s

JenkinsfileDL

@@ -5,16 +5,13 @@ pipeline {
             args '-v /root/.cache:/root/.cache -u root'
         }
     }
-    environment {
-        SACRED_IGNORE_GIT = 'TRUE'
-    }
     parameters {
         string(name: 'EPOCHS', defaultValue: '10', description: 'Liczba Epok')
     }
     stages {
-        stage('Przygotowania') {
+        stage('Preparation') {
             steps {
-                sh 'pip install pandas tensorflow scikit-learn imbalanced-learn sacred pymongo mlflow'
+                sh 'pip install pandas tensorflow scikit-learn imbalanced-learn sacred pymongo'
             }
         }
         stage('Pobierz dane') {
@@ -27,17 +24,14 @@ pipeline {
         stage('Trenuj model') {
             steps {
                 script {
-                    sh 'mlflow run . -P epochs=$EPOCHS'
+                    // sh "python3 train.py --epochs $EPOCHS"
+                    sh "python3 train.py"
                 }
             }
         }
         stage('Zarchiwizuj model') {
             steps {
-                sh '''
+                archiveArtifacts artifacts: 'model.h5', fingerprint: true
-                    mkdir -p model
-                    cp -r mlruns/* model/
-                '''
-                archiveArtifacts artifacts: 'model/**', fingerprint: true
             }
         }
     }

train.py

@@ -1,26 +1,22 @@
 from sacred import Experiment
-from sacred.observers import MongoObserver
+from sacred.observers import MongoObserver, FileStorageObserver
 import os
-import mlflow
-import mlflow.keras
-from mlflow.models.signature import infer_signature
-from mlflow.models import Model
 
 os.environ["SACRED_NO_GIT"] = "1"
 
 ex = Experiment('s487187-training', interactive=True, save_git_info=False)
 ex.observers.append(MongoObserver(url='mongodb://admin:IUM_2021@172.17.0.1:27017', db_name='sacred'))
 
+
 @ex.config
 def my_config():
     data_file = 'data.csv' 
-    model_file = 'model'
+    model_file = 'model.h5'
     epochs = 10
     batch_size = 32
     test_size = 0.2
     random_state = 42
 
-
 @ex.capture
 def train_model(data_file, model_file, epochs, batch_size, test_size, random_state):
     import pandas as pd
@@ -29,48 +25,45 @@ def train_model(data_file, model_file, epochs, batch_size, test_size, random_sta
     import tensorflow as tf
     from imblearn.over_sampling import SMOTE
 
-    with mlflow.start_run():
+    smote = SMOTE(random_state=random_state)
+    data = pd.read_csv(data_file, sep=';')
 
-        smote = SMOTE(random_state=random_state)
+    print('Total rows:', len(data))
-        data = pd.read_csv(data_file, sep=';')
+    print('Rows with medal:', len(data.dropna(subset=['Medal'])))
 
-        data = pd.get_dummies(data, columns=['Sex', 'Medal'])
+    data = pd.get_dummies(data, columns=['Sex', 'Medal'])
-        data = data.drop(columns=['Name', 'Team', 'NOC', 'Games', 'Year', 'Season', 'City', 'Sport', 'Event'])
+    data = data.drop(columns=['Name', 'Team', 'NOC', 'Games', 'Year', 'Season', 'City', 'Sport', 'Event'])
 
-        scaler = MinMaxScaler()
+    scaler = MinMaxScaler()
-        data = pd.DataFrame(scaler.fit_transform(data), columns=data.columns)
+    data = pd.DataFrame(scaler.fit_transform(data), columns=data.columns)
 
-        X = data.filter(regex='Sex|Age')
+    X = data.filter(regex='Sex|Age')
-        y = data.filter(regex='Medal')
+    y = data.filter(regex='Medal')
-        y = pd.get_dummies(y)
+    y = pd.get_dummies(y)
 
-        X = X.fillna(0)
+    X = X.fillna(0)
-        y = y.fillna(0)
+    y = y.fillna(0)
 
-        y = y.values
+    y = y.values
 
-        X_resampled, y_resampled = smote.fit_resample(X, y)
+    X_resampled, y_resampled = smote.fit_resample(X, y)
-        X_train, X_test, y_train, y_test = train_test_split(X_resampled, y_resampled, test_size=test_size, random_state=random_state)
+    X_train, X_test, y_train, y_test = train_test_split(X_resampled, y_resampled, test_size=test_size, random_state=random_state)
 
-        model = tf.keras.models.Sequential()
+    model = tf.keras.models.Sequential()
-        model.add(tf.keras.layers.Dense(64, input_dim=X_train.shape[1], activation='relu')) 
+    model.add(tf.keras.layers.Dense(64, input_dim=X_train.shape[1], activation='relu')) 
-        model.add(tf.keras.layers.Dense(32, activation='relu'))
+    model.add(tf.keras.layers.Dense(32, activation='relu'))
-        model.add(tf.keras.layers.Dense(y.shape[1], activation='softmax')) 
+    model.add(tf.keras.layers.Dense(y.shape[1], activation='softmax')) 
 
-        model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
+    model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
 
-        model.fit(X_train, y_train, epochs=epochs, batch_size=batch_size)
+    model.fit(X_train, y_train, epochs=epochs, batch_size=batch_size)
-        loss, accuracy = model.evaluate(X_test, y_test)
+    loss, accuracy = model.evaluate(X_test, y_test)
+    print('Test accuracy:', accuracy)
+    print('Test loss:', loss)
 
-        mlflow.log_metric("loss", loss)
+    model.save(model_file)
-        mlflow.log_metric("accuracy", accuracy)
 
-        signature = infer_signature(X_train, model.predict(X_train))
+    return accuracy  
-        input_example = Model.log_input_example(X_train.iloc[0])
-
-        mlflow.keras.log_model(model, model_file, signature=signature, input_example=input_example)
-
-        return accuracy  
 
 @ex.main
 def run_experiment():