Upload 4 files

app.py

@@ -0,0 +1,87 @@
+# Import the libraries
+import gradio as gr
+import joblib
+import pandas as pd
+
+# 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
+model = 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_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
+def predict_insu_charges(age, bmi, children, sex, smoker, region):
+    sample = {
+        'Age': age,
+        'bmi' : bmi,
+        'children' : children,
+        'sex' : sex,
+        'smoker' : smoker,
+        'region' : region
+    }
+    data_point = pd.DataFrame([sample])
+    result = model.predict(data_point)
+    print(result)
+    return result 
+
+# 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
+
+    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
+age_input = gr.number(label="Age")
+bmi_input = gr.number(label="BMI")
+children_input = gr.number(label="Number of children")
+sex_input = gr.Dropdown(['Female','Male'],label="Age")
+smoker_input = gr.Dropdown(['Yes','No'],label="smoker?")
+region_input = gr.Dropdown(['SouthWest','NorthWest','SouthEast','NorthEast'],label="Age")
+                      
+model_output = gr.Label(label="charges")
+
+# Create the gradio interface, make title "HealthyLife Insurance Charge Prediction"
+demo = gr.Interface(fn=predict_insu_charges,
+                    inputs = ['age_input', 'bmi_input','children_input','sex_input','smoker_input','region_input'],
+                    outputs = model_output, 
+                    title = "HealthyLife Insurance Charge Prediction",
+                    description = "For predicting insurance charges",
+                    allow_flagging = "auto")
+
+interface.launch(share=True)
+
+# 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:e9341658ee84e297a6b15c9262019ebe8a2dc3679a326700703f5a6116b9958d
+size 4887

requirements.txt

@@ -0,0 +1,2 @@
+scikit-learn=1.5.0
+overwriting requirements.txt

train.py

@@ -0,0 +1,68 @@
+import numpy as np
+import pandas as pd
+import seaborn as sns
+import joblib
+import matplotlib.pyplot as plt
+from sklearn.model_selection import train_test_split, RandomizedSearchCV
+from sklearn.metrics import classification_report
+from sklearn.metrics import mean_squared_error
+from sklearn.preprocessing import OneHotEncoder
+from sklearn.compose import make_column_transformer
+from sklearn.preprocessing import StandardScaler
+from sklearn.linear_model import LinearRegression
+from sklearn.pipeline import make_pipeline
+from sklearn.pipeline import Pipeline
+from sklearn.impute import SimpleImputer
+from sklearn.preprocessing import StandardScaler
+from sklearn.compose import ColumnTransformer
+from sklearn.metrics import mean_squared_error, r2_score
+
+data = pd.read_csv("/Users/debjanighosh/insurance.csv")
+
+target = 'charges'
+
+numerical_features = ['age', 'bmi','children']
+categorical_features = ['sex','smoker','region']
+
+print("Creating data subsets")
+
+X = data[numerical_features + categorical_features]
+y = data[target]
+
+Xtrain, Xtest, ytrain, ytest = train_test_split(
+    X,y,
+    test_size=0.2,
+    random_state=42
+)
+
+numerical_pipeline = Pipeline([
+    ('imputer',SimpleImputer(strategy='median')),
+    ('scaler',StandardScaler())
+])  
+
+categorical_pipeline = Pipeline([
+    ('imputer',SimpleImputer(strategy='most_frequent')),
+    ('onehot',OneHotEncoder(handle_unknown='ignore'))
+])  
+
+preprocessor = make_column_transformer(
+    (numerical_pipeline, numerical_features),
+    (categorical_pipeline, categorical_features)
+)
+
+model_linear_regression = LinearRegression()
+
+print ("Estimating Best Model Pipeline")
+
+model_pipeline = make_pipeline(
+    preprocessor,
+    model_linear_regression
+)
+
+model_pipeline.fit(Xtrain, ytrain)
+print("Logging Metrics")
+print(f"R2 Score:{r2_score(ytest, model_pipeline.predict(Xtest))}")
+print("Serializing Model")
+saved_model_path = "model.joblib"
+
+joblib.dump(model_pipeline, saved_model_path)