From dc2b14232671bcec9f03709cd750554beae23701 Mon Sep 17 00:00:00 2001
From: piotr6789 <piotr.ulanicki4@gmail.com>
Date: Thu, 27 May 2021 10:31:00 +0200
Subject: [PATCH] delete test

---
 logistic-regression.py | 49 ++++++++++++++++--------------------------
 1 file changed, 19 insertions(+), 30 deletions(-)

diff --git a/logistic-regression.py b/logistic-regression.py
index 199ea77..a1be23d 100644
--- a/logistic-regression.py
+++ b/logistic-regression.py
@@ -6,7 +6,7 @@ from nltk.tokenize import word_tokenize
 from gensim import downloader
 
 FEATURES = ['content', 'id', 'label']
-PATHS = ['train/in.tsv', 'train/expected.tsv', 'dev-0/in.tsv', 'test-A/in.tsv', './dev-0/out.tsv', './test-A/out.tsv']
+PATHS = ['train/in.tsv', 'train/expected.tsv', 'dev-0/in.tsv', './dev-0/out.tsv']
 PRE_TRAINED = 'word2vec-google-news-300'
 
 class NeuralNetwork(torch.nn.Module):
@@ -26,36 +26,32 @@ def get_data(FEATURES, PATHS):
   x_train = pd.read_table(PATHS[0], error_bad_lines = False, header = None, quoting = csv.QUOTE_NONE, names = FEATURES[:2])
   y_train = pd.read_table(PATHS[1], error_bad_lines = False, header = None, quoting = csv.QUOTE_NONE, names = FEATURES[2:])
   x_dev = pd.read_table(PATHS[2], error_bad_lines = False, header = None, quoting = csv.QUOTE_NONE, names = FEATURES[:2])
-  x_test = pd.read_table(PATHS[3], error_bad_lines = False, header = None, quoting = csv.QUOTE_NONE, names = FEATURES[:2])
 
-  return x_train, y_train, x_dev, x_test
+  return x_train, y_train, x_dev
 
-def preprocess(x_train, y_train, x_dev, x_test):
+def preprocess(x_train, y_train, x_dev):
   x_train = x_train[FEATURES[0]].str.lower()
   x_dev = x_dev[FEATURES[0]].str.lower()
-  x_test = x_test[FEATURES[0]].str.lower()
   y_train = y_train[FEATURES[2]]
 
-  return x_train, y_train, x_dev, x_test
+  return x_train, y_train, x_dev
 
-def tokenize(x_train, x_dev, x_test):
+def tokenize(x_train, x_dev):
   x_train = [word_tokenize(i) for i in x_train]
   x_dev = [word_tokenize(i) for i in x_dev]
-  x_test = [word_tokenize(i) for i in x_test]
 
-  return x_train, x_dev, x_test
+  return x_train, x_dev
 
 def use_word2vec():
   w2v = downloader.load(PRE_TRAINED)
 
   return w2v
 
-def document_vector(w2v, x_train, x_dev, x_test):
+def document_vector(w2v, x_train, x_dev):
   x_train = [np.mean([w2v[word] for word in doc if word in w2v] or [np.zeros(300)], axis = 0) for doc in x_train]
   x_dev = [np.mean([w2v[word] for word in doc if word in w2v] or [np.zeros(300)], axis = 0) for doc in x_dev]
-  x_test = [np.mean([w2v[word] for word in doc if word in w2v] or [np.zeros(300)], axis = 0) for doc in x_test]
 
-  return x_train, x_dev, x_test
+  return x_train, x_dev
 
 def basic_config():
   INPUT_DIM = 300
@@ -84,8 +80,8 @@ def train(nn_model, BATCH_SIZE, criterion, optimizer, x_train, y_train):
         loss.backward()
         optimizer.step()
 
-def prediction(nn_model, BATCH_SIZE, x_dev, x_test):
-  y_dev, y_test = [], []
+def prediction(nn_model, BATCH_SIZE, x_dev):
+  y_dev = []
   nn_model.eval()
   with torch.no_grad():
       for i in range(0, len(x_dev), BATCH_SIZE):
@@ -94,30 +90,23 @@ def prediction(nn_model, BATCH_SIZE, x_dev, x_test):
           outputs = nn_model(X.float())
           prediction = (outputs > 0.5)
           y_dev += prediction.tolist()
-      for i in range(0, len(x_test), BATCH_SIZE):
-          X = x_test[i:i+BATCH_SIZE]
-          X = torch.tensor(X)
-          outputs = nn_model(X.float())
-          prediction = (outputs > 0.5)
-          y_test += prediction.tolist()
 
-  return y_dev, y_test
+  return y_dev
 
-def get_result(y_dev, y_test):
-  np.asarray(y_dev, dtype = np.int32).tofile(PATHS[4], sep='\n')
-  np.asarray(y_test, dtype = np.int32).tofile(PATHS[5], sep='\n')
+def get_result(y_dev):
+  np.asarray(y_dev, dtype = np.int32).tofile(PATHS[3], sep='\n')
 
 def main():
-  x_train, y_train, x_dev, x_test = get_data(FEATURES, PATHS)
-  x_train, y_train, x_dev, x_test = preprocess(x_train, y_train, x_dev, x_test)
-  x_train, x_dev, x_test = tokenize(x_train, x_dev, x_test)
+  x_train, y_train, x_dev = get_data(FEATURES, PATHS)
+  x_train, y_train, x_dev = preprocess(x_train, y_train, x_dev)
+  x_train, x_dev = tokenize(x_train, x_dev)
   w2v = use_word2vec()
-  x_train, x_dev, x_test = document_vector(w2v, x_train, x_dev, x_test)
+  x_train, x_dev = document_vector(w2v, x_train, x_dev)
   INPUT_DIM, BATCH_SIZE = basic_config()
   nn_model, optimizer, criterion = init_model(INPUT_DIM)
   train(nn_model, BATCH_SIZE, criterion, optimizer, x_train, y_train)
-  y_dev, y_test = prediction(nn_model, BATCH_SIZE, x_dev, x_test)
-  get_result(y_dev, y_test)
+  y_dev = prediction(nn_model, BATCH_SIZE, x_dev)
+  get_result(y_dev)
 
 if _name_ == '_main_':
   main()