Spaces:
Runtime error
Runtime error
File size: 3,685 Bytes
ad2de74 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 |
# Import the libraries
import joblib
import pandas as pd
import numpy as np
import json
import uuid
from pathlib import Path
import gradio as gr
from sklearn.compose import make_column_transformer
from sklearn.preprocessing import StandardScaler, OneHotEncoder
from sklearn.impute import SimpleImputer
from sklearn.pipeline import Pipeline
# 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'
exec(open("train.py").read())
# Load the freshly trained model from disk
saved_model = joblib.load("random_forest_pipeline.pkl")
print("Model loaded from random_forest_pipeline.pkl")
# Prepare the logging functionality
log_file = Path("logs/") / f"data_{uuid.uuid4()}.json"
log_folder = log_file.parent
log_folder.mkdir(parents=True, exist_ok=True)
#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
#)
# CommitScheduler is not available, so we use a lock mechanism for the example
class SimpleLock:
def __init__(self, lock_file="lockfile"):
self.lock_file = Path(lock_file)
def __enter__(self):
while self.lock_file.exists():
pass # Simple spinlock
self.lock_file.touch()
def __exit__(self, exc_type, exc_val, exc_tb):
self.lock_file.unlink()
scheduler = SimpleLock()
# 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):
# Create a DataFrame with the input data
data = {
'age': [age],
'bmi': [bmi],
'children': [children],
'sex': [sex],
'smoker': [smoker],
'region': [region]
}
df = pd.DataFrame(data)
## Make prediction using the loaded model
prediction = saved_model.predict(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
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.inputs.Number(label="Age")
bmi_input = gr.inputs.Number(label="BMI")
children_input = gr.inputs.Number(label="Children")
sex_input = gr.inputs.Radio(choices=['male', 'female'], label="Sex")
smoker_input = gr.inputs.Radio(choices=['yes', 'no'], label="Smoker")
region_input = gr.inputs.Dropdown(choices=['northeast', 'northwest', 'southeast', 'southwest'], label="Region")
# Create the gradio interface, make title "HealthyLife Insurance Charge Prediction"
demo = gr.Interface(
fn=predict,
inputs=[age_input, bmi_input, children_input, sex_input, smoker_input, region_input],
outputs="number",
title="HealthyLife Insurance Charge Prediction"
)
# Launch with a load balancer
demo.queue()
demo.launch(share=False)
|