Upload 3 files

app.py

@@ -0,0 +1,100 @@
+# Import the libraries
+import os
+import time
+import json
+import uuid
+import joblib
+import pandas as pd
+import gradio as gr
+import math
+
+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'
+
+
+
+
+# Load the freshly trained model from disk
+insurance_charge_predictor = 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="anirudhabokil/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
+
+
+
+# Set up UI components for input and output
+age = gr.Number(label="Age")
+bmi = gr.Number(label="BMI")
+children = gr.Number(label="Children")
+sex = gr.Dropdown(['male','female'], label="Sex")
+smoker = gr.Dropdown(['yes','no'], label="Smoker")
+region = gr.Dropdown(['southwest','southeast','northwest','northeast'], label="Region")
+
+model_output = gr.Label(label="Insurance Charge")
+
+def predict_insurance_charge(age, bmi, children, sex, smoker, region):
+  sample = {
+      'age': age,
+      'bmi': bmi,
+      'children': children,
+      'sex': sex,
+      'smoker': smoker,
+      'region': region
+  }
+  df = pd.DataFrame([sample])
+  print(sample)
+  prediction = insurance_charge_predictor.predict(df).tolist()
+  #print(prediction)
+
+
+  # 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': 123
+              }
+          ))
+          f.write("\n")
+  #round prediction[0] to 2 decimal
+  return round(prediction[0], 2)
+
+
+# Create the gradio interface, make title "HealthyLife Insurance Charge Prediction"
+demo = gr.Interface(fn=predict_insurance_charge,
+                    inputs=[age, bmi, children, sex, smoker, region],
+                    outputs=model_output,
+                    title="HealthyLife Insurance Charge Prediction",
+                    description="This API allows you uo predict insurance charge",
+                    flagging_mode="auto",
+                    concurrency_limit=8)
+
+# Launch with a load balancer
+demo.queue()
+demo.launch(share=True, debug=True)

model.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca19cf08ff09c79c763cb148aadf97192aa4212459bc5b0e71a983a2e1f3e44b
+size 4030

requirements.txt

@@ -0,0 +1,3 @@
+scikit-learn==1.5.2
+numpy==1.26.4
+pandas==2.2.2