
#
|
37 |
-
|
|
|
38 |
##POSTAL
|
39 |
Postal_input = int(Postal_)
|
40 |
# Postal_input = 680705
|
41 |
input[feature_names.index('Postal')] = Postal_input
|
42 |
|
43 |
##DISTANCE TO MRT
|
44 |
-
search_term =
|
45 |
-
query_string='https://
|
46 |
resp = requests.get(query_string)
|
47 |
data = json.loads(resp.content)
|
48 |
print(query_string)
|
@@ -60,33 +58,38 @@ def main_fn(Postal_,age_,town_,storey_,room_):
|
|
60 |
Height = (height_input+2)//3
|
61 |
input[feature_names.index('storey_height')] = Height
|
62 |
|
63 |
-
##
|
64 |
-
|
65 |
-
# town_input = 'CHOA CHU KANG'
|
66 |
-
input[feature_names.index("town_"+town_input)] = 1
|
67 |
|
68 |
-
##
|
69 |
-
|
70 |
-
# room_input = '4 ROOM'
|
71 |
-
input[feature_names.index("flat_num_"+room_input)] = 1
|
72 |
|
73 |
-
##AGE/ TRANSACTION YEAR [Current default to
|
74 |
age_input = int(age_)
|
75 |
# age_input = 30
|
76 |
-
input[feature_names.index('age_transation')] = age_input
|
77 |
-
input[feature_names.index('transaction_yr')] = 2022 #Default to 2022 first
|
78 |
|
79 |
-
#
|
|
|
|
|
|
|
|
|
80 |
|
|
|
81 |
Actual = dict(zip(feature_names,input))
|
82 |
Actual_df = pd.DataFrame(Actual, index=[0])
|
83 |
|
|
|
84 |
resale_adj_price = model.predict(Actual_df)[0]
|
85 |
|
86 |
-
#
|
87 |
-
|
88 |
-
|
89 |
-
|
|
|
|
|
|
|
|
|
|
|
90 |
|
91 |
return int(price)
|
92 |
|
|
|
4 |
import pickle
|
5 |
import os
|
6 |
import pandas as pd
|
7 |
+
import datetime
|
8 |
+
from datetime import datetime
|
|
|
9 |
|
10 |
def main_fn(Postal_,age_,town_,storey_,room_):
|
11 |
+
#Load model
|
12 |
+
filename = 'finalized_model2.sav'
|
13 |
+
if os.path.exists("./finalized_model2.sav"):
|
|
|
14 |
model = pickle.load(open(filename, 'rb'))
|
15 |
print('loaded model')
|
16 |
else:
|
17 |
print('failed loading model')
|
18 |
|
19 |
+
#extract feature names
|
20 |
+
feature_names = model.feature_names_in_.tolist()
|
21 |
input = [0]*len(feature_names)
|
|
|
22 |
|
23 |
#Set up mrt_list
|
24 |
mrt_name = []
|
|
|
30 |
loc = tuple([float(i) for i in item['location']])
|
31 |
mrt_loc.append(loc)
|
32 |
|
33 |
+
# #Test input
|
34 |
+
# Postal_,age_,town_,storey_,room_ = 680705, 30, 'CHOA CHU KANG', 12, '5 ROOM'
|
35 |
+
|
36 |
##POSTAL
|
37 |
Postal_input = int(Postal_)
|
38 |
# Postal_input = 680705
|
39 |
input[feature_names.index('Postal')] = Postal_input
|
40 |
|
41 |
##DISTANCE TO MRT
|
42 |
+
search_term = Postal_
|
43 |
+
query_string= 'https://www.onemap.gov.sg/api/common/elastic/search?searchVal={}&returnGeom=Y&getAddrDetails=Y&pageNum=1'.format(search_term)
|
44 |
resp = requests.get(query_string)
|
45 |
data = json.loads(resp.content)
|
46 |
print(query_string)
|
|
|
58 |
Height = (height_input+2)//3
|
59 |
input[feature_names.index('storey_height')] = Height
|
60 |
|
61 |
+
##Town
|
62 |
+
input[feature_names.index("town")]=town_
|
|
|
|
|
63 |
|
64 |
+
##Room
|
65 |
+
input[feature_names.index("flat_num")]=room_
|
|
|
|
|
66 |
|
67 |
+
##AGE/ TRANSACTION YEAR [Current default to 2024]
|
68 |
age_input = int(age_)
|
69 |
# age_input = 30
|
|
|
|
|
70 |
|
71 |
+
# Get the current date
|
72 |
+
current_date = datetime.now()
|
73 |
+
|
74 |
+
input[feature_names.index('age_transation')] = age_input
|
75 |
+
input[feature_names.index('transaction_yr')] = current_date.year #Default to 2024 first
|
76 |
|
77 |
+
# Create final_dataframe as input to model
|
78 |
