
import project 

import numpy as np
import torch

project.notebook()


records = project.sql_query(""" 
    SELECT vector, category FROM talks
    WHERE  vector IS NOT NULL
    ORDER BY slug ASC;
""")

(x, y), (z, t)                       \
    = train_set, test_set            \
    = splits                         \
    = project.split_in_sets( records )

project.describe_sets(splits)

train_set  =>  (0, 1376) (1, 1572) (2, 1052) 
test_set   =>  (0,  243) (1,  275) (2,  192)


class Network(torch.nn.Module): 
    
    def __init__(self):
        super().__init__()
        
        self.fc1  = torch.nn.Linear( 300, 200 )
        self.fc2  = torch.nn.Linear( 200, 100 )
        self.fc3  = torch.nn.Linear( 100,  50 )
        self.fc4  = torch.nn.Linear(  50,  10 )
        self.fc5  = torch.nn.Linear(  10,   3 )
    
    def forward(self, x):
        
        x = x.reshape(x.shape[0], -1)

        x = torch.nn.functional.relu( self.fc1(x) )
        x = torch.nn.functional.relu( self.fc2(x) )
        x = torch.nn.functional.relu( self.fc3(x) )
        x = torch.nn.functional.relu( self.fc4(x) )
        x = torch.nn.functional.relu( self.fc5(x) )
        
        return x

model = Network()
print(model)

criterion = torch.nn.CrossEntropyLoss(
    weight=project.class_weights(y, as_type='tensor')
)

optimizer = torch.optim.AdamW (
    model.parameters(),
    lr=.001, eps=1e-08, weight_decay=.01
)

performance = project.train_nn ( model, x, y, criterion,optimizer, epochs=10, li=1000 )
results     = project.test_nn  ( model, z, t )

t, p, (accuracy,precision,recall), rl = results
project.plot_train(performance)

Network(
  (fc1): Linear(in_features=300, out_features=200, bias=True)
  (fc2): Linear(in_features=200, out_features=100, bias=True)
  (fc3): Linear(in_features=100, out_features=50, bias=True)
  (fc4): Linear(in_features=50, out_features=10, bias=True)
  (fc5): Linear(in_features=10, out_features=3, bias=True)
)
AdamW (
Parameter Group 0
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1e-08
    lr: 0.001
    weight_decay: 0.01
)
CrossEntropyLoss()

TRAINING

  0%|          | 0/4000 [00:00<?, ?it/s]

loss 1000:  1.069
loss 2000:  0.921
loss 3000:  0.785
loss 4000:  0.762

  0%|          | 0/4000 [00:00<?, ?it/s]

loss 1000:  0.712
loss 2000:  0.696
loss 3000:  0.695
loss 4000:  0.692

  0%|          | 0/4000 [00:00<?, ?it/s]

loss 1000:  0.656
loss 2000:  0.645
loss 3000:  0.673
loss 4000:  0.662

  0%|          | 0/4000 [00:00<?, ?it/s]

loss 1000:  0.638
loss 2000:  0.622
loss 3000:  0.655
loss 4000:  0.652

  0%|          | 0/4000 [00:00<?, ?it/s]

Feed-Forward Neural Network in PyTorch¶