Spaces:
Running
Running
sivakornchong
commited on
Commit
•
d5050b9
1
Parent(s):
aab7ecd
v1.1
Browse files- .gitignore +1 -0
- app.py +3 -8
- main.py +20 -88
- requirements.txt +2 -1
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
./h5
|
app.py
CHANGED
@@ -4,20 +4,15 @@ from main import main_fn
|
|
4 |
#Input structure
|
5 |
##Postal_,age_,town_,storey_,room_ = 680705, 30, 'CHOA CHU KANG', 12, '5 ROOM'
|
6 |
|
7 |
-
town_list = ['ANG MO KIO', 'BEDOK', 'BISHAN', 'BUKIT BATOK', 'BUKIT MERAH', 'BUKIT PANJANG', 'BUKIT TIMAH', 'CENTRAL AREA', 'CHOA CHU KANG', 'CLEMENTI', 'GEYLANG', 'HOUGANG', 'JURONG EAST', 'JURONG WEST', 'KALLANG/WHAMPOA', 'MARINE PARADE', 'PASIR RIS', 'PUNGGOL', 'QUEENSTOWN', 'SEMBAWANG', 'SENGKANG', 'SERANGOON', 'TAMPINES', 'TOA PAYOH', 'WOODLANDS', 'YISHUN']
|
8 |
-
room_list = ['1 ROOM', '2 ROOM', '3 ROOM', '4 ROOM', '5 ROOM', 'EXECUTIVE', 'MULTI-GENERATION']
|
9 |
|
10 |
iface = gr.Interface(
|
11 |
fn=main_fn,
|
12 |
inputs= [
|
13 |
-
gr.inputs.
|
14 |
-
gr.inputs.Number(default=25, label='Years since lease commencement (TOP)'),
|
15 |
-
gr.inputs.Dropdown(choices=town_list, type="value", default=None, label='Town'),
|
16 |
-
gr.inputs.Number(default=11, label='Floor'),
|
17 |
-
gr.inputs.Dropdown(choices=room_list, type="value", default=None, label='Room')
|
18 |
],
|
19 |
outputs= [
|
20 |
-
gr.outputs.Textbox(type="text", label='
|
|
|
21 |
]
|
22 |
)
|
23 |
iface.launch()
|
|
|
4 |
#Input structure
|
5 |
##Postal_,age_,town_,storey_,room_ = 680705, 30, 'CHOA CHU KANG', 12, '5 ROOM'
|
6 |
|
|
|
|
|
7 |
|
8 |
iface = gr.Interface(
|
9 |
fn=main_fn,
|
10 |
inputs= [
|
11 |
+
gr.inputs.Textbox(type="text", label='Name'),
|
|
|
|
|
|
|
|
|
12 |
],
|
13 |
outputs= [
|
14 |
+
gr.outputs.Textbox(type="text", label='Gender')
|
15 |
+
gr.outputs.Number(label = 'Percentage confidence')
|
16 |
]
|
17 |
)
|
18 |
iface.launch()
|
main.py
CHANGED
@@ -1,96 +1,28 @@
|
|
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 |
-
|
9 |
-
|
10 |
-
|
11 |
-
def main_fn(Postal_,age_,town_,storey_,room_):
|
12 |
##Input structure into model is##
|
13 |
-
filename =
|
14 |
-
|
15 |
-
|
16 |
-
|
17 |
-
print('loaded model')
|
18 |
else:
|
19 |
print('failed loading model')
|
20 |
|
21 |
-
|
22 |
-
|
23 |
-
|
24 |
-
|
25 |
-
|
26 |
-
|
27 |
-
|
28 |
-
|
29 |
-
|
30 |
-
|
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 |
-
|
95 |
-
|
96 |
-
print(
|
|
|
|
|
|
|
|
|
|
|
1 |
import os
|
2 |
import pandas as pd
|
3 |
+
import keras
|
4 |
+
### This is to predict gender
|
5 |
|
6 |
+
def main_fn(Name_):
|
|
|
|
|
|
|
7 |
##Input structure into model is##
|
8 |
+
filename = "training_2/gender_v1_freezebert.h5"
|
9 |
+
if os.path.exists(filename):
|
10 |
+
model = tf.keras.models.load_model((filename), custom_objects={'KerasLayer':hub.KerasLayer})
|
11 |
+
print('loaded model')
|
|
|
12 |
else:
|
13 |
print('failed loading model')
|
14 |
|
15 |
+
prob = model.predict([Name_])
|
16 |
+
female_prob = prob[0][0]
|
17 |
+
if female_prob>0.5:
|
18 |
+
gender = 'female'
|
19 |
+
prob = female_prob
|
20 |
+
else:
|
21 |
+
gender = 'male'
|
22 |
+
prob = (1-female_prob)
|
23 |
+
return gender, prob
|
24 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
25 |
if __name__ == "__main__":
|
26 |
+
Name_ = 'John'
|
27 |
+
gender, female_prob = main_fn(Name_)
|
28 |
+
print(gender)
|
requirements.txt
CHANGED
@@ -1,2 +1,3 @@
|
|
1 |
-
|
|
|
2 |
scikit-learn==1.0.2
|
|
|
1 |
+
keras
|
2 |
+
pandas
|
3 |
scikit-learn==1.0.2
|