ISI-9 ready-made, MultinomialNB

.gitignore

@@ -1,3 +1,4 @@
+in.tsv
 model.pkl
 *~
 *.swp

.idea/.gitignore

@@ -0,0 +1,2 @@
+# Default ignored files
+/workspace.xml

.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 3.7" 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.iml" filepath="$PROJECT_DIR$/.idea/paranormal-or-skeptic.iml" />
+    </modules>
+  </component>
+</project>

.idea/paranormal-or-skeptic.iml

@@ -0,0 +1,11 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="jdk" jdkName="Python 3.7" jdkType="Python SDK" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+  <component name="TestRunnerService">
+    <option name="PROJECT_TEST_RUNNER" value="Unittests" />
+  </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>

solution.py

@@ -0,0 +1,38 @@
+import pandas as pd
+import numpy as np
+import csv
+from sklearn.naive_bayes import MultinomialNB
+from sklearn.feature_extraction.text import CountVectorizer
+count_vect = CountVectorizer()
+
+#load data:
+train = pd.read_csv("train/in.tsv", delimiter="\t", header=None, names=["text","date"], quoting=csv.QUOTE_NONE)
+texts = train["text"]
+y = pd.read_csv("train/expected.tsv", header=None)
+
+#print(y)
+#train
+X_train_counts = count_vect.fit_transform(texts)
+clf = MultinomialNB().fit(X_train_counts, y)
+print(texts[0])
+print(len(texts))
+print(len(y))
+
+#predict
+dev0 = pd.read_csv("dev-0/in.tsv", delimiter="\t", header=None, names=["text","date"], quoting=csv.QUOTE_NONE)["text"]
+testA = pd.read_csv("test-A/in.tsv", delimiter="\t", header=None, names=["text","date"], quoting=csv.QUOTE_NONE)["text"]
+
+dev0_new_counts = count_vect.transform(dev0)
+testA_new_counts = count_vect.transform(testA)
+
+predicted_dev0 = clf.predict(dev0_new_counts)
+predicted_testA = clf.predict(testA_new_counts)
+
+print(len(dev0))
+print(len(predicted_dev0))
+
+with open("dev-0/out.tsv"):
+    print(predicted_dev0)
+
+with open("test-A/out.tsv"):
+    print(predicted_testA)