weszlo

dev-0/out.tsv

@@ -21,9 +21,9 @@
 0
 0
 0
-0
 1
 0
+0
 1
 0
 0
@@ -98,7 +98,6 @@
 0
 0
 0
-0
 1
 0
 0
@@ -113,6 +112,7 @@
 0
 0
 0
+0
 1
 0
 0
@@ -200,8 +200,8 @@
 0
 1
 0
-1
 0
+1
 0
 0
 0
@@ -338,7 +338,6 @@
 0
 0
 0
-0
 1
 0
 0
@@ -376,6 +375,7 @@
 0
 0
 0
+0
 1
 1
 0
@@ -467,18 +467,18 @@
 0
 0
 1
-1
-1
 0
+1
 0
 0
+1
 0
 0
 0
-1
 0
 0
 0
+1
 0
 0
 0
@@ -544,8 +544,8 @@
 0
 0
 0
-1
 0
+1
 0
 0
 0
@@ -797,12 +797,12 @@
 0
 0
 0
-0
 1
 0
 0
 0
 0
+0
 1
 0
 0
@@ -842,13 +842,13 @@
 1
 0
 1
-0
 1
 0
 0
 0
 0
 0
+0
 1
 0
 0
@@ -894,8 +894,8 @@
 0
 1
 1
-1
 0
+1
 0
 0
 0
@@ -982,7 +982,6 @@
 0
 0
 0
-0
 1
 0
 0
@@ -996,6 +995,7 @@
 0
 0
 0
+0
 1
 0
 0
@@ -1020,8 +1020,8 @@
 0
 0
 1
-1
 0
+1
 0
 0
 0
@@ -1151,7 +1151,7 @@
 0
 0
 0
-0
+1
 0
 0
 0
@@ -1235,7 +1235,7 @@
 0
 0
 0
-1
+0
 0
 0
 0
@@ -1297,7 +1297,6 @@
 0
 0
 0
-0
 1
 0
 0
@@ -1360,6 +1359,7 @@
 0
 0
 0
+0
 1
 1
 0
@@ -1434,14 +1434,14 @@
 0
 0
 0
-0
 1
 0
 0
-1
 0
 1
 1
+1
+0
 0
 0
 0
@@ -1533,7 +1533,6 @@
 0
 0
 0
-0
 1
 0
 0
@@ -1541,6 +1540,7 @@
 0
 0
 0
+0
 1
 1
 0
@@ -1857,12 +1857,11 @@
 0
 0
 0
-1
 0
 0
 0
-1
 0
+1
 0
 0
 0
@@ -1878,6 +1877,7 @@
 0
 0
 0
+1
 0
 0
 0
@@ -2064,11 +2064,11 @@
 0
 0
 0
-1
 0
 0
 0
 0
+1
 0
 0
 0
@@ -2378,7 +2378,6 @@
 0
 0
 0
-0
 1
 0
 0
@@ -2387,6 +2386,7 @@
 0
 0
 0
+0
 1
 0
 1
@@ -2858,7 +2858,7 @@
 0
 0
 0
-0
+1
 0
 0
 0
@@ -2876,7 +2876,7 @@
 1
 0
 0
-1
+0
 0
 0
 0
@@ -2943,8 +2943,8 @@
 0
 0
 0
-1
 0
+1
 0
 0
 0
@@ -3213,7 +3213,6 @@
 0
 0
 0
-0
 1
 0
 0
@@ -3229,6 +3228,7 @@
 0
 0
 0
+0
 1
 0
 0
@@ -3515,6 +3515,7 @@
 0
 0
 0
+1
 0
 0
 0
@@ -3522,7 +3523,6 @@
 0
 0
 0
-1
 0
 0
 0
@@ -3605,10 +3605,10 @@
 0
 0
 0
-1
 0
 0
 0
+1
 0
 0
 0
@@ -4039,8 +4039,8 @@
 0
 0
 0
-1
 0
+1
 0
 0
 0
@@ -4414,7 +4414,6 @@
 1
 0
 0
-0
 1
 0
 0
@@ -4424,9 +4423,10 @@
 0
 0
 0
+1
+0
 0
 0
-1
 0
 0
 0
@@ -4711,7 +4711,6 @@
 0
 0
 0
-1
 0
 0
 0
@@ -4720,6 +4719,7 @@
 0
 0
 0
+1
 0
 0
 0
@@ -4752,8 +4752,8 @@
 1
 0
 0
-1
 0
+1
 0
 0
 0
@@ -4935,9 +4935,9 @@
 0
 0
 1
-1
 0
 0
+1
 0
 0
 0
@@ -4966,9 +4966,9 @@
 0
 0
 0
-1
 0
 0
+1
 0
 0
 0
@@ -5057,6 +5057,7 @@
 0
 0
 0
+1
 0
 0
 0
@@ -5071,7 +5072,6 @@
 0
 0
 0
-1
 0
 0
 0
@@ -5085,7 +5085,6 @@
 0
 0
 0
-1
 0
 0
 0
@@ -5098,6 +5097,7 @@
 0
 1
 1
+1
 0
 0
 0
@@ -5135,16 +5135,16 @@
 0
 0
 0
-1
 0
 0
 0
 0
 0
-1
 0
 1
 0
+1
+1
 0
 0
 0
@@ -5237,7 +5237,7 @@
 0
 1
 1
-0
+1
 1
 0
 0
@@ -5247,17 +5247,16 @@
 0
 0
 0
-1
 0
 0
 0
 0
 0
+1
 0
 0
 0
 0
-1
 0
 0
 0
@@ -5270,3 +5269,4 @@
 0
 0
 0
+1