Actual = dict(zip(feature_names,input))
|
79 |
Actual_df = pd.DataFrame(Actual, index=[0])
|
80 |
|
81 |
+
# Use model to predict adjusted price
|
82 |
resale_adj_price = model.predict(Actual_df)[0]
|
83 |
|
84 |
+
# Readjust back to actual price
|
85 |
+
# Calculate the quarter
|
86 |
+
quarter = (current_date.month - 1) // 3 + 1
|
87 |
+
# Format the quarter in the desired format
|
88 |
+
formatted_quarter = f"{quarter}Q{current_date.year}"
|
89 |
+
RPI_pd = pd.read_csv('data/RPI_dict.csv', header=None)
|
90 |
+
RPI_dict = dict(zip(RPI_pd[0], RPI_pd[1]))
|
91 |
+
RPI = float(RPI_dict[formatted_quarter])
|
92 |
+
price = resale_adj_price*(RPI/133.9)
|
93 |
|
94 |
return int(price)
|
95 |
|
main_old.py
ADDED
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import json
|
2 |
+
import requests
|
3 |
+
from misc import nearest_mrt
|
4 |
+
import pickle
|
5 |
+
import os
|
6 |
+
import pandas as pd
|
7 |
+
|
8 |
+
###This is to create MRT names and MRT locations
|
9 |
+
|
10 |
+
|
11 |
+
def main_fn(Postal_,age_,town_,storey_,room_):
|
12 |
+
##Input structure into model is##
|
13 |
+
filename = 'finalized_model.sav'
|
14 |
+
|
15 |
+
if os.path.exists("./finalized_model.sav"):
|
16 |
+
model = pickle.load(open(filename, 'rb'))
|
17 |
+
print('loaded model')
|
18 |
+
else:
|
19 |
+
print('failed loading model')
|
20 |
+
|
21 |
+
#extract feature names#
|
22 |
+
feature_names = model.feature_names
|
23 |
+
input = [0]*len(feature_names)
|
24 |
+
# print(feature_names)
|
25 |
+
|
26 |
+
#Set up mrt_list
|
27 |
+
mrt_name = []
|
28 |
+
mrt_loc = []
|
29 |
+
with open('data/mrt_list.json', 'r') as file:
|
30 |
+
for line in file:
|
31 |
+
item = json.loads(line)
|
32 |
+
mrt_name.append(item['MRT'])
|
33 |
+
loc = tuple([float(i) for i in item['location']])
|
34 |
+
mrt_loc.append(loc)
|
35 |
+
|
36 |
+
#Query for latitude and longitude
|
37 |
+
|
38 |
+
##POSTAL
|
39 |
+
Postal_input = int(Postal_)
|
40 |
+
# Postal_input = 680705
|
41 |
+
input[feature_names.index('Postal')] = Postal_input
|
42 |
+
|
43 |
+
##DISTANCE TO MRT
|
44 |
+
search_term = Postal_input
|
45 |
+
query_string='https://developers.onemap.sg/commonapi/search?searchVal={}&returnGeom=Y&getAddrDetails=Y&pageNum=1'.format(search_term)
|
46 |
+
resp = requests.get(query_string)
|
47 |
+
data = json.loads(resp.content)
|
48 |
+
print(query_string)
|
49 |
+
print(data)
|
50 |
+
chosen_result = data['results'][0]
|
51 |
+
|
52 |
+
#Calculate the distance to nearest MRT
|
53 |
+
distance_km, nearest_mr = nearest_mrt(chosen_result['LATITUDE'], chosen_result['LONGITUDE'], mrt_name, mrt_loc)
|
54 |
+
input[feature_names.index('distance_mrt')] = distance_km
|
55 |
+
|
56 |
+
##STOREY
|
57 |
+
#Height is input, but then converted to the scale we used for iterating model
|
58 |
+
height_input = int(storey_)
|
59 |
+
# height_input = 51
|
60 |
+
Height = (height_input+2)//3
|
61 |
+
input[feature_names.index('storey_height')] = Height
|
62 |
+
|
63 |
+
##TOWN
|
64 |
+
town_input = town_
|
65 |
+
# town_input = 'CHOA CHU KANG'
|
66 |
+
input[feature_names.index("town_"+town_input)] = 1
|
67 |
+
|
68 |
+
##ROOM
|
69 |
+
room_input = room_
|
70 |
+
# room_input = '4 ROOM'
|
71 |
+
input[feature_names.index("flat_num_"+room_input)] = 1
|
72 |
+
|
73 |
+
##AGE/ TRANSACTION YEAR [Current default to 2022]
|
74 |
+
age_input = int(age_)
|
75 |
+
