app.py

# Import the libraries
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, RandomizedSearchCV

from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score, classification_report

# 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'

# Run training script 
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestRegressor
   
import joblib

# Choose and instantiate RandomForestRegressor model
model = RandomForestRegressor()


# Train the model using the training data
model.fit(X_train, y_train)

# Save the trained model to a file (e.g., 'insurance_model.joblib')
joblib.dump(model, 'model.joblib')


# Load the freshly trained model from disk
model = joblib.load('model.joblib')

# Prepare the logging functionality
log_file = Path("logs/") / f"data_{uuid.uuid4()}.json"
log_folder = log_file.parent
log_file.parent.mkdir(exist_ok=True)


#######################################################################################################################
scheduler = CommitScheduler(
    repo_id="-----------",  # 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

import pandas as pd
import joblib

# Assuming 'model' is a trained model loaded using joblib.load()

def predict(age, sex, bmi, children, smoker, region):
    """Predicts insurance charges based on customer features.

    Args:
        age (int): Age of the customer.
        sex (int): Gender of the customer (0 for female, 1 for male).
        bmi (float): Body Mass Index of the customer.
        children (int): Number of children the customer has.
        smoker (int): Smoking status of the customer (0 for yes, 1 for no).
        region (int): Region of the customer (1-4 representing different regions).

    Returns:
        float: Predicted insurance charges.
    """

    # Create a DataFrame with the input features
    input_data = pd.DataFrame({
        'age': [age],
        'sex': [sex],
        'bmi': [bmi],
        'children': [children],
        'smoker': [smoker],
        'region': [region]
    })

    # Make the prediction using the loaded model
    prediction = model.predict(input_data)

    # Return the prediction
    return prediction[0]



    # 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
import gradio as gr

age = gr.inputs.Slider(minimum=18, maximum=64, default=30, step=1, label="Age")
sex = gr.inputs.Radio(["female", "male"], type)


# Create the gradio interface, make title "HealthyLife Insurance Charge Prediction"
import gradio as gr

# ... (previous code for model training and predict function) ...

# Set up UI components for input and output
age = gr.inputs.Slider(minimum=18, maximum=64, default=30, step=1, label="Age")
sex = gr.inputs.Radio(["female", "male"], type="value", default="female", label="Sex")  # Corrected type
bmi = gr.inputs.Number(default=25, label="BMI")
children = gr.inputs.Slider(minimum=0, maximum=5, default=0, step=1, label="Children")
smoker = gr.inputs.Radio(["yes", "no"], type="value", default="no", label="Smoker")  # Corrected type
region = gr.inputs.Dropdown(["southwest", "southeast", "northwest", "northeast"], type="value", default="southwest", label="Region")  # Corrected type

# Create the Gradio interface
demo = gr.Interface(
    fn=predict, 
    inputs=[age, sex, bmi, children, smoker, region], 
    outputs="number",
    title="HealthyLife Insurance Charge Prediction"
)

# Launch with a load balancer
demo.queue()
demo.launch(share=False)