mlflow

MLProject

@@ -0,0 +1,11 @@
+name: 437622-mlflow
+
+docker_env:
+    image: jpogodzinski/ium:1
+
+entry_points:
+    main:
+        parameters:
+            epochs: {type: int, default: 15}
+            batch_size: {type: int, default: 16}
+        command: "python3 zad8-mlflow.py {epochs} {batch_size}"

evaluation.txt

@@ -1,3 +1,4 @@
 0.5406397482957525
 0.5406397482957525
 0.5406397482957525
+0.5406397482957525

zad5.py

@@ -29,7 +29,7 @@ model.add(layers.Dense(5, activation="relu", name="layer4"))
 model.add(layers.Dense(1, activation="relu", name="output"))
 
 model.compile(
-    optimizer=keras.optimizers.RMSprop(),
+    optimizer=keras.optimizers.Adam(),
     loss=keras.losses.MeanSquaredError(),
     )
 

zad7-sacred-mongo.py

@@ -0,0 +1,75 @@
+from sacred import Experiment
+from sacred.observers import MongoObserver
+import pandas as pd
+import numpy as np
+from tensorflow import keras
+from sklearn.metrics import accuracy_score
+from tensorflow.keras import layers
+
+
+ex = Experiment("437622-mongo", interactive=False, save_git_info=False)
+#ex.observers.append(MongoObserver(url='mongodb://mongo_user:mongo_password_IUM_2021@172.17.0.1:27017', db_name='sacred'))
+
+@ex.config
+def my_config():
+    epochs = 15
+    batch_size = 16
+
+@ex.capture
+def prepare_model(epochs, batch_size, _run):
+    model_name = "model"
+    train = pd.read_csv('train.csv', header=None, skiprows=1)
+    indexNames = train[train[1] == 2].index
+    train.drop(indexNames, inplace=True)
+    cols = [0, 2, 3]
+    X = train[cols].to_numpy()
+    y = train[1].to_numpy()
+    X = np.asarray(X).astype('float32')
+
+    model = keras.Sequential(name="winner")
+    model.add(keras.Input(shape=(3), name="game_info"))
+    model.add(layers.Dense(4, activation="relu", name="layer1"))
+    model.add(layers.Dense(8, activation="relu", name="layer2"))
+    model.add(layers.Dense(8, activation="relu", name="layer3"))
+    model.add(layers.Dense(5, activation="relu", name="layer4"))
+    model.add(layers.Dense(1, activation="relu", name="output"))
+
+    model.compile(
+        optimizer=keras.optimizers.RMSprop(),
+        loss=keras.losses.MeanSquaredError(),
+    )
+
+    history = model.fit(
+        X,
+        y,
+        batch_size=batch_size,
+        epochs=epochs, )
+
+    model.save(model_name)
+
+    test = pd.read_csv('test.csv', header=None, skiprows=1)
+    cols = [0, 2, 3]
+    indexNames = test[test[1] == 2].index
+    test.drop(indexNames, inplace=True)
+    X_test = test[cols].to_numpy()
+    y_test = test[1].to_numpy()
+    X_test = np.asarray(X_test).astype('float32')
+
+    predictions = model.predict(X_test)
+    pd.DataFrame(predictions).to_csv('results.csv', sep='\t', index=False, header=False)
+
+
+    acc = accuracy_score(y_test, predictions)
+    print('Accuracy: ', acc)
+    return acc
+
+@ex.automain
+def my_main(epochs, batch_size):
+    print(prepare_model())
+
+ex.run()
+ex.add_artifact('model')
+
+
+
+

zad8-mlflow.py

@@ -0,0 +1,64 @@
+import sys
+import pandas as pd
+import numpy as np
+from tensorflow import keras
+from sklearn.metrics import accuracy_score
+from tensorflow.keras import layers
+import mlflow
+
+def train(epochs, batch_size):
+    model_name = "model"
+    train = pd.read_csv('train.csv', header=None, skiprows=1)
+    indexNames = train[train[1] == 2].index
+    train.drop(indexNames, inplace=True)
+    cols = [0, 2, 3]
+    X = train[cols].to_numpy()
+    y = train[1].to_numpy()
+    X = np.asarray(X).astype('float32')
+
+    model = keras.Sequential(name="winner")
+    model.add(keras.Input(shape=(3), name="game_info"))
+    model.add(layers.Dense(4, activation="relu", name="layer1"))
+    model.add(layers.Dense(8, activation="relu", name="layer2"))
+    model.add(layers.Dense(8, activation="relu", name="layer3"))
+    model.add(layers.Dense(5, activation="relu", name="layer4"))
+    model.add(layers.Dense(1, activation="relu", name="output"))
+
+    model.compile(
+        optimizer=keras.optimizers.Adam(),
+        loss=keras.losses.MeanSquaredError(),
+    )
+
+    history = model.fit(
+        X,
+        y,
+        batch_size=batch_size,
+        epochs=epochs, )
+
+    model.save(model_name)
+
+    test = pd.read_csv('test.csv', header=None, skiprows=1)
+    cols = [0, 2, 3]
+    indexNames = test[test[1] == 2].index
+    test.drop(indexNames, inplace=True)
+    X_test = test[cols].to_numpy()
+    y_test = test[1].to_numpy()
+    X_test = np.asarray(X_test).astype('float32')
+
+    predictions = model.predict(X_test)
+    pd.DataFrame(predictions).to_csv('results.csv', sep='\t', index=False, header=False)
+
+    acc = accuracy_score(y_test, predictions)
+    print('Accuracy: ', acc)
+    return acc, model
+
+
+epochs = int(sys.argv[1]) if len(sys.argv) > 1 else 15
+batch_size = int(sys.argv[2]) if len(sys.argv) > 2 else 16
+
+with mlflow.start_run():
+    acc, model = train(epochs, batch_size)
+    mlflow.log_param("epochs", epochs)
+    mlflow.log_param("batch_size", batch_size)
+    mlflow.log_metric("accuracy", acc)
+    mlflow.keras.log_model(model, 'model')