eval script

Jenkinsfile.eval

@@ -0,0 +1,14 @@
+pipeline {
+    stages {
+        stage('Copy') {
+            steps {
+                sh 'python3 evalScript.py'
+            }
+        }
+    }
+    post {
+        always {
+            emailext body: "${currentBuild.currentResult}", subject: 's444417-evaluation build status', to: 'e19191c5.uam.onmicrosoft.com@emea.teams.ms'
+        }
+    }
+}

README.md

@@ -4,8 +4,8 @@ IUM_6
 Zadanie 1
 1. stworzono job [s444417-training](https://tzietkiewicz.vm.wmi.amu.edu.pl:8080/job/s444417-training/)
 2. s444417-training uruchamia się automatycznie po zakończeniu joba s444417-create-dataset, plik "Jenkinsfile", przy pomocy build job. Kopiuje zbiór danych przy pomocy copyArtifact w pliku "Jenkinsfile3"
-3. "Jenkinsfile3" archiveArtifacts linia 12
-4. Powiadomienia, "Jenkinsfile3" linia 11
+3. "Jenkinsfile3" przy pomocy archiveArtifacts
+4. Powiadomienia, "Jenkinsfile3" przy pomocy emailext
 5. Parametr podany jest w pliku "startscript1.sh" w linii 11, przy wołaniu skryptu uruchamiającego uczenie "startscript2.sh", parametr oznacza ilość epok
 
 Zadanie 2

result.txt

@@ -1,2 +1,2 @@
-predictions: [84.40604, 472.22028, 106.96647, 141.08197, 105.62965, 55.602768, 107.484055, 185.62663, 48.709442, 86.00946]
-expected: [190.  330.   78.   54.4  39.   69.   48.  200.  100.   85. ]
+predictions: [166.16302, 211.04045, 123.3409, 42.00785, 87.86473, 109.27005, 169.75987, 173.21875, 232.33553, 142.31973]
+expected: [ 80.   42.   64.   72.   14.   97.4  75.  200.  140.   61. ]

saved_model/MyModel_tf/keras_metadata.pb

@@ -2,4 +2,4 @@
 ëroot"_tf_keras_sequential*Æ{"name": "sequential", "trainable": true, "expects_training_arg": true, "dtype": "float32", "batch_input_shape": null, "must_restore_from_config": false, "class_name": "Sequential", "config": {"name": "sequential", "layers": [{"class_name": "InputLayer", "config": {"batch_input_shape": {"class_name": "__tuple__", "items": [null, null]}, "dtype": "float32", "sparse": false, "ragged": false, "name": "normalization_input"}}, {"class_name": "Normalization", "config": {"name": "normalization", "trainable": true, "batch_input_shape": {"class_name": "__tuple__", "items": [null, null]}, "dtype": "float32", "axis": {"class_name": "__tuple__", "items": [-1]}, "mean": null, "variance": null}}, {"class_name": "Dense", "config": {"name": "dense", "trainable": true, "dtype": "float32", "units": 1, "activation": "linear", "use_bias": true, "kernel_initializer": {"class_name": "GlorotUniform", "config": {"seed": null}}, "bias_initializer": {"class_name": "Zeros", "config": {}}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}}]}, "shared_object_id": 5, "input_spec": [{"class_name": "InputSpec", "config": {"dtype": null, "shape": {"class_name": "__tuple__", "items": [null, null]}, "ndim": 2, "max_ndim": null, "min_ndim": null, "axes": {}}}], "build_input_shape": {"class_name": "TensorShape", "items": [null, null]}, "is_graph_network": true, "full_save_spec": {"class_name": "__tuple__", "items": [[{"class_name": "TypeSpec", "type_spec": "tf.TensorSpec", "serialized": [{"class_name": "TensorShape", "items": [null, null]}, "float32", "normalization_input"]}], {}]}, "save_spec": {"class_name": "TypeSpec", "type_spec": "tf.TensorSpec", "serialized": [{"class_name": "TensorShape", "items": [null, null]}, "float32", "normalization_input"]}, "keras_version": "2.8.0", "backend": "tensorflow", "model_config": {"class_name": "Sequential", "config": {"name": "sequential", "layers": [{"class_name": "InputLayer", "config": {"batch_input_shape": {"class_name": "__tuple__", "items": [null, null]}, "dtype": "float32", "sparse": false, "ragged": false, "name": "normalization_input"}, "shared_object_id": 0}, {"class_name": "Normalization", "config": {"name": "normalization", "trainable": true, "batch_input_shape": {"class_name": "__tuple__", "items": [null, null]}, "dtype": "float32", "axis": {"class_name": "__tuple__", "items": [-1]}, "mean": null, "variance": null}, "shared_object_id": 1}, {"class_name": "Dense", "config": {"name": "dense", "trainable": true, "dtype": "float32", "units": 1, "activation": "linear", "use_bias": true, "kernel_initializer": {"class_name": "GlorotUniform", "config": {"seed": null}, "shared_object_id": 2}, "bias_initializer": {"class_name": "Zeros", "config": {}, "shared_object_id": 3}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}, "shared_object_id": 4}]}}, "training_config": {"loss": {"class_name": "MeanSquaredError", "config": {"reduction": "auto", "name": "mean_squared_error"}, "shared_object_id": 7}, "metrics": null, "weighted_metrics": null, "loss_weights": null, "optimizer_config": {"class_name": "Adam", "config": {"name": "Adam", "learning_rate": 1, "decay": 0.0, "beta_1": 0.8999999761581421, "beta_2": 0.9990000128746033, "epsilon": 1e-07, "amsgrad": false}}}}2