# age_input = 30
|
76 |
+
input[feature_names.index('age_transation')] = age_input
|
77 |
+
input[feature_names.index('transaction_yr')] = 2022 #Default to 2022 first
|
78 |
+
|
79 |
+
#Create final_dataframe as input to model
|
80 |
+
|
81 |
+
Actual = dict(zip(feature_names,input))
|
82 |
+
Actual_df = pd.DataFrame(Actual, index=[0])
|
83 |
+
|
84 |
+
resale_adj_price = model.predict(Actual_df)[0]
|
85 |
+
|
86 |
+
#New resale index is set arbitrarily as 170
|
87 |
+
resale_index = 170
|
88 |
+
price = resale_adj_price*resale_index/133.9
|
89 |
+
print(Actual_df)
|
90 |
+
|
91 |
+
return int(price)
|
92 |
+
|
93 |
+
if __name__ == "__main__":
|
94 |
+
Postal_,age_,town_,storey_,room_ = 680705, 30, 'CHOA CHU KANG', 12, '5 ROOM'
|
95 |
+
price = main_fn(Postal_,age_,town_,storey_,room_)
|
96 |
+
print(price)
|
test.ipynb
ADDED
@@ -0,0 +1,428 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cells": [
|
3 |
+
{
|
4 |
+
"cell_type": "code",
|
5 |
+
"execution_count": 64,
|
6 |
+
"id": "a94c4760-bcad-4c09-83e7-e5391b059b59",
|
7 |
+
"metadata": {},
|
8 |
+
"outputs": [],
|
9 |
+
"source": [
|
10 |
+
"import json\n",
|
11 |
+
"import requests\n",
|
12 |
+
"from misc import nearest_mrt\n",
|
13 |
+
"import pickle\n",
|
14 |
+
"import os\n",
|
15 |
+
"import pandas as pd\n",
|
16 |
+
"import datetime\n",
|
17 |
+
"from datetime import datetime"
|
18 |
+
]
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"cell_type": "code",
|
22 |
+
"execution_count": 5,
|
23 |
+
"id": "dfd76296-5048-433b-a29a-cc073dd9d814",
|
24 |
+
"metadata": {},
|
25 |
+
"outputs": [
|
26 |
+
{
|
27 |
+
"name": "stdout",
|
28 |
+
"output_type": "stream",
|
29 |
+
"text": [
|
30 |
+
"loaded model\n"
|
31 |
+
]
|
32 |
+
}
|
33 |
+
],
|
34 |
+
"source": [
|
35 |
+
"filename = 'finalized_model2.sav'\n",
|
36 |
+
"\n",
|
37 |
+
"if os.path.exists(\"./finalized_model2.sav\"):\n",
|
38 |
+
" model = pickle.load(open(filename, 'rb'))\n",
|
39 |
+
" print('loaded model')\n",
|
40 |
+
"else:\n",
|
41 |
+
" print('failed loading model')"
|
42 |
+
]
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"cell_type": "code",
|
46 |
+
"execution_count": 8,
|
47 |
+
"id": "361df0d9-1659-42ac-9dca-8cdde2ac3a15",
|
48 |
+
"metadata": {},
|
49 |
+
"outputs": [
|
50 |
+
{
|
51 |
+
"data": {
|
52 |
+
"text/html": [
|
53 |
+
"<style>#sk-container-id-1 {color: black;}#sk-container-id-1 pre{padding: 0;}#sk-container-id-1 div.sk-toggleable {background-color: white;}#sk-container-id-1 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-1 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-1 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-1 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-1 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-1 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-1 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-1 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-1 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-1 div.sk-item {position: relative;z-index: 1;}#sk-container-id-1 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-1 div.sk-item::before, #sk-container-id-1 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-1 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-1 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-1 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-1 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-1 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-1 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-1 div.sk-label-container {text-align: center;}#sk-container-id-1 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-1 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>Pipeline(steps=[('columntransformer',\n",
