.dvc/.gitignore

@@ -1,3 +0,0 @@
-/config.local
-/tmp
-/cache

.dvc/config

@@ -1,4 +0,0 @@
-[core]
-    remote = ium_ssh_remote
-['remote "ium_ssh_remote"']
-    url = ssh://ium-sftp@tzietkiewicz.vm.wmi.amu.edu.pl

.dvcignore

@@ -1,3 +0,0 @@
-# Add patterns of files dvc should ignore, which could improve
-# the performance. Learn more at
-# https://dvc.org/doc/user-guide/dvcignore

.gitignore

@@ -20,5 +20,3 @@ evaluation_results.txt
 model_out
 trend.png
 sacred_runs
-mlruns
-/data

Dockerfile

@@ -5,13 +5,11 @@ WORKDIR /app
 ADD ./requirements.txt .
 RUN pip install -r requirements.txt
 
-ADD ./download_dataset.sh .
+ADD . .
 ARG KAGGLE_USERNAME
 ARG KAGGLE_KEY
 
 RUN chmod a+x *.sh
 RUN ./download_dataset.sh
 
-ADD . .
-
 CMD python train_model.py

Jenkinsfile-dvc

@@ -1,41 +0,0 @@
-pipeline {
-    parameters {
-        string(
-            defaultValue: 'marcinkostrzewski',
-            description: 'Kaggle username',
-            name: 'KAGGLE_USERNAME',
-            trim: false
-        )
-        password(
-            defaultValue: '',
-            description: 'Kaggle token taken from kaggle.json file, as described in https://github.com/Kaggle/kaggle-api#api-credentials',
-            name: 'KAGGLE_KEY'
-        )
-    }
-
-    agent {
-        dockerfile {
-            additionalBuildArgs "--build-arg KAGGLE_USERNAME=${params.KAGGLE_USERNAME} --build-arg KAGGLE_KEY=${params.KAGGLE_KEY} -t s444409-create-dataset"
-        }
-    }
-
-    stages {
-         stage("Run DVC") {
-            steps{
-                withCredentials([
-                    sshUserPrivateKey(
-                        credentialsId: '48ac7004-216e-4260-abba-1fe5db753e18',
-                        keyFileVariable: 'IUM_SFTP_KEY',
-                        passphraseVariable: '',
-                        usernameVariable: 'USER'
-                    )
-                ]) {
-                    sh 'dvc remote modify --local ium_ssh_remote keyfile $IUM_SFTP_KEY'
-                    sh 'dvc remote modify --local ium_ssh_remote password IUM@2021'
-                    sh 'dvc pull'
-                    sh 'dvc repro'
-                }
-            }
-         }
-    }
-}

Jenkinsfile-predict-s444356

@@ -1,34 +0,0 @@
-pipeline {
-    agent {
-        docker {
-            image 's444409-create-dataset'
-        }
-    }
-    parameters {
-        string(
-            defaultValue: '{\\"inputs\\": [[0.51, 0.86], [0.79, 0.79], [0.74, 0.77], [0.66, 0.73]]}',
-            description: 'Input',
-            name: 'INPUT',
-            trim: true
-        )
-        buildSelector(
-			defaultSelector: lastSuccessful(),
-			description: 'Which build to use for copying artifacts',
-			name: 'BUILD_SELECTOR'
-		)
-    }
-    
-    stages {
-        stage('Get dataset from artifact') {
-            steps {
-                copyArtifacts projectName: 's444356-training/master', selector: buildParameter('BUILD_SELECTOR')
-            }
-        }
-        stage('Predict values using model from artifact') {
-            steps {
-                sh "echo ${params.INPUT} > input_example.json"
-                sh "python predict_s444356.py"
-            }
-        }
-    }
-}

Jenkinsfile-predict-s444356-from-registry

@@ -1,16 +0,0 @@
-pipeline {
-    agent {
-        docker {
-            image 's444409-create-dataset'
-            args '-v /mlruns:/mlruns'
-        }
-    }
-    
-    stages {
-        stage('Predict values using model from artifact') {
-            steps {
-                sh "python predict_s444356-from-registry.py"
-            }
-        }
-    }
-}

