Preparation to ISI-003

.idea/.gitignore

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

.idea/Pierwsze.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="jdk" jdkName="Python 3.8 (untitled)" jdkType="Python SDK" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

.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 +1,7 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="JavaScriptSettings">
+    <option name="languageLevel" value="ES6" />
+  </component>
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.8 (untitled)" 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/Pierwsze.iml" filepath="$PROJECT_DIR$/.idea/Pierwsze.iml" />
+    </modules>
+  </component>
+</project>

.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>

code.py

@@ -1,57 +0,0 @@
-from collections import defaultdict
-import math
-import pickle
-
-def calc_class_logprob(expected_path):
-    paranormal_classcount=0
-    skeptic_classcount=0
-    with open(expected_path) as f:
-        for line in f:
-            if 'P' in line:
-                paranormal_classcount += 1
-            if 'S' in line:
-                skeptic_classcount += 1
-
-    paranormal_prob = paranormal_classcount / (paranormal_classcount + skeptic_classcount)
-    skeptic_prob = skeptic_classcount / (paranormal_classcount + skeptic_classcount)
-
-    return math.log(paranormal_prob), math.log(skeptic_prob)
-
-
-def calc_word_count(in_path, expected_path):
-    word_counts = {'paranormal':defaultdict(int), 'skeptic': defaultdict(int)}
-    with open(in_path) as in_file, open(expected_path)  as  expected_file:
-        for line, exp in zip(in_file, expected_file):
-            class_ = exp.rstrip('\n').replace(' ','')
-            text, timestamp = line.rstrip('\n').split('\t')
-            tokens = text.lower().split(' ')
-            for token in tokens:
-                if class_ == 'P':
-                    word_counts['paranormal'][token] += 1
-                elif class_ == 'S':
-                    word_counts['skeptic'][token] += 1
-    return word_counts
-
-def calc_word_logprobs(word_counts):
-    total_skeptic = sum(word_counts['skeptic'].values()) + len(word_counts['skeptic'].keys())
-    total_paranormal = sum(word_counts['paranormal'].values()) + len(word_counts['paranormal'].keys())
-
-    word_logprobs= {'paranormal': {}, 'skeptic': {}}
-    for class_ in word_counts.keys(): # sceptic paranormal
-        for token, tokens in word_counts[class_].items():
-            if class_ == 'skeptic':
-                word_prob = (tokens+1)/total_skeptic
-            else:
-                word_prob = (tokens+1)/total_paranormal
-            word_logprobs[class_][token] = math.log(word_prob)
-    return word_logprobs
-
-
-def main():
-    paranomal_class_logprob, skeptic_class_logprob = calc_class_logprob("F:/UAM/SEMESTR_I_MGR/SYSTEMY_INTELIGENTNE/ic4g/train/expected.tsv")
-    word_counts=calc_word_count("F:/UAM/SEMESTR_I_MGR/SYSTEMY_INTELIGENTNE/ic4g/train/in.tsv","F:/UAM/SEMESTR_I_MGR/SYSTEMY_INTELIGENTNE/ic4g/train/expected.tsv")
-    word_logprobs = calc_word_logprobs(word_counts)
-    pickle.dump([paranomal_class_logprob, skeptic_class_logprob, word_logprobs], open('naive_base_model.pkl','wb'))
-
-
-main()