This commit is contained in:
Robert Bendun 2023-05-13 00:46:35 +02:00
parent 2deab093cf
commit 46c54bfdf8
7 changed files with 38 additions and 34 deletions

View File

@ -1,5 +1,5 @@
FROM ubuntu:22.04
RUN apt update && apt install -y vim make python3 python3-pip python-is-python3 gcc g++ golang wget unzip git
RUN pip install pandas matplotlib scikit-learn
RUN pip install pandas matplotlib scikit-learn tensorflow
CMD "bash"

View File

@ -8,7 +8,7 @@ node {
checkout([$class: 'GitSCM', branches: [[name: 'ztm']], extensions: [], userRemoteConfigs: [[url: 'https://git.wmi.amu.edu.pl/s452639/ium_452639']]])
sh 'cd src; ./prepare-ztm-data.sh'
archiveArtifacts artifacts: 'src/stop_times.normalized.tsv,src/stop_times.train.tsv,src/stop_times.test.tsv,src/stop_times.valid.tsv',
archiveArtifacts artifacts: 'src/stop_times.normalized.tsv,src/stop_times.train.tsv,src/stop_times.test.tsv,src/stop_times.valid.tsv,src/stop_times.categories.tsv',
followSymlinks: false
}
}

2
run.sh
View File

@ -3,4 +3,4 @@
set -xe
docker build -t ium .
docker run -it ium
docker run -v .:/ium/ -it ium

2
src/.gitignore vendored Normal file
View File

@ -0,0 +1,2 @@
model.keras
pics

View File

@ -4,7 +4,7 @@ from sklearn.model_selection import train_test_split
data = pd.read_csv('./stop_times.normalized.tsv', sep='\t')
train, test = train_test_split(data, test_size=0.5)
train, test = train_test_split(data, test_size=0.8)
valid, test = train_test_split(test, test_size=0.5)
train.to_csv('stop_times.train.tsv', sep='\t')

15
src/tf_test.py Normal file
View File

@ -0,0 +1,15 @@
from tf_train import *
import numpy as np
def test():
global model, le
test_x, test_y, _ = load_data('./stop_times.test.tsv', le)
test_x = tf.convert_to_tensor(test_x, dtype=tf.float32)
test_y = tf.convert_to_tensor(test_y)
model = tf.keras.models.load_model('model.keras')
pd.DataFrame(model.predict(test_x), columns=le.classes_).to_csv('stop_times.predictions.tsv', sep='\t')
if __name__ == "__main__":
test()

View File

@ -22,6 +22,10 @@ def load_data(path: str, le: LabelEncoder):
num_classes = len(le.classes_)
def train():
global le
model = tf.keras.Sequential([
tf.keras.layers.Input(shape=(2,)),
tf.keras.layers.Dense(4 * num_classes, activation='relu'),
@ -34,8 +38,6 @@ model.compile(optimizer='adam',
loss=tf.keras.losses.SparseCategoricalCrossentropy(),
metrics=['accuracy'])
def train():
global model, le
train_x, train_y, _ = load_data('./stop_times.train.tsv', le)
train_x = tf.convert_to_tensor(train_x, dtype=tf.float32)
train_y = tf.convert_to_tensor(train_y)
@ -50,22 +52,7 @@ def train():
with open('history', 'w') as f:
print(repr(history), file=f)
model.save_weights('model.ckpt')
model.save('model.keras')
def test():
global model, le
test_x, test_y, _ = load_data('./stop_times.test.tsv', le)
test_x = tf.convert_to_tensor(test_x, dtype=tf.float32)
test_y = tf.convert_to_tensor(test_y)
model.load_weights('model.ckpt')
model.evaluate(test_x, test_y)
SUBCOMMANDS = {
"test": test,
"train": train,
}
import sys
assert len(sys.argv) == 2
assert sys.argv[1] in SUBCOMMANDS.keys()
SUBCOMMANDS[sys.argv[1]]()
if __name__ == "__main__":
train()