uploading updated files

app.py

@@ -3,58 +3,58 @@ import os
 import uuid
 import joblib
 import json
-
+import time
 import gradio as gr
 import pandas as pd
 
+from huggingface_hub import HfApi
 from huggingface_hub import CommitScheduler
 from pathlib import Path
+from sklearn.model_selection import train_test_split
+from sklearn.ensemble import RandomForestRegressor
+from sklearn.pipeline import Pipeline
+from sklearn.compose import ColumnTransformer
+from sklearn.preprocessing import OneHotEncoder
+from datetime import datetime
+
+# Load the Hugging Face API token
+hf_token = os.getenv("HF_TOKEN")
 
+# Initialize Hugging Face API
+api = HfApi()
 # 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'
+os.system("python train.py")
 # Load the freshly trained model from disk 
-
+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="-----------",  # provide a name "insurance-charge-mlops-logs" for the repo_id
+    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
+    token=hf_token
 )
-# Create variable for model.joblib
-insurance_charge_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.Number(label='Sex')
-smoker_input = gr.Number(label='Smoker')
-region_input = gr.Number(label='Region')
-type_input = gr.Dropdown(
-    ['Low', 'Mean', 'High'],
-    label='Type'
-)
 # Define the predict function which will take features, convert to dataframe and make predictions using the saved model
-def insurance_charge_predictor(age, bmi, children, sex, smoker, region, type):
-    sample = {
-        'Age': age,
-        'BMI': bmi,
-        'Children': children,
-        'Sex': sex,
-        'Smoker': smoker,
-        'Region': region,
-        'Type': type
-    }
 # the functions runs when 'Submit' is clicked or when a API request is made
+def insurance_charge_predictor(age, bmi, children, sex, smoker, region):
+    input_data = pd.DataFrame({
+        'Age': [age],
+        'BMI': [bmi],
+        'Children': [children],
+        'Sex': [sex],
+        'Smoker': [smoker],
+        'Region': [region]
+    })
 
+    prediction = model.predict(input_data)
     # While the prediction is made, log both the inputs and outputs to a  log file
-    data_point = pd.DataFrame([sample])
-    prediction = insurance_charge_predictor.predict(data_point).tolist()
     # While writing to the log file, ensure that the commit scheduler is locked to avoid parallel
     # access
     with scheduler.lock:
@@ -75,16 +75,24 @@ def insurance_charge_predictor(age, bmi, children, sex, smoker, region, type):
     return prediction[0]
 
 # Set up UI components for input and output
-demo = gr.Interface(
-    fn=Predict_Insurance_Charge,
-    inputs=[age_input, bmi_input, children_input, sex_input, smoker_input, region_input],
-    outputs=model_output,
 # Create the gradio interface, make title "HealthyLife Insurance Charge Prediction"
-    title="HealthyLife Insurance Charge Prediction",
-    description="This API allows you to predict optimal insurance charges for customers",
-    allow_flagging="auto",
-    concurrency_limit=8
-)
+  with gr.Blocks(title="HealthyLife Insurance Charge Prediction") as demo:
+    status = gr.State(["none"])
+    with gr.Row():
+        with gr.Column():
+            region = gr.Dropdown(choices=["northeast", "northwest", "southeast", "southwest"], label="Region")
+            sex = gr.Radio(choices=["male", "female"], label="Sex")
+            smoker = gr.Radio(choices=["yes", "no"], label="Smoker")
+            age = gr.Slider(minimum=18, maximum=100, value=25, label="Age", step=1)
+            bmi = gr.Slider(minimum=10, maximum=50, value=25, label="BMI")
+            children = gr.Slider(minimum=0, maximum=10, value=0, label="Children", step=1)
+
+        with gr.Column():
+            output = gr.Number(label="Predicted Insurance Charge")
+            predict_btn = gr.Button("Submit")
+
+            predict_btn.click(predict_charges, inputs=[age, sex, bmi, children, smoker, region], outputs=output)
+
 # Launch with a load balancer
 demo.queue()
-demo.launch(share=False)
+demo.launch(share=True, show_error=True)

model.joblib

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e86925f6e1316a2a1a54e48362efd01b134efba34c8249a5b33488539321dbf4
-size 3654
+oid sha256:8aa4571e72863112ad036c9d864d5227d4821da21f1044fac06c0a1b983fc4cd
+size 4526

train.py

@@ -0,0 +1,54 @@
+# Import libraries
+import pandas as pd
+import joblib 
+
+from sklearn.preprocessing import StandardScaler, OneHotEncoder
+from sklearn.compose import make_column_transformer
+from sklearn.compose import ColumnTransformer
+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
+
+# Read the data
+data_df = pd.read_csv("insurance.csv")
+# Process the data
+data_df = data_df.drop(columns=['index'])
+
+X = data_df.drop(columns='charges')
+y = data_df['charges']
+
+categorical_features = X.select_dtypes(include=['object']).columns
+numeric_features = X.select_dtypes(include=['number']).columns
+
+print("Creating data subsets")
+
+preprocessor = make_column_transformer(
+    (StandardScaler(), numeric_features),
+    (OneHotEncoder(handle_unknown='ignore'), categorical_features)
+)
+
+Xtrain, Xtest, ytrain, ytest = train_test_split(
+    X, y,
+    test_size=0.2,
+    random_state=42
+)
+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)