 û
root.layer_with_weights-0"_tf_keras_layer*Ä{"name": "normalization", "trainable": true, "expects_training_arg": false, "dtype": "float32", "batch_input_shape": {"class_name": "__tuple__", "items": [null, null]}, "stateful": false, "must_restore_from_config": true, "class_name": "Normalization", "config": {"name": "normalization", "trainable": true, "batch_input_shape": {"class_name": "__tuple__", "items": [null, null]}, "dtype": "float32", "axis": {"class_name": "__tuple__", "items": [-1]}, "mean": null, "variance": null}, "shared_object_id": 1, "build_input_shape": {"class_name": "TensorShape", "items": [null, 8]}}2

 ¿root.layer_with_weights-1"_tf_keras_layer*ˆ{"name": "dense", "trainable": true, "expects_training_arg": false, "dtype": "float32", "batch_input_shape": null, "stateful": false, "must_restore_from_config": false, "class_name": "Dense", "config": {"name": "dense", "trainable": true, "dtype": "float32", "units": 1, "activation": "linear", "use_bias": true, "kernel_initializer": {"class_name": "GlorotUniform", "config": {"seed": null}, "shared_object_id": 2}, "bias_initializer": {"class_name": "Zeros", "config": {}, "shared_object_id": 3}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}, "shared_object_id": 4, "input_spec": {"class_name": "InputSpec", "config": {"dtype": null, "shape": null, "ndim": null, "max_ndim": null, "min_ndim": 2, "axes": {"-1": 8}}, "shared_object_id": 8}, "build_input_shape": {"class_name": "TensorShape", "items": [null, 8]}}2

-¸
-root.keras_api.metrics.0"_tf_keras_metric*<2A>
{"class_name": "Mean", "name": "loss", "dtype": "float32", "config": {"name": "loss", "dtype": "float32"}, "shared_object_id": 9}2