|
54 |
+
" ColumnTransformer(transformers=[('standardscaler',\n",
|
55 |
+
" StandardScaler(),\n",
|
56 |
+
" ['distance_mrt',\n",
|
57 |
+
" 'age_transation',\n",
|
58 |
+
" 'transaction_yr', 'Postal',\n",
|
59 |
+
" 'storey_height']),\n",
|
60 |
+
" ('pipeline',\n",
|
61 |
+
" Pipeline(steps=[('onehotencoder',\n",
|
62 |
+
" OneHotEncoder(handle_unknown='ignore',\n",
|
63 |
+
" sparse_output=False))]),\n",
|
64 |
+
" ['town', 'flat_num'])])),\n",
|
65 |
+
" ('xgbregressor',\n",
|
66 |
+
" XGBRegressor(base_scor...\n",
|
67 |
+
" feature_types=None, gamma=1, grow_policy=None,\n",
|
68 |
+
" importance_type=None,\n",
|
69 |
+
" interaction_constraints=None, learning_rate=None,\n",
|
70 |
+
" max_bin=None, max_cat_threshold=None,\n",
|
71 |
+
" max_cat_to_onehot=None, max_delta_step=None,\n",
|
72 |
+
" max_depth=7, max_leaves=None,\n",
|
73 |
+
" min_child_weight=None, missing=nan,\n",
|
74 |
+
" monotone_constraints=None, multi_strategy=None,\n",
|
75 |
+
" n_estimators=None, n_jobs=None,\n",
|
76 |
+
" num_parallel_tree=None, random_state=None, ...))])</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" ><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">Pipeline</label><div class=\"sk-toggleable__content\"><pre>Pipeline(steps=[('columntransformer',\n",
|
77 |
+
" ColumnTransformer(transformers=[('standardscaler',\n",
|
78 |
+
" StandardScaler(),\n",
|
79 |
+
" ['distance_mrt',\n",
|
80 |
+
" 'age_transation',\n",
|
81 |
+
" 'transaction_yr', 'Postal',\n",
|
82 |
+
" 'storey_height']),\n",
|
83 |
+
" ('pipeline',\n",
|
84 |
+
" Pipeline(steps=[('onehotencoder',\n",
|
85 |
+
" OneHotEncoder(handle_unknown='ignore',\n",
|
86 |
+
" sparse_output=False))]),\n",
|
87 |
+
" ['town', 'flat_num'])])),\n",
|
88 |
+
" ('xgbregressor',\n",
|
89 |
+
" XGBRegressor(base_scor...\n",
|
90 |
+
" feature_types=None, gamma=1, grow_policy=None,\n",
|
91 |
+
" importance_type=None,\n",
|
92 |
+
" interaction_constraints=None, learning_rate=None,\n",
|
93 |
+
" max_bin=None, max_cat_threshold=None,\n",
|
94 |
+
" max_cat_to_onehot=None, max_delta_step=None,\n",
|
95 |
+
" max_depth=7, max_leaves=None,\n",
|
96 |
+
" min_child_weight=None, missing=nan,\n",
|
97 |
+
" monotone_constraints=None, multi_strategy=None,\n",
|
98 |
+
" n_estimators=None, n_jobs=None,\n",
|
99 |
+
" num_parallel_tree=None, random_state=None, ...))])</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" ><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">columntransformer: ColumnTransformer</label><div class=\"sk-toggleable__content\"><pre>ColumnTransformer(transformers=[('standardscaler', StandardScaler(),\n",
|
100 |
+
" ['distance_mrt', 'age_transation',\n",
|
101 |
+
" 'transaction_yr', 'Postal',\n",
|
102 |
+
" 'storey_height']),\n",
|
103 |
+
" ('pipeline',\n",
|
104 |
+
" Pipeline(steps=[('onehotencoder',\n",
|
105 |
+
" OneHotEncoder(handle_unknown='ignore',\n",
|
106 |
+
" sparse_output=False))]),\n",
|
107 |
+
