File size: 3,376 Bytes
3b271ab 4d75887 3b271ab edda0ff 3b271ab edda0ff 3b271ab edda0ff 4d75887 3b271ab edda0ff 3b271ab |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 |
# Import the libraries
import os
import uuid
import joblib
import json
import gradio as gr
import pandas as pd
from huggingface_hub import CommitScheduler
from pathlib import Path
# Run the training script placed in the same directory as app.py
# The training script will train and persist a linear regression
# model with the filename 'model.joblib'
#hugging face HATES !python, python. this seems to be okay
exec(open("train.py").read())
# Load the freshly trained model from disk
insurance_model = joblib.load("model.joblib")
# Prepare the logging functionality
log_file = Path("logs/") / f"data_{uuid.uuid4()}.json"
log_folder = log_file.parent
scheduler = CommitScheduler(
repo_id="insurance-charge-mlops-logs", # provide a name "insurance-charge-mlops-logs" for the repo_id
repo_type="dataset",
folder_path=log_folder,
path_in_repo="data",
every=2
)
# Define the predict function which will take features, convert to dataframe and make predictions using the saved model
# the functions runs when 'Submit' is clicked or when a API request is made
def predict(age, bmi, children, sex, smoker, region):
# input2 = {
# "age": 10,
# "bmi": 30,
# "children": 6,
# "sex": 'female',
# "smoker": 'yes',
# "region": 'northwest'
# }
input = {
"age": age,
"bmi": bmi,
"children": children,
"sex": sex,
"smoker": smoker,
"region": region
}
input_df = pd.DataFrame([input])
prediction = insurance_model.predict(input_df)
# While the prediction is made, log both the inputs and outputs to a log file
# While writing to the log file, ensure that the commit scheduler is locked to avoid parallel
# access
# this was already in here so i'm leaving it for loggin
with scheduler.lock:
with log_file.open("a") as f:
f.write(json.dumps(
{
'age': age,
'bmi': bmi,
'children': children,
'sex': sex,
'smoker': smoker,
'region': region,
'prediction': prediction[0]
}
))
f.write("\n")
return prediction[0]
# Set up UI components for input and output
age_input = gr.Number(label="Age")
bmi_input = gr.Number(label="BMI")
children_input = gr.Slider(minimum=0.0, maximum=15.0, step=1.0, label="Children")
sex_input = gr.Radio(['male', 'female'], label="sex")
smoker_input = gr.Radio(choices=['yes', 'no'], label="smoker")
region_input = gr.Dropdown(['southwest', 'southeast', 'northwest', 'northeast'], label="region")
output = gr.Label(label="Insurance Price")
# Create the gradio interface, make title "HealthyLife Insurance Charge Prediction"
# demo was the existing name in this file, so using that.
demo = gr.Interface(
fn=predict,
inputs=[age_input, bmi_input, children_input, sex_input, smoker_input, region_input],
outputs=output,
title="HealthyLife Insurance Charge Prediction",
description="This API allows you to predict insurance prices for HealthlyLife Insurance",
allow_flagging="auto",
concurrency_limit=8
)
# Launch with a load balancer
# these two lines were in the file already
demo.queue()
# demo.launch(share=True, debug=True)
demo.launch(share=False)
|