From 552f4cd593bbb29e3756cd5070c4a35d782a38e1 Mon Sep 17 00:00:00 2001
From: Damian Bregier <dambre@st.amu.edu.pl>
Date: Wed, 26 May 2021 10:53:19 +0200
Subject: [PATCH] FIX: Typo fix which messed with outputs

---
 regression.py | 42 +++++++++++++++++++++++++++++-------------
 1 file changed, 29 insertions(+), 13 deletions(-)

diff --git a/regression.py b/regression.py
index 6eece22..c4f3811 100644
--- a/regression.py
+++ b/regression.py
@@ -21,11 +21,13 @@ class MyNeuralNetwork(torch.nn.Module):
 
 word2vec = gensim.downloader.load('word2vec-google-news-300')
 def get_word2vec(document):
+
     return np.mean([word2vec[token] for token in document if token in word2vec] or [np.zeros(300)], axis=0)
 
 #Basic paths + reading from files
 XtrainingData = pd.read_table('train/in.tsv.xz', error_bad_lines=False, header=None, quoting=QUOTE_NONE, names=['content', 'id'])
 YtrainingData = pd.read_table('train/expected.tsv', error_bad_lines=False, header=None, quoting=QUOTE_NONE, names=['label'])['label']
+
 XtestData = pd.read_table('test-A/in.tsv.xz', error_bad_lines=False, header=None, quoting=QUOTE_NONE, names=['content', 'id'])
 XdevData = pd.read_table('dev-0/in.tsv.xz', error_bad_lines=False, header=None, quoting=QUOTE_NONE, names=['content', 'id'])
 
@@ -42,43 +44,57 @@ XdevData = [get_word2vec(document) for document in XdevData]
 eph = 30
 batches = 5
 network = MyNeuralNetwork(300, 600, 1)
-criterion = torch.nn.BCELoss()
-optimizer = torch.optim.SGD(network.parameters(), lr=0.02)
+crit = torch.nn.BCELoss()
+opt = torch.optim.SGD(network.parameters(), lr=0.03)
 
+########Accuracy for different parameters according to Geval###########
+#0.7561 for 5 epochs and 5 batches
+#0.7728 for 30 epochs and 5 batches
+#0.7712 for 30 epochs and 15 batches
+#######################################################################
 #Model training according to source files from classes
 for epoch in range(eph):
     network.train()
+
     for i in range(0, YtrainingData.shape[0], batches):
         x = XtrainingData[i :i + batches]
         x = torch.tensor(x)
         y = YtrainingData[i :i + batches]
         y = torch.tensor(y.astype(np.float32).to_numpy()).reshape(-1, 1)
 
-        outputs = network(x.float())
-        loss = criterion(outputs, y)
-        optimizer.zero_grad()
+        outcome = network(x.float())
+        loss = crit(outcome, y)
+        opt.zero_grad()
         loss.backward()
-        optimizer.step()
+        opt.step()
 
 #Basic evaluation
-YpredDev = []
 YtestPred = []
+YpredDev = []
 
 with torch.no_grad():
     for i in range(0, len(XdevData), batches):
         x = XdevData[i :i + batches]
         x = torch.tensor(x)
-        outputs = network(x.float())
-        prediction = outputs > 0.5
-        YpredDev += prediction.tolist()
+        outcome = network(x.float())
+        predict = outcome > 0.5
+
+        YpredDev += predict.tolist()
 
     for i in range(0, len(XtestData), batches):
         x = XtestData[i :i + batches]
         x = torch.tensor(x)
-        outputs = network(x.float())
-        prediction = outputs > 0.5
-        YtestPred += prediction.tolist()
+        outcome = network(x.float())
+        predict = outcome > 0.5
+
+        YtestPred += predict.tolist()
 
 #Saving outputs
 np.asarray(YpredDev, dtype=np.int32).tofile('./dev-0/out.tsv', sep='\n')
 np.asarray(YtestPred, dtype=np.int32).tofile('./test-A/out.tsv', sep='\n')
+
+########Accuracy for different parameters according to Geval###########
+#0.7561 for 5 epochs and 5 batches
+#0.7728 for 30 epochs and 5 batches
+#0.7712 for 30 epochs and 15 batches
+#######################################################################