s444356

.idea/.gitignore

@@ -0,0 +1,3 @@
+# Default ignored files
+/shelf/
+/workspace.xml

.idea/inspectionProfiles/Project_Default.xml

@@ -0,0 +1,18 @@
+<component name="InspectionProjectProfileManager">
+  <profile version="1.0">
+    <option name="myName" value="Project Default" />
+    <inspection_tool class="PyUnresolvedReferencesInspection" enabled="true" level="WARNING" enabled_by_default="true">
+      <option name="ignoredIdentifiers">
+        <list>
+          <option value="main.*" />
+          <option value="nltk.translate.bleu_score.corpus_bleu" />
+        </list>
+      </option>
+    </inspection_tool>
+    <inspection_tool class="SpellCheckingInspection" enabled="false" level="TYPO" enabled_by_default="false">
+      <option name="processCode" value="true" />
+      <option name="processLiterals" value="true" />
+      <option name="processComments" value="true" />
+    </inspection_tool>
+  </profile>
+</component>

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/misc.xml

@@ -0,0 +1,4 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.8 (base)" project-jdk-type="Python SDK" />
+</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 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <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="$PROJECT_DIR$" vcs="Git" />
+  </component>
+</project>

run.py

@@ -0,0 +1,49 @@
+from naivebayes import NaiveBayesTextClassifier
+from spacy.lang.en.stop_words import STOP_WORDS as en_stop
+
+naive_bayes = NaiveBayesTextClassifier(
+    categories=[0, 1],
+    stop_words=en_stop
+)
+
+with open('train/in.tsv', 'r', encoding='utf8') as f:
+    train = f.readlines()
+
+with open('train/expected.tsv', 'r', encoding='utf8') as f:
+    expected = f.readlines()
+
+for i in range(0, len(expected)):
+    expected[i] = int(expected[i])
+
+step = 15000
+start, end = 0, step
+
+for i in range(0, len(expected), step):
+    naive_bayes.train(train[start:end], expected[start:end])
+    if start + step < len(expected):
+        start += step
+    else:
+        start = 0
+    end = min(start + step, len(expected))
+
+
+
+with open('dev-0/in.tsv', 'r', encoding='utf8') as f:
+    dev_0 = f.readlines()
+
+predicted_dev_0 = naive_bayes.classify(dev_0)
+
+with open('dev-0/out.tsv', 'wt') as f:
+    for p in predicted_dev_0:
+        f.write(str(p) + '\n')
+f.close()
+
+with open('test-A/in.tsv', 'r', encoding='utf8') as f:
+    test_A = f.readlines()
+
+predicted_test_A = naive_bayes.classify(test_A)
+
+with open('test-A/out.tsv', 'wt') as f:
+    for p in predicted_test_A:
+        f.write(str(p) + '\n')
+f.close()