mlflow task added

MLproject

@@ -0,0 +1,11 @@
+name: 434742-mlflow
+
+docker_env:
+    image: patlaz/ium:1.0
+
+entry_points:
+    main:
+        parameters:
+            epochs: {type: int, default: 10}
+            batch_size: {type: int, default: 16}
+        command: "python3 avocado-mlflow.py {epochs} {batch_size}"

avocado-mlflow.py

@@ -0,0 +1,71 @@
+import sys
+from keras.backend import batch_dot, mean
+import pandas as pd
+import numpy as np
+from six import int2byte
+from sklearn import preprocessing
+from sklearn.linear_model import LinearRegression
+from sklearn.metrics import mean_squared_error
+import tensorflow as tf
+from tensorflow import keras
+from tensorflow.keras.layers import Input, Dense, Activation,Dropout
+from tensorflow.keras.models import Model
+from tensorflow.keras.callbacks import EarlyStopping
+from keras.models import Sequential
+import mlflow 
+
+
+
+def my_main(epochs, batch_size):
+
+    # odczytanie danych z plików
+    avocado_train = pd.read_csv('avocado_train.csv')
+    avocado_test = pd.read_csv('avocado_test.csv')
+    avocado_validate = pd.read_csv('avocado_validate.csv')
+
+
+    # podzial na X i y
+    X_train = avocado_train[['average_price', 'total_volume', '4046', '4225', '4770', 'total_bags', 'small_bags', 'large_bags', 'xlarge_bags']]
+    y_train = avocado_train[['type']]
+    X_test = avocado_test[['average_price', 'total_volume', '4046', '4225', '4770', 'total_bags', 'small_bags', 'large_bags', 'xlarge_bags']]
+    y_test = avocado_test[['type']]
+
+    print(X_train.shape[1])
+    # keras model
+    model = Sequential()
+    model.add(Dense(9, input_dim = X_train.shape[1], kernel_initializer='normal', activation='relu'))
+    model.add(Dense(1,kernel_initializer='normal', activation='sigmoid'))
+
+    early_stop = EarlyStopping(monitor="val_loss", mode="min", verbose=1, patience=10)
+
+    # kompilacja
+    model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
+
+    # trenowanie modelu
+    model.fit(X_train, y_train, epochs=epochs, batch_size=batch_size, validation_data=(X_test, y_test))
+
+    # predykcja
+    prediction = model.predict(X_test)
+
+    # ewaluacja
+    rmse = mean_squared_error(y_test, prediction)
+
+    # zapisanie modelu
+    model.save('avocado_model.h5')
+
+    return rmse, 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():
+        
+    rmse, model = my_main(epochs, batch_size)
+
+    mlflow.log_param("epochs", epochs)
+    mlflow.log_param("batch_size", batch_size)
+    mlflow.log_metric("rmse", rmse) 
+    mlflow.keras.log_model(model, 'avocado_model.h5')

requirements.txt

@@ -6,4 +6,5 @@ numpy==1.19.5
 kaggle==1.5.12
 keras==2.4.3
 scikit_learn==0.24.2
-pymongo
+pymongo
+mlflow