nn - bigrams

run.py

@@ -1,4 +1,15 @@
-#%%
+# -*- coding: utf-8 -*-
+"""Untitled0.ipynb
+
+Automatically generated by Colaboratory.
+
+Original file is located at
+    https://colab.research.google.com/drive/1vjpmLsNPjPLM1_5fBGbBYg-ZqdXQeGQH
+"""
+
+from google.colab import drive
+drive.mount('/content/gdrive/')
+
 # importy
 from torchtext.vocab import build_vocab_from_iterator
 from torch.utils.data import DataLoader
@@ -11,7 +22,7 @@ from os.path import exists
 
 vocab_size = 30000
 embed_size = 150
-#%%
+
 # funkcje pomocnicze
 def clean(text):
     text = str(text).strip().lower()
@@ -32,7 +43,7 @@ def get_word_lines_from_data(d):
     for line in d:
         yield get_words_from_line(line)
 
-#%%
+
 class Model(torch.nn.Module):
     def __init__(self, vocabulary_size, embedding_size):
         super(Model, self).__init__()
@@ -45,7 +56,7 @@ class Model(torch.nn.Module):
     def forward(self, x):
         return self.model(x)
 
-#%%
+
 class Trigrams(torch.utils.data.IterableDataset):
     def __init__(self, data, vocabulary_size):
         self.vocab = build_vocab_from_iterator(
@@ -69,26 +80,27 @@ class Trigrams(torch.utils.data.IterableDataset):
            (self.vocab[t] for t in itertools.chain.from_iterable(get_word_lines_from_data(self.data))))
 
 
-#%%
 # ładowanie danych treningowych
-train_in = pd.read_csv("train/in.tsv.xz", sep='\t', header=None, encoding="UTF-8", on_bad_lines="skip", quoting=csv.QUOTE_NONE, nrows=300000)[[6, 7]]
+train_in = pd.read_csv("gdrive/MyDrive/train/in.tsv.xz", sep='\t', header=None, encoding="UTF-8", on_bad_lines="skip", quoting=csv.QUOTE_NONE, nrows=300000)[[6, 7]]
-train_expected = pd.read_csv("train/expected.tsv", sep='\t', header=None, encoding="UTF-8", on_bad_lines="skip", quoting=csv.QUOTE_NONE, nrows=300000)
+train_expected = pd.read_csv("gdrive/MyDrive/train/expected.tsv", sep='\t', header=None, encoding="UTF-8", on_bad_lines="skip", quoting=csv.QUOTE_NONE, nrows=300000)
 train_data = pd.concat([train_in, train_expected], axis=1)
 train_data = train_data[6] + train_data[0] + train_data[7]
 train_data = train_data.apply(clean)
 train_dataset = Trigrams(train_data, vocab_size)
 
-#%%
 # trenowanie/wczytywanie modelu
 device = 'cuda' if torch.cuda.is_available() else 'cpu'
 model = Model(vocab_size, embed_size).to(device)
+print(device)
 if(not exists('model1.bin')):
-    data = DataLoader(train_dataset, batch_size=200)
+    data = DataLoader(train_dataset, batch_size=8000)
     optimizer = torch.optim.Adam(model.parameters())
     criterion = torch.nn.NLLLoss()
 
     model.train()
     step = 0
+    for i in range(2):
+      print(f"EPOCH {i}=========================")
       for x, y in data:
           x = x.to(device)
           y = y.to(device)
@@ -105,9 +117,11 @@ if(not exists('model1.bin')):
 else:
     model.load_state_dict(torch.load('model1.bin'))
 
-#%%
+
 vocab = train_dataset.vocab
 
+import nltk
+nltk.download('punkt')
 def predict(tokens):
     ixs = torch.tensor(vocab.forward(tokens)).to(device)
     out = model(ixs)
@@ -134,11 +148,11 @@ def predict_file(result_path, data):
             f.write(result + "\n")
             print(result)
 
-#%%
+
-dev_data = pd.read_csv("dev-0/in.tsv.xz", sep='\t', header=None, quoting=csv.QUOTE_NONE)[6]
+dev_data = pd.read_csv("gdrive/MyDrive/dev-0/in.tsv.xz", sep='\t', header=None, quoting=csv.QUOTE_NONE)[6]
 dev_data = dev_data.apply(clean)
 predict_file("dev-0/out.tsv", dev_data)
 
-test_data = pd.read_csv("test-A/in.tsv.xz", sep='\t', header=None, quoting=csv.QUOTE_NONE)[6]
+test_data = pd.read_csv("gdrive/MyDrive/test-A/in.tsv.xz", sep='\t', header=None, quoting=csv.QUOTE_NONE)[6]
 test_data = test_data.apply(clean)
 predict_file("test-A/out.tsv", test_data)