Jenkinsfile-train

@@ -23,7 +23,6 @@ pipeline {
     agent {
         docker {
             image 's444409-create-dataset'
-            args '-v /mlruns:/mlruns'
         }
     }
     
@@ -35,14 +34,13 @@ pipeline {
         }
         stage('Train model') {
             steps {
-                sh "python train_model.py -e ${params.EPOCHS} -b ${params.BATCHSIZE}"
-                archiveArtifacts artifacts: 'model_out', onlyIfSuccessful: true
-                archiveArtifacts artifacts: 'mlruns/**', onlyIfSuccessful: true
-                sh 'rm -r mlruns'
+                sh "python train_model.py with 'epochs=${params.EPOCHS}' 'batch_size=${params.BATCHSIZE}'"
             }
         }
-        stage('Evaluate model') {
+        stage('Archive model and evaluate it') {
             steps {
+               archiveArtifacts artifacts: 'model_out', onlyIfSuccessful: true
+               archiveArtifacts artifacts: 'sacred_runs/**', onlyIfSuccessful: true
                build job: "s444409-evaluation/${params.BRANCH}/", parameters: [string(name: 'BRANCH', value: "${params.BRANCH}")]
             }
         }

MLproject

@@ -1,14 +0,0 @@
-name: ium_s444409
-
-docker_env:
-  image: s444409-create-dataset
-  volumes: ["/tmp/mlruns:/mlruns:rw"]
-
-entry_points:
-  main:
-    parameters:
-      epochs: {type: float, default: 5}
-      batch_size: {type: float, default: 64}
-    command: "python train_model.py -e {epochs} -b {batch_size}"
-  eval:
-    command: "python eval_model.py"

data.dvc

@@ -1,5 +0,0 @@
-outs:
-- md5: 107d31dc52f58274023d18db2f0c5b7a.dir
-  size: 24456416
-  nfiles: 17
-  path: data

dvc.lock

@@ -1,4 +0,0 @@
-schema: '2.0'
-stages:
-  prepare:
-    cmd: download_dataset.sh

dvc.yaml

@@ -1,16 +0,0 @@
-stages:
-  prepare:
-    cmd: download_dataset.sh
-    
-  train:
-    cmd: python3 train_model.py
-    deps:
-      - data/Plant_1_Generation_data.csv.train
-    params:
-      - batch_size
-      - epochs
-  
-  eval:
-    deps: 
-      - model_out
-    cmd: python3 eval_model.py

environment.yml

@@ -1,11 +0,0 @@
-name: ium444409
-channels:
-  - conda-forge
-  - defaults
-dependencies:
-  - kaggle
-  - pandas
-  - pytorch
-  - matplotlib
-  - mlflow
-prefix: C:\Users\komar\.conda\envs\ium444409

model.py

@@ -24,7 +24,7 @@ class MLP(nn.Module):
 
     def forward(self, x):
         x = x.view(x.size(0), -1)
-        return self.layers(x.float())
+        return self.layers(x)
 
 
 class PlantsDataset(Dataset):

params.yaml

@@ -1,2 +0,0 @@
-batch_size: 64
-epochs: 5

predict_s444356-from-registry.py

@@ -1,14 +0,0 @@
-import json
-import mlflow
-import numpy as np
-
-logged_model = '/mlruns/13/da5c6167bb45403fa35569849a1fbc13/artifacts/model'
-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.float64).reshape(-1, 2)
-
-
-print(f'Prediction: {loaded_model.predict(input_example)}')

predict_s444356.py

@@ -1,14 +0,0 @@
-import json
-import mlflow
-import numpy as np
-
-logged_model = 'mlruns/1/4b83e774512444188fb587288818c298/artifacts/model'
-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.float64).reshape(-1, 2)
-
-
-print(f'Prediction: {loaded_model.predict(input_example)}')

requirements.txt

@@ -4,8 +4,4 @@ torch==1.11.0
 numpy~=1.22.3
 matplotlib==3.5.2
 sacred==0.8.2
-pymongo==4.1.1
-mlflow==1.25.1
-dvc==2.10.2
-dvc-ssh==0.0.1a0
-paramiko==2.11.0
+pymongo==4.1.1

train_model.py

@@ -1,11 +1,12 @@
 import argparse
-from urllib.parse import urlparse
 
-import mlflow
 import numpy as np
+import pandas as pd
 import torch
+from sacred.observers import FileStorageObserver, MongoObserver
 from torch import nn
-from torch.utils.data import DataLoader
+from torch.utils.data import DataLoader, Dataset
+from sacred import Experiment
 
 from model import PlantsDataset, MLP, train, test
 
@@ -14,30 +15,13 @@ default_epochs = 5
 
 device = "cuda" if torch.cuda.is_available() else "cpu"
 
