v1.1

.gitignore

@@ -0,0 +1 @@
+./h5

app.py

@@ -4,20 +4,15 @@ 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')
+            gr.inputs.Textbox(type="text", label='Name'),
         ], 
     outputs= [
-            gr.outputs.Textbox(type="text", label='Predicted House Price ($)')
+            gr.outputs.Textbox(type="text", label='Gender')
+            gr.outputs.Number(label = 'Percentage confidence')
         ]
     )
 iface.launch()

main.py

@@ -1,96 +1,28 @@
-import json
-import requests
-from misc import nearest_mrt
-import pickle
 import os
 import pandas as pd
+import keras
+### This is to predict gender
 
-###This is to create MRT names and MRT locations
-
-
-def main_fn(Postal_,age_,town_,storey_,room_):
+def main_fn(Name_):
 ##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')
+    filename = "training_2/gender_v1_freezebert.h5"
+    if os.path.exists(filename):
+      model = tf.keras.models.load_model((filename), custom_objects={'KerasLayer':hub.KerasLayer})
+      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)
-
+    prob = model.predict([Name_])
+    female_prob = prob[0][0]
+    if female_prob>0.5:
+        gender = 'female'
+        prob = female_prob
+    else:
+        gender = 'male'
+        prob = (1-female_prob)
+    return gender, prob
+    
 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)
+    Name_ = 'John'
+    gender, female_prob = main_fn(Name_)
+    print(gender)

requirements.txt

@@ -1,2 +1,3 @@
-geopy
+keras
+pandas
 scikit-learn==1.0.2