Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -1,39 +1,20 @@
|
|
| 1 |
import gradio as gr
|
| 2 |
import pandas as pd
|
| 3 |
import numpy as np
|
| 4 |
-
import pickle
|
| 5 |
|
| 6 |
-
#
|
| 7 |
-
|
| 8 |
-
# ---------------------------
|
| 9 |
-
with open("dynamic_pricing_model.pkl", "rb") as f:
|
| 10 |
-
model = pickle.load(f)
|
| 11 |
|
| 12 |
-
# ---------------------------
|
| 13 |
-
# PREDICTION FUNCTION
|
| 14 |
-
# ---------------------------
|
| 15 |
def predict_dynamic_pricing(
|
| 16 |
-
zone_id,
|
| 17 |
-
|
| 18 |
-
|
| 19 |
-
|
| 20 |
-
weather_factor,
|
| 21 |
-
event_factor,
|
| 22 |
-
temperature,
|
| 23 |
-
traffic_index,
|
| 24 |
-
distance_km,
|
| 25 |
-
duration_min,
|
| 26 |
-
base_fare,
|
| 27 |
-
hour,
|
| 28 |
-
day_of_week,
|
| 29 |
-
is_weekend,
|
| 30 |
-
rate_per_km=6
|
| 31 |
):
|
| 32 |
|
| 33 |
-
# Recalculate demand/supply ratio
|
| 34 |
demand_supply_ratio = np.clip(demand / (supply + 1), 0, 3)
|
| 35 |
|
| 36 |
-
# Create input row
|
| 37 |
row = pd.DataFrame([{
|
| 38 |
"zone_id": zone_id,
|
| 39 |
"hour": hour,
|
|
@@ -52,45 +33,38 @@ def predict_dynamic_pricing(
|
|
| 52 |
"demand_supply_ratio": demand_supply_ratio
|
| 53 |
}])
|
| 54 |
|
| 55 |
-
|
| 56 |
-
|
|
|
|
| 57 |
|
| 58 |
-
|
| 59 |
-
base_price = float(base_fare)
|
| 60 |
|
| 61 |
-
# Final dynamic price
|
| 62 |
-
final_price = base_price * surge_factor
|
| 63 |
-
|
| 64 |
-
return base_price, surge_factor, final_price
|
| 65 |
-
|
| 66 |
-
# ---------------------------
|
| 67 |
-
# GRADIO UI
|
| 68 |
-
# ---------------------------
|
| 69 |
demo = gr.Interface(
|
| 70 |
fn=predict_dynamic_pricing,
|
| 71 |
inputs=[
|
| 72 |
-
gr.Number(label="Zone ID"
|
| 73 |
-
gr.Number(label="Demand"
|
| 74 |
-
gr.Number(label="Supply"
|
| 75 |
-
gr.Number(label="Driver Availability"
|
| 76 |
-
gr.Number(label="Weather Factor
|
| 77 |
-
gr.Number(label="Event Factor
|
| 78 |
-
gr.Number(label="Temperature
|
| 79 |
-
gr.Number(label="Traffic Index
|
| 80 |
-
gr.Number(label="Distance (km)"
|
| 81 |
-
gr.Number(label="Duration (min)"
|
| 82 |
-
gr.Number(label="Base Fare"
|
| 83 |
-
gr.Number(label="Hour
|
| 84 |
-
gr.Number(label="Day of Week
|
| 85 |
-
gr.Number(label="Is Weekend
|
| 86 |
],
|
| 87 |
outputs=[
|
| 88 |
gr.Number(label="Base Price"),
|
| 89 |
-
gr.Number(label="
|
| 90 |
-
gr.Number(label="Final Dynamic Price")
|
| 91 |
],
|
| 92 |
title="Dynamic Pricing Model",
|
| 93 |
-
description="
|
| 94 |
)
|
| 95 |
|
| 96 |
demo.launch()
|
|
|
|
|
|
| 1 |
import gradio as gr
|
| 2 |
import pandas as pd
|
| 3 |
import numpy as np
|
| 4 |
+
import joblib # Use joblib instead of pickle
|
| 5 |
|
| 6 |
+
# Load model
|
| 7 |
+
model = joblib.load("dynamic_pricing_model.joblib")
|
|
|
|
|
|
|
|
|
|
| 8 |
|
|
|
|
|
|
|
|
|
|
| 9 |
def predict_dynamic_pricing(
|
| 10 |
+
zone_id, demand, supply, driver_availability,
|
| 11 |
+
weather_factor, event_factor, temperature, traffic_index,
|
| 12 |
+
distance_km, duration_min, base_fare,
|
| 13 |
+
hour, day_of_week, is_weekend, rate_per_km=6
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
):
|
| 15 |
|
|
|
|
| 16 |
demand_supply_ratio = np.clip(demand / (supply + 1), 0, 3)
|
| 17 |
|
|
|
|
| 18 |
row = pd.DataFrame([{
|
| 19 |
"zone_id": zone_id,
|
| 20 |
"hour": hour,
|
|
|
|
| 33 |
"demand_supply_ratio": demand_supply_ratio
|
| 34 |
}])
|
| 35 |
|
| 36 |
+
surge = float(model.predict(row)[0])
|
| 37 |
+
base_price = base_fare + distance_km * rate_per_km
|
| 38 |
+
final_price = base_price * surge
|
| 39 |
|
| 40 |
+
return base_price, surge, final_price
|
|
|
|
| 41 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 42 |
demo = gr.Interface(
|
| 43 |
fn=predict_dynamic_pricing,
|
| 44 |
inputs=[
|
| 45 |
+
gr.Number(label="Zone ID"),
|
| 46 |
+
gr.Number(label="Demand"),
|
| 47 |
+
gr.Number(label="Supply"),
|
| 48 |
+
gr.Number(label="Driver Availability"),
|
| 49 |
+
gr.Number(label="Weather Factor"),
|
| 50 |
+
gr.Number(label="Event Factor"),
|
| 51 |
+
gr.Number(label="Temperature"),
|
| 52 |
+
gr.Number(label="Traffic Index"),
|
| 53 |
+
gr.Number(label="Distance (km)"),
|
| 54 |
+
gr.Number(label="Duration (min)"),
|
| 55 |
+
gr.Number(label="Base Fare"),
|
| 56 |
+
gr.Number(label="Hour"),
|
| 57 |
+
gr.Number(label="Day of Week"),
|
| 58 |
+
gr.Number(label="Is Weekend")
|
| 59 |
],
|
| 60 |
outputs=[
|
| 61 |
gr.Number(label="Base Price"),
|
| 62 |
+
gr.Number(label="Surge Factor"),
|
| 63 |
+
gr.Number(label="Final Dynamic Price")
|
| 64 |
],
|
| 65 |
title="Dynamic Pricing Model",
|
| 66 |
+
description="AI-based real-time surge pricing."
|
| 67 |
)
|
| 68 |
|
| 69 |
demo.launch()
|
| 70 |
+
|