" ['town', 'flat_num'])])</pre></div></div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-3\" type=\"checkbox\" ><label for=\"sk-estimator-id-3\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">standardscaler</label><div class=\"sk-toggleable__content\"><pre>['distance_mrt', 'age_transation', 'transaction_yr', 'Postal', 'storey_height']</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-4\" type=\"checkbox\" ><label for=\"sk-estimator-id-4\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">StandardScaler</label><div class=\"sk-toggleable__content\"><pre>StandardScaler()</pre></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-5\" type=\"checkbox\" ><label for=\"sk-estimator-id-5\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">pipeline</label><div class=\"sk-toggleable__content\"><pre>['town', 'flat_num']</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-6\" type=\"checkbox\" ><label for=\"sk-estimator-id-6\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">OneHotEncoder</label><div class=\"sk-toggleable__content\"><pre>OneHotEncoder(handle_unknown='ignore', sparse_output=False)</pre></div></div></div></div></div></div></div></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-7\" type=\"checkbox\" ><label for=\"sk-estimator-id-7\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">XGBRegressor</label><div class=\"sk-toggleable__content\"><pre>XGBRegressor(base_score=None, booster=None, callbacks=None,\n",
|
108 |
+
" colsample_bylevel=None, colsample_bynode=None,\n",
|
109 |
+
" colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
|
110 |
+
" enable_categorical=False, eval_metric=None, feature_types=None,\n",
|
111 |
+
" gamma=1, grow_policy=None, importance_type=None,\n",
|
112 |
+
" interaction_constraints=None, learning_rate=None, max_bin=None,\n",
|
113 |
+
" max_cat_threshold=None, max_cat_to_onehot=None,\n",
|
114 |
+
" max_delta_step=None, max_depth=7, max_leaves=None,\n",
|
115 |
+
" min_child_weight=None, missing=nan, monotone_constraints=None,\n",
|
116 |
+
" multi_strategy=None, n_estimators=None, n_jobs=None,\n",
|
117 |
+
" num_parallel_tree=None, random_state=None, ...)</pre></div></div></div></div></div></div></div>"
|
118 |
+
],
|
119 |
+
"text/plain": [
|
120 |
+
"Pipeline(steps=[('columntransformer',\n",
|
121 |
+
" ColumnTransformer(transformers=[('standardscaler',\n",
|
122 |
+
" StandardScaler(),\n",
|
123 |
+
" ['distance_mrt',\n",
|
124 |
+
" 'age_transation',\n",
|
125 |
+
" 'transaction_yr', 'Postal',\n",
|
126 |
+
" 'storey_height']),\n",
|
127 |
+
" ('pipeline',\n",
|
128 |
+
" Pipeline(steps=[('onehotencoder',\n",
|
129 |
+
" OneHotEncoder(handle_unknown='ignore',\n",
|
130 |
+
" sparse_output=False))]),\n",
|
131 |
+
" ['town', 'flat_num'])])),\n",
|
132 |
+
" ('xgbregressor',\n",
|
133 |
+
" XGBRegressor(base_scor...\n",
|
134 |
+
" feature_types=None, gamma=1, grow_policy=None,\n",
|
135 |
+
" importance_type=None,\n",
|
136 |
+
" interaction_constraints=None, learning_rate=None,\n",
|
137 |
+
" max_bin=None, max_cat_threshold=None,\n",
|
138 |
+
" max_cat_to_onehot=None, max_delta_step=None,\n",
|
139 |
+
" max_depth=7, max_leaves=None,\n",
|
140 |
+
" min_child_weight=None, missing=nan,\n",
|
141 |
+
" monotone_constraints=None, multi_strategy=None,\n",
|
142 |
+
" n_estimators=None, n_jobs=None,\n",
|
143 |
+
" num_parallel_tree=None, random_state=None, ...))])"
