init

.idea/.gitignore

@@ -0,0 +1,8 @@
+# Default ignored files
+/shelf/
+/workspace.xml
+# Datasource local storage ignored files
+/dataSources/
+/dataSources.local.xml
+# Editor-based HTTP Client requests
+/httpRequests/

.idea/misc.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectRootManager" version="2" languageLevel="JDK_16" project-jdk-name="gpu" project-jdk-type="Python SDK">
+    <output url="file://$PROJECT_DIR$/out" />
+  </component>
+</project>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/paranormal-or-skeptic-ISI-public.iml" filepath="$PROJECT_DIR$/.idea/paranormal-or-skeptic-ISI-public.iml" />
+    </modules>
+  </component>
+</project>

.idea/paranormal-or-skeptic-ISI-public.iml

@@ -0,0 +1,9 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="JAVA_MODULE" version="4">
+  <component name="NewModuleRootManager" inherit-compiler-output="true">
+    <exclude-output />
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

.idea/vcs.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="" vcs="Git" />
+  </component>
+</project>

log_reg.py

@@ -0,0 +1,86 @@
+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.l01 = torch.nn.Linear(300, 500)
+        self.l02 = torch.nn.Linear(500, 1)
+
+    def forward(self, x):
+        x = self.l01(x)
+        x = torch.relu(x)
+        x = self.l02(x)
+        x = torch.sigmoid(x)
+        return x
+
+
+def doc2vec(doc):
+    return np.mean([word2vec[word] for word in doc if word in word2vec] or [np.zeros(300)], axis=0)
+
+
+x_train = pd.read_table('train/in.tsv.xz', compression='xz', sep='\t', header=None, error_bad_lines=False, quoting=3)
+y_train = pd.read_table('train/expected.tsv', sep='\t', header=None, quoting=3)
+x_dev = pd.read_table('dev-0/in.tsv.xz', compression='xz', sep='\t', header=None, quoting=3)
+x_test = pd.read_table('test-A/in.tsv.xz', compression='xz', sep='\t', header=None, quoting=3)
+
+y_train = y_train[0]
+x_train = x_train[0].str.lower()
+x_train = [word_tokenize(x) for x in x_train]
+x_dev = x_dev[0].str.lower()
+x_dev = [word_tokenize(x) for x in x_dev]
+x_test = x_test[0].str.lower()
+x_test = [word_tokenize(x) for x in x_test]
+
+word2vec = gensim.load('word2vec-google-news-300')
+x_train = [doc2vec(doc) for doc in x_train]
+x_dev = [doc2vec(doc) for doc in x_dev]
+x_test = [doc2vec(doc) for doc in x_test]
+
+model = NeuralNetworkModel()
+BATCH_SIZE = 1024
+criterion = torch.nn.BCELoss()
+optimizer = torch.optim.Adam(model.parameters())
+
+for epoch in range(5):
+    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)
+        optimizer.zero_grad()
+        outputs = model(X.float())
+        loss = criterion(outputs, y)
+        loss.backward()
+        optimizer.step()
+
+y_dev = []
+y_test = []
+model.eval()
+
+with torch.no_grad():
+    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())
+        y = (outputs > 0.5)
+        y_dev.extend(y)
+
+    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())
+        y = (outputs >= 0.5)
+        y_test.extend(y)
+
+y_dev = np.asarray(y_dev, dtype=np.int32)
+Y_dev = pd.DataFrame({'label': y_dev})
+Y_dev.to_csv(r'dev-0/out.tsv', sep='\t', index=False, header=False)
+y_test = np.asarray(y_test, dtype=np.int32)
+Y_test = pd.DataFrame({'label': y_test})
+Y_test.to_csv(r'test-A/out.tsv', sep='\t', index=False, header=False)