Sync App files

drug_app.py

@@ -0,0 +1,60 @@
+import gradio as gr
+import skops.io as sio
+
+pipe = sio.load("./Model/drug_pipeline.skops", trusted=True)
+
+
+def predict_drug(age, sex, blood_pressure, cholesterol, na_to_k_ratio):
+    """Predict drugs based on patient features.
+
+    Args:
+        age (int): Age of patient
+        sex (str): Sex of patient 
+        blood_pressure (str): Blood pressure level
+        cholesterol (str): Cholesterol level
+        na_to_k_ratio (float): Ratio of sodium to potassium in blood
+
+    Returns:
+        str: Predicted drug label"""
+
+    features = [age, sex, blood_pressure, cholesterol, na_to_k_ratio]
+    predicted_drug = pipe.predict([features])[0]
+
+    label = f"Predicted Drug: {predicted_drug}"
+    return label
+
+
+inputs = [
+    gr.Slider(15, 74, step=1, label="Age"),
+    gr.Radio(["M", "F"], label="Sex"),
+    gr.Radio(["HIGH", "LOW", "NORMAL"], label="Blood Pressure"),
+    gr.Radio(["HIGH", "NORMAL"], label="Cholesterol"),
+    gr.Slider(6.2, 38.2, step=0.1, label="Na_to_K"),
+]
+outputs = [gr.Label(num_top_classes=5)]
+
+examples = [
+    [30, "M", "HIGH", "NORMAL", 15.4],
+    [35, "F", "LOW", "NORMAL", 8],
+    [50, "M", "HIGH", "HIGH", 34],
+]
+
+
+title = "Drug Classification"
+description = "Enter the details to correctly identify Drug type?"
+article = "This app is a part of the Beginner's Guide to CI/CD for Machine Learning. It teaches how to automate training, evaluation, and deployment of models to Hugging Face using GitHub Actions."
+
+
+gr.Interface(
+    fn=predict_drug,
+    inputs=inputs,
+    outputs=outputs,
+    examples=examples,
+    title=title,
+    description=description,
+    article=article,
+    theme=gr.themes.Soft(),
+).launch()
+
+
+# I also want to publish show mlflow results, maybe some logs, maybe auc scores ans stuff

test/test_model.py

@@ -0,0 +1,31 @@
+import pandas as pd
+from sklearn.model_selection import train_test_split
+import skops.io as sio
+from sklearn.metrics import roc_auc_score
+
+class TestModel():
+
+    def __init__(self, df):
+
+        drug_df = pd.read_csv('/Users/muratdemiralay/Downloads/drug200.csv')
+        X = drug_df.drop("Drug", axis=1).values
+        y = drug_df.Drug.values
+        self.X_train, self.X_test, self.y_train, self.y_test = train_test_split(
+        X, y, test_size=0.3, random_state=125)
+
+        self.model = sio.load("Model/drug_pipeline.skops")
+
+    def test_auc(self):
+        
+        preds = self.model.predict_proba(self.X_test)[:,1]
+        auc = roc_auc_score(self.y_test, preds)
+        assert auc > 0.8, "Auc is below acceptable threshold"
+
+    def test_missing_values(self):
+
+        assert self.drug_df.isna().sum().sum() == 0, "Dataset contains missing values"
+
+    def test_pipeline_execution(self):
+
+        assert len(self.X_train) > 0, "Training data is empty!"
+        assert len(self.y_train) > 0, "Labels are empty!"