Log

results.txt

@@ -0,0 +1,5 @@
+Likelihood	0.0000
+Accuracy	0.7574
+F1.0	0.6305
+Precision	0.6840
+Recall	0.5847

script.py

@@ -0,0 +1,114 @@
+import gensim.downloader
+from nltk.tokenize import word_tokenize
+import numpy as np
+import pandas as pd
+import torch
+
+
+word2vec = gensim.downloader.load("word2vec-google-news-300")
+
+
+def get_word2vec(document):
+    return np.mean(
+        [word2vec[token] for token in document if token in word2vec] or [np.zeros(300)],
+        axis=0,
+    )
+
+
+class LogNetwork(torch.nn.Module):
+    def __init__(self, input_size, hidden_size, num_classes):
+        super(LogNetwork, self).__init__()
+        self.fc1 = torch.nn.Linear(input_size, hidden_size)
+        self.fc2 = torch.nn.Linear(hidden_size, num_classes)
+
+    def forward(self, x):
+        x = self.fc1(x)
+        x = torch.relu(x)
+        x = self.fc2(x)
+        x = torch.sigmoid(x)
+        return x
+
+
+train_x = pd.read_table(
+    "train/in.tsv.xz",
+    error_bad_lines=False,
+    header=None,
+    quoting=3,
+    usecols=["content"],
+    names=["content", "id"],
+    nrows=225000,
+)
+train_y = pd.read_table(
+    "train/expected.tsv",
+    error_bad_lines=False,
+    header=None,
+    quoting=3,
+    usecols=["label"],
+    names=["label"],
+    nrows=225000,
+)
+dev_x = pd.read_table(
+    "dev-0/in.tsv.xz",
+    error_bad_lines=False,
+    header=None,
+    quoting=3,
+    usecols=["content"],
+    names=["content", "id"],
+)
+test_x = pd.read_table(
+    "test-A/in.tsv.xz",
+    error_bad_lines=False,
+    header=None,
+    quoting=3,
+    usecols=["content"],
+    names=["content", "id"],
+)
+
+train_x = [word_tokenize(row) for row in train_x.content.str.lower()]
+dev_x = [word_tokenize(row) for row in dev_x.content.str.lower()]
+test_x = [word_tokenize(row) for row in test_x.content.str.lower()]
+
+train_x = [get_word2vec(document) for document in train_x]
+dev_x = [get_word2vec(document) for document in dev_x]
+test_x = [get_word2vec(document) for document in test_x]
+
+network = LogNetwork(300, 600, 1)
+criterion = torch.nn.BCELoss()
+optim = torch.optim.SGD(network.parameters(), lr=0.01)
+epochs = 7
+batch_size = 15
+
+for _ in range(epochs):
+    network.train()
+    for i in range(0, train_y.shape[0], batch_size):
+        x = train_x[i : i + batch_size]
+        x = torch.tensor(x)
+        y = train_y[i : i + batch_size]
+        y = torch.tensor(y.astype(np.float32).to_numpy()).reshape(-1, 1)
+        outputs = network(x.float())
+        loss = criterion(outputs, y)
+        optim.zero_grad()
+        loss.backward()
+        optim.step()
+
+
+dev_pred = []
+test_pred = []
+with torch.no_grad():
+    for i in range(0, len(dev_x), batch_size):
+        x = dev_x[i : i + batch_size]
+        x = torch.tensor(x)
+        outputs = network(x.float())
+        prediction = outputs >= 0.5
+        dev_pred += prediction.tolist()
+    for i in range(0, len(test_x), batch_size):
+        x = test_x[i : i + batch_size]
+        x = torch.tensor(x)
+        outputs = network(x.float())
+        prediction = outputs >= 0.5
+        test_pred += prediction.tolist()
+
+np.asarray(dev_pred, dtype=np.int32).tofile("./dev-0/out.tsv", sep="\n")
+np.asarray(test_pred, dtype=np.int32).tofile("./test-A/out.tsv", sep="\n")
+
+print("Saved")