Add final solution

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")

neural-network.py

@@ -1,102 +0,0 @@
-import os
-import pandas as pd
-import tensorflow as tf
-import numpy as np
-import torch
-import torch.nn as nn
-from tensorflow.keras.layers.experimental.preprocessing import TextVectorization
-
-os.environ['CUDA_VISIBLE_DEVICES'] = '-1'
-
-print('debug 1')
-train_df = pd.read_csv('train/in.tsv', header=None, sep='\t')
-test_df = pd.read_csv('test-A/in.tsv', header=None, sep='\t')
-dev_df = pd.read_csv('dev-0/in.tsv', header=None, sep='\t')
-train_expected = pd.read_csv('train/expected.tsv', header=None, sep='\t')
-
-train_text = train_df[0].tolist()
-test_text = test_df[0].tolist()
-dev_text = test_df[0].tolist()
-
-text_data = train_text + test_text + dev_text
-
-vectorize_layer = TextVectorization(max_tokens=5, output_mode="int")
-text_data = tf.data.Dataset.from_tensor_slices(text_data)
-vectorize_layer.adapt(text_data.batch(64))
-
-inputs = tf.keras.layers.Input(shape=(1,), dtype=tf.string, name="text")
-outputs = vectorize_layer(inputs)
-model = tf.keras.Model(inputs, outputs)
-
-print('uwaga debug')
-x_train = list(map(model.predict, train_text))
-y_train = train_expected[0]
-x_test = list(map(model.predict, test_text))
-loss_function = nn.CrossEntropyLoss()
-
-x_train = pd.DataFrame(x_train)
-x_test = pd.DataFrame(x_test)
-y_train = pd.DataFrame(y_train[0])
-
-# (model.predict(["Murder in the forset!"]))
-
-
-class FeedforwardNeuralNetModel(nn.Module):
-    def __init__(self, input_dim, hidden_dim, output_dim):
-        super(FeedforwardNeuralNetModel, self).__init__()
-        # Linear function
-        self.fc1 = nn.Linear(input_dim, hidden_dim)
-
-        # Non-linearity
-        self.sigmoid = nn.Sigmoid()
-
-        # Linear function (readout)
-        self.fc2 = nn.Linear(hidden_dim, output_dim)
-
-    def forward(self, x):
-        # Linear function  # LINEAR
-        out = self.fc1(x)
-
-        # Non-linearity  # NON-LINEAR
-        out = self.sigmoid(out)
-
-        # Linear function (readout)  # LINEAR
-        out = self.fc2(out)
-        return out
-
-num_epochs = 2
-
-for epoch in range(num_epochs):
-    if (epoch + 1) % 25 == 0:
-        print("Epoch completed: " + str(epoch + 1))
-    print(f"Epoch number: {epoch}")
-    train_loss = 0
-    for index, row in x_train.iterrows():
-        print(index)
-
-        # Forward pass to get output
-        probs = x_train[0][index]
-        # Get the target label
-        target = y_train[0][index]
-
-        # Calculate Loss: softmax --> cross entropy loss
-        loss = loss_function(probs, target)
-        # Accumulating the loss over time
-        train_loss += loss.item()
-
-        # Getting gradients w.r.t. parameters
-        loss.backward()
-
-
-
-    train_loss = 0
-
-
-bow_ff_nn_predictions = []
-original_lables_ff_bow = []
-with torch.no_grad():
-    for index, row in x_test.iterrows():
-        probs = x_test[0][index]
-        bow_ff_nn_predictions.append(torch.argmax(probs, dim=1).cpu().numpy()[0])
-
-print(bow_ff_nn_predictions)