|
144 |
+
]
|
145 |
+
},
|
146 |
+
"execution_count": 8,
|
147 |
+
"metadata": {},
|
148 |
+
"output_type": "execute_result"
|
149 |
+
}
|
150 |
+
],
|
151 |
+
"source": [
|
152 |
+
"model"
|
153 |
+
]
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"cell_type": "code",
|
157 |
+
"execution_count": 20,
|
158 |
+
"id": "e4764df8-efdf-42e9-ade6-ff8062b5bac3",
|
159 |
+
"metadata": {},
|
160 |
+
"outputs": [],
|
161 |
+
"source": [
|
162 |
+
"#extract feature names#\n",
|
163 |
+
"feature_names = model.feature_names_in_.tolist()\n",
|
164 |
+
"input = [0]*len(feature_names)"
|
165 |
+
]
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"cell_type": "code",
|
169 |
+
"execution_count": 21,
|
170 |
+
"id": "9eb9aa6a-4e67-4f51-9566-775fed6ac4ff",
|
171 |
+
"metadata": {},
|
172 |
+
"outputs": [
|
173 |
+
{
|
174 |
+
"data": {
|
175 |
+
"text/plain": [
|
176 |
+
"['distance_mrt',\n",
|
177 |
+
" 'age_transation',\n",
|
178 |
+
" 'transaction_yr',\n",
|
179 |
+
" 'Postal',\n",
|
180 |
+
" 'storey_height',\n",
|
181 |
+
" 'town',\n",
|
182 |
+
" 'flat_num']"
|
183 |
+
]
|
184 |
+
},
|
185 |
+
"execution_count": 21,
|
186 |
+
"metadata": {},
|
187 |
+
"output_type": "execute_result"
|
188 |
+
}
|
189 |
+
],
|
190 |
+
"source": [
|
191 |
+
"feature_names"
|
192 |
+
]
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"cell_type": "code",
|
196 |
+
"execution_count": 22,
|
197 |
+
"id": "3f2fd14c-2df7-481f-b837-502d717a892b",
|
198 |
+
"metadata": {},
|
199 |
+
"outputs": [],
|
200 |
+
"source": [
|
201 |
+
"#Set up mrt_list\n",
|
202 |
+
"mrt_name = []\n",
|
203 |
+
"mrt_loc = []\n",
|
204 |
+
"with open('data/mrt_list.json', 'r') as file:\n",
|
205 |
+
" for line in file:\n",
|
206 |
+
" item = json.loads(line)\n",
|
207 |
+
" mrt_name.append(item['MRT'])\n",
|
208 |
+
" loc = tuple([float(i) for i in item['location']])\n",
|
209 |
+
" mrt_loc.append(loc)"
|
210 |
+
]
|
211 |
+
},
|
212 |
+
{
|
213 |
+
"cell_type": "code",
|
214 |
+
"execution_count": 23,
|
215 |
+
"id": "b2d0339f-91bb-4514-890c-b561857af14c",
|
216 |
+
"metadata": {},
|
217 |
+
"outputs": [],
|
218 |
+
"source": [
|
219 |
+
"#Test input\n",
|
220 |
+
"Postal_,age_,town_,storey_,room_ = 680705, 30, 'CHOA CHU KANG', 12, '5 ROOM'"
|
221 |
+
]
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"cell_type": "code",
|
225 |
+
"execution_count": 24,
|
226 |
+
"id": "30e85e47-70f7-4b2a-a242-b25b00449276",
|
227 |
+
"metadata": {},
|
228 |
+
"outputs": [],
|
229 |
+
"source": [
|
230 |
+
"##POSTAL\n",
|
231 |
+
"Postal_input = int(Postal_)\n",
|
232 |
+
"# Postal_input = 680705\n",
|
233 |
+
"input[feature_names.index('Postal')] = Postal_input"
|
234 |
+
]
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"cell_type": "code",
|
238 |
+
"execution_count": 45,
|
239 |
+
"id": "f02d1a92-fc2a-49ed-a3e3-87d976e779c9",
|
240 |
+
"metadata": {},
|
241 |
+
"outputs": [
|
242 |
+
{
|
243 |
+
"name": "stdout",
|
244 |
+
"output_type": "stream",
|
245 |
+
"text": [
|
246 |
+
