From e8a48f51f38deb296aa6c61b2c63a6d7b1afe4c6 Mon Sep 17 00:00:00 2001
From: Alicja Szulecka <73056579+AliSzu@users.noreply.github.com>
Date: Sun, 14 Apr 2024 12:24:44 +0200
Subject: [PATCH] model and prediction scripts
---
.../inspectionProfiles/profiles_settings.xml | 6 -
.idea/misc.xml | 4 -
.idea/vcs.xml | 6 -
.idea/workspace.xml | 76 ------------
model.py | 111 ++++++++++++++++++
prediction.py | 69 +++++++++++
6 files changed, 180 insertions(+), 92 deletions(-)
delete mode 100644 .idea/inspectionProfiles/profiles_settings.xml
delete mode 100644 .idea/misc.xml
delete mode 100644 .idea/vcs.xml
delete mode 100644 .idea/workspace.xml
create mode 100644 model.py
create mode 100644 prediction.py
diff --git a/.idea/inspectionProfiles/profiles_settings.xml b/.idea/inspectionProfiles/profiles_settings.xml
deleted file mode 100644
index 105ce2d..0000000
--- a/.idea/inspectionProfiles/profiles_settings.xml
+++ /dev/null
@@ -1,6 +0,0 @@
-
-
-
-
-
-
\ No newline at end of file
diff --git a/.idea/misc.xml b/.idea/misc.xml
deleted file mode 100644
index f5a93a6..0000000
--- a/.idea/misc.xml
+++ /dev/null
@@ -1,4 +0,0 @@
-
-
-
-
\ No newline at end of file
diff --git a/.idea/vcs.xml b/.idea/vcs.xml
deleted file mode 100644
index c8397c9..0000000
--- a/.idea/vcs.xml
+++ /dev/null
@@ -1,6 +0,0 @@
-
-
-
-
-
-
\ No newline at end of file
diff --git a/.idea/workspace.xml b/.idea/workspace.xml
deleted file mode 100644
index 68be8ea..0000000
--- a/.idea/workspace.xml
+++ /dev/null
@@ -1,76 +0,0 @@
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
- {
- "keyToString": {
- "RunOnceActivity.OpenProjectViewOnStart": "true",
- "RunOnceActivity.ShowReadmeOnStart": "true",
- "WebServerToolWindowFactoryState": "false",
- "last_opened_file_path": "/home/students/s464914/PycharmProjects/ium_464914",
- "node.js.detected.package.eslint": "true",
- "node.js.detected.package.tslint": "true",
- "node.js.selected.package.eslint": "(autodetect)",
- "node.js.selected.package.tslint": "(autodetect)",
- "vue.rearranger.settings.migration": "true"
- }
-}
-
-
-
-
- 1710696754593
-
-
- 1710696754593
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
\ No newline at end of file
diff --git a/model.py b/model.py
new file mode 100644
index 0000000..570e587
--- /dev/null
+++ b/model.py
@@ -0,0 +1,111 @@
+import torch
+import torch.nn as nn
+import torch.optim as optim
+from torch.utils.data import DataLoader, Dataset
+import pandas as pd
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import LabelEncoder
+import torch.nn.functional as F
+
+
+device = (
+ "cuda"
+ if torch.cuda.is_available()
+ else "cpu"
+)
+
+class Model(nn.Module):
+ def __init__(self, input_features=54, hidden_layer1=25, hidden_layer2=30, output_features=8):
+ super().__init__()
+ self.fc1 = nn.Linear(input_features,output_features)
+ self.bn1 = nn.BatchNorm1d(hidden_layer1) # Add batch normalization
+ self.fc2 = nn.Linear(hidden_layer1, hidden_layer2)
+ self.bn2 = nn.BatchNorm1d(hidden_layer2) # Add batch normalization
+ self.out = nn.Linear(hidden_layer2, output_features)
+
+ def forward(self, x):
+ x = F.relu(self.fc1(x)) # Apply batch normalization after first linear layer
+ #x = F.relu(self.bn2(self.fc2(x))) # Apply batch normalization after second linear layer
+ #x = self.out(x)
+ return x
+
+def main():
+ forest_train = pd.read_csv('forest_train.csv')
+ forest_val = pd.read_csv('forest_val.csv')
+
+ print(forest_train.head())
+
+
+ X_train = forest_train.drop(columns=['Cover_Type']).values
+ y_train = forest_train['Cover_Type'].values
+
+ X_val = forest_val.drop(columns=['Cover_Type']).values
+ y_val = forest_val['Cover_Type'].values
+
+
+ # Initialize model, loss function, and optimizer
+ model = Model().to(device)
+ criterion = nn.CrossEntropyLoss()
+ optimizer = optim.Adam(model.parameters(), lr=0.001)
