app.py

import gradio as gr
import torch, numpy as np, pandas as pd
import skimage 
import pickle

defaultColumns = ['MSSubClass',
 'MSZoning',
 'LotFrontage',
 'LotArea',
 'Street',
 'Alley',
 'LotShape',
 'LandContour',
 'Utilities',
 'LotConfig',
 'LandSlope',
 'Neighborhood',
 'Condition1',
 'Condition2',
 'BldgType',
 'HouseStyle',
 'OverallQual',
 'OverallCond',
 'YearBuilt',
 'YearRemodAdd',
 'RoofStyle',
 'RoofMatl',
 'Exterior1st',
 'Exterior2nd',
 'MasVnrType',
 'MasVnrArea',
 'ExterQual',
 'ExterCond',
 'Foundation',
 'BsmtQual',
 'BsmtCond',
 'BsmtExposure',
 'BsmtFinType1',
 'BsmtFinSF1',
 'BsmtFinType2',
 'BsmtFinSF2',
 'BsmtUnfSF',
 'TotalBsmtSF',
 'Heating',
 'HeatingQC',
 'CentralAir',
 'Electrical',
 '1stFlrSF',
 '2ndFlrSF',
 'LowQualFinSF',
 'GrLivArea',
 'BsmtFullBath',
 'BsmtHalfBath',
 'FullBath',
 'HalfBath',
 'BedroomAbvGr',
 'KitchenAbvGr',
 'KitchenQual',
 'TotRmsAbvGrd',
 'Functional',
 'Fireplaces',
 'FireplaceQu',
 'GarageType',
 'GarageYrBlt',
 'GarageFinish',
 'GarageCars',
 'GarageArea',
 'GarageQual',
 'GarageCond',
 'PavedDrive',
 'WoodDeckSF',
 'OpenPorchSF',
 'EnclosedPorch',
 '3SsnPorch',
 'ScreenPorch',
 'PoolArea',
 'PoolQC',
 'Fence',
 'MiscFeature',
 'MiscVal',
 'MoSold',
 'YrSold',
 'SaleType',
 'SaleCondition']

categorical_columns = ['MSZoning',
 'Street',
 'Alley',
 'LotShape',
 'LandContour',
 'Utilities',
 'LotConfig',
 'LandSlope',
 'Neighborhood',
 'Condition1',
 'Condition2',
 'BldgType',
 'HouseStyle',
 'RoofStyle',
 'RoofMatl',
 'Exterior1st',
 'Exterior2nd',
 'MasVnrType',
 'ExterQual',
 'ExterCond',
 'Foundation',
 'BsmtQual',
 'BsmtCond',
 'BsmtExposure',
 'BsmtFinType1',
 'BsmtFinType2',
 'Heating',
 'HeatingQC',
 'CentralAir',
 'Electrical',
 'KitchenQual',
 'Functional',
 'FireplaceQu',
 'GarageType',
 'GarageFinish',
 'GarageQual',
 'GarageCond',
 'PavedDrive',
 'PoolQC',
 'Fence',
 'MiscFeature',
 'SaleType',
 'SaleCondition']

with open("model.pkl", "rb") as f:
    model = pickle.load(f)

def house_price(LotArea, LotFrontage, YearBuilt, GrLivArea, GarageArea):

    lot_area = float(LotArea)
    lot_frontage = float(LotFrontage)
    year_built = float(YearBuilt)
    gr_liv_area = float(GrLivArea)
    garage_area = float(GarageArea)

    default = [20,
     'RL',
     lot_frontage,
     lot_area,
     'Pave',
     'Grvl',
     'Reg',
     'Lvl',
     'AllPub',
     'Inside',
     'Gtl',
     'NAmes',
     'Norm',
     'Norm',
     '1Fam',
     '1Story',
     5,
     5,
     year_built,
     1950,
     'Gable',
     'CompShg',
     'VinylSd',
     'VinylSd',
     'None',
     0.0,
     'TA',
     'TA',
     'PConc',
     'TA',
     'TA',
     'No',
     'Unf',
     0.0,
     'Unf',
     0.0,
     0.0,
     0.0,
     'GasA',
     'Ex',
     'Y',
     'SBrkr',
     864,
     0,
     0,
     gr_liv_area,
     0.0,
     0.0,
     2,
     0,
     3,
     1,
     'TA',
     6,
     'Typ',
     0,
     'Gd',
     'Attchd',
     2005.0,
     'Unf',
     2.0,
     garage_area,
     'TA',
     'TA',
     'Y',
     0,
     0,
     0,
     0,
     0,
     0,
     'Gd',
     'MnPrv',
     'Shed',
     0,
     6,
     2007,
     'WD',
     'Normal']

    df=pd.DataFrame([default], columns = defaultColumns)
    df[categorical_columns] = df[categorical_columns].astype("category")
    df[categorical_columns] = df[categorical_columns].apply(lambda x: x.cat.codes)
    df = (df - df.mean()) / df.std()
    df.fillna(-1, inplace=True)

    predictions = model.predict(df)

    return predictions[0]

iface = gr.Interface(
    fn=house_price,
    title="House Prices",
    allow_flagging="never",
    inputs=[
        gr.inputs.Number(default=9600, label="LotArea"),
        gr.inputs.Number(default=60.0, label="LotFrontage"),
        gr.inputs.Number(default=2005, label="YearBuilt"),
        gr.inputs.Number(default=864, label="GrLivArea"),
        gr.inputs.Number(default=730, label="GarageArea"),
    ],
    outputs="text")
iface.launch()