main.py

@@ -1,24 +1,65 @@
+from gensim.test.utils import common_texts
+from gensim.models import Word2Vec
+
 from sklearn import preprocessing
-from sklearn.feature_extraction.text import TfidfVectorizer
-from sklearn.naive_bayes import MultinomialNB
-from sklearn.pipeline import make_pipeline
 
+import pandas as pd
 import numpy as np
+import gensim
+import torch
 
-eng = preprocessing.LabelEncoder()
+class NeuralNetworkModel(torch.nn.Module):
 
-with open("train/in.tsv") as myFile:
-    tmp = myFile.readlines()
-    with open("train/expected.tsv") as finFile:
-        fin = finFile.readlines() 
-        fin = eng.fit_transform(fin)
-        with open("test-A/in.tsv") as tFile:
-            fic = tFile.readlines() 
-            gnb = make_pipeline(TfidfVectorizer(),MultinomialNB())
-            model = gnb.fit(tmp, fin)
-            fin_pred = model.predict(fic)
-            fin_pred = np.array(fin_pred)
-            np.set_printoptions(threshold = np.inf)
-            eFile = np.array2string(fin_pred.flatten(), precision = 2, separator = '\n',suppress_small = True)
-            myFile = open("test-A/out.tsv", "a")
-            myFile.write(eFile)
+    def __init__(self):
+        super(NeuralNetworkModel, self).__init__()
+        self.fc1 = torch.nn.Linear(maxim, 500)
+        self.fc2 = torch.nn.Linear(500, 1)
+
+    def forward(self, x):
+        x = self.fc1(x)
+        x = torch.relu(x)
+        x = self.fc2(x)
+        x = torch.sigmoid(x)
+        return x
+
+with open("train/in.tsv") as xd:
+    x1 = xd.readlines()
+    with open("train/expected.tsv") as xdd:
+        y1 = xdd.readlines() 
+        with open("test-A/in.tsv") as xddd:
+            x = xddd.readlines() 
+
+maxim = 500
+bLen = 5
+
+exp = Word2Vec(x1, min_count = 1, vector_size = 500, workers = 3, window = 3, sg = 1)
+exp1 = Word2Vec(x, min_count = 1, vector_size = 500, workers = 3, window = 3, sg = 1)
+exp2 = NeuralNetworkModel()
+
+x1 = exp.wv
+x = exp1.wv
+
+crt = torch.nn.BCELoss()
+miz = torch.optim.SGD(exp2.parameters(), lr = 0.1)
+
+for each in range(10):
+    lossScore, accScore, sums = 0
+    exp2.train()
+    for i in range(0, y1.shape[0], bLen):
+        x = x1[i : i + bLen]
+        x = torch.tensor(x.astype(np.float32).todense())
+        y = y1[i : i + bLen]
+        y = torch.tensor(y.astype(np.float32)).reshape(-1, 1)
+        y2 = exp2(x)
+        accScore += torch.sum((y2 > 0.5) == y).item()
+        sums += y.shape[0] 
+
+        miz.zero_grad()
+        loss = crt(y2, Y)
+        loss.backward()
+        miz.step()
+
+        lossScore += loss.item() * Y.shape[0] 
+        with open('test-A/out.tsv', 'w') as file:
+            for each in y2:
+                file.write("%f\n" % each)