|
import pickle |
|
import gradio as gr |
|
|
|
|
|
with open('./Automatidata_gui.pickle', 'rb') as file: |
|
model = pickle.load(file) |
|
|
|
|
|
def automatidata(VendorID, passenger_count, Distance, Duration, rush_hour): |
|
inputs = [[VendorID, passenger_count, Distance, Duration, rush_hour]] |
|
prediction = model.predict(inputs) |
|
prediction_value = prediction[0][0] |
|
return f"Fare amount(approx.) = {round(prediction_value, 2)} $" |
|
|
|
|
|
automatidata_ga = gr.Interface(fn=automatidata, |
|
inputs=[ |
|
gr.Number(1, 2, label="VendorID - [1 or 2]"), |
|
gr.Number(0, 6, label="Passenger Count - [1 to 6]"), |
|
gr.Number(label="Distance in miles"), |
|
gr.Number(label="Duration in mins"), |
|
gr.Number(0, 1, label="Rush Hour - [0 or 1]") |
|
], |
|
outputs="text", title="New York City Taxi and Limousine Commission (TLC) - Taxi Fares Estimator", |
|
examples = [ |
|
[2,1,2.33,15.09,0], |
|
[1,2,4.22,24.29,0], |
|
[1,1,0.71,6.66,0], |
|
[2,1,0.97,8.37,0], |
|
[2,3,1.48,8.92,0], |
|
], |
|
description="Predicting Taxi Fare Amount Using Machine Learning.", |
|
theme='dark' |
|
) |
|
|
|
automatidata_ga.launch(share=True) |
|
|
