evaluate

Jenkins/Jenkinsfile.training

@@ -17,7 +17,6 @@ node {
         stage('Copy artifacts') {
             copyArtifacts filter: 'train_data.csv', fingerprintArtifacts: true, projectName: 's444452-create-dataset'
             copyArtifacts filter: 'test_data.csv', fingerprintArtifacts: true, projectName: 's444452-create-dataset'
-            copyArtifacts filter: 'dev_data.csv', fingerprintArtifacts: true, projectName: 's444452-create-dataset'
         }
         stage('Run script') {
             withEnv(["TRAIN_PARAMS=${params.TRAIN_PARAMS}"]) {
@@ -25,7 +24,7 @@ node {
             }
         }
         stage('Archive artifacts') {
-            archiveArtifacts "neural_network_evaluation.txt, model/**"
+            archiveArtifacts "model/**"
         }
         }
     } catch (e) {

Scripts/train_neural_network.py

@@ -1,14 +1,12 @@
 #!/usr/bin/python
 import datetime
 import os
-import pprint
 import sys
 import pandas as pd
-from keras.models import Sequential, load_model
+from keras.models import Sequential
 from keras import layers
 from keras.preprocessing.text import Tokenizer
 from keras.preprocessing.sequence import pad_sequences
-from sklearn.metrics import precision_score, recall_score, f1_score, accuracy_score
 import logging
 
 logging.getLogger("tensorflow").setLevel(logging.ERROR)
@@ -20,32 +18,14 @@ batch_size = 0
 pad_length = 0
 
 
-def tokenize(x, x_train, x_test):
+def tokenize(x, x_train):
     global pad_length, num_words
     tokenizer = Tokenizer(num_words=num_words)
     tokenizer.fit_on_texts(x)
     train_x = tokenizer.texts_to_sequences(x_train)
-    test_x = tokenizer.texts_to_sequences(x_test)
     vocabulary_length = len(tokenizer.word_index) + 1
-
     train_x = pad_sequences(train_x, padding='post', maxlen=pad_length)
-    test_x = pad_sequences(test_x, padding='post', maxlen=pad_length)
-    return train_x, test_x, vocabulary_length
-
-
-def evaluate_and_save(model, x, y, abs_path):
-    loss, accuracy = model.evaluate(x, y, verbose=False)
-    y_predicted = (model.predict(x) >= 0.5).astype(int)
-    with open(os.path.join(abs_path, 'neural_network_evaluation.txt'), "w") as log_file:
-        for obj in (
-                ('Accuracy: ', accuracy), ('Loss: ', loss), ('Precision: ', precision_score(y, y_predicted)),
-                ('Recall: ', recall_score(y, y_predicted)), ('F1: ', f1_score(y, y_predicted)),
-                ('Accuracy: ', accuracy_score(y, y_predicted))):
-            pprint.pprint(obj, log_file)
-
-
-def load_trained_model(abs_path, model_name):
-    return load_model(os.path.join(abs_path, model_name))
+    return train_x, vocabulary_length
 
 
 def save_model(model):
@@ -99,12 +79,11 @@ def main():
     train_data = load_data(abs_data_path, 'train_data.csv')
     test_data = load_data(abs_data_path, 'test_data.csv')
     x_train, y_train = split_data(train_data)
-    x_test, y_test = split_data(test_data)
-    x_train, x_test, vocab_size = tokenize(pd.concat([x_train, x_test]), x_train, x_test)
+    x_test, _ = split_data(test_data)
+    x_train, vocab_size = tokenize(pd.concat([x_train, x_test]), x_train)
     model = get_model(vocab_size)
     train_model(model, x_train, y_train)
     save_model(model)
-    evaluate_and_save(model, x_test, y_test, abs_data_path)
 
 
 if __name__ == '__main__':