Merge remote-tracking branch 'origin/master'

# Conflicts:
#	neural-network.py

feed-forward-nn.py

@@ -0,0 +1,169 @@
+import csv
+
+import gensim.downloader
+import numpy as np
+import pandas as pd
+import torch
+import torch.nn as nn
+from nltk import word_tokenize
+
+
+# Feed forward neural network model
+class FeedforwardNeuralNetModel(nn.Module):
+    def __init__(self, input_dim, hidden_dim, output_dim):
+        super(FeedforwardNeuralNetModel, self).__init__()
+
+        # Linear function 1: vocab_size --> 500
+        self.fc1 = nn.Linear(input_dim, hidden_dim)
+        # Non-linearity 1
+        self.relu1 = nn.ReLU()
+
+        # Linear function 2: 500 --> 500
+        self.fc2 = nn.Linear(hidden_dim, hidden_dim)
+        # Non-linearity 2
+        self.relu2 = nn.ReLU()
+
+        # Linear function 3 (readout): 500 --> 3
+        self.fc3 = nn.Linear(hidden_dim, output_dim)
+
+    def forward(self, x):
+        # Linear function 1
+        out = self.fc1(x)
+        # Non-linearity 1
+        out = self.relu1(out)
+
+        # Non-linearity 2
+        out = self.relu2(out)
+
+        # Linear function 3 (readout)
+        out = self.fc3(out)
+
+        return torch.sigmoid(out)
+
+
+col_names = ["content", "id", "label"]
+
+# Loading dataset
+train_set_features = pd.read_table(
+    "train/in.tsv.xz",
+    error_bad_lines=False,
+    quoting=csv.QUOTE_NONE,
+    header=None,
+    names=col_names[:2],
+)
+train_set_labels = pd.read_table(
+    "train/expected.tsv",
+    error_bad_lines=False,
+    quoting=csv.QUOTE_NONE,
+    header=None,
+    names=col_names[2:],
+)
+dev_set = pd.read_table(
+    "dev-0/in.tsv.xz",
+    error_bad_lines=False,
+    header=None,
+    quoting=csv.QUOTE_NONE,
+    names=col_names[:2],
+)
+test_set = pd.read_table(
+    "test-A/in.tsv.xz",
+    error_bad_lines=False,
+    header=None,
+    quoting=csv.QUOTE_NONE,
+    names=col_names[:2],
+)
+
+
+# Lowercase text
+X_train = train_set_features["content"].str.lower()
+y_train = train_set_labels["label"]
+
+X_dev = dev_set["content"].str.lower()
+X_test = test_set["content"].str.lower()
+
+# Tokenize text with nltk
+X_train = [word_tokenize(content) for content in X_train]
+X_dev = [word_tokenize(content) for content in X_dev]
+X_test = [word_tokenize(content) for content in X_test]
+
+# Vectorize text
+word2vec = gensim.downloader.load("word2vec-google-news-300")
+X_train = [
+    np.mean(
+        [word2vec[word] for word in content if word in word2vec] or [np.zeros(300)],
+        axis=0,
+    )
+    for content in X_train
+]
+X_dev = [
+    np.mean(
+        [word2vec[word] for word in content if word in word2vec] or [np.zeros(300)],
+        axis=0,
+    )
+    for content in X_dev
+]
+X_test = [
+    np.mean(
+        [word2vec[word] for word in content if word in word2vec] or [np.zeros(300)],
+        axis=0,
+    )
+    for content in X_test
+]
+
+# Model config
+input_dim = 300
+hidden_layer = 600
+output_dim = 1
+batch_size = 10
+epochs = 10
+
+# Model init
+model = FeedforwardNeuralNetModel(input_dim, hidden_layer, output_dim)
+optimizer = torch.optim.SGD(model.parameters(), lr=0.01)
+criterion = torch.nn.BCELoss()
+
+# Learning model
+for epoch in range(epochs):
+    model.train()
+    for i in range(0, y_train.shape[0], batch_size):
+        X = X_train[i : i + batch_size]
+        X = torch.tensor(X)
+        y = y_train[i : i + batch_size]
+        y = torch.tensor(y.astype(np.float32).to_numpy()).reshape(-1, 1)
+
+        outputs = model(X.float())
+        loss = criterion(outputs, y)
+
+        optimizer.zero_grad()
+        loss.backward()
+        optimizer.step()
+
+
+# Making predictions for dev-0 & and test-A
+test_prediction = []
+dev_prediction = []
+model.eval()
+with torch.no_grad():
+    for i in range(0, len(X_test), batch_size):
+        X = X_test[i : i + batch_size]
+        X = torch.tensor(X)
+
+        outputs = model(X.float())
+
+        prediction = outputs > 0.5
+        test_prediction += prediction.tolist()
+
+    for i in range(0, len(X_dev), batch_size):
+        X = X_dev[i : i + batch_size]
+        X = torch.tensor(X)
+
+        outputs = model(X.float())
+
+        prediction = outputs > 0.5
+        dev_prediction += prediction.tolist()
+
+
+test_prediction = np.asarray(test_prediction, dtype=np.int32)
+dev_prediction = np.asarray(dev_prediction, dtype=np.int32)
+test_prediction.tofile("./test-A/out.tsv", sep="\n")
+dev_prediction.tofile("./dev-0/out.tsv", sep="\n")