Kopec-B/pricing-optimization

1import gradio as gr
2import pandas as pd
3import numpy as np
4import joblib
5
6# Load the pre-trained model
7model = joblib.load('pricing_optimization_model.pkl')
8
9
10# Function to predict order demand
11def predict_order_demand(year, month, day, demand_elasticity, warehouse_whse_j, warehouse_whse_s, category_003,
12                         category_004, category_005, category_006, category_007, category_008, category_009,
13                         category_011, category_013, category_015, category_017, category_018, category_019,
14                         category_020, category_021, category_022, category_023, category_024, category_025,
15                         category_026, category_028, category_030, category_031, category_032, category_033):
16    # Prepare the input data as a pandas DataFrame
17    input_data = pd.DataFrame({
18        'Year': [year],
19        'Month': [month],
20        'Day': [day],
21        'Demand_Elasticity': [demand_elasticity],
22        'Warehouse_Whse_J': [warehouse_whse_j],
23        'Warehouse_Whse_S': [warehouse_whse_s],
24        'Product_Category_Category_003': [category_003],
25        'Product_Category_Category_004': [category_004],
26        'Product_Category_Category_005': [category_005],
27        'Product_Category_Category_006': [category_006],
28        'Product_Category_Category_007': [category_007],
29        'Product_Category_Category_008': [category_008],
30        'Product_Category_Category_009': [category_009],
31        'Product_Category_Category_011': [category_011],
32        'Product_Category_Category_013': [category_013],
33        'Product_Category_Category_015': [category_015],
34        'Product_Category_Category_017': [category_017],
35        'Product_Category_Category_018': [category_018],
36        'Product_Category_Category_019': [category_019],
37        'Product_Category_Category_020': [category_020],
38        'Product_Category_Category_021': [category_021],
39        'Product_Category_Category_022': [category_022],
40        'Product_Category_Category_023': [category_023],
41        'Product_Category_Category_024': [category_024],
42        'Product_Category_Category_025': [category_025],
43        'Product_Category_Category_026': [category_026],
44        'Product_Category_Category_028': [category_028],
45        'Product_Category_Category_030': [category_030],
46        'Product_Category_Category_031': [category_031],
47        'Product_Category_Category_032': [category_032],
48        'Product_Category_Category_033': [category_033]
49    })
50
51    # Use the model to predict the order demand
52    prediction = model.predict(input_data)
53
54    return prediction[0]
55
56
57# Define the Gradio interface
58iface = gr.Interface(
59    fn=predict_order_demand,
60    inputs=[
61        gr.Slider(minimum=2012, maximum=2025, step=1, label="Year", value=2022),
62        gr.Slider(minimum=1, maximum=12, step=1, label="Month", value=6),
63        gr.Slider(minimum=1, maximum=31, step=1, label="Day", value=15),
64        gr.Slider(minimum=-1.0, maximum=1.0, step=0.1, label="Demand Elasticity", value=0.05),
65        gr.Slider(minimum=0, maximum=1, step=1, label="Warehouse Whse_J", value=0),
66        gr.Slider(minimum=0, maximum=1, step=1, label="Warehouse Whse_S", value=0),
67        gr.Slider(minimum=0, maximum=1, step=1, label="Category 003", value=0),
68        gr.Slider(minimum=0, maximum=1, step=1, label="Category 004", value=0),
69        gr.Slider(minimum=0, maximum=1, step=1, label="Category 005", value=0),
70        gr.Slider(minimum=0, maximum=1, step=1, label="Category 006", value=0),
71        gr.Slider(minimum=0, maximum=1, step=1, label="Category 007", value=0),
72        gr.Slider(minimum=0, maximum=1, step=1, label="Category 008", value=0),
73        gr.Slider(minimum=0, maximum=1, step=1, label="Category 009", value=0),
74        gr.Slider(minimum=0, maximum=1, step=1, label="Category 011", value=0),
75        gr.Slider(minimum=0, maximum=1, step=1, label="Category 013", value=0),
76        gr.Slider(minimum=0, maximum=1, step=1, label="Category 015", value=0),
77        gr.Slider(minimum=0, maximum=1, step=1, label="Category 017", value=0),
78        gr.Slider(minimum=0, maximum=1, step=1, label="Category 018", value=0),
79        gr.Slider(minimum=0, maximum=1, step=1, label="Category 019", value=0),
80        gr.Slider(minimum=0, maximum=1, step=1, label="Category 020", value=0),
81        gr.Slider(minimum=0, maximum=1, step=1, label="Category 021", value=0),
82        gr.Slider(minimum=0, maximum=1, step=1, label="Category 022", value=0),
83        gr.Slider(minimum=0, maximum=1, step=1, label="Category 023", value=0),
84        gr.Slider(minimum=0, maximum=1, step=1, label="Category 024", value=0),
85        gr.Slider(minimum=0, maximum=1, step=1, label="Category 025", value=0),
86        gr.Slider(minimum=0, maximum=1, step=1, label="Category 026", value=0),
87        gr.Slider(minimum=0, maximum=1, step=1, label="Category 028", value=0),
88        gr.Slider(minimum=0, maximum=1, step=1, label="Category 030", value=0),
89        gr.Slider(minimum=0, maximum=1, step=1, label="Category 031", value=0),
90        gr.Slider(minimum=0, maximum=1, step=1, label="Category 032", value=0),
91        gr.Slider(minimum=0, maximum=1, step=1, label="Category 033", value=0)
92    ],
93    outputs=gr.Number(label="Predicted Order Demand")
94)
95
96# Launch the Gradio app with sharing enabled
97iface.launch(share=True)
98