Upload 3 files

First version of the prediction model.

app.py

@@ -0,0 +1,88 @@
+
+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
+
+
+# Preparing 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",
+     repo_type="dataset",
+     folder_path=log_folder,
+     path_in_repo="data",
+     every=2
+ )
+
+charges_predictor = joblib.load('model.joblib')
+
+age_input = gr.Number(label='Age')
+bmi_input = gr.Number(label='BMI')
+children_input = gr.Number(label='Children')
+sex_input = gr.Dropdown(['male', 'female', 'N/A'], value='N/A', label='Sex')
+smoker_input = gr.Dropdown(['yes', 'no', 'N/A'], value='N/A', label="Smoker")
+region_input = gr.Dropdown(['southeast', 'southwest', 'northeast', 'northwest', 'N/A'], 
+                           value='N/A', label='Region')
+
+
+model_output = gr.Label(label='Charges')
+
+# the functions runs when 'Submit' is clicked or when a API request is made
+def predict_charges(age, bmi, children, sex, smoker, region, prediction):
+    sample = {
+        'Age': age,
+        'BMI': bmi,
+        'Children': children,
+        'Sex': sex,
+        'Smoker': smoker,
+        'Region': region,
+        'Prediction': prediction
+    }
+    data_point = pd.DataFrame([sample])
+    print('data point: ', data_point)
+    prediction = charges_predictor.predict(data_point).tolist()
+
+
+    with scheduler.lock:
+          with log_file.open("a") as f:
+              f.write(json.dumps(
+                 {
+                     'Region': region,
+                     'Smoker': smoker,
+                     'BMI': bmi,
+                     'Children': children,
+                     'Sex': sex,
+                     'Smoker': smoker,
+                     'Age': age,
+                     'Prediction': prediction[0]
+                  }
+              ))
+              f.write("\n")
+
+    return prediction[0]
+
+
+# Setting up UI components for input and output
+demo = gr.Interface(
+    fn=predict_charges,
+    inputs=[region_input, smoker_input, bmi_input,
+            children_input, sex_input, age_input],
+    outputs=model_output,
+    title="HealthyLife Insurance Charge Prediction",
+    description="This API allows you to predict the appropiate charges for each patient",
+    allow_flagging="auto",
+    concurrency_limit=8
+)
+
+# Launch with a load balancer
+demo.queue()
+demo.launch(share=False)

model.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecff8e1c811de2d1d5ffff71183e2568f008dbde9c603480e0ae420aeff81838
+size 4113

requirements.txt

@@ -0,0 +1,4 @@
+scikit-learn==1.6.1
+joblib==1.4.2
+numpy==2.2.1
+gradio==5.11.0