+¸
0root.keras_api.metrics.0"_tf_keras_metric*<2A>
{"class_name": "Mean", "name": "loss", "dtype": "float32", "config": {"name": "loss", "dtype": "float32"}, "shared_object_id": 9}2

src/evalScript.py

@@ -0,0 +1,42 @@
+import os
+import sys
+import pandas as pd
+import tensorflow as tf
+
+cwd = os.path.abspath(os.path.dirname(sys.argv[0]))
+modelPath = 'saved_model/MyModel_tf'
+pathTrain = cwd + "/../Participants_Data_HPP/Train.csv"
+pathTest = cwd + "/../Participants_Data_HPP/Test.csv"
+
+features = ["UNDER_CONSTRUCTION", "RERA", "BHK_NO.", "SQUARE_FT", "READY_TO_MOVE", "RESALE", "LONGITUDE", "LATITUDE", "TARGET(PRICE_IN_LACS)"]
+
+# get dataset
+house_price_train = pd.read_csv(pathTrain)[features]
+
+# get test dataset
+house_price_test = pd.read_csv(pathTest)[features]
+
+house_price_test_features = house_price_test.copy()
+# pop column
+house_price_test_expected = house_price_test_features.pop('TARGET(PRICE_IN_LACS)')
+
+# load model
+new_model = tf.keras.models.load_model(modelPath)
+
+# Check its architecture
+# new_model.summary()
+
+# Evaluate the restored model
+loss = new_model.evaluate(house_price_test_features, house_price_test_expected, verbose=2)
+print(loss)
+#print('Restored model, accuracy: {:5.2f}%'.format(100 * acc))
+
+count = 0
+try: 
+    with open('trainResults.csv', 'r') as trainResults:
+        count = sum(1 for _ in trainResults)
+except:
+    pass
+
+with open('trainResults.csv', 'a+') as trainResults:
+  trainResults.write(f"{count},{loss}" + "\n")

src/trainScript.py

@@ -45,26 +45,39 @@ house_price_test_expected = house_price_test_features.pop('TARGET(PRICE_IN_LACS)
 house_price_features = np.array(house_price_features)
 
 # checkoints
-checkpoint_path = "training_1/cp.ckpt"
-checkpoint_dir = os.path.dirname(checkpoint_path)
+# checkpoint_path = "training_1/cp.ckpt"
+# checkpoint_dir = os.path.dirname(checkpoint_path)
 # Create a callback that saves the model's weights
 # cp_callback = tf.keras.callbacks.ModelCheckpoint(filepath=checkpoint_path, save_weights_only=True, verbose=1)
 # model keras.Sequential
 # one output tensor
-linear_model = tf.keras.Sequential([
-  normalize,
-  layers.Dense(1)
-])
-linear_model.compile(loss = tf.losses.MeanSquaredError(),
-                      optimizer = tf.optimizers.Adam(1))
+
+modelPath = 'saved_model/MyModel_tf'
+try: 
+  linear_model = tf.keras.models.load_model(modelPath)
+  print("open existing model")
+except Exception as ex:
+  print(ex)
+  linear_model = tf.keras.Sequential([
+    normalize,
+    layers.Dense(1)
+  ])
+  linear_model.compile(loss = tf.losses.MeanSquaredError(),
+                        optimizer = tf.optimizers.Adam(1))
+  print("creating new model")
 
 # train model
-history = linear_model.fit(house_price_features, house_price_labels, epochs=int(numberOfEpoch), )
+history = linear_model.fit(
+  house_price_features, 
+  house_price_labels, 
+  epochs=int(numberOfEpoch), 
+  validation_data = (house_price_test_features,house_price_test_expected),
+  verbose=1)
 #callbacks=[cp_callback])
 # print(history)
 
 # save model
-linear_model.save('saved_model/my_model')
+linear_model.save(modelPath, save_format='tf')
 
 test_results = {}
 test_results['linear_model'] = linear_model.evaluate(
@@ -82,4 +95,3 @@ flatten_pred = flatten(pred)
 with open(cwd + "/../result.txt", "w+") as resultFile:
   resultFile.write("predictions: " + str(flatten_pred) + '\n')
   resultFile.write("expected: " + str(labels_test_sample.to_numpy()))
-

trainResults.csv

@@ -0,0 +1,5 @@
+0,306900.46875
+1,304823.75
+2,298283.34375
+3,303093.53125
+4,304189.1875