+
+ # Convert to PyTorch tensors
+ X_train = torch.tensor(X_train, dtype=torch.float32).to(device)
+ y_train = torch.tensor(y_train, dtype=torch.long).to(device)
+ X_val = torch.tensor(X_val, dtype=torch.float32).to(device)
+ y_val = torch.tensor(y_val, dtype=torch.long).to(device)
+
+ # Create DataLoader
+ train_loader = DataLoader(list(zip(X_train, y_train)), batch_size=64, shuffle=True)
+ val_loader = DataLoader(list(zip(X_val, y_val)), batch_size=64)
+
+ # Training loop
+ epochs = 10
+ for epoch in range(epochs):
+ model.train() # Set model to training mode
+ running_loss = 0.0
+ for inputs, labels in train_loader:
+ inputs, labels = inputs.to(device), labels.to(device)
+
+ optimizer.zero_grad()
+
+ outputs = model(inputs)
+ loss = criterion(outputs, labels)
+ loss.backward()
+ optimizer.step()
+
+ running_loss += loss.item() * inputs.size(0)
+
+ # Calculate training loss
+ epoch_loss = running_loss / len(train_loader.dataset)
+
+ # Validation
+ model.eval() # Set model to evaluation mode
+ val_running_loss = 0.0
+ correct = 0
+ total = 0
+ with torch.no_grad():
+ for inputs, labels in val_loader:
+ inputs, labels = inputs.to(device), labels.to(device)
+
+ outputs = model(inputs)
+ val_loss = criterion(outputs, labels)
+ val_running_loss += val_loss.item() * inputs.size(0)
+
+ _, predicted = torch.max(outputs, 1)
+ total += labels.size(0)
+ correct += (predicted == labels).sum().item()
+
+ # Calculate validation loss and accuracy
+ val_epoch_loss = val_running_loss / len(val_loader.dataset)
+ val_accuracy = correct / total
+
+ print(f"Epoch {epoch+1}/{epochs}, "
+ f"Train Loss: {epoch_loss:.4f}, "
+ f"Val Loss: {val_epoch_loss:.4f}, "
+ f"Val Accuracy: {val_accuracy:.4f}")
+
+
+ torch.save(model.state_dict(), 'model.pth')
+
+if __name__ == "__main__":
+ main()
diff --git a/prediction.py b/prediction.py
new file mode 100644
index 0000000..f071bc4
--- /dev/null
+++ b/prediction.py
@@ -0,0 +1,69 @@
+import torch
+import torch.nn as nn
+import torch.optim as optim
+from torch.utils.data import DataLoader, Dataset
+import pandas as pd
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import LabelEncoder
+import torch.nn.functional as F
+
+device = (
+ "cuda"
+ if torch.cuda.is_available()
+ else "cpu"
+)
+
+class Model(nn.Module):
+ def __init__(self, input_features=54, hidden_layer1=25, hidden_layer2=30, output_features=8):
+ super().__init__()
+ self.fc1 = nn.Linear(input_features,output_features)
+ self.bn1 = nn.BatchNorm1d(hidden_layer1) # Add batch normalization
+ self.fc2 = nn.Linear(hidden_layer1, hidden_layer2)
+ self.bn2 = nn.BatchNorm1d(hidden_layer2) # Add batch normalization
+ self.out = nn.Linear(hidden_layer2, output_features)
+
+ def forward(self, x):
+ x = F.relu(self.fc1(x))
+ return x
+
+def load_model(model, model_path):
+ model.load_state_dict(torch.load(model_path))
+ model.eval()
+
+def predict(model, input_data):
+ # Convert input data to PyTorch tensor
+
+ # Perform forward pass
+ with torch.no_grad():
+ output = model(input_data)
+
+ _, predicted_class = torch.max(output, 0)
+
+ return predicted_class.item() # Return the predicted class label
+
+
+def main():
+ forest_test = pd.read_csv('forest_test.csv')
+
+ X_test = forest_test.drop(columns=['Cover_Type']).values
+ y_test = forest_test['Cover_Type'].values
+
+ X_test = torch.tensor(X_test, dtype=torch.float32).to(device)
+
+ model = Model().to(device)
+ model_path = 'model.pth' # Path to your saved model file
+ load_model(model, model_path)
+
+ predictions = []
+ for input_data in X_test:
+ predicted_class = predict(model, input_data)
+ predictions.append(predicted_class)
+
+ with open(r'predictions.txt', 'w') as fp:
+ for item in predictions:
+ # write each item on a new line
+ fp.write("%s\n" % item)
+
+
+if __name__ == "__main__":
+ main()
\ No newline at end of file