done

.idea/.gitignore

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

.idea/inspectionProfiles/Project_Default.xml

@@ -0,0 +1,12 @@
+<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="script.many_stop_words" />
+        </list>
+      </option>
+    </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" 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>

script.py

@@ -0,0 +1,39 @@
+import numpy
+import lzma
+from sklearn.naive_bayes import MultinomialNB
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.pipeline import make_pipeline
+from sklearn import preprocessing
+
+PIPELINE = make_pipeline(TfidfVectorizer(), MultinomialNB())
+LABEL_ENC = preprocessing.LabelEncoder()
+
+
+def get_file(path):
+    with open(path, encoding='utf-8') as file:
+        return file.readlines()
+
+
+def get_xz(path):
+    with lzma.open(path, 'rt', encoding='utf-8') as file:
+        return file.readlines()
+
+
+def get_model(train_in, train_expected):
+    train_expected = LABEL_ENC.fit_transform(train_expected)
+    model = PIPELINE.fit(train_in, train_expected)
+    return model
+
+
+def do_prediction(path_a, path_b, train_expected_path):
+    train_in = get_xz(path_b)
+    train_expected = get_file(train_expected_path)
+    train_test_in = get_xz(path_a + '/in.tsv.xz')
+    model = get_model(train_in, train_expected)
+    prediction = model.predict(train_test_in)
+    numpy.savetxt(path_a + "/out.tsv", prediction, '%d')
+
+
+if __name__ == '__main__':
+    do_prediction("dev-0", "./train/in.tsv.xz", "./train/expected.tsv")
+    do_prediction("test-A", "./train/in.tsv.xz", "./train/expected.tsv")