Merge branch 'master' of https://git.wmi.amu.edu.pl/s426289/paranormal-or-skeptic-ISI-public

main.py

@@ -0,0 +1,94 @@
+import gensim.downloader as gensim
+import numpy as np
+import pandas as pd
+import torch
+from nltk.tokenize import word_tokenize
+
+
+class NeuralNetworkModel(torch.nn.Module):
+    def __init__(self):
+        super(NeuralNetworkModel, self).__init__()
+        self.1 = torch.nn.Linear(300, 300)
+        self.2 = torch.nn.Linear(300, 1)
+
+    def forward(self, x):
+        x = self.1(x)
+        x = torch.relu(x)
+        x = self.2(x)
+        x = torch.sigmoid(x)
+        return x
+        
+nm = NeuralNetworkModel()
+dev_train = []
+test_train = []
+word2vec = gensim.load('word2vec-google-news-300')
+
+
+np.mean([word2vec[word] for word in doc if word in word2vec] or [np.zeros(300)], axis=0)
+
+
+def model_train():
+
+train = pd.read_table('train/in.tsv.xz', compression='xz', sep='\t', quoting=3)
+trainy = pd.read_table('train/expected.tsv', sep='\t', quoting=3)
+trainy = trainy[0]
+
+def model_prepare():
+dev = pd.read_table('dev-0/in.tsv.xz', compression='xz', sep='\t', quoting=3)
+test = pd.read_table('test-A/in.tsv.xz', compression='xz', sep='\t', quoting=3)
+
+
+
+train = [word_tokenize(x) for x in train]
+dev = [word_tokenize(x) for x in dev]
+test = [word_tokenize(x) for x in test]
+
+
+
+def word_2_voc():
+train = [d2v(doc) for doc in train]
+dev = [d2v(doc) for doc in dev]
+test = [d2v(doc) for doc in test]
+
+
+criterion = torch.nn.BCELoss()
+optimizer = torch.optim.Adam(model.parameters())
+
+print ("1")
+
+for epoch in range(5):
+    model.train()
+    for i in range(0, y_train.shape[0], 5):
+        X = train[i:i + 5]
+        X = torch.tensor(X)
+        y = trainy[i:i + 5]
+        y = torch.tensor(y.astype(np.float32).to_numpy()).reshape(-1, 1)
+        optimizer.zero_grad()
+        outputs = nm(X.float())
+        loss = criterion(outputs, y)
+        loss.backward()
+        optimizer.step()
+
+
+
+print ("2")
+
+with torch.no_grad():
+    for i in range(0, len(dev), 5):
+        X = dev[i:i + 5]
+        X = torch.tensor(X)
+        outputs = nm(X.float())
+        y = (outputs > 0.5)
+        dev_train.extend(y)
+
+    for i in range(0, len(test), 5):
+        X = test[i:i + 5]
+        X = torch.tensor(X)
+        outputs = nm(X.float())
+        y = (outputs >= 0.5)
+        testy.extend(y)
+
+
+dev_train.to_csv(r'dev-0/out.tsv', sep='\t', index=False, header=False)
+test_train.to_csv(r'test-A/out.tsv', sep='\t', index=False, header=False)
+