uploaded initial artifacts for model deployment

app.py

@@ -0,0 +1,112 @@
+# 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'
+
+age = gr.Number(label='Age')
+sex = gr.Dropdown(['female','male'], label='Sex')
+bmi = gr.Number(label='Body-Mass-Index (BMI)')
+children = gr.Number(label='Number of children dependents')
+smoker = gr.Dropdown(['yes','no'], label='Smoker')
+region = gr.Dropdown(['northeast',
+                      'northwest',
+                      'southeast',
+                      'southwest',], label='Region')
+
+model_output = gr.Label(label="Insurance Charge Amount")
+
+
+# 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="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
+
+
+    # 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
+
+def insurance_charge_amount(age, sex, bmi, children, smoker, region):
+    sample = {
+        'Age': age,
+        'Sex': sex,
+        'Body-Mass-Index (BMI)': bmi,
+        'Number of children dependents': children,
+        'Smoker': smoker,
+        'Region': region
+    }
+
+    data_point = pd.DataFrame([sample])
+    prediction = insurance_charge_predictor.predict(data_point).tolist()
+
+    with scheduler.lock:
+        with log_file.open("a") as f:
+            f.write(json.dumps(
+                {
+                    'Age': age,
+                    'Sex': sex,
+                    'Body-Mass-Index (BMI)': bmi,
+                    'Number of children dependents': children,
+                    'Smoker': smoker,
+                    'Region': region,
+                    'prediction': prediction[0]
+                }
+            ))
+            f.write("\n")
+
+    return prediction[0]
+
+demo = gr.Interface(
+    fn=insurance_charge_amount,
+    inputs=[age, sex, bmi, 
+            children, smoker, region],
+    outputs=model_output,
+    title="HealthyLife Insurance Charge Prediction",
+    description="This API allows you to calculate an estimated Insurance Charge Amount",
+    allow_flagging="auto",
+    concurrency_limit=8
+)
+
+# Set up UI components for input and output
+ui_inputs = [age, sex, bmi, children, smoker, region]
+ui_output = model_output
+
+# Create the gradio interface, make title "HealthyLife Insurance Charge Prediction"
+demo = gr.Interface(
+    fn=insurance_charge_amount,
+    inputs=ui_inputs,
+    outputs=ui_output,
+    title="HealthyLife Insurance Charge Prediction",
+    description="This API allows you to calculate an estimated Insurance Charge Amount",
+    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 sha256:7daba9429128f97d5a4a7ecd5a3446e52671ea84db941314407dfecd2e480c16
+size 3950

requirements.txt

@@ -0,0 +1 @@
+scikit-learn==1.2.2

train.py

@@ -0,0 +1,64 @@
+
+import pandas as pd
+import joblib
+
+from sklearn.datasets import fetch_openml
+
+from sklearn.preprocessing import StandardScaler, OneHotEncoder
+from sklearn.compose import make_column_transformer
+
+from sklearn.pipeline import make_pipeline
+
+from sklearn.model_selection import train_test_split
+
+from sklearn.linear_model import LinearRegression
+from sklearn.metrics import mean_squared_error, r2_score
+
+data_df = pd.read_csv('insurance.csv')
+
+target = 'charges'
+numeric_features = [
+    'age',
+    'bmi',
+    'children'
+]
+categorical_features = [
+    'smoker',
+    'sex',
+    'region']
+
+print("Creating data subsets")
+
+X = data_df[numeric_features + categorical_features]
+y = data_df[target]
+
+Xtrain, Xtest, ytrain, ytest = train_test_split(
+    X, y,
+    test_size=0.2,
+    random_state=100
+)
+
+preprocessor = make_column_transformer(
+    (StandardScaler(), numeric_features),
+    (OneHotEncoder(handle_unknown='ignore'), categorical_features)
+)
+
+model_linear_regression = LinearRegression(n_jobs=-1)
+
+print("Estimating Model Pipeline")
+
+model_pipeline = make_pipeline(
+    preprocessor,
+    model_linear_regression
+)
+
+model_pipeline.fit(Xtrain, ytrain)
+
+print("Logging Metrics")
+print(f"R-squared: {r2_score(ytest, model_pipeline.predict(Xtest))}")
+
+print("Serializing Model")
+
+saved_model_path = "model.joblib"
+
+joblib.dump(model_pipeline, saved_model_path)