-# mlflow.set_tracking_uri("http://172.17.0.1:5000")
-mlflow.set_experiment("s444409")
-
-
-def setup_args():
-    args_parser = argparse.ArgumentParser(prefix_chars='-')
-    args_parser.add_argument('-b', '--batchSize', type=int, default=default_batch_size)
-    args_parser.add_argument('-e', '--epochs', type=int, default=default_epochs)
-
-    return args_parser.parse_args()
-
-
-if __name__ == "__main__":
-    args = setup_args()
-    batch_size = args.batchSize
-    epochs = args.epochs
 
+def main(batch_size, epochs, _run):
     print(f"Using {device} device")
 
     plant_test = PlantsDataset('data/Plant_1_Generation_Data.csv.test')
     plant_train = PlantsDataset('data/Plant_1_Generation_Data.csv.train')
 
-    input_example = np.array([plant_test.x_train.numpy()[0]])
-
     train_dataloader = DataLoader(plant_train, batch_size=batch_size)
     test_dataloader = DataLoader(plant_test, batch_size=batch_size)
 
@@ -51,37 +35,37 @@ if __name__ == "__main__":
 
     loss_fn = nn.MSELoss()
     optimizer = torch.optim.Adam(model.parameters(), lr=1e-3)
-
+    for t in range(epochs):
+        print(f"Epoch {t + 1}\n-------------------------------")
+        train(train_dataloader, model, loss_fn, optimizer)
+        last_loss = test(test_dataloader, model, loss_fn)
+        _run.log_scalar('training.loss', last_loss, t)
     print("Done!")
 
     torch.save(model.state_dict(), './model_out')
     print("Model saved in ./model_out file.")
-    with mlflow.start_run() as run:
-        print("MLflow run experiment_id: {0}".format(run.info.experiment_id))
-        print("MLflow run artifact_uri: {0}".format(run.info.artifact_uri))
 
-        mlflow.log_param("batch_size", batch_size)
-        mlflow.log_param("epochs", epochs)
-        for t in range(epochs):
-            print(f"Epoch {t + 1}\n-------------------------------")
-            train(train_dataloader, model, loss_fn, optimizer)
-            last_loss = test(test_dataloader, model, loss_fn)
-            mlflow.log_metric("rmse", last_loss)
 
-        with torch.no_grad():
-            preds = model(plant_test.x_train)
-            signature = mlflow.models.signature.infer_signature(plant_test.x_train.numpy(), preds.numpy())
-        tracking_url_type_store = urlparse(mlflow.get_tracking_uri()).scheme
-        if tracking_url_type_store != "file":
-            mlflow.log_artifact('model.py')
-            mlflow.pytorch.log_model(
-                model,
-                "s444409",
-                registered_model_name="s444409",
-                signature=signature,
-                input_example=input_example,
-                code_paths=['model.py']
-            )
-        else:
-            mlflow.pytorch.log_model(model, "s444409", signature=signature, input_example=input_example,
-                                     code_paths=['model.py'])
+def setup_experiment():
+    ex = Experiment('Predict power output for a given time')
+    ex.observers.append(FileStorageObserver('sacred_runs'))
+    ex.observers.append(MongoObserver(url='mongodb://admin:IUM_2021@172.17.0.1:27017',
+                                      db_name='sacred'))
+    return ex
+
+
+ex = setup_experiment()
+
+
+@ex.config
+def experiment_config():
+    batch_size = 64
+    epochs = 5
+
+
+@ex.automain
+def run(batch_size, epochs, _run):
+    main(batch_size, epochs, _run)
+
+
+ex.add_artifact('model_out')