finished basic ff model and torch data reader

classifier/nn_ff.py

@@ -1,9 +1,10 @@
-from utils.nn_reader import read_csv
+"""
+Simple feed-forward neural network in PyTorch for baseline results on Scicite data.
+Date: July 5th, 2020
+"""
 
 import torch
-
-
-
+from utils.nn_reader import read_csv_nn
 
 
 class Feedforward(torch.nn.Module):
@@ -26,63 +27,41 @@ class Feedforward(torch.nn.Module):
             return output
 
 
-"""
-from sklearn.datasets import make_blobs
-def blob_label(y, label, loc): # assign labels
-    target = numpy.copy(y)
-    for l in loc:
-        target[y == l] = label
-    return target
-X_train, y_train = make_blobs(n_samples=40, n_features=2, cluster_std=1.5, shuffle=True)
-X_train = torch.FloatTensor(X_train)
-y_train = torch.FloatTensor(blob_label(y_train, 0, [0]))
-y_train = torch.FloatTensor(blob_label(y_train, 1, [1,2,3]))
-x_test, y_test = make_blobs(n_samples=10, n_features=2, cluster_std=1.5, shuffle=True)
-x_test = torch.FloatTensor(x_test)
-y_test = torch.FloatTensor(blob_label(y_test, 0, [0]))
-y_test = torch.FloatTensor(blob_label(y_test, 1, [1,2,3]))
-"""
-
 
-X_train = torch.as_tensor(X_train)
-X_test = torch.as_tensor(X_test)
-y_train = torch.as_tensor(y_train)
+if __name__=='__main__':
+    X_train, y_train, X_test = read_csv_nn()
 
+    X_train = torch.FloatTensor(X_train)
+    X_test = torch.FloatTensor(X_test)
+    y_train_ = torch.FloatTensor(y_train)
+    y_train = torch.max(torch.FloatTensor(y_train_),1)[1]
 
     model = Feedforward(28, 9, 3)
     criterion = torch.nn.CrossEntropyLoss()
     optimizer = torch.optim.SGD(model.parameters(), lr = 0.01)
 
-
-
     model.eval()
     y_pred = model(X_train)
-y_pred = torch.Tensor([list(x).index(x.max()) for x in y_pred])
-y_pred = 
-before_train = criterion(y_train, y_pred)
+    before_train = criterion(y_pred, y_train)
     print('Test loss before training' , before_train.item())
 
-
-
     model.train()
-epoch = 20
+    epoch = 2000
     for epoch in range(epoch):
         optimizer.zero_grad()
-    # Forward pass
+        # forward pass
         y_pred = model(X_train)
-    # Compute Loss
-    loss = criterion(y_pred.squeeze(), y_train)
+        loss = criterion(y_pred, y_train)
        
         print('Epoch {}: train loss: {}'.format(epoch, loss.item()))
-    # Backward pass
+        # backward pass
         loss.backward()
         optimizer.step()
 
-
     model.eval()
-y_pred = model(X_test)
-after_train = criterion(y_pred.squeeze(), y_test) 
-print('Test loss after Training' , after_train.item())
+    y_pred = model(X_train)
+    after_train = criterion(y_pred, y_train) 
+    print('Training loss after training' , after_train.item())
 
 
 

utils/nn_reader.py

@@ -1,7 +1,11 @@
 import numpy as np
-from iterables import chain
+from itertools import chain
 from utils.csv import read_csv_file
 
+# TODO: clean up, transform into class, allow for command-line arguments
+
+def read_csv_nn(scicite_dir=None):
+
 	train_file_path = 'data/tsv/train.tsv'
 	test_file_path = 'data/tsv/test.tsv'
 	train_raw = read_csv_file(train_file_path, '\t')
@@ -25,7 +29,7 @@ y_dim = len(y_unique)
 	y_train = np.zeros((nobs,y_dim))
 
 	for j in range(y_dim):
-    y_train[:,j] = y_raw == y_unique[j]
+		y_train[:,j] = y_train_raw == y_unique[j]
 
 	test_raw = read_csv_file(test_file_path, '\t')
 	features = [x.features for x in test_raw]
@@ -40,4 +44,6 @@ for j in range(nfeats):
 			if f in features[i]:
 				X_test[i,j] = 1
 
+	return X_train, y_train, X_test
+