evaluation.py

IUM_05.py

@@ -1,4 +1,5 @@
 import torch
+import sys
 from torch import nn
 import numpy as np
 import pandas as pd
@@ -15,21 +16,21 @@ class LogisticRegressionModel(nn.Module):
         return self.sigmoid(out)
 
 
-data_train = pd.read_csv("train.csv")
+train = pd.read_csv("train.csv")
-data_test  = pd.read_csv("test.csv")
+test = pd.read_csv("test.csv")
-data_val   = pd.read_csv("valid.csv")
+valid  = pd.read_csv("valid.csv")
 
-x_train = data_train[['age','anaemia','creatinine_phosphokinase','diabetes', 'ejection_fraction', 'high_blood_pressure', 'platelets', 'serum_creatinine', 'serum_sodium', 'sex', 'smoking']].astype(np.float32)
+xtrain = train[['age','anaemia','creatinine_phosphokinase','diabetes', 'ejection_fraction', 'high_blood_pressure', 'platelets', 'serum_creatinine', 'serum_sodium', 'sex', 'smoking']].astype(np.float32)
-y_train = data_train['DEATH_EVENT'].astype(np.float32)
+ytrain = train['DEATH_EVENT'].astype(np.float32)
 
-x_test = data_test[['age','anaemia','creatinine_phosphokinase','diabetes', 'ejection_fraction', 'high_blood_pressure', 'platelets', 'serum_creatinine', 'serum_sodium', 'sex', 'smoking']].astype(np.float32)
+xtest = test[['age','anaemia','creatinine_phosphokinase','diabetes', 'ejection_fraction', 'high_blood_pressure', 'platelets', 'serum_creatinine', 'serum_sodium', 'sex', 'smoking']].astype(np.float32)
-y_test = data_test['DEATH_EVENT'].astype(np.float32)
+ytest = test['DEATH_EVENT'].astype(np.float32)
 
-fTrain = torch.from_numpy(x_train.values)
+xTrain = torch.from_numpy(xtrain.values)
-tTrain = torch.from_numpy(y_train.values.reshape(179,1))
+yTrain = torch.from_numpy(ytrain.values.reshape(179,1))
 
-fTest= torch.from_numpy(x_test.values)
+xTest = torch.from_numpy(xtest.values)
-tTest = torch.from_numpy(y_test.values)
+yTest = torch.from_numpy(ytest.values)
 
 batch_size = 10
 num_epochs = 5
@@ -47,14 +48,14 @@ for epoch in range(num_epochs):
     model.train()
     optimizer.zero_grad()
     # Forward pass
-    y_pred = model(fTrain)
+    y_pred = model(xTrain)
     # Compute Loss
-    loss = criterion(y_pred, tTrain)
+    loss = criterion(y_pred, yTrain)
     # print(loss.item())
     # Backward pass
     loss.backward()
     optimizer.step()
-y_pred = model(fTest)
+y_pred = model(xTest)
 print(y_pred.data)
 
 torch.save(model.state_dict(), 'DEATH_EVENT.pth')

Jenkinsfile_evaluation

@@ -0,0 +1,45 @@
+pipeline {
+   agent {
+      dockerfile true
+   }
+   parameters{
+      buildSelector(
+            defaultSelector: lastSuccessful(),
+            description: 'Which build to use for copying artifacts',
+            name: 'WHICH_BUILD_DATA'
+        )
+        buildSelector(
+            defaultSelector: lastSuccessful(),
+            description: 'Which build to use for copying artifacts',
+            name: 'WHICH_BUILD_TRAIN'
+        )
+   }
+   stages {
+      stage('copyArtifacts') {
+            steps {
+                copyArtifacts fingerprintArtifacts: true, projectName: 's434732-create-dataset', selector: buildParameter('WHICH_BUILD_DATA')
+            }
+        }
+      stage('Run_script'){
+         steps{
+            copyArtifacts fingerprintArtifacts: true, projectName: 's434732-training/master', selector: buildParameter('WHICH_BUILD_TRAIN')
+            sh 'python3 "./evaluation.py" >> result.txt'
+         }
+      }
+      stage('archiveArtifacts') {
+         steps {
+            archiveArtifacts 'result.txt'
+         }
+      }
+   }
+   post {
+        success {
+            mail body: 'SUCCESS EVALUATION', subject: 's434732', to: '26ab8f35.uam.onmicrosoft.com@emea.teams.ms'
+        }
+
+        failure {
+            mail body: 'FAILURE EVALUATION', subject: 's434732', to: '26ab8f35.uam.onmicrosoft.com@emea.teams.ms'
+        }
+
+   }
+}