neural-network2.py

@@ -1,151 +0,0 @@
-import pandas as pd
-from gensim.utils import simple_preprocess
-from gensim.parsing.porter import PorterStemmer
-from gensim import corpora
-
-import torch.nn as nn
-import torch.nn.functional as F
-import torch.optim as optim
-import torch
-
-
-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 F.softmax(out, dim=1)
-
-
-device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-
-train_expected = pd.read_csv('train/expected.tsv', header=None, sep='\t')
-train_df = pd.read_csv('train/in.tsv', header=None, sep='\t')
-# test_df = pd.read_csv('test-A/in.tsv', header=None, sep='\t')
-test_df = pd.read_csv('dev-0/in.tsv', header=None, sep='\t')
-y_train = pd.DataFrame(train_expected[0])
-
-
-train_df[0] = [simple_preprocess(text, deacc=True) for text in train_df[0]]
-porter_stemmer = PorterStemmer()
-train_df['stemmed_tokens'] = [[porter_stemmer.stem(word) for word in tokens] for tokens in train_df[0]]
-test_df[0] = [simple_preprocess(text, deacc=True) for text in test_df[0]]
-test_df['stemmed_tokens'] = [[porter_stemmer.stem(word) for word in tokens] for tokens in test_df[0]]
-
-x_test = pd.DataFrame(test_df['stemmed_tokens'])
-x_train = pd.DataFrame(train_df['stemmed_tokens'])
-
-
-def make_dict(top_data_df_small, padding=True):
-    if padding:
-        print("Dictionary with padded token added")
-        review_dict = corpora.Dictionary([['pad']])
-        review_dict.add_documents(top_data_df_small['stemmed_tokens'])
-    else:
-        print("Dictionary without padding")
-        review_dict = corpora.Dictionary(top_data_df_small['stemmed_tokens'])
-    return review_dict
-
-
-# Make the dictionary without padding for the basic models
-review_dict = make_dict(train_df, padding=False)
-
-VOCAB_SIZE = len(review_dict)
-NUM_LABELS = 2
-
-
-# Function to make bow vector to be used as input to network
-def make_bow_vector(review_dict, sentence):
-    vec = torch.zeros(VOCAB_SIZE, dtype=torch.float64, device=device)
-    for word in sentence:
-        vec[review_dict.token2id[word]] += 1
-    return vec.view(1, -1).float()
-
-
-input_dim = VOCAB_SIZE
-hidden_dim = 10
-output_dim = 2
-num_epochs = 2
-
-ff_nn_bow_model = FeedforwardNeuralNetModel(input_dim, hidden_dim, output_dim)
-ff_nn_bow_model.to(device)
-
-loss_function = nn.CrossEntropyLoss()
-optimizer = optim.SGD(ff_nn_bow_model.parameters(), lr=0.001)
-
-losses = []
-iter = 0
-
-def make_target(label):
-    if label == 0:
-        return torch.tensor([0], dtype=torch.long, device=device)
-    elif label == 1:
-        return torch.tensor([1], dtype=torch.long, device=device)
-
-
-# Start training
-for epoch in range(num_epochs):
-    if (epoch + 1) % 25 == 0:
-        print("Epoch completed: " + str(epoch + 1))
-    print(f"Epoch number: {epoch}")
-    train_loss = 0
-    for index, row in x_train.iterrows():
-        print(index)
-        # Clearing the accumulated gradients
-        optimizer.zero_grad()
-
-        # Make the bag of words vector for stemmed tokens
-        bow_vec = make_bow_vector(review_dict, row['stemmed_tokens'])
-
-        # Forward pass to get output
-        probs = ff_nn_bow_model(bow_vec)
-
-        # Get the target label
-        target = make_target(y_train[0][index])
-
-        # Calculate Loss: softmax --> cross entropy loss
-        loss = loss_function(probs, target)
-        # Accumulating the loss over time
-        train_loss += loss.item()
-
-        # Getting gradients w.r.t. parameters
-        loss.backward()
-
-        # Updating parameters
-        optimizer.step()
-
-    train_loss = 0
-
-
-bow_ff_nn_predictions = []
-original_lables_ff_bow = []
-with torch.no_grad():
-    for index, row in x_test.iterrows():
-        bow_vec = make_bow_vector(review_dict, row['stemmed_tokens'])
-        probs = ff_nn_bow_model(bow_vec)
-        bow_ff_nn_predictions.append(torch.argmax(probs, dim=1).cpu().numpy()[0])
-