first commit

app.py

@@ -0,0 +1,23 @@
+import gradio as gr
+from main import main_fn
+
+#Input structure
+##Postal_,age_,town_,storey_,room_ = 680705, 30, 'CHOA CHU KANG', 12, '5 ROOM'
+
+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']
+room_list = ['1 ROOM', '2 ROOM', '3 ROOM', '4 ROOM', '5 ROOM', 'EXECUTIVE', 'MULTI-GENERATION']
+
+iface = gr.Interface(
+    fn=main_fn, 
+    inputs= [
+            gr.inputs.Number(default=680705, label='Postal Code'),
+            gr.inputs.Number(default=25, label='Years since lease commencement (TOP)'),
+            gr.inputs.Dropdown(choices=town_list, type="value", default=None, label='Town'),
+            gr.inputs.Number(default=11, label='Floor'),
+            gr.inputs.Dropdown(choices=room_list, type="value", default=None, label='Room')
+        ], 
+    outputs= [
+            gr.outputs.Textbox(type="text", label='Predicted House Price ($)')
+        ]
+    )
+iface.launch()

gender_v1_freezebert.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da62d65566a82c6b846e56852812f384a5682978a573c0c9470aaaec71be1efa
+size 438157232

main.py

@@ -0,0 +1,96 @@
+import json
+import requests
+from misc import nearest_mrt
+import pickle
+import os
+import pandas as pd
+
+###This is to create MRT names and MRT locations
+
+
+def main_fn(Postal_,age_,town_,storey_,room_):
+##Input structure into model is##
+    filename = 'finalized_model.sav'
+
+    if os.path.exists("./finalized_model.sav"):
+        model = pickle.load(open(filename, 'rb'))
+        print('loaded model')
+    else:
+        print('failed loading model')
+
+    #extract feature names#
+    feature_names = model.feature_names
+    input = [0]*len(feature_names)
+    # print(feature_names)
+
+    #Set up mrt_list
+    mrt_name = []
+    mrt_loc = []
+    with open('data/mrt_list.json', 'r') as file:
+        for line in file:
+            item = json.loads(line)
+            mrt_name.append(item['MRT'])
+            loc = tuple([float(i) for i in item['location']])
+            mrt_loc.append(loc)
+
+    #Query for latitude and longitude
+
+    ##POSTAL
+    Postal_input = int(Postal_)
+    # Postal_input = 680705
+    input[feature_names.index('Postal')] = Postal_input
+
+    ##DISTANCE TO MRT
+    search_term = Postal_input
+    query_string='https://developers.onemap.sg/commonapi/search?searchVal={}&returnGeom=Y&getAddrDetails=Y&pageNum=1'.format(search_term)
+    resp = requests.get(query_string)
+    data = json.loads(resp.content)
+    print(query_string)
+    print(data)
+    chosen_result = data['results'][0]
+
+    #Calculate the distance to nearest MRT
+    distance_km, nearest_mr = nearest_mrt(chosen_result['LATITUDE'], chosen_result['LONGITUDE'], mrt_name, mrt_loc)
+    input[feature_names.index('distance_mrt')] = distance_km
+
+    ##STOREY
+    #Height is input, but then converted to the scale we used for iterating model
+    height_input = int(storey_)
+    # height_input = 51
+    Height = (height_input+2)//3
+    input[feature_names.index('storey_height')] = Height
+
+    ##TOWN
+    town_input = town_
+    # town_input = 'CHOA CHU KANG'
+    input[feature_names.index("town_"+town_input)] = 1
+
+    ##ROOM
+    room_input = room_
+    # room_input = '4 ROOM'
+    input[feature_names.index("flat_num_"+room_input)] = 1
+
+    ##AGE/ TRANSACTION YEAR [Current default to 2022]
+    age_input = int(age_)
+    # age_input = 30
+    input[feature_names.index('age_transation')] = age_input
+    input[feature_names.index('transaction_yr')] = 2022  #Default to 2022 first
+
+    #Create final_dataframe as input to model
+
+    Actual = dict(zip(feature_names,input))
+    Actual_df = pd.DataFrame(Actual, index=[0])
+
+    resale_adj_price = model.predict(Actual_df)[0]
+
+    #New resale index is set arbitrarily as 170
+    resale_index = 170
+    price = resale_adj_price*resale_index/133.9
+    print(Actual_df)
+
+    return int(price)
+
+if __name__ == "__main__":
+    Postal_,age_,town_,storey_,room_ = 680705, 30, 'CHOA CHU KANG', 12, '5 ROOM'
+    price = main_fn(Postal_,age_,town_,storey_,room_)
+    print(price)

requirements.txt

@@ -0,0 +1,2 @@
+geopy
+scikit-learn==1.0.2