ium_151636/script7.py

import pandas as pd
import torch
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import DataLoader, Dataset
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelEncoder
import pickle
from sacred import Experiment
from sacred.observers import FileStorageObserver, MongoObserver

ex = Experiment("s151636", interactive=True, save_git_info=False)
ex.observers.append(FileStorageObserver('experiments'))
ex.observers.append(MongoObserver(url='mongodb://admin:IUM_2021@172.17.0.1:27017', db_name='sacred'))

# Define the neural network model
class Model(nn.Module):
    def __init__(self):
        super(Model, self).__init__()
        self.fc1 = nn.Linear(1, 64)
        self.fc2 = nn.Linear(64, 1)
        self.relu = nn.ReLU()

    def forward(self, x):
        x = self.fc1(x)
        x = self.relu(x)
        x = self.fc2(x)
        return x

# Define a custom dataset
class CustomDataset(Dataset):
    def __init__(self, X, y):
        self.X = torch.FloatTensor(X.values.reshape(-1, 1))
        self.y = torch.FloatTensor(y.values.reshape(-1, 1))

    def __len__(self):
        return len(self.X)

    def __getitem__(self, idx):
        return self.X[idx], self.y[idx]

@ex.main
def train_model():
    # Load the dataset
    df = pd.read_csv('data.csv')

    # Select the relevant columns (e.g., 'Rating' and 'Writer')
    data = df[['Rating', 'Writer']]

    # Drop rows with missing values
    data = data.dropna()

    # Convert the 'Writer' column to numeric using label encoding
    encoder = LabelEncoder()
    data['Writer'] = encoder.fit_transform(data['Writer'])

    # Split the data into training and testing sets
    X = data['Writer']
    y = data['Rating']

    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

    # Create the model instance
    model = Model()

    # Define the loss function and optimizer
    criterion = nn.MSELoss()
    optimizer = optim.Adam(model.parameters())

    # Create dataloaders for training and testing
    train_dataset = CustomDataset(X_train, y_train)
    test_dataset = CustomDataset(X_test, y_test)
    train_dataloader = DataLoader(train_dataset, batch_size=64, shuffle=True)
    test_dataloader = DataLoader(test_dataset, batch_size=64)

    # Train the model
    for epoch in range(10):
        model.train()
        for inputs, targets in train_dataloader:
            optimizer.zero_grad()
            outputs = model(inputs)
            loss = criterion(outputs, targets)
            loss.backward()
            optimizer.step()

    # Save the model to a file
    torch.save(model.state_dict(), 'model.pth')

    # Save the encoder to a file
    with open('encoder.pkl', 'wb') as f:
        pickle.dump(encoder, f)

    # Make predictions on new data
    new_writer = 'Jim Cash'
    new_writer_encoded = torch.tensor(encoder.transform([new_writer])).float()

    model.eval()
    rating_prediction = model(new_writer_encoded)
    print("Predicted rating for the writer 'Jim Cash':", rating_prediction.item())

    # Create dataloaders for evaluation
    test_dataset = CustomDataset(X_test, y_test)
    test_dataloader = DataLoader(test_dataset, batch_size=64)

    # Evaluate the model
    model.eval()
    predictions = []
    targets = []
    for inputs, targets_batch in test_dataloader:
        outputs = model(inputs)
        predictions.extend(outputs.tolist())
        targets.extend(targets_batch.tolist())

    # Calculate evaluation metrics
    predictions = torch.FloatTensor(predictions).squeeze()
    targets = torch.FloatTensor(targets).squeeze()

    rmse = mean_squared_error(targets, predictions, squared=False)


ex.run()