"https://www.onemap.gov.sg/api/common/elastic/search?searchVal=680705&returnGeom=Y&getAddrDetails=Y&pageNum=1\n",
|
247 |
+
"{'found': 1, 'totalNumPages': 1, 'pageNum': 1, 'results': [{'SEARCHVAL': '705 CHOA CHU KANG STREET 53 SINGAPORE 680705', 'BLK_NO': '705', 'ROAD_NAME': 'CHOA CHU KANG STREET 53', 'BUILDING': 'NIL', 'ADDRESS': '705 CHOA CHU KANG STREET 53 SINGAPORE 680705', 'POSTAL': '680705', 'X': '18296.4178872742', 'Y': '41364.999289671', 'LATITUDE': '1.39036325274643', 'LONGITUDE': '103.746124351793'}]}\n"
|
248 |
+
]
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"data": {
|
252 |
+
"text/plain": [
|
253 |
+
"'Choa Chu Kang MRT Station'"
|
254 |
+
]
|
255 |
+
},
|
256 |
+
"execution_count": 45,
|
257 |
+
"metadata": {},
|
258 |
+
"output_type": "execute_result"
|
259 |
+
}
|
260 |
+
],
|
261 |
+
"source": [
|
262 |
+
"##DISTANCE TO MRT\n",
|
263 |
+
"search_term = Postal_\n",
|
264 |
+
"query_string= 'https://www.onemap.gov.sg/api/common/elastic/search?searchVal={}&returnGeom=Y&getAddrDetails=Y&pageNum=1'.format(search_term)\n",
|
265 |
+
"resp = requests.get(query_string)\n",
|
266 |
+
"data = json.loads(resp.content)\n",
|
267 |
+
"print(query_string)\n",
|
268 |
+
"print(data)\n",
|
269 |
+
"chosen_result = data['results'][0]\n",
|
270 |
+
"\n",
|
271 |
+
"#Calculate the distance to nearest MRT\n",
|
272 |
+
"distance_km, nearest_mr = nearest_mrt(chosen_result['LATITUDE'], chosen_result['LONGITUDE'], mrt_name, mrt_loc)\n",
|
273 |
+
"input[feature_names.index('distance_mrt')] = distance_km\n",
|
274 |
+
"nearest_mr"
|
275 |
+
]
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"cell_type": "code",
|
279 |
+
"execution_count": 62,
|
280 |
+
"id": "c3c84b64-3932-4226-bb32-d7dfc3551c6d",
|
281 |
+
"metadata": {},
|
282 |
+
"outputs": [
|
283 |
+
{
|
284 |
+
"data": {
|
285 |
+
"text/plain": [
|
286 |
+
"[0.5863143456991471, 30, 2024, 680705, 4, 'CHOA CHU KANG', '5 ROOM']"
|
287 |
+
]
|
288 |
+
},
|
289 |
+
"execution_count": 62,
|
290 |
+
"metadata": {},
|
291 |
+
"output_type": "execute_result"
|
292 |
+
}
|
293 |
+
],
|
294 |
+
"source": [
|
295 |
+
"##STOREY\n",
|
296 |
+
"#Height is input, but then converted to the scale we used for iterating model\n",
|
297 |
+
"height_input = int(storey_)\n",
|
298 |
+
"# height_input = 51\n",
|
299 |
+
"Height = (height_input+2)//3\n",
|
300 |
+
"input[feature_names.index('storey_height')] = Height\n",
|
301 |
+
"\n",
|
302 |
+
"##Town\n",
|
303 |
+
"input[feature_names.index(\"town\")]=town_\n",
|
304 |
+
"\n",
|
305 |
+
"##Room\n",
|
306 |
+
"input[feature_names.index(\"flat_num\")]=room_\n",
|
307 |
+
"\n",
|
308 |
+
"##AGE/ TRANSACTION YEAR [Current default to 2024]\n",
|
309 |
+
"age_input = int(age_)\n",
|
310 |
+
"# age_input = 30\n",
|
311 |
+
"\n",
|
312 |
+
"# Get the current date\n",
|
313 |
+
"current_date = datetime.now()\n",
|
314 |
+
"\n",
|
315 |
+
"input[feature_names.index('age_transation')] = age_input\n",
|
316 |
+
"input[feature_names.index('transaction_yr')] = current_date.year #Default to 2024 first\n",
|
317 |
+
"\n",
|
318 |
+
"input"
|
319 |
+
]
|