Jenkinsfile_train

@@ -21,12 +21,12 @@ pipeline {
         )
    }
    stages {
-      stage('checkout') {
+      stage('copyArtifacts') {
             steps {
                copyArtifacts fingerprintArtifacts: true, projectName: 's434732-create-dataset', selector: buildParameter('WHICH_BUILD')
             }
         }
-      stage('Docker'){
+      stage('Run_script'){
          steps{
             sh 'python3 "./training.py" ${BATCH_SIZE} ${EPOCHS} > model_pred.txt'
          }
@@ -40,6 +40,7 @@ pipeline {
     }
     post {
         success {
+            build job: 's434732-evaluation/master'
             mail body: 'SUCCESS TRAINING', subject: 's434732', to: '26ab8f35.uam.onmicrosoft.com@emea.teams.ms'
         }
 

evaluation.py

@@ -1,153 +1,54 @@
-import sys
 import torch
-import torch.nn as nn
+import sys
+from torch import nn
+import numpy as np
 import pandas as pd
-import torch.nn.functional as F
+from sklearn.metrics import accuracy_score
-from torch.utils.data import DataLoader, TensorDataset, random_split
+from sklearn.metrics import f1_score
-from sklearn import preprocessing
+np.set_printoptions(suppress=False)
 
 
-batch_size = 64
+class LogisticRegressionModel(nn.Module):
-
+    def __init__(self, input_dim, output_dim):
-train = pd.read_csv('train.csv')
+        super(LogisticRegressionModel, self).__init__()
-test = pd.read_csv('test.csv')
+        self.linear = nn.Linear(input_dim, output_dim)
-
+        self.sigmoid = nn.Sigmoid()
-categorical_cols = train.select_dtypes(include=object).columns.values
+    def forward(self, x):
-
+        out = self.linear(x)
-input_cols = train.columns.values[1:-1]
+        return self.sigmoid(out)
-output_cols = train.columns.values[-1:]
 
 
-def dataframe_to_arrays(dataframe):
+train = pd.read_csv("train.csv")
-    # Make a copy of the original dataframe
+test = pd.read_csv("test.csv")
-    dataframe1 = dataframe.copy(deep=True)
+valid  = pd.read_csv("valid.csv")
-    # Convert non-numeric categorical columns to numbers
-    for col in categorical_cols:
-        dataframe1[col] = dataframe1[col].astype('category').cat.codes
-    # Extract input & outupts as numpy arrays
 
-    min_max_scaler = preprocessing.MinMaxScaler()
+xtrain = train[['age','anaemia','creatinine_phosphokinase','diabetes', 'ejection_fraction', 'high_blood_pressure', 'platelets', 'serum_creatinine', 'serum_sodium', 'sex', 'smoking']].astype(np.float32)
-    x_scaled = min_max_scaler.fit_transform(dataframe1)
+ytrain = train['DEATH_EVENT'].astype(np.float32)
-    dataframe1 = pd.DataFrame(x_scaled, columns = dataframe1.columns)
 
-    inputs_array = dataframe1[input_cols].to_numpy()
+xtest = test[['age','anaemia','creatinine_phosphokinase','diabetes', 'ejection_fraction', 'high_blood_pressure', 'platelets', 'serum_creatinine', 'serum_sodium', 'sex', 'smoking']].astype(np.float32)
-    targets_array = dataframe1[output_cols].to_numpy()
+ytest = test['DEATH_EVENT'].astype(np.float32)
-    return inputs_array, targets_array
 
