def train_regression(net: Network,
dataset: pd.DataFrame,
max_epochs: int,
learning_rate: float,
batch_size: int = 1):
"""
Train net for a regression task.
The dataset consists of features and regression value (in the last column).
"""
train_df, valid_df = split_dataset(dataset, 0.2)
train_losses = []
validation_losses = []
for epoch in range(max_epochs):
train_loss = 0
validation_loss = 0
for i in range(0, len(train_df) - batch_size, batch_size):
x = np.array(train_df.iloc[i:i + batch_size, :-1])
y = np.reshape(np.array(train_df.iloc[i:i + batch_size, -1]),
(batch_size, 1))
loss = net.fit(x, y, learning_rate, batch_size)
train_loss += loss
for i in range(0, len(valid_df) - batch_size, batch_size):
x = np.array(valid_df.iloc[i:i + batch_size, :-1])
y = np.reshape(np.array(valid_df.iloc[i:i + batch_size, -1]),
(batch_size, 1))
loss = net.validate(x, y, learning_rate, batch_size)
validation_loss += loss
train_losses.append(train_loss / len(train_df))
validation_losses.append(validation_loss / len(valid_df))
return train_losses, validation_losses
def train_classification(net: Network,
dataset: pd.DataFrame,
max_epochs: int,
learning_rate: float,
batch_size: int = 1,
multiclass: bool = False):
"""
Train net for a classification task.
The dataset consists of features and class label (in the last column).
If the multiclass is True, uses one-hot encoding.
"""
train_df, valid_df = split_dataset(dataset, 0.2)
train_y_df = pd.get_dummies(
train_df['cls'], dtype=float) if multiclass else train_df['cls'] - 1.0
valid_y_df = pd.get_dummies(
valid_df['cls'], dtype=float) if multiclass else valid_df['cls'] - 1.0
y_dim = train_y_df.shape[1] if multiclass else 1
train_losses = []
validation_losses = []
for epoch in range(max_epochs):
train_loss = 0
validation_loss = 0
for i in range(0, len(train_df) - batch_size, batch_size):
x = np.array(train_df.iloc[i:i + batch_size, :-1])
y = np.reshape(np.array(train_y_df.iloc[i:i + batch_size]),
(batch_size, y_dim))
loss = net.fit(x, y, learning_rate, batch_size)
train_loss += loss
for i in range(0, len(valid_df) - batch_size, batch_size):
x = np.array(valid_df.iloc[i:i + batch_size, :-1])
y = np.reshape(np.array(valid_y_df.iloc[i:i + batch_size]),
(batch_size, y_dim))
loss = net.validate(x, y, learning_rate, batch_size)
validation_loss += loss
train_losses.append(train_loss / len(train_df))
validation_losses.append(validation_loss / len(valid_df))
return train_losses, validation_losses
