main.py

@@ -1,121 +0,0 @@
-from gensim.models import KeyedVectors
-import nltk
-import numpy as np
-import pandas as pd
-import torch
-import csv
-
-# nltk.download('punkt')
-
-# http://dsmodels.nlp.ipipan.waw.pl/dsmodels/wiki-forms-all-100-skipg-ns.txt.gz
-# word2vec = KeyedVectors.load_word2vec_format(
-#     'wiki-forms-all-100-skipg-ns.txt.gz', binary=False)
-# word2vec.save("word2vec.bin")
-
-def ReadFile(path):
-    variable = pd.read_table(path, error_bad_lines=False,
-                             sep='\t', quoting=csv.QUOTE_NONE, header=None)
-    return variable
-
-
-train = ReadFile('train/train.tsv')
-x_dev = ReadFile('dev-0/in.tsv')
-y_dev = ReadFile('dev-0/expected.tsv')
-x_test = ReadFile('test-A/in.tsv')
-
-x_train = train[1].values
-y_train = train[0].values
-x_dev = x_dev[0].values
-x_test = x_test[0].values
-batch_size = 12
-
-word2vec = KeyedVectors.load("word2vec.bin")
-
-
-
-def Tokenize(data):
-    new_data = [nltk.word_tokenize(x) for x in data]
-
-    for doc in new_data:
-        i = 0
-        while i < len(doc):
-            if doc[i].isalpha():
-                doc[i] = doc[i].lower()
-            else:
-                del doc[i]
-            i += 1
-    return new_data
-
-
-def Generate(path):
-    predict = model(torch.tensor(x_dev_vec.astype(np.float32)))
-    predict = predict.cpu().detach().numpy()
-    predict = (predict > 0.5)
-    predict = np.asarray(predict, dtype=np.int32)
-    predict.tofile(path, sep='\n')
-
-
-x_train_tokenized = Tokenize(x_train)
-x_dev_tokenized = Tokenize(x_dev)
-x_test_tokenized = Tokenize(x_test)
-
-x_train = [np.mean([word2vec[word] for word in content if word in word2vec] or [
-    np.zeros(100)], axis=0) for content in x_train]
-x_train_tensor = torch.tensor(
-    np.array(x_train, dtype=np.float32).astype(np.float32))
-x_train_vec = np.array(x_train, dtype=np.float32)
-
-x_dev = [np.mean([word2vec[word] for word in content if word in word2vec] or [
-    np.zeros(100)], axis=0) for content in x_dev]
-x_dev_vec = np.array(x_dev, dtype=np.float32)
-
-x_test = [np.mean([word2vec[word] for word in content if word in word2vec] or [
-    np.zeros(100)], axis=0) for content in x_test]
-x_test_vec = np.array(x_test, dtype=np.float32)
-
-
-class Model(torch.nn.Module):
-
-    def __init__(self):
-        super(Model, self).__init__()
-        self.var1 = torch.nn.Linear(100, 200)
-        self.var2 = torch.nn.Linear(200, 1)
-
-    def forward(self, x):
-        x = self.var1(x)
-        x = torch.relu(x)
-        x = self.var2(x)
-        x = torch.sigmoid(x)
-        return x
-
-
-
-model = Model()
-criterion = torch.nn.BCELoss()
-optimizer = torch.optim.SGD(model.parameters(), lr=0.01)
-
-for element in range(7):
-    loss_score = 0
-    acc_score = 0
-    items_total = 0
-    model.train()
-
-    for i in range(0, y_train.shape[0], batch_size):
-        X = x_train_vec[i:i + batch_size]
-        X = torch.tensor(X.astype(np.float32))
-        Y = y_train[i:i + batch_size]
-        Y = torch.tensor(Y.astype(np.float32)).reshape(-1, 1)
-        Y_predictions = model(X)
-        acc_score += torch.sum((Y_predictions > 0.5) == Y).item()
-        items_total += Y.shape[0]
-
-        optimizer.zero_grad()
-        loss = criterion(Y_predictions, Y)
-        loss.backward()
-        optimizer.step()
-
-        loss_score += loss.item() * Y.shape[0]
-    print(element)
-
-Generate('dev-0/out.tsv')
-Generate('test-A/out.tsv')