feat(model): Integrate with evaluator and accuracy score

Author: Kaushl2208

atarashi/agents/models/test.py

@@ -1,11 +1,34 @@
 import joblib
+import os
+import pickle
 import argparse
 from atarashi.libs.commentPreprocessor import CommentPreprocessor
 from sklearn.svm import LinearSVC
 from sklearn.feature_extraction.text import CountVectorizer
 from sklearn.linear_model import LogisticRegression
 from sklearn.naive_bayes import MultinomialNB
 
+def new(processed_comment,model):
+
+    temp = os.path.dirname(os.path.abspath(__file__))
+    # pathv = os.path.join(temp, 'binaryFiles/vectorizer.pkl')
+    
+    with open(os.path.join(temp, 'binaryFiles/vectorizer.pkl'), 'rb') as f:
+        loaded_vect = joblib.load(f)
+    if model == "lr_classifier":
+        classifier = joblib.load(os.path.join(temp, 'binaryFiles/lr_model.pkl'))
+        license_name = classifier.predict((loaded_vect.transform([processed_comment])))
+    
+    elif model == "nb_classifier":
+        classifier = joblib.load(os.path.join(temp, 'binaryFiles/nb_model.pkl'))
+        license_name = classifier.predict((loaded_vect.transform([processed_comment])))      
+    
+    elif model == "svc_classifier":
+        classifier = joblib.load(os.path.join(temp, 'binaryFiles/svc_model.pkl'))
+        license_name = classifier.predict((loaded_vect.transform([processed_comment])))
+
+    return license_name
+
 
 def similarity_calc(filePath, model):
 
@@ -22,24 +45,14 @@ def similarity_calc(filePath, model):
     :rtype: list(JSON Format)  
     '''
 
+    match = []
+    
     commentFile = CommentPreprocessor.extract(filePath)
     with open(commentFile) as file:
         doc = file.read()
-    
-    match = []
     processed_comment = CommentPreprocessor.preprocess(doc)
-    loaded_vect = joblib.load("atarashi/agents/models/binaryFiles/vectorizer.pkl")
-    if model == "lr_classifier":
-        classifier = joblib.load("atarashi/agents/models/binaryFiles/nb_model.pkl")
-        license_name = classifier.predict((loaded_vect.transform([processed_comment])))
+    license_name = new(processed_comment,model)
 
-    elif model == "nb_classifier":
-        classifier = joblib.load("atarashi/agents/models/binaryFiles/nb_model.pkl")
-        license_name = classifier.predict((loaded_vect.transform([processed_comment])))      
-    
-    elif model == "svc_classifier":
-        classifier = joblib.load("atarashi/agents/models/binaryFiles/nb_model.pkl")
-        license_name = classifier.predict((loaded_vect.transform([processed_comment])))
 
     match.append({
       'shortname': license_name[0],

atarashi/atarashii.py

@@ -58,6 +58,7 @@ def atarashii_runner(inputFile, processedLicense, agent_name, similarity="Cosine
     scanner = WordFrequencySimilarity(processedLicense)
   elif agent_name == "lr_classifier" or agent_name == "svc_classifier" or agent_name == "nb_classifier":
     result = similarity_calc(inputFile,agent_name)
+    return result
   elif agent_name == "DLD":
     scanner = DameruLevenDist(processedLicense)
   elif agent_name == "tfidf":

atarashi/evaluator/evaluator.py

@@ -51,6 +51,12 @@ def getCommand(agent_name, similarity):
     command = "atarashi -a wordFrequencySimilarity"
   elif agent_name == "DLD":
     command = "atarashi -a DLD"
+  elif agent_name == "lr_classifier":
+    command = "atarashi -a lr_classifier"
+  elif agent_name == "nb_classifier":
+    command = "atarashi -a nb_classifier"
+  elif agent_name == "svc_classifier":
+    command = "atarashi -a svc_classifier"
   elif agent_name == "tfidf":
     command = "atarashi -a tfidf"
     if similarity == "CosineSim":
@@ -129,9 +135,9 @@ def evaluate(command):
 if __name__ == "__main__":
   parser = argparse.ArgumentParser()
   parser.add_argument("-a", "--agent_name", required=True,
-                      choices=['wordFrequencySimilarity', 'DLD', 'tfidf', 'Ngram'], help="Name of the agent that you want to evaluate")
+                      choices=['wordFrequencySimilarity', 'DLD',"lr_classifier","svc_classifier","nb_classifier", 'tfidf', 'Ngram'], help="Name of the agent that you want to evaluate")
   parser.add_argument("-s", "--similarity", required=False,
-                      default=" ", choices=["ScoreSim", "CosineSim", "DiceSim", " ", "BigramCosineSim"], help="Specify the similarity algorithm that you want to evaluate"
+                      default=" ", choices=["ScoreSim", "CosineSim", "DiceSim", "BigramCosineSim"], help="Specify the similarity algorithm that you want to evaluate"
                       " First 2 are for TFIDF and last 3 are for Ngram")
   args = parser.parse_args()
   agent_name = args.agent_name