torch part 1

main.py

@@ -3,7 +3,38 @@ from sklearn.preprocessing import LabelEncoder
 from sklearn.naive_bayes import GaussianNB, MultinomialNB
 from sklearn.pipeline import Pipeline
 from sklearn.feature_extraction.text import TfidfVectorizer
+import torch
+from gensim import downloader
+from nltk.tokenize import word_tokenize
 
+class NetworkModel(torch.nn.Module):
+
+    def __init__(self):
+        dim = 200
+        super(NeuralNetworkModel, self).__init__()
+        self.fc1 = torch.nn.Linear(dim, 500)
+        self.fc2 = torch.nn.Linear(500, 1)
+
+    def forward(self, x):
+        x = self.fc1(x)
+        x = torch.relu(x)
+        x = self.fc2(x)
+        x = torch.sigmoid(x)
+        return x
+
+word2vec = downloader.load("word2vec-google-news-300")
+
+def word2vecOnDoc(document):
+    return numpy.mean(
+        [word2vec[token] for token in document if token in word2vec] or [numpy.zeros(300)],
+        axis=0,
+    )
+
+def prepareData(data):
+    data = [word_tokenize(row) for row in data]
+    print(data)
+    data = [word2vecOnDoc(document) for document in data]
+    return data
 
 def trainModel(trainFileIn, trainFileExpected):
     with open(trainFileExpected, 'r') as f:
@@ -12,23 +43,47 @@ def trainModel(trainFileIn, trainFileExpected):
     with open(trainFileIn, 'r') as f:
         inData = f.readlines()
 
-    expectedDataEncoded = LabelEncoder().fit_transform(expectedData)
+    expectedData = prepareData(expectedData)
+    inData = prepareData(inData)
+#    networkModel = NetworkModel(300, 300, 1)
+#    criterion = torch.nn.BCELoss()
+#    optim = torch.optim.SGD(network.parameters(), lr=0.02)
+#    epochs = 1
+#    batchSize = 2
 
-    pipeline = Pipeline(steps=[
-        ('tfidf', TfidfVectorizer()),
-        ('naive-bayes', MultinomialNB())
-    ])
-
-    return pipeline.fit(inData, expectedDataEncoded)
+#    for _ in range(epochs):
+#        network.train()
+#        for i in range(0, inData.shape[0], batchSize):
+#            x = inData[i : i + batchSize]
+#            x = torch.tensor(x)
+#            y = expectedData[i : i + batchSize]
+#            y = torch.tensor(y.astype(np.float32).to_numpy()).reshape(-1, 1)
+#            outputs = network(x.float())
+#            loss = criterion(outputs, y)
+#            print(loss)
+#            optim.zero_grad()
+#            loss.backward()
+#            optim.step()
+#    return networkModel
 
 def evaluateModel(model, inFile, outFile):
-    with open(inFile, 'r') as f:
-        inData = f.readlines()
-    prediction = model.predict(inData)
-    numpy.savetxt(outFile, prediction, fmt='%d', delimiter='\n')
+    with open(inFile, 'r') as f: 
+       inData = f.readlines()
+
+    inData = prepareData(inData)
+
+    pred = []
+    with torch.no_grad():
+        for i in range(0, len(inData), batch_size):
+            x = inData[i : i + batch_size]
+            x = torch.tensor(x)
+            outputs = model(x.float())
+            prediction = outputs >= 0.5
+            pred += prediction.tolist()
+    numpy.asarray(pred, dtype=numpyp.int32).tofile(outFile, sep="\n")
 
 model = trainModel("train/in.tsv", "train/expected.tsv")
-evaluateModel(model, "dev-0/in.tsv", "dev-0/out.tsv")
-evaluateModel(model, "test-A/in.tsv", "test-A/out.tsv")
+#evaluateModel(model, "dev-0/in.tsv", "dev-0/out.tsv")
+#evaluateModel(model, "test-A/in.tsv", "test-A/out.tsv")