-inputs_array_training, targets_array_training = dataframe_to_arrays(train)
+xTrain = torch.from_numpy(xtrain.values)
+yTrain = torch.from_numpy(ytrain.values.reshape(179,1))
+
+xTest = torch.from_numpy(xtest.values)
+yTest = torch.from_numpy(ytest.values)
+
+batch_size = int(sys.argv[1]) if len(sys.argv) > 1 else 10
+num_epochs = int(sys.argv[2]) if len(sys.argv) > 2 else 5
+learning_rate = 0.002
+input_dim = 11
+output_dim = 1
+
+model = LogisticRegressionModel(input_dim, output_dim)
+model.load_state_dict(torch.load('DEATH_EVENT.pth'))
+criterion = torch.nn.BCELoss(reduction='mean')
+optimizer = torch.optim.SGD(model.parameters(), lr = learning_rate)
 
 
-inputs_array_testing, targets_array_testing = dataframe_to_arrays(test)
+prediction= model(xTest)
 
 
-inputs_training = torch.from_numpy(inputs_array_training).type(torch.float32)
+accuracy_score = accuracy_score(yTest, np.argmax(prediction.detach().numpy(), axis=1))
-targets_training = torch.from_numpy(targets_array_training).type(torch.float32)
+print("accuracy_score", accuracy_score)
-
+print("F1", f1_score(yTest, np.argmax(prediction.detach().numpy(), axis=1), average=None))
-inputs_testing = torch.from_numpy(inputs_array_testing).type(torch.float32)
-targets_testing = torch.from_numpy(targets_array_testing).type(torch.float32)
-
-train_dataset = TensorDataset(inputs_training, targets_training)
-val_dataset = TensorDataset(inputs_testing, targets_testing)
-
-train_loader = DataLoader(train_dataset, batch_size, shuffle=True)
-val_loader = DataLoader(val_dataset, batch_size*2)
-
-input_size = len(input_cols)
-output_size = len(output_cols)
-
-
-
-class FootbalModel(nn.Module):
-    def __init__(self):
-        super().__init__()
-        self.linear = nn.Linear(input_size, output_size)
-
-    def forward(self, xb):
-        out = self.linear(xb)
-        return out
-
-    def training_step(self, batch):
-        inputs, targets = batch
-        # Generate predictions
-        out = self(inputs)
-        # Calcuate loss
-        # loss = F.l1_loss(out, targets)
-        loss = F.mse_loss(out, targets)
-        return loss
-
-    def validation_step(self, batch):
-        inputs, targets = batch
-        # Generate predictions
-        out = self(inputs)
-        # Calculate loss
-        # loss = F.l1_loss(out, targets)
-        loss = F.mse_loss(out, targets)
-        return {'val_loss': loss.detach()}
-
-    def validation_epoch_end(self, outputs):
-        batch_losses = [x['val_loss'] for x in outputs]
-        epoch_loss = torch.stack(batch_losses).mean()
-        return {'val_loss': epoch_loss.item()}
-
-    def epoch_end(self, epoch, result, num_epochs):
-        # Print result every 20th epoch
-        if (epoch + 1) % 20 == 0 or epoch == num_epochs - 1:
-            print("Epoch [{}], val_loss: {:.4f}".format(epoch + 1, result['val_loss']))
-
-model = FootbalModel()
-model.load_state_dict(torch.load('FootballModel.pth'))
-list(model.parameters())
-
-
-# def evaluate(model, val_loader):
-#     outputs = [model.validation_step(batch) for batch in val_loader]
-#     return model.validation_epoch_end(outputs)
-#
-# def fit(epochs, lr, model, train_loader, val_loader, opt_func=torch.optim.SGD):
-#     history = []
-#     optimizer = opt_func(model.parameters(), lr)
-#     for epoch in range(epochs):
-#         # Training Phase
-#         for batch in train_loader:
-#             loss = model.training_step(batch)
-#             loss.backward()
-#             optimizer.step()
-#             optimizer.zero_grad()
-#         # Validation phase
-#         result = evaluate(model, val_loader)
-#         model.epoch_end(epoch, result, epochs)
-#         history.append(result)
-#     return history
-#
-#
-# result = evaluate(model, val_loader) # Use the the evaluate function
-#
-# # epochs = 100
-# lr = 1e-6
-# history3 = fit(epochs, lr, model, train_loader, val_loader)
-#
-def predict_single(input, target, model):
-    inputs = input.unsqueeze(0)
-    predictions = model(input)
-    print(type(predictions))# fill this
-    prediction = predictions[0].detach()
-    print(prediction)
-    print("Prediction:", prediction)
-    if prediction >= 0.5:
-      print('Neutral')
-    else:
-      print('not neutral')
-
-# inputs_testing = torch.from_numpy(inputs_array_testing).type(torch.float32)
-# targets_testing = torch.from_numpy(targets_array_testing).type(torch.float32)
-
-# inputs = input.unsqueeze(0)
-# predictions = model(targets_testing)
-
-
-for i in range(len(val_dataset)):
-    input, target = val_dataset[i]
-    predict_single(input, target, model)
-
-
-# torch.save(model.state_dict(), 'FootballModel.pth')

