Sane words, with score

.idea/workspace.xml

@@ -3,11 +3,11 @@
   <component name="ChangeListManager">
     <list default="true" id="d25a65da-2ba0-4272-a0a5-c59cbecb6088" name="Default Changelist" comment="">
       <change beforePath="$PROJECT_DIR$/.idea/workspace.xml" beforeDir="false" afterPath="$PROJECT_DIR$/.idea/workspace.xml" afterDir="false" />
-      <change beforePath="$PROJECT_DIR$/dev-0/out.tsv" beforeDir="false" />
-      <change beforePath="$PROJECT_DIR$/dev-0/out_float.tsv" beforeDir="false" />
+      <change beforePath="$PROJECT_DIR$/dev-0/out.tsv" beforeDir="false" afterPath="$PROJECT_DIR$/dev-0/out.tsv" afterDir="false" />
+      <change beforePath="$PROJECT_DIR$/dev-0/out_float.tsv" beforeDir="false" afterPath="$PROJECT_DIR$/dev-0/out_float.tsv" afterDir="false" />
       <change beforePath="$PROJECT_DIR$/solution2.py" beforeDir="false" afterPath="$PROJECT_DIR$/solution2.py" afterDir="false" />
-      <change beforePath="$PROJECT_DIR$/test-A/out.tsv" beforeDir="false" />
-      <change beforePath="$PROJECT_DIR$/test-A/out_float.tsv" beforeDir="false" />
+      <change beforePath="$PROJECT_DIR$/test-A/out.tsv" beforeDir="false" afterPath="$PROJECT_DIR$/test-A/out.tsv" afterDir="false" />
+      <change beforePath="$PROJECT_DIR$/test-A/out_float.tsv" beforeDir="false" afterPath="$PROJECT_DIR$/test-A/out_float.tsv" afterDir="false" />
     </list>
     <option name="EXCLUDED_CONVERTED_TO_IGNORED" value="true" />
     <option name="SHOW_DIALOG" value="false" />

solution2.py

@@ -65,6 +65,18 @@ print(y)
 
 print("Training...")
 criterion = torch.nn.MSELoss(reduction='sum')
+
+dev_data = pandas.read_csv('dev-0/in.tsv', sep='\t', names=['Domain', 'Word', 'Frequency'], header=None)
+dev_x1 = Normalize(torch.tensor(dev_data['Frequency'], dtype=torch.float), x1)
+dev_x2 = Normalize(torch.tensor(count_vowels(dev_data['Word']), dtype=torch.float), x2)
+
+dev_x3 = Normalize(torch.tensor(dev_data['Domain'].astype('category').cat.codes, dtype=torch.float), x3)
+dev_x4 = Normalize(torch.tensor(count_polish_diacritics(dev_data['Word']), dtype=torch.float), x4)
+dev_x5 = Normalize(torch.tensor(dev_data['Word'].str.len(), dtype=torch.float), x5)
+
+dev_x = torch.stack((dev_x1, dev_x2, dev_x3, dev_x4, dev_x5), 0)
+dev_y_pred = pandas.DataFrame(pandas.read_csv('dev-0/out.tsv', encoding="utf-8", delimiter='\t', header=None))
+
 for i in range(80):
     for j in range(1000):
         y_predicted = model(x)
@@ -81,32 +93,34 @@ for i in range(80):
             W2 = W2 - learning_rate * W2.grad
             b2 = b2 - learning_rate * b2.grad
 
+            dev_y_test = model(dev_x)
+            dev_y_test_f = dev_y_test.numpy()
+            dev_y_test = np.where(dev_y_test_f > 0.5, 1, 0)
+            print(dev_y_test)
+            score = f1_score(dev_y_test, dev_y_pred)
+
 
         W1.requires_grad_(True)
         b1.requires_grad_(True)
         W2.requires_grad_(True)
         b2.requires_grad_(True)
 
+        if (score < 0.35):
+            break
+
+
+
+    print(score)
+    print(str(i), " ; ", cost)
+    print(str(i), " ; ", cost)
 
 
-    if (cost.item() < 1700):
-        break
-    #print("Dev0 pred...")
-    # dev
 
 
 
 print("Dev0 pred...")
 #dev data:
-dev_data = pandas.read_csv('dev-0/in.tsv', sep='\t', names=['Domain', 'Word', 'Frequency'], header=None)
-dev_x1 = Normalize(torch.tensor(dev_data['Frequency'], dtype=torch.float), x1)
-dev_x2 = Normalize(torch.tensor(count_vowels(dev_data['Word']), dtype=torch.float), x2)
 
-dev_x3 = Normalize(torch.tensor(dev_data['Domain'].astype('category').cat.codes, dtype=torch.float), x3)
-dev_x4 = Normalize(torch.tensor(count_polish_diacritics(dev_data['Word']), dtype=torch.float), x4)
-dev_x5 = Normalize(torch.tensor(dev_data['Word'].str.len(), dtype=torch.float), x5)
-
-dev_x = torch.stack((dev_x1, dev_x2, dev_x3, dev_x4, dev_x5), 0)
 dev_y_test = pandas.DataFrame(pandas.read_csv('dev-0/expected.tsv', encoding="utf-8", delimiter='\t', header=None))
 
 dev_y = model(dev_x)