add solution for lab8
Some checks failed
s444018-training/pipeline/head There was a failure building this commit
s444018-evaluation/pipeline/head This commit looks good

This commit is contained in:
Szymon Parafiński 2022-05-16 01:58:32 +02:00
parent fa51d4a87a
commit d572509234
7 changed files with 108 additions and 29 deletions

View File

@ -13,6 +13,7 @@ RUN pip3 install matplotlib
RUN pip3 install torch RUN pip3 install torch
RUN pip3 install sacred RUN pip3 install sacred
RUN pip3 install pymongo RUN pip3 install pymongo
RUN pip3 install mflow
ARG CUTOFF ARG CUTOFF
ARG KAGGLE_USERNAME ARG KAGGLE_USERNAME
@ -27,6 +28,8 @@ COPY lab2/download.sh .
COPY biblioteka_DL/dllib.py . COPY biblioteka_DL/dllib.py .
COPY biblioteka_DL/evaluate.py . COPY biblioteka_DL/evaluate.py .
COPY biblioteka_DL/imdb_top_1000.csv . COPY biblioteka_DL/imdb_top_1000.csv .
COPY predict.py .
COPY registry.py .
RUN chmod +x ./download.sh RUN chmod +x ./download.sh
RUN ./download.sh RUN ./download.sh

29
Jenkinsfile_predict Normal file
View File

@ -0,0 +1,29 @@
pipeline {
agent {
docker {
image 'docker_image'
}
}
parameters {
buildSelector(
defaultSelector: lastSuccessful(),
description: 'Which build to use for copying artifacts for predict',
name: 'BUILD_SELECTOR')
string(
defaultValue: '{\\"inputs\\": [900.0]}',
description: 'Input file',
name: 'INPUT',
trim: true
)
}
stages {
stage('Script') {
steps {
copyArtifacts projectName: 's444409-training/main', selector: buildParameter('BUILD_SELECTOR')
sh "echo ${params.INPUT} > input_example.json"
sh "python predict.py"
}
}
}
}

16
Jenkinsfile_registry Normal file
View File

@ -0,0 +1,16 @@
pipeline {
agent {
docker {
image 'docker_image'
args '-v /mlruns:/mlruns'
}
}
stages {
stage('Script') {
steps {
sh 'python3 ./registry.py'
}
}
}
}

View File

@ -1,9 +1,10 @@
pipeline { pipeline {
agent { agent {
dockerfile { docker {
additionalBuildArgs "--build-arg KAGGLE_USERNAME=${params.KAGGLE_USERNAME} --build-arg KAGGLE_KEY=${params.KAGGLE_KEY} --build-arg CUTOFF=${params.CUTOFF} -t docker_image" image 'docker_image'
} args '-v /mlruns:/mlruns'
} }
}
parameters { parameters {
string( string(
defaultValue: '1000', defaultValue: '1000',
@ -22,6 +23,9 @@ pipeline {
steps { steps {
sh 'python3 ./biblioteka_DL/dllib.py with "epochs=$EPOCHS"' sh 'python3 ./biblioteka_DL/dllib.py with "epochs=$EPOCHS"'
archiveArtifacts artifacts: 'model.pkl, s444018_sacred_FileObserver/**/*.*, result.csv', followSymlinks: false archiveArtifacts artifacts: 'model.pkl, s444018_sacred_FileObserver/**/*.*, result.csv', followSymlinks: false
archiveArtifacts artifacts: 'mlruns/**'
archiveArtifacts artifacts: 'my_model/**'
build job: 's444018-evaluation/master/'
} }
} }
} }