training.py

@@ -16,25 +16,25 @@ class LogisticRegressionModel(nn.Module):
         return self.sigmoid(out)
 
 
-data_train = pd.read_csv("train.csv")
+train = pd.read_csv("train.csv")
-data_test  = pd.read_csv("test.csv")
+test = pd.read_csv("test.csv")
-data_val   = pd.read_csv("valid.csv")
+valid  = pd.read_csv("valid.csv")
 
-x_train = data_train[['age','anaemia','creatinine_phosphokinase','diabetes', 'ejection_fraction', 'high_blood_pressure', 'platelets', 'serum_creatinine', 'serum_sodium', 'sex', 'smoking']].astype(np.float32)
+xtrain = train[['age','anaemia','creatinine_phosphokinase','diabetes', 'ejection_fraction', 'high_blood_pressure', 'platelets', 'serum_creatinine', 'serum_sodium', 'sex', 'smoking']].astype(np.float32)
-y_train = data_train['DEATH_EVENT'].astype(np.float32)
+ytrain = train['DEATH_EVENT'].astype(np.float32)
 
-x_test = data_test[['age','anaemia','creatinine_phosphokinase','diabetes', 'ejection_fraction', 'high_blood_pressure', 'platelets', 'serum_creatinine', 'serum_sodium', 'sex', 'smoking']].astype(np.float32)
+xtest = test[['age','anaemia','creatinine_phosphokinase','diabetes', 'ejection_fraction', 'high_blood_pressure', 'platelets', 'serum_creatinine', 'serum_sodium', 'sex', 'smoking']].astype(np.float32)
-y_test = data_test['DEATH_EVENT'].astype(np.float32)
+ytest = test['DEATH_EVENT'].astype(np.float32)
 
-fTrain = torch.from_numpy(x_train.values)
+xTrain = torch.from_numpy(xtrain.values)
-tTrain = torch.from_numpy(y_train.values.reshape(179,1))
+yTrain = torch.from_numpy(ytrain.values.reshape(179,1))
 
-fTest= torch.from_numpy(x_test.values)
+xTest = torch.from_numpy(xtest.values)
-tTest = torch.from_numpy(y_test.values)
+yTest = torch.from_numpy(ytest.values)
 
 batch_size = int(sys.argv[1]) if len(sys.argv) > 1 else 10
 num_epochs = int(sys.argv[2]) if len(sys.argv) > 2 else 5
-learning_rate = 0.001
+learning_rate = 0.002
 input_dim = 11
 output_dim = 1
 
@@ -48,14 +48,14 @@ for epoch in range(num_epochs):
     model.train()
     optimizer.zero_grad()
     # Forward pass
-    y_pred = model(fTrain)
+    y_pred = model(xTrain)
     # Compute Loss
-    loss = criterion(y_pred, tTrain)
+    loss = criterion(y_pred, yTrain)
     # print(loss.item())
     # Backward pass
     loss.backward()
     optimizer.step()
-y_pred = model(fTest)
+y_pred = model(xTest)
 print(y_pred.data)
 
 torch.save(model.state_dict(), 'DEATH_EVENT.pth')