zad5

Dockerfile

@@ -13,6 +13,7 @@ WORKDIR /app
 # Skopiujmy nasz skrypt do katalogu /app w kontenerze
 COPY ./skrypt_download.py ./
 COPY ./skrypt_stat.py ./
+COPY ./IUM_05.py ./
 
 RUN mkdir /.kaggle
 RUN chmod -R 777 /.kaggle

IUM_05.py

@@ -0,0 +1,152 @@
+from sklearn.model_selection import train_test_split
+import torch
+import torch.nn as nn
+import pandas as pd
+import torch.nn.functional as F
+from torch.utils.data import DataLoader, TensorDataset, random_split
+from sklearn import preprocessing
+
+results = pd.read_csv('results.csv')
+#brak wierszy z NaN
+results.dropna()
+
+#normalizacja itp
+for collumn in ['home_team', 'away_team', 'tournament', 'city', 'country']:
+    results[collumn] = results[collumn].str.lower()
+
+categorical_cols = results.select_dtypes(include=object).columns.values
+
+
+train, test = train_test_split(results, test_size= 1 - 0.4)
+
+#valid, test = train_test_split(test, test_size=0.5)
+input_cols = train.columns.values[1:-1]
+output_cols = train.columns.values[-1:]
+
+
+def dataframe_to_arrays(dataframe):
+    # Make a copy of the original dataframe
+    dataframe1 = dataframe.copy(deep=True)
+    # 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()
+    x_scaled = min_max_scaler.fit_transform(dataframe1)
+    dataframe1 = pd.DataFrame(x_scaled, columns = dataframe1.columns)
+
+    inputs_array = dataframe1[input_cols].to_numpy()
+    targets_array = dataframe1[output_cols].to_numpy()
+    return inputs_array, targets_array
+
+inputs_array_training, targets_array_training = dataframe_to_arrays(train)
+
+
+inputs_array_testing, targets_array_testing = dataframe_to_arrays(test)
+
+
+inputs_training = torch.from_numpy(inputs_array_training).type(torch.float32)
+targets_training = torch.from_numpy(targets_array_training).type(torch.float32)
+
+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)
+
+batch_size = 64
+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()
+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)                # fill this
+    prediction = predictions[0].detach()
+    print("Prediction:", prediction)
+    if prediction >= 0.5:
+      print('Neutral')
+    else:
+      print('not neutral')
+
+
+
+for i in range(len(val_dataset)):
+    input, target = val_dataset[i]
+    predict_single(input, target, model)
+
+
+torch.save(model.state_dict(), 'FootballModel.pth')

Jenkinsfile

@@ -27,10 +27,12 @@ node {
 					def image = docker.build("s434732/ium") 
 					image.inside {
 					sh 'python3 ./skrypt_download.py'
+					sh 'python3 ./IUM_05.py > model.txt'
 					
 					archiveArtifacts "train.csv"
 					archiveArtifacts "test.csv"
 					archiveArtifacts "valid.csv"
+					archiveArtifacts 'model.txt'
 					
 					}
                     

skrypt_download.py

@@ -15,7 +15,7 @@ results.dropna()
 #normalizacja itp
 for collumn in ['home_team', 'away_team', 'tournament', 'city', 'country']:
     results[collumn] = results[collumn].str.lower()
-    
+
 # Podział zbioru 6:1:1
 train, test = train_test_split(results, test_size= 1 - 0.6)