001-kaggle-iris-test.py

"""
Here's the standard #1 - the iris test
"""


import pandas as pd

# Import the pandas dataset from the usual place. Everything as usual.

dataset = pd.read_csv('../input/iris.data.csv', names=['sepal_length', 'sepal_width', 'petal_length', 'petal_width', 'species'])

dataset['species'] = pd.Categorical(dataset['species']).codes

dataset = dataset.sample(frac=1, random_state=1234)

train_input = dataset.values[:120, :4]
train_target = dataset.values[:120, 4]

test_input = dataset.values[120:, :4]
test_target = dataset.values[120:, 4]

# Noe the PyTorch part.

import torch

torch.manual_seed(1234)

hidden_units = 5

net = torch.nn.Sequential(
    torch.nn.Linear(4, hidden_units),
    torch.nn.ReLU(),
    torch.nn.Linear(hidden_units, 3)
)

# the 'loss function' and the 'optimiser'
criterion = torch.nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(net.parameters(), lr=0.1, momentum=0.9)

# The training itself
epochs = 50

for epoch in range(epochs):
    inputs = torch.autograd.Variable(torch.Tensor(train_input).float())
    targets = torch.autograd.Variable(torch.Tensor(train_target).long())

    optimizer.zero_grad()
    out = net(inputs)
    loss = criterion(out, targets)
    loss.backward()
    optimizer.step()

    if epoch == 0 or (epoch + 1) % 10 == 0:
        print('Epoch %d Loss: %.4f' % (epoch + 1, loss.item()))

# Now test the result
import numpy as np

inputs = torch.autograd.Variable(torch.Tensor(test_input).float())
targets = torch.autograd.Variable(torch.Tensor(test_target).long())

optimizer.zero_grad()
out = net(inputs)
_, predicted = torch.max(out.data, 1)

error_count = test_target.size - np.count_nonzero((targets == predicted).numpy())
print('Errors: %d; Accuracy: %d%%' % (error_count, 100 * torch.sum(targets == predicted) / test_target.size))

"""
The result:
Epoch 1 Loss: 1.2181
Epoch 10 Loss: 0.6745
Epoch 20 Loss: 0.2447
Epoch 30 Loss: 0.1397
Epoch 40 Loss: 0.1001
Epoch 50 Loss: 0.0855
Errors: 0; Accuracy: 100%

Process finished with exit code 0

Worked. Really fast!
"""