Upload 6 files

DecisionTreeRegressor.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ba618d8dfdc11ff61401abd935637e999db1f6fc3653617fe2f7324e368e1fd
+size 5880

KNeighborsRegressor.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3be5cbb151093ff7c19bf4caefb9732a3565a04f38a836c011f681528b270703
+size 305517

RandomForestRegressor.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33dbfd7156d96d252a7b9ec8d9d12278194064a673dc7b9e5dbe9760c49811c9
+size 356963890

XGBRegressor.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c1ad245b6488479d02dd3107f0fce80fa6b0b9c365e4f818928c9008e993a2c
+size 10591527

app.py

@@ -0,0 +1,65 @@
+import streamlit as st
+import sklearn
+import numpy as np
+import pickle
+import pandas as pd
+
+random_forest = 'RandomForestRegressor.pkl'
+k_nearest = 'KNeighborsRegressor.pkl'
+decision_tree = 'DecisionTreeRegressor.pkl'
+xgboost = 'XGBRegressor.pkl'
+
+r_f = pickle.load(open(random_forest, 'rb'))
+k_n = pickle.load(open(k_nearest, 'rb'))
+d_t = pickle.load(open(decision_tree, 'rb'))
+x_b = pickle.load(open(xgboost, 'rb'))
+
+def predict_house_price(latitude,longitude,province,bedrooms,bathrooms):
+    dct = {'latitude':[latitude],
+    'longitude':[longitude],
+    'province':[province],
+    'bedrooms':[bedrooms],
+    'bathrooms':[bathrooms]}
+    pdt = pd.DataFrame.from_dict(dct)
+    predictions={}
+    price_r_f = r_f.predict(pdt)
+    predictions['r_f'] = round(np.exp(price_r_f.tolist()[0]),2)
+    price_k_n = k_n.predict(pdt)
+    predictions['k_n'] = round(np.exp(price_k_n.tolist()[0]),2)
+    price_d_t = d_t.predict(pdt)
+    predictions['d_t'] = round(np.exp(price_d_t.tolist()[0]),2)
+    price_x_b = x_b.predict(pdt)
+    predictions['x_b'] = round(np.exp(price_x_b.tolist()[0]),2)
+    return predictions
+
+def main():
+    st.label_visibility='collapse'
+    st.title("House Price Prediction using KIJIJI data and different algorithms")
+    latitude = st.slider("Latitude : ", min_value = 41.00000, max_value = 65.00000, step = 0.001)
+    longitude = st.slider("Longitude : ", min_value = -140.00000, max_value = -51.00000, step = 0.001)
+    bedrooms = st.slider("Bedrooms : ", min_value = 1, max_value = 6, step = 1)
+    bathrooms = st.slider("Bathrooms : ", min_value = 1.0, max_value = 6.0, step = 0.5)
+    pro = {0: 'alberta',
+            1: 'britishcolumbia',
+            2: 'manitoba',
+            3: 'newbrunswick',
+            4: 'newfoundland',
+            5: 'novascotia',
+            6: 'ontario',
+            7: 'princeedwardisland',
+            8: 'quebec',
+            9: 'saskatchewan',
+            10: 'territories'}
+    prov = st.selectbox("Choose a Province: ", list(pro.values()))
+    province = list(pro.keys())[list(pro.values()).index(prov)]
+    if st.button("Predict"):
+        pd = predict_house_price(latitude,longitude,province,bedrooms,bathrooms)
+        st.write('Price Prediction from Random Forest Regressor ${}'.format(pd['r_f']))
+        st.write('Price Prediction from K-Neighbors Regressor ${}'.format(pd['k_n']))
+        st.write('Price Prediction from Decision Tree Regressor ${}'.format(pd['d_t']))
+        st.write('Price Prediction from XGB Regressor ${}'.format(pd['x_b']))
+
+
+if __name__ == '__main__': #
+    main()
+

requirements.txt

@@ -0,0 +1,7 @@
+matplotlib==3.6.2
+streamlit==1.12.0
+Pillow==9.2.0
+numpy==1.23.1
+pandas==1.4.3
+plotly==5.11.0
+sklearn==0.0