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

Fixes for lab5, lab6
Some checks failed
s434704-training/pipeline/head There was a failure building this commit
Details

Browse Source
This commit is contained in:
Wojciech Jarmosz 2021-05-15 03:50:19 +02:00
parent eab03a1f84
commit 9aa2b7d4ad
3 changed files with 25 additions and 33 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
Jenkinsfile vendored
View File

@ -18,7 +18,7 @@ stages {
// sh "chmod 777 ./data_download.sh" // sh "chmod 777 ./data_download.sh"
// sh "./data_download.sh" // sh "./data_download.sh"
// Zapisanie artefaktów // Zapisanie artefaktów
archiveArtifacts "results.txt" archiveArtifacts "results_lab5.txt"
archiveArtifacts "MoviesOnStreamingPlatforms_updated.dev" archiveArtifacts "MoviesOnStreamingPlatforms_updated.dev"
archiveArtifacts "MoviesOnStreamingPlatforms_updated.test" archiveArtifacts "MoviesOnStreamingPlatforms_updated.test"
archiveArtifacts "MoviesOnStreamingPlatforms_updated.train" archiveArtifacts "MoviesOnStreamingPlatforms_updated.train"

27
linear_regression.py
View File

@ -23,24 +23,19 @@ test_Y = tf.convert_to_tensor(test_data[["IMDb"]])
normalizer = preprocessing.Normalization(input_shape=[3,]) normalizer = preprocessing.Normalization(input_shape=[3,])
normalizer.adapt(train_X) normalizer.adapt(train_X)
if os.path.isdir('linear_regression'): model = keras.Sequential([
model = keras.models.load_model('linear_regression') keras.Input(shape=(len(columns_to_use),)),
else: normalizer,
model = keras.Sequential([ layers.Dense(30, activation='relu'),
keras.Input(shape=(len(columns_to_use),)), layers.Dense(10, activation='relu'),
normalizer, layers.Dense(25, activation='relu'),
layers.Dense(30, activation='relu'), layers.Dense(1)
layers.Dense(10, activation='relu'), ])
layers.Dense(25, activation='relu'),
layers.Dense(1)
])
model.compile(loss='mean_absolute_error', model.compile(loss='mean_absolute_error',
optimizer=tf.keras.optimizers.Adam(0.001)) optimizer=tf.keras.optimizers.Adam(0.001))
model.fit(train_X, train_Y, verbose=0, epochs=100) model.fit(train_X, train_Y, verbose=0, epochs=100)
model.save('linear_regression')
# Predykcja na danych testowych # Predykcja na danych testowych
results = model.predict(test_X) results = model.predict(test_X)

29
training.py
View File

@ -27,22 +27,19 @@ train_Y = tf.convert_to_tensor(train_data[["IMDb"]])
normalizer = preprocessing.Normalization(input_shape=[3,]) normalizer = preprocessing.Normalization(input_shape=[3,])
normalizer.adapt(train_X) normalizer.adapt(train_X)
if os.path.isdir('linear_regression'): model = keras.Sequential([
model = keras.models.load_model('linear_regression') keras.Input(shape=(len(columns_to_use),)),
else: normalizer,
model = keras.Sequential([ layers.Dense(30, activation='relu'),
keras.Input(shape=(len(columns_to_use),)), layers.Dense(10, activation='relu'),
normalizer, layers.Dense(25, activation='relu'),
layers.Dense(30, activation='relu'), layers.Dense(1)
layers.Dense(10, activation='relu'), ])
layers.Dense(25, activation='relu'),
layers.Dense(1)
])
model.compile(loss='mean_absolute_error', model.compile(loss='mean_absolute_error',
optimizer=tf.keras.optimizers.Adam(0.001), optimizer=tf.keras.optimizers.Adam(0.001),
metrics=[tf.keras.metrics.RootMeanSquaredError()]) metrics=[tf.keras.metrics.RootMeanSquaredError()])
model.fit(train_X, train_Y, verbose=verbose, epochs=epochs) model.fit(train_X, train_Y, verbose=verbose, epochs=epochs)
model.save('linear_regression.h5') model.save('linear_regression.h5')