Add application.

HousingAndDevelopmentBoardResalePriceIndex1Q2009100Quarterly.csv

@@ -0,0 +1,138 @@
+quarter,index
+1990-Q1,24.3
+1990-Q2,24.4
+1990-Q3,25
+1990-Q4,24.7
+1991-Q1,24.9
+1991-Q2,25.5
+1991-Q3,25.2
+1991-Q4,25.1
+1992-Q1,25.8
+1992-Q2,27.4
+1992-Q3,28
+1992-Q4,28.6
+1993-Q1,30.2
+1993-Q2,39.6
+1993-Q3,47.7
+1993-Q4,49
+1994-Q1,50.4
+1994-Q2,51.7
+1994-Q3,54.6
+1994-Q4,54.8
+1995-Q1,57.3
+1995-Q2,63.9
+1995-Q3,67.7
+1995-Q4,73.7
+1996-Q1,80.5
+1996-Q2,90.9
+1996-Q3,96.4
+1996-Q4,99
+1997-Q1,98.6
+1997-Q2,97.5
+1997-Q3,93.6
+1997-Q4,88
+1998-Q1,81.7
+1998-Q2,78.3
+1998-Q3,74.9
+1998-Q4,72.3
+1999-Q1,71.2
+1999-Q2,72.2
+1999-Q3,78.1
+1999-Q4,79.8
+2000-Q1,80.3
+2000-Q2,79.3
+2000-Q3,77.6
+2000-Q4,75.8
+2001-Q1,73.2
+2001-Q2,72.1
+2001-Q3,70.6
+2001-Q4,69.6
+2002-Q1,69.1
+2002-Q2,69.2
+2002-Q3,69.9
+2002-Q4,69.9
+2003-Q1,71
+2003-Q2,72.5
+2003-Q3,74.3
+2003-Q4,75.1
+2004-Q1,75.3
+2004-Q2,76.2
+2004-Q3,76.3
+2004-Q4,77.1
+2005-Q1,77.2
+2005-Q2,73.5
+2005-Q3,73.2
+2005-Q4,73.5
+2006-Q1,73.6
+2006-Q2,74.3
+2006-Q3,74.2
+2006-Q4,74.9
+2007-Q1,75.8
+2007-Q2,78.1
+2007-Q3,83.2
+2007-Q4,88
+2008-Q1,91.3
+2008-Q2,95.4
+2008-Q3,99.4
+2008-Q4,100.8
+2009-Q1,100
+2009-Q2,101.4
+2009-Q3,105
+2009-Q4,109
+2010-Q1,112.1
+2010-Q2,116.6
+2010-Q3,121.3
+2010-Q4,124.4
+2011-Q1,126.4
+2011-Q2,130.4
+2011-Q3,135.4
+2011-Q4,137.7
+2012-Q1,138.5
+2012-Q2,140.3
+2012-Q3,143.1
+2012-Q4,146.7
+2013-Q1,148.6
+2013-Q2,149.4
+2013-Q3,148.1
+2013-Q4,145.8
+2014-Q1,143.5
+2014-Q2,141.5
+2014-Q3,139.1
+2014-Q4,137
+2015-Q1,135.6
+2015-Q2,135
+2015-Q3,134.6
+2015-Q4,134.8
+2016-Q1,134.7
+2016-Q2,134.7
+2016-Q3,134.7
+2016-Q4,134.6
+2017-Q1,133.9
+2017-Q2,133.7
+2017-Q3,132.8
+2017-Q4,132.6
+2018-Q1,131.6
+2018-Q2,131.7
+2018-Q3,131.6
+2018-Q4,131.4
+2019-Q1,131
+2019-Q2,130.8
+2019-Q3,130.9
+2019-Q4,131.5
+2020-Q1,131.5
+2020-Q2,131.9
+2020-Q3,133.9
+2020-Q4,138.1
+2021-Q1,142.2
+2021-Q2,146.4
+2021-Q3,150.6
+2021-Q4,155.7
+2022-Q1,159.5
+2022-Q2,163.9
+2022-Q3,168.1
+2022-Q4,171.9
+2023-Q1,173.6
+2023-Q2,176.2
+2023-Q3,178.5
+2023-Q4,180.4
+2024-Q1,183.5

