train

Jenkinsfile

@@ -26,7 +26,7 @@ pipeline {
             {
                 steps
                 {
-                    copyArtifacts(fingerprintArtifacts: true, projectName: 's434788-create-dataset', selector: buildParameter('WHICH_BUILD'))
+                    copyArtifacts(fingerprintArtifacts: true, projectName: 's434695-create-dataset', selector: buildParameter('WHICH_BUILD'))
                 }
             }
             stage('train')
@@ -34,14 +34,16 @@ pipeline {
                 steps
                 {
                     catchError {
-                        sh 'python3.8 Zadanie_06_and_07_training.py ${BATCH_SIZE} ${EPOCHS}'
+                        sh 'python3.8 train.py ${BATCH_SIZE} ${EPOCHS}'
+                        sh 'python3.8 sacred1.py ${BATCH_SIZE} ${EPOCHS}'
+                        sh 'python3.8 sacred2.py ${BATCH_SIZE} ${EPOCHS}'
                     }
                 }
             }
 
 		stage('Archive artifacts') {
 			steps{
-				archiveArtifacts 'wine_model.h5'
+				archiveArtifacts 'vgsales_model.h5'
                 archiveArtifacts 'my_runs/**'
 			}
 		}

sacred1.py

@@ -1,12 +1,16 @@
 #! /usr/bin/python3
-from tensorflow.keras.models import Sequential, load_model
+import sys
-from tensorflow.keras.layers import Dense
-from sklearn.metrics import accuracy_score, classification_report
 import pandas as pd
-from sklearn.model_selection import train_test_split
-import wget
 import numpy as np
-import requests
+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 tensorflow.keras.models import Sequential
 from sacred.observers import FileStorageObserver
 from sacred import Experiment
 from datetime import datetime

sacred2.py

@@ -1,12 +1,16 @@
 #! /usr/bin/python3
-from tensorflow.keras.models import Sequential, load_model
+import sys
-from tensorflow.keras.layers import Dense
-from sklearn.metrics import accuracy_score, classification_report
 import pandas as pd
-from sklearn.model_selection import train_test_split
-import wget
 import numpy as np
-import requests
+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 tensorflow.keras.models import Sequential
 from sacred.observers import FileStorageObserver
 from sacred import Experiment
 from datetime import datetime

train.py

@@ -10,39 +10,63 @@ from tensorflow.keras.layers import Input, Dense, Activation,Dropout
 from tensorflow.keras.models import Model
 from tensorflow.keras.callbacks import EarlyStopping
 from tensorflow.keras.models import Sequential
+from sacred import Experiment
+from datetime import datetime
+from sacred.observers import FileStorageObserver
+from sacred.observers import MongoObserver
+import pymongo
 
-# odczytanie danych z plików
+ex = Experiment("434695-mongo", interactive=False, save_git_info=False)
-vgsales_train = pd.read_csv('train.csv')
+ex.observers.append(MongoObserver(url='mongodb://mongo_user:mongo_password_IUM_2021@172.17.0.1:27017', db_name='sacred'))
-vgsales_test = pd.read_csv('test.csv')
+ex.observers.append(FileStorageObserver('my_runs'))
-vgsales_dev = pd.read_csv('dev.csv')
 
-vgsales_train['Nintendo'] = vgsales_train['Publisher'].apply(lambda x: 1 if x=='Nintendo' else 0)
-vgsales_test['Nintendo'] = vgsales_test['Publisher'].apply(lambda x: 1 if x=='Nintendo' else 0)
-vgsales_dev['Nintendo'] = vgsales_dev['Publisher'].apply(lambda x: 1 if x=='Nintendo' else 0)
 
-# podzial na X i y
+@ex.config
-X_train = vgsales_train.drop(['Rank','Name','Platform','Year','Genre','Publisher'],axis = 1)
+def my_config():
-y_train = vgsales_train[['Nintendo']]
+    batch_param = int(sys.argv[1])
-X_test = vgsales_test.drop(['Rank','Name','Platform','Year','Genre','Publisher'],axis = 1)
+    epoch_param = int(sys.argv[2])
-y_test = vgsales_test[['Nintendo']]
 
-print(X_train.shape[1])
+def regression_model(epoch_param, batch_param, _run):
-# keras model
+    _run.info["prepare_model_ts"] = str(datetime.now())
-model = Sequential()
+    # odczytanie danych z plików
-model.add(Dense(9, input_dim = X_train.shape[1], kernel_initializer='normal', activation='relu'))
+    vgsales_train = pd.read_csv('train.csv')
-model.add(Dense(1,kernel_initializer='normal', activation='sigmoid'))
+    vgsales_test = pd.read_csv('test.csv')
+    vgsales_dev = pd.read_csv('dev.csv')
 
-early_stop = EarlyStopping(monitor="val_loss", mode="min", verbose=1, patience=10)
+    vgsales_train['Nintendo'] = vgsales_train['Publisher'].apply(lambda x: 1 if x=='Nintendo' else 0)
+    vgsales_test['Nintendo'] = vgsales_test['Publisher'].apply(lambda x: 1 if x=='Nintendo' else 0)
+    vgsales_dev['Nintendo'] = vgsales_dev['Publisher'].apply(lambda x: 1 if x=='Nintendo' else 0)
 
-# kompilacja
+    # podzial na X i y
-model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
+    X_train = vgsales_train.drop(['Rank','Name','Platform','Year','Genre','Publisher'],axis = 1)
+    y_train = vgsales_train[['Nintendo']]
+    X_test = vgsales_test.drop(['Rank','Name','Platform','Year','Genre','Publisher'],axis = 1)
+    y_test = vgsales_test[['Nintendo']]
 
-# model fit
+    print(X_train.shape[1])
-epochs = int(sys.argv[1])
+    # keras model
-batch_size = int(sys.argv[2])
+    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'))
 
-# trenowanie modelu
+    early_stop = EarlyStopping(monitor="val_loss", mode="min", verbose=1, patience=10)
-model.fit(X_train, y_train, epochs=epochs, batch_size=batch_size, validation_data=(X_test, y_test))
 
-# zapisanie modelu
+    # kompilacja
-model.save('vgsales_model.h5')
+    model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
+
+    # model fit
+    epochs = int(sys.argv[1])
+    batch_size = int(sys.argv[2])
+
+    # trenowanie modelu
+    model.fit(X_train, y_train, epochs=epochs, batch_size=batch_size, validation_data=(X_test, y_test))
+
+    # zapisanie modelu
+    model.save('vgsales_model.h5')
+
+@ex.main
+def my_main(epoch_param, batch_param):
+    print(regression_model())
+
+r = ex.run()
+ex.add_artifact("vgsales_model.h5")