View File

@ -1,25 +1,22 @@
import sys import sys
import torch import torch
import mlflow
import torch.nn as nn import torch.nn as nn
import pandas as pd import pandas as pd
import numpy as np import numpy as np
import matplotlib.pyplot as plt import matplotlib.pyplot as plt
from mlflow.models import infer_signature
from sklearn.model_selection import train_test_split from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score, mean_squared_error from sklearn.metrics import accuracy_score, mean_squared_error
from sacred.observers import MongoObserver, FileStorageObserver from sacred.observers import MongoObserver, FileStorageObserver
from sacred import Experiment from sacred import Experiment
from urllib.parse import urlparse
# mlflow.set_tracking_uri("http://172.17.0.1:5000")
mlflow.set_experiment("s444018")
ex = Experiment(save_git_info=False) epochs = int(sys.argv[1]) if len(sys.argv) > 1 else 20
ex.observers.append(MongoObserver(url='mongodb://admin:IUM_2021@172.17.0.1:27017',
db_name='sacred'))
ex.observers.append(FileStorageObserver('s444018_sacred_FileObserver'))
@ex.config
def my_config():
epochs = "1000"
def drop_relevant_columns(imbd_data): def drop_relevant_columns(imbd_data):
@ -88,8 +85,7 @@ class LinearRegressionModel(torch.nn.Module):
return y_pred return y_pred
@ex.automain def my_main(epochs):
def my_main(epochs, _run):
# num_epochs = 1000 # num_epochs = 1000
# num_epochs = int(sys.argv[1]) # num_epochs = int(sys.argv[1])
@ -153,23 +149,23 @@ def my_main(epochs, _run):
# save model # save model
torch.save(model, "model.pkl") torch.save(model, "model.pkl")
predicted = [] input_example = gross_test_g
expected = [] siganture = infer_signature(gross_test_g, X_train)
tracking_url_type_store = urlparse(mlflow.get_tracking_uri()).scheme
# print(tracking_url_type_store)
for i in range(0, len(X_test)): if tracking_url_type_store != "file":
predicted.append(np.argmax(model(X_test[i]).detach().numpy(), axis=0)) mlflow.pytorch.log_model(model, "model", registered_model_name="s444018", signature=siganture,
expected.append(gross_test_g[i]) input_example=input_example)
else:
mlflow.pytorch.log_model(model, "model", signature=siganture, input_example=input_example)
mlflow.pytorch.save_model(model, "my_model", signature=siganture, input_example=input_example)
for i in range(0, len(expected)):
expected[i] = expected[i][0]
rmse = mean_squared_error(gross_test_g, pred, squared=False)
mse = mean_squared_error(gross_test_g, pred) mse = mean_squared_error(gross_test_g, pred)
_run.log_scalar("RMSE", rmse) mlflow.log_param("MSE", mse)
_run.log_scalar("MSE", mse) mlflow.log_param("epochs", epochs)
_run.info['epochs'] = epochs
# ex.run()
ex.add_artifact("model.pkl")
with mlflow.start_run() as run:
my_main(epochs)

16
predict.py Normal file
View File

@ -0,0 +1,16 @@
import json
import mlflow
import sys
import numpy as np
#input = sys.argv[1]
logged_model = 'mlruns/1/70439eb482b54d56b54b0ecc6f1ca96f/artifacts/s444409'
loaded_model = mlflow.pyfunc.load_model(logged_model)
with open('input_example.json') as f:
data = json.load(f)
input_example = np.array([data['inputs'][0]], dtype=np.float32)
print(f'Prediction: {loaded_model.predict(input_example)}')

15
registry.py Normal file
View File

@ -0,0 +1,15 @@
import mlflow
import json
import numpy as np
logged_model = '/mlruns/12/1c2b9737c0204b0ca825811c35fb6c64/artifacts/s444409'
# Load model as a PyFuncModel.
loaded_model = mlflow.pyfunc.load_model(logged_model)
with open(f'{logged_model}/input_example.json') as f:
data = json.load(f)
input_example = np.array([data['inputs'][0]], dtype=np.float32)
# Predict on a Pandas DataFrame.
import pandas as pd
print(f'Prediction: {loaded_model.predict(input_example)}')