app.py

@@ -0,0 +1,152 @@
+# References:
+# https://www.tanishq.ai/blog/posts/2021-11-16-gradio-huggingface.html
+
+from fastai.tabular.all import *
+import numpy as np
+import pandas as pd
+import gradio as gr
+
+def prepare_input():
+    df['remaining_lease_'] = df.remaining_lease.apply(lambda x: int(str(x).replace("years","").replace("months","").split()[0]))
+    df['address'] = df['street_name'] + " BLK " + df['block']
+    df['month_'] = df['month'].astype('category')
+    df['resale_price_'] = np.log(df['resale_price'])
+    # normalize price
+    train_price_mean = df['resale_price_'].mean()
+    df['resale_price_'] = df['resale_price_'] - train_price_mean
+    train_price_std = df['resale_price_'].std()
+    df['resale_price_'] = df['resale_price_'] / train_price_std
+    return train_price_mean, train_price_std
+
+def restore_price(p):
+    p *= train_price_std
+    p += train_price_mean
+    return np.exp(p)
+
+learn = load_learner('export.pkl')
+
+data_directory = './'
+price2017 = pd.read_csv(data_directory + 'resale-flat-prices-based-on-registration-date-from-jan-2017-onwards.csv')
+
+df = price2017
+
+train_price_mean, train_price_std = prepare_input()
+
+splits = EndSplitter(valid_last=True)(range_of(df))
+
+def tostr(i):
+    s = str(i)
+    if len(s) == 2:
+        return s
+    else:
+        s = '0'+s
+        return s
+        
+inp_cols = ['flat_model', 'storey_range', 'street_name', 'address', 'flat_type', 'town', 'month_', 'remaining_lease_', 'floor_area_sqm']
+uniques_month_ = list(map(str, df.iloc[splits[0]]['month_'].unique()))
+uniques = {}
+modes = {}
+for c in inp_cols:
+    if c == 'month_':
+        uniques[c] = list(map(str,list(range(1997,2030))))
+        uniques['month_2'] = list(map(tostr,list(range(1,13))))
+        modes[c] = str(df.iloc[splits[0]][c].mode()[0])[:4]
+        modes['month_2'] = str(df.iloc[splits[0]][c].mode()[0])[5:7]
+    else:
+        uniques[c] = list(map(str, df.iloc[splits[0]][c].unique()))
+        modes[c] = str(df.iloc[splits[0]][c].mode()[0])
+
+# HDB resale price index from https://beta.data.gov.sg/collections/152/datasets/d_14f63e595975691e7c24a27ae4c07c79/view
+df_rpi = pd.read_csv('HousingAndDevelopmentBoardResalePriceIndex1Q2009100Quarterly.csv')
+def get_rpi(year, month):
+    quarters = ['Q1']*3 + ['Q2']*3 + ['Q3']*3 + ['Q4']*3 
+    months = list(range(1,13))
+    quarter = quarters[months.index(month)]
+    quarter = str(year) + '-' + quarter
+    rpi = df_rpi[df_rpi.quarter==quarter]['index']
+    #print(rpi)
+    #print(rpi.loc[4])
+    return  float(rpi.iloc[0] if len(rpi) > 0 else 0)
+
+# Get scale factor from rpi
+def get_rpi_ym(year_month):
+    print(year_month)
+    y = int(year_month[0:4])
+    m = int(year_month[5:7])
+    rpi = get_rpi(y,m)
+    return rpi if rpi > 0 else 1
+        
+def get_rpi_factor(year_month):
+    print("getting..." + year_month)
+    if year_month in uniques_month_:
+        # within training period
+        return 1
+    else:
+        predicted_ym = uniques_month_[-1]
+        predicted_ym_rpi = get_rpi_ym(predicted_ym) 
+        #print(predicted_ym_rpi)
+        #print(get_rpi_ym(year_month))
+        #return 1 - (predicted_ym_rpi - get_rpi_ym(year_month) )/predicted_ym_rpi
+        return (get_rpi_ym(year_month))/predicted_ym_rpi
+    
+def update_inp_with_trained_cat(idx = 0):
+    inp_ = df.iloc[idx]
+    inp = inp_[inp_cols]
+    updated = False
+    skipped = False
+    for c in inp.keys():
+        if (type(inp[c]) == str):
+            if not inp[c] in uniques[c]:
+                inp = inp.copy()
+                updated = True
+                if c == 'month_':
+                    lastdate = df.iloc[max(splits[0])].month
+                    inp[c] = lastdate     
+                else:
+                    inp[c] = ''
+                    skipped = True
+    # add rpi factor
+    inp['rpi_factor'] = get_rpi_factor(df.iloc[idx]['month_'])
+    return inp_, inp, updated, skipped
+
+p=False
+price_scaler = 1
+def predict(flat_model, storey_range, street_name, address, flat_type, town, month_, month_2, remaining_lease_, floor_area_sqm):
+    price_scaler = 1
+    inp = {}
+    
+    inp['flat_model'] = flat_model
+    inp['storey_range'] = storey_range    
+    inp['street_name'] = street_name    
+    inp['address'] = address    
+    inp['flat_type'] = flat_type    
+    inp['town'] = town    
+    inp['month_'] = month_+"-"+month_2 
+    inp['remaining_lease_'] = float(remaining_lease_)
+    inp['floor_area_sqm'] = float(floor_area_sqm)
+    print(inp['month_'])
+    price_scaler = inp['rpi_factor'] = get_rpi_factor(inp['month_'])
+
+    # predict with the latest trained month
+    if not inp['month_'] in uniques_month_:
+        #price_scaler = 1.02
+        inp['month_'] = uniques_month_[-1]
+    
+    row, clas, probs = learn.predict(pd.Series(inp))
+    pred = restore_price(row['resale_price_'].iloc[0]) * price_scaler
+    return int(pred), price_scaler
+    
+
+inputs = []
+for c in inp_cols:
+    if c=='month_':
+        c2='month_2'
+        inputs += [gr.Dropdown(choices=list(uniques[c]), label='year', info='year of valuation', value=modes[c])]
+        inputs += [gr.Dropdown(choices=list(uniques[c2]), label='month', info='month of valuation', value=modes[c2])]
+    else:
+        inputs += [gr.Dropdown(choices=list(uniques[c]), label=c, info=c, value=modes[c])]
+    
+#[gr.Dropdown(choices=list(uniques["flat_model"]), label="flat_model", info="flat_model", value=modes["flat_model"])]
+
+gr.Interface(fn=predict, inputs=inputs, outputs=[gr.Number(label="Predicted Value (S$)"), gr.Number(label="This result is adjusted automatically by the following factor (derived from Resale Price Index 1990Q1-2024Q1))")], title="Enter the HDB info to predict the price\n(Trained with old data from 1997-01 to 2020-01 on purpose to test the model durability to predict future prices. Prediction nearer to the train data period is more accurate with mean-abs-error of ~S$20k.)").launch()
+    

export.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b02e28935beba4d857d557d9b916caada98de6c9e0c6517c2539fd89a868f79
+size 10126378