Initial commit

app.py

@@ -0,0 +1,144 @@
+import gradio as gr
+import numpy as np
+from PIL import Image
+import requests
+import pandas as pd
+import matplotlib.pyplot as plt
+import numpy as np
+import joblib
+import hopsworks
+from tqdm import tqdm
+
+# Login to hopsworks and get the feature store
+
+
+
+columnHeaders = ['area','streetName','number','sqm','rooms','soldDate','monthlyFee','monthlyCost','floor','yearBuilt','agency','lat','lon','gdp','unemployment','interestRate']
+
+
+def downloadModel():
+    # Download saved Autogluon model from Hopsworks 
+    project = hopsworks.login()
+    mr = project.get_model_registry()
+    temp = mr.get_model("xgboost_model", version=3)
+    model_path = temp.download()
+
+    xgb_model = joblib.load(model_path + "/xgboost_model.pkl")
+    print(xgb_model)
+    return xgb_model
+
+def getAddressInfo(streetName, number):
+    address = getAddress(streetName, number)
+    ...
+    lat = None
+    lon = None
+    return lat, lon
+
+def getAddress(streetName, number):
+    ...
+    return None
+
+def getFinancialInfo():
+    ...
+    gdp, unemployment, interestRate = None, None, None
+    return gdp, unemployment, interestRate
+
+def dateToFloat(date):
+    year, month, day = str(date).split('-')
+    day = day.split(' ')[0]
+    return int(year) + int(month) / 12 + int(day) / 365
+
+def normalize(x, minVal, maxVal, feature):
+    # Not fantastic, but it suffices
+    if feature in ['lat', 'lon'] and x == 0:
+        return 0
+
+    res = (x - minVal) / (maxVal - minVal)
+    return min(max(res, 0), 1)
+
+def normalizeData(df):
+    # We do this manually because we want the UI to be able to transform the input data the same way
+    featureToMinMax = {
+        'sqm': (10, 800),
+        'rooms': (1, 20),
+        'monthlyFee': (0, 60000),
+        'monthlyCost': (0, 20000),
+        'floor': (-3, 35),
+        'yearBuilt': (1850, 2023),
+        'lat': (58.8, 60.2),
+        'lon': (17.5, 19.1),
+        'gdp': (505.1, 630.14),
+        'unemployment': (6.36, 8.66),
+        'interestRate': (-0.5, 2.64),
+        'price': (1.5e5, 7e7),
+        'number': (0, 300),
+        'soldDate': (2010, 2025)
+    } # Extracted from the data
+
+    # Normalize select numerical values to a value between 0 and 1
+    print('Normalizing data...')
+    for feature, minMax in tqdm(featureToMinMax.items()):
+        min = minMax[0]
+        max = minMax[1]
+        if feature == 'soldDate':
+            df[feature] = df[feature].apply(lambda x: dateToFloat(x))
+
+        df[feature] = df[feature].apply(lambda x: normalize(x, min, max, feature))
+
+    return df
+
+
+model = downloadModel()
+
+def sthlm(area, streetName, number, sqm, rooms, monthlyFee, monthlyCost, floor, yearBuilt):
+    soldDate = '2021-01-01' # TODO
+    price = None
+    agency = None
+    brf = None
+    lat, lon = getAddressInfo(streetName, number)
+    gdp, unemployment, interestRate = getFinancialInfo(soldDate)
+
+    # Parse the input so we can run it through the model
+    # Create a dataframe from the input values
+    input_variables = pd.DataFrame(
+        [[area,streetName,number,sqm,rooms,soldDate,monthlyFee,monthlyCost,floor,yearBuilt,agency,lat,lon,gdp,unemployment,interestRate]], columns=columnHeaders)
+    
+    df = normalizeData(input_variables)
+
+    # Save first row as a numpy array
+    input_list = df.iloc[0].to_numpy()
+
+    # 'res' is a list of predictions returned as the label.
+    res = model.predict(np.asarray(input_list).reshape(1, -1))
+
+    print(res)
+
+    return 100
+
+
+# All features present in the sthlm dataset
+numericalInputs = ['number', 'sqm','rooms', 'monthlyFee','monthlyCost','floor','yearBuilt']
+categoricalInputs = ['area']
+inputs = [gr.inputs.Textbox(lines=1, label='streetName')]
+catToInput = {
+    'feature': ['a', 'b', 'c']
+}
+    
+# Generate the input form
+for feature in numericalInputs:
+    inputs.append(gr.inputs.Number(default=0, label=feature))
+
+for feature in categoricalInputs:
+    inputs.append(gr.inputs.Dropdown(
+        choices=catToInput.get('feature'), default="a", label=feature))
+
+# Create the interface
+demo = gr.Interface(
+    fn=sthlm,
+    title="Stockholm Housing Valuation",
+    description="Predict the price of an apartment in Stockholm",
+    allow_flagging="never",
+    inputs=inputs,
+    outputs=['number'])
+
+demo.launch()

requirements.txt

@@ -0,0 +1,8 @@
+hopsworks
+joblib
+gradio
+numpy
+pandas
+requests
+scikit-learn
+tqdm