Update app.py
Browse files
app.py
CHANGED
@@ -2,7 +2,6 @@ import gradio as gr
|
|
2 |
import pickle
|
3 |
import json
|
4 |
import numpy as np
|
5 |
-
import pandas as pd
|
6 |
|
7 |
# Load model and columns
|
8 |
with open("kigali_model.pickle", "rb") as f:
|
@@ -13,49 +12,52 @@ with open("columns.json", "r") as f:
|
|
13 |
|
14 |
# Define the location and property type mappings
|
15 |
location_mapping = {
|
16 |
-
'
|
17 |
-
'
|
18 |
-
'
|
19 |
-
'
|
20 |
-
'
|
21 |
-
'
|
22 |
-
'
|
23 |
-
'nyarutarama': 8
|
24 |
}
|
25 |
|
26 |
property_type_mapping = {
|
27 |
-
'
|
28 |
-
'
|
29 |
-
'
|
30 |
-
'villa': 4
|
31 |
}
|
32 |
|
33 |
def transform_data(size_sqm, number_of_bedrooms, number_of_bathrooms, number_of_floors, parking_space, location, property_type):
|
34 |
-
# Prepare the input array
|
35 |
x = np.zeros(len(data_columns))
|
|
|
|
|
36 |
x[0] = size_sqm
|
37 |
x[1] = number_of_bedrooms
|
38 |
x[2] = number_of_bathrooms
|
39 |
x[3] = number_of_floors
|
40 |
-
x[
|
41 |
|
|
|
42 |
if location in location_mapping:
|
43 |
loc_index = data_columns.index(location)
|
44 |
x[loc_index] = 1
|
45 |
-
|
|
|
46 |
if property_type in property_type_mapping:
|
47 |
prop_index = data_columns.index(property_type)
|
48 |
x[prop_index] = 1
|
49 |
|
50 |
return np.array([x])
|
51 |
|
|
|
52 |
def predict(size_sqm, number_of_bedrooms, number_of_bathrooms, number_of_floors, parking_space, location, property_type):
|
53 |
# Transform input data
|
54 |
input_data_transformed = transform_data(size_sqm, number_of_bedrooms, number_of_bathrooms, number_of_floors, parking_space, location, property_type)
|
55 |
|
56 |
# Predict using the model
|
57 |
prediction = model.predict(input_data_transformed)
|
58 |
-
return prediction[0]
|
59 |
|
60 |
# Define Gradio interface components
|
61 |
inputs = [
|
@@ -65,9 +67,11 @@ inputs = [
|
|
65 |
gr.Number(label="Number of Floors", value=0),
|
66 |
gr.Number(label="Parking Space", value=0),
|
67 |
gr.Dropdown(choices=list(location_mapping.keys()), label="Location"),
|
68 |
-
gr.Dropdown(choices=list(property_type_mapping.keys()), label="Property Type")
|
|
|
69 |
]
|
70 |
|
|
|
71 |
outputs = gr.Textbox(label="Prediction (FRW)")
|
72 |
|
73 |
# Footer content
|
@@ -78,7 +82,7 @@ gr.Interface(
|
|
78 |
fn=predict,
|
79 |
inputs=inputs,
|
80 |
outputs=outputs,
|
81 |
-
title="Property Price Prediction
|
82 |
description="Enter property details to get the price prediction.",
|
83 |
article=footer
|
84 |
-
).launch(
|
|
|
2 |
import pickle
|
3 |
import json
|
4 |
import numpy as np
|
|
|
5 |
|
6 |
# Load model and columns
|
7 |
with open("kigali_model.pickle", "rb") as f:
|
|
|
12 |
|
13 |
# Define the location and property type mappings
|
14 |
location_mapping = {
|
15 |
+
'kacyiru': 1,
|
16 |
+
'kanombe': 2,
|
17 |
+
'kibagabaga': 3,
|
18 |
+
'kicukiro': 4,
|
19 |
+
'kimironko': 5,
|
20 |
+
'nyamirambo': 6,
|
21 |
+
'nyarutarama': 7
|
|
|
22 |
}
|
23 |
|
24 |
property_type_mapping = {
|
25 |
+
'bungalow': 1,
|
26 |
+
'house': 2,
|
27 |
+
'villa': 3
|
|
|
28 |
}
|
29 |
|
30 |
def transform_data(size_sqm, number_of_bedrooms, number_of_bathrooms, number_of_floors, parking_space, location, property_type):
|
31 |
+
# Prepare the input array with zeros
|
32 |
x = np.zeros(len(data_columns))
|
33 |
+
|
34 |
+
# Assign input values to the corresponding columns
|
35 |
x[0] = size_sqm
|
36 |
x[1] = number_of_bedrooms
|
37 |
x[2] = number_of_bathrooms
|
38 |
x[3] = number_of_floors
|
39 |
+
x[5] = parking_space # Ensure that parking_space aligns with the correct index in your model
|
40 |
|
41 |
+
# Apply location mapping
|
42 |
if location in location_mapping:
|
43 |
loc_index = data_columns.index(location)
|
44 |
x[loc_index] = 1
|
45 |
+
|
46 |
+
# Apply property type mapping
|
47 |
if property_type in property_type_mapping:
|
48 |
prop_index = data_columns.index(property_type)
|
49 |
x[prop_index] = 1
|
50 |
|
51 |
return np.array([x])
|
52 |
|
53 |
+
|
54 |
def predict(size_sqm, number_of_bedrooms, number_of_bathrooms, number_of_floors, parking_space, location, property_type):
|
55 |
# Transform input data
|
56 |
input_data_transformed = transform_data(size_sqm, number_of_bedrooms, number_of_bathrooms, number_of_floors, parking_space, location, property_type)
|
57 |
|
58 |
# Predict using the model
|
59 |
prediction = model.predict(input_data_transformed)
|
60 |
+
return round(prediction[0], 2) # round prediction for better readability
|
61 |
|
62 |
# Define Gradio interface components
|
63 |
inputs = [
|
|
|
67 |
gr.Number(label="Number of Floors", value=0),
|
68 |
gr.Number(label="Parking Space", value=0),
|
69 |
gr.Dropdown(choices=list(location_mapping.keys()), label="Location"),
|
70 |
+
gr.Dropdown(choices=list(property_type_mapping.keys()), label="Property Type"),
|
71 |
+
# Add new inputs for other columns, like furnished, proximity, etc.
|
72 |
]
|
73 |
|
74 |
+
|
75 |
outputs = gr.Textbox(label="Prediction (FRW)")
|
76 |
|
77 |
# Footer content
|
|
|
82 |
fn=predict,
|
83 |
inputs=inputs,
|
84 |
outputs=outputs,
|
85 |
+
title="KIGALI Property Price Prediction (Real Time AI APPLICATION",
|
86 |
description="Enter property details to get the price prediction.",
|
87 |
article=footer
|
88 |
+
).launch(debug=True)
|