s434704/ium_434704
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Run training

Browse Source
This commit is contained in:
Wojciech Jarmosz 2021-05-14 00:58:33 +02:00
parent 999da6af32
commit b73ac931cb
3 changed files with 11 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
Jenkinsfile vendored
View File

@ -10,11 +10,13 @@ stages {
steps {
withEnv(["KAGGLE_USERNAME=${params.KAGGLE_USERNAME}",
"KAGGLE_KEY=${params.KAGGLE_KEY}", "CUTOFF=${params.CUTOFF}" ]) {
// Skrypt z lab 5 - prosta sieć neuronowa
sh 'python3 linear_regression.py'
// Wygenerowanie podziału danych
sh 'python3 script.py'
// Uruchomienie skryptu
sh "chmod 777 ./data_download.sh"
sh "./data_download.sh"
// Stare skrypty bashowe do podziału zbioru
// sh "chmod 777 ./data_download.sh"
// sh "./data_download.sh"
// Zapisanie artefaktów
archiveArtifacts "MoviesOnStreamingPlatforms_updated.dev"
archiveArtifacts "MoviesOnStreamingPlatforms_updated.test"

6
script.py
View File

@ -34,7 +34,11 @@ test_ratio = 0.1
film_train, film_test = train_test_split(film_data, test_size=1 - train_ratio)
film_valid, film_test = train_test_split(film_test, test_size=test_ratio/(test_ratio + validation_ratio))
film_valid, film_test = train_test_split(film_test, test_size=test_ratio/(test_ratio + validation_ratio))
pd.to_csv(film_train, 'MoviesOnStreamingPlatforms_updated.train')
pd.to_csv(film_test, 'MoviesOnStreamingPlatforms_updated.test')
pd.to_csv(film_valid, 'MoviesOnStreamingPlatforms_updated.valid')
# Statystki głównego zbioru i podzbiorów
for i, data_set in enumerate([film_data, film_train, film_valid, film_test]):

6
training.py
View File

@ -9,17 +9,13 @@ from tensorflow.keras.layers.experimental import preprocessing
pd.set_option("display.max_columns", None)
cols = ['0','ID','Title','Year','Age','IMDb','Rotten Tomatoes','Netflix','Hulu','Prime Video','Disney+','Type','Directors','Genres','Country','Language','Runtime']
# Wczytanie danych
train_data = pd.read_csv("./MoviesOnStreamingPlatforms_updated.train", header=None, usecols=cols)
train_data = pd.read_csv("./MoviesOnStreamingPlatforms_updated.train")
# Stworzenie modelu
columns_to_use = ['Year', 'Runtime', 'Netflix']
train_X = tf.convert_to_tensor(train_data[columns_to_use])
train_Y = tf.convert_to_tensor(train_data[["IMDb"]])
test_X = tf.convert_to_tensor(test_data[columns_to_use])
test_Y = tf.convert_to_tensor(test_data[["IMDb"]])
normalizer = preprocessing.Normalization(input_shape=[3,])
normalizer.adapt(train_X)