320 |
+
},
|
321 |
+
{
|
322 |
+
"cell_type": "code",
|
323 |
+
"execution_count": 69,
|
324 |
+
"id": "8b5702ee-3891-4373-b2cf-97c1b1b23e66",
|
325 |
+
"metadata": {},
|
326 |
+
"outputs": [
|
327 |
+
{
|
328 |
+
"data": {
|
329 |
+
"text/plain": [
|
330 |
+
"468224.38"
|
331 |
+
]
|
332 |
+
},
|
333 |
+
"execution_count": 69,
|
334 |
+
"metadata": {},
|
335 |
+
"output_type": "execute_result"
|
336 |
+
}
|
337 |
+
],
|
338 |
+
"source": [
|
339 |
+
"#Create final_dataframe as input to model\n",
|
340 |
+
"\n",
|
341 |
+
"Actual = dict(zip(feature_names,input))\n",
|
342 |
+
"Actual_df = pd.DataFrame(Actual, index=[0])\n",
|
343 |
+
"resale_adj_price = model.predict(Actual_df)[0]\n",
|
344 |
+
"resale_adj_price"
|
345 |
+
]
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"cell_type": "code",
|
349 |
+
"execution_count": 70,
|
350 |
+
"id": "e289a971-ca3b-47ac-95db-19c5c97f0ccb",
|
351 |
+
"metadata": {},
|
352 |
+
"outputs": [],
|
353 |
+
"source": [
|
354 |
+
"# Calculate the quarter\n",
|
355 |
+
"quarter = (current_date.month - 1) // 3 + 1\n",
|
356 |
+
"# Format the quarter in the desired format\n",
|
357 |
+
"formatted_quarter = f\"{quarter}Q{current_date.year}\""
|
358 |
+
]
|
359 |
+
},
|
360 |
+
{
|
361 |
+
"cell_type": "code",
|
362 |
+
"execution_count": 71,
|
363 |
+
"id": "8b6c863c-cf92-4fe8-964a-8cfbb779dd0f",
|
364 |
+
"metadata": {},
|
365 |
+
"outputs": [
|
366 |
+
{
|
367 |
+
"data": {
|
368 |
+
"text/plain": [
|
369 |
+
"'1Q2024'"
|
370 |
+
]
|
371 |
+
},
|
372 |
+
"execution_count": 71,
|
373 |
+
"metadata": {},
|
374 |
+
"output_type": "execute_result"
|
375 |
+
}
|
376 |
+
],
|
377 |
+
"source": [
|
378 |
+
"formatted_quarter"
|
379 |
+
]
|
380 |
+
},
|
381 |
+
{
|
382 |
+
"cell_type": "code",
|
383 |
+
"execution_count": 74,
|
384 |
+
"id": "c0286b33-90a1-40bd-85ef-9dcc13fd0f9a",
|
385 |
+
"metadata": {},
|
386 |
+
"outputs": [
|
387 |
+
{
|
388 |
+
"data": {
|
389 |
+
"text/plain": [
|
390 |
+
"636421.4805825242"
|
391 |
+
]
|
392 |
+
},
|
393 |
+
"execution_count": 74,
|
394 |
+
"metadata": {},
|
395 |
+
"output_type": "execute_result"
|
396 |
+
}
|
397 |
+
],
|
398 |
+
"source": [
|
399 |
+
"RPI_pd = pd.read_csv('data/RPI_dict.csv', header=None)\n",
|
400 |
+
"RPI_dict = dict(zip(RPI_pd[0], RPI_pd[1]))\n",
|
401 |
+
"RPI = float(RPI_dict[formatted_quarter])\n",
|
402 |
+
"price = resale_adj_price*(RPI/133.9) \n",
|
403 |
+
"price"
|
404 |
+
]
|
405 |
+
}
|
406 |
+
],
|
407 |
+
"metadata": {
|
408 |
+
"kernelspec": {
|
409 |
+
"display_name": "HDB_pred",
|
410 |
+
"language": "python",
|
411 |
+
"name": "hdb_pred"
|
412 |
+
},
|
413 |
+
"language_info": {
|
414 |
+
"codemirror_mode": {
|
415 |
+
"name": "ipython",
|
416 |
+
"version": 3
|
417 |
+
},
|
418 |
+
"file_extension": ".py",
|
419 |
+
"mimetype": "text/x-python",
|
420 |
+
"name": "python",
|
421 |
+
"nbconvert_exporter": "python",
|
422 |
+
"pygments_lexer": "ipython3",
|
423 |
+
"version": "3.11.7"
|
424 |
+
}
|
425 |
+
},
|
426 |
+
"nbformat": 4,
|
427 |
+
"nbformat_minor": 5
|
428 |
+
}
|