Major refactors in order to make server the main source folder

ADA/SA/sentiment_analyzer.py → ADA/server/agent/SA/sentiment_analyzer.py

@@ -42,14 +42,14 @@ class SentimentAnalyzer:
         return self.expr_clf.predict([instance.vector for instance in instances])
 
 
-semeval_2014_train_path = 'data/SemEval-2014/SemEval_2014_Laptop_Train_with_labelled_parse_trees.xml'
-semeval_2014_test_path = 'data/SemEval-2014/SemEval_2014_Laptop_Test_with_labelled_parse_trees.xml'
+semeval_2014_train_path = 'server/agent/SA/data/SemEval-2014/SemEval_2014_Laptop_Train_with_labelled_parse_trees.xml'
+semeval_2014_test_path = 'server/agent/SA/data/SemEval-2014/SemEval_2014_Laptop_Test_with_labelled_parse_trees.xml'
 amazon_train_path = 'data/Amazon/amazon_camera_train.xml'
 amazon_test_path = 'data/Amazon/amazon_camera_test2.xml'  # 'data/Amazon/prepared_amazon_camera_reviews.xml'
-semeval_train_path = 'data/SemEval-2016/ABSA16_Laptops_Train_SB1_v2_with_labelled_parse_trees.xml'
-semeval_test_path = 'data/SemEval-2016/ABSA16_Laptops_Test_with_labelled_parse_trees.xml' #
-tweet_train_path = 'data/acl-14-short-data/tweet_train_with_labelled_parse_trees.xml'
-tweet_test_path = 'data/acl-14-short-data/tweet_test_with_labelled_parse_trees.xml'
+semeval_train_path = 'server/agent/SA/data/SemEval-2016/ABSA16_Laptops_Train_SB1_v2_with_labelled_parse_trees.xml'
+semeval_test_path = 'server/agent/SA/data/SemEval-2016/ABSA16_Laptops_Test_with_labelled_parse_trees.xml'  #
+tweet_train_path = 'server/agent/SA/data/acl-14-short-data/tweet_train_with_labelled_parse_trees.xml'
+tweet_test_path = 'server/agent/SA/data/acl-14-short-data/tweet_test_with_labelled_parse_trees.xml'
 train_path = semeval_2014_train_path
 test_path = semeval_2014_test_path
 

ADA/SA/vectorizer.py → ADA/server/agent/SA/vectorizer.py

@@ -7,7 +7,7 @@ from nltk.stem import PorterStemmer
 
 class Vectorizer:
 
-    sentiment_lexicon = pd.read_csv('data/SocialSent/2000.tsv', index_col=0, header=None, names=['mean', 'std'], sep='\t', error_bad_lines=False)
+    sentiment_lexicon = pd.read_csv('server/agent/SA/data/SocialSent/2000.tsv', index_col=0, header=None, names=['mean', 'std'], sep='\t', error_bad_lines=False)
     negations = ['not', 'no', 'never', 'n\'t', 'neither', 'seldom', 'hardly']
     copulas = ['is', '\'s', 'was', 'were']
     adjetives_and_nouns = ['JJ', 'JJR', 'JJS', 'ADJP', 'NN', 'NNS', 'NP']

ADA/agent.py → ADA/server/agent/agent.py

 from nltk.tokenize import sent_tokenize
 import re
-from review_tokenizer import ReviewTokenizer
+from agent.review_tokenizer import ReviewTokenizer
 from anytree import PostOrderIter
 import pickle
-from argument import *
+from agent.argument import *
 from functools import reduce
-from SA.bert_analyzer import BertAnalyzer
+from agent.SA.bert_analyzer import BertAnalyzer
 
 class Agent:
     sentiment_threshold = 0.95
@@ -14,7 +14,7 @@ class Agent:
 
     def __init__(self):
         # load classifier
-        f = open('camera_review_classifier.pickle', 'rb')
+        f = open('agent/camera_review_classifier.pickle', 'rb')
         self.classifier = pickle.load(f)
         f.close()
 

ADA/analyze_data.py → ADA/server/agent/analyze_data.py

-import nltk
 from nltk.tokenize import sent_tokenize
 import pandas as pd
 import re
 from nltk.sentiment.vader import SentimentIntensityAnalyzer
-from anytree import Node, PostOrderIter
+from anytree import PostOrderIter
 from functools import reduce
 from matplotlib import pyplot
 from scipy.stats import pearsonr
 from sklearn.metrics import mean_absolute_error
 import pickle
-from review_tokenizer import tokenize_review, reduce_noise
-from argument import *
+from server.agent.review_tokenizer import tokenize_review, reduce_noise
+from server.agent.argument import *
 
 reviewables = [camera, image, video, battery, flash, audio, price, shipping, lens, zoom, af]
 features = [image, video, battery, flash, audio, price, shipping, lens, zoom, af]
@@ -165,7 +164,7 @@ def get_strengths(qbaf):
 
 #############
 
-all_reviews = pd.read_csv('camera_prepared_data.tsv', sep='\t', error_bad_lines=False)
+all_reviews = pd.read_csv('amazon_data/camera_prepared_data.tsv', sep='\t', error_bad_lines=False)
 
 camera_strengths = []
 star_rating_averages = []

ADA/communicator.py → ADA/server/agent/communicator.py

-from argumentquery import ArgumentQuery
-from dataloader import DataLoader
-from argument import *
-from agent import Agent
+from agent.argumentquery import ArgumentQuery
+from agent.argument import *
+from agent.agent import Agent
 import inflect
 from nltk.stem.snowball import SnowballStemmer