MLFlow

Dockerfile

@@ -12,8 +12,8 @@ WORKDIR app
 ARG EPOCHS
 ENV EPOCHS=${EPOCHS}
 
-COPY ml_training.py ./
+COPY mlflow_training.py ./
 COPY heart_2020_cleaned.csv ./
 
 
-CMD ["python3", "./ml_training.py $EPOCHS"]
+CMD ["python3", "./mlflow_training.py $EPOCHS"]

MLProject

@@ -0,0 +1,12 @@
+name: s444465
+
+docker_env:
+    image: s444465/ium:mlflow
+
+entry_points:
+    main:
+        parameters:
+            epochs: {type: float, default: 10}
+        command: "python mlflow_training.py {epochs}"
+    test:
+        command: "python mlflow_training.py test"

mlflow_training.py

@@ -0,0 +1,94 @@
+import mlflow
+import numpy as np
+import pandas as pd
+import tensorflow as tf
+from sklearn.metrics import accuracy_score
+from sklearn.model_selection import train_test_split
+from mlflow.models.signature import infer_signature
+from sklearn.preprocessing import StandardScaler
+import sys
+
+mlflow.set_experiment("s444465")
+
+
+def evaluate_model(model, test_x, test_y):
+    test_loss, test_acc, test_rec = model.evaluate(test_x, test_y, verbose=1)
+    # print("Accuracy:", test_acc)
+    # print("Loss:", test_loss)
+    # print("Recall:", test_rec)
+    return test_acc, test_loss, test_rec
+
+
+def main():
+    no_of_epochs = int(sys.argv[1]) if (len(sys.argv) == 2 and sys.argv[1].isdigit()) else 10
+    is_testing = (len(sys.argv) == 2) and not sys.argv[1].isdigit() and sys.argv[1] == "test"
+
+    mlflow.log_param("epochs", no_of_epochs)
+    scaler = StandardScaler()
+    feature_names = ["BMI", "SleepTime", "Sex", "Diabetic", "PhysicalActivity", "Smoking", "AlcoholDrinking"]
+
+    dataset = pd.read_csv('heart_2020_cleaned.csv')
+    dataset = dataset.dropna()
+
+    dataset["Diabetic"] = dataset["Diabetic"].apply(lambda x: True if "Yes" in x else False)
+    dataset["HeartDisease"] = dataset["HeartDisease"].apply(lambda x: True if x == "Yes" else False)
+    dataset["PhysicalActivity"] = dataset["PhysicalActivity"].apply(lambda x: True if x == "Yes" else False)
+    dataset["Smoking"] = dataset["Smoking"].apply(lambda x: True if x == "Yes" else False)
+    dataset["AlcoholDrinking"] = dataset["AlcoholDrinking"].apply(lambda x: True if x == "Yes" else False)
+    dataset["Sex"] = dataset["Sex"].apply(lambda x: 1 if x == "Female" else 0)
+
+    dataset_train, dataset_test = train_test_split(dataset, test_size=.1, train_size=.9, random_state=1)
+
+    print(dataset_test.shape)
+
+    model = tf.keras.Sequential([
+        tf.keras.layers.Dense(16, activation='relu'),
+        tf.keras.layers.Dense(8, activation='relu'),
+        tf.keras.layers.Dense(4, activation='relu'),
+        tf.keras.layers.Dense(1, activation='sigmoid')
+    ])
+
+    model.compile(
+        loss=tf.keras.losses.binary_crossentropy,
+        optimizer=tf.keras.optimizers.Adam(lr=0.01),
+        metrics=["accuracy", tf.keras.metrics.Recall(name='recall')]
+    )
+
+    train_X = dataset_train[feature_names].astype(np.float32)
+    train_Y = dataset_train["HeartDisease"].astype(np.float32)
+    test_X = dataset_test[feature_names].astype(np.float32)
+    test_Y = dataset_test["HeartDisease"].astype(np.float32)
+
+    train_X = scaler.fit_transform(train_X)
+    # train_Y = scaler.fit_transform(train_Y)
+    test_X = scaler.fit_transform(test_X)
+    # test_Y = scaler.fit_transform(test_Y)
+
+
+    print(train_Y.value_counts())
+
+    train_X = tf.convert_to_tensor(train_X)
+    train_Y = tf.convert_to_tensor(train_Y)
+
+    test_X = tf.convert_to_tensor(test_X)
+    test_Y = tf.convert_to_tensor(test_Y)
+
+    model.fit(train_X, train_Y, epochs=no_of_epochs)
+    model.save("trained_model")
+
+    acc, loss, rec = evaluate_model(model, test_X, test_Y)
+
+    mlflow.log_metric("accuracy", acc)
+    mlflow.log_metric("loss", loss)
+
+    signature = infer_signature(np.array(train_X), np.array(train_Y))
+
+    mlflow.sklearn.log_model(model, "mlflow_model", signature=signature, input_example=np.array(test_X[0]))
+    if is_testing:
+        predictions = model.predict(np.array(test_X))
+        predictions = [int(i > 0.5) for i in predictions]
+        accuracy = accuracy_score(np.array(test_Y), predictions)
+        mlflow.log_metric("eval_accuracy", accuracy)
+
+
+main()