Czyszczenie kodu. Rozwiazane zadanie regresji logistycznej.

rlrozwiazanie.py

@@ -0,0 +1,165 @@
+import gzip
+from sklearn import metrics
+import pandas as pd
+import numpy as np
+
+from gensim.models import KeyedVectors
+
+import re
+import torch
+from torch.utils.data import TensorDataset, DataLoader
+
+def get_str_cleaned(str_dirty):
+    punctuation = '!"#$%&\'()*+,-./:;<=>?@[\\\\]^_`{|}~'
+    new_str = str_dirty.lower()
+    new_str = re.sub(' +', ' ', new_str)
+    for char in punctuation:
+        new_str = new_str.replace(char,'')
+    return new_str
+
+train_X = [] 
+train_y = []
+with gzip.open('train/train.tsv.gz','r') as fin:        
+    for line in fin:
+        sline = line.decode('UTF-8').replace("\n", "").split("\t")
+        cleared = get_str_cleaned(''.join(sline[1:]))
+        
+        if len(cleared)>0:
+            train_y.append(int(sline[0]))
+            train_X.append(cleared)
+
+train_X_data = pd.DataFrame(train_X)
+#Korpusy można pobrać z:
+#http://dsmodels.nlp.ipipan.waw.pl/dsmodels/nkjp+wiki-forms-all-100-cbow-hs.txt.gz
+#http://dsmodels.nlp.ipipan.waw.pl/dsmodels/wiki-forms-all-100-skipg-ns.txt.gz
+#w2v = KeyedVectors.load_word2vec_format('../../../ncexclude/nkjp+wiki-forms-all-100-cbow-hs.txt.gz', binary=False)
+w2v = KeyedVectors.load_word2vec_format('../../../ncexclude/wiki-forms-all-100-skipg-ns.txt.gz', binary=False)
+#w2v.save("word2vec.wordvectors")
+#w2v = KeyedVectors.load("word2vec.wordvectors")
+
+def document_vector(doc):
+    try:
+        doc2 = []
+        doc = doc.split(' ')
+        for word in doc:
+            if word in w2v:
+                doc2.append(word)
+        return np.mean(w2v[doc2], axis=0)
+    except:
+        return np.zeros(100)
+
+train_X_data = train_X_data[train_X_data.columns[0]].apply(document_vector)
+
+dev_X = []
+with open('dev-0/in.tsv','r') as dev_in_file:
+    for line in dev_in_file:
+        dev_X.append(get_str_cleaned(line.rstrip('\n')))
+
+dev_y = []
+with open('dev-0/expected.tsv','r') as dev_expected_file:
+    for line in dev_expected_file:
+        dev_y.append(int(line.rstrip('\n')))
+
+
+dev_X_data = pd.DataFrame(dev_X)
+dev_X_data = dev_X_data[dev_X_data.columns[0]].apply(document_vector)
+
+
+class LogisticRegressionModel(torch.nn.Module):
+
+    def __init__(self):
+        super(LogisticRegressionModel, self).__init__()
+        self.fc = torch.nn.Linear(100,1)
+
+    def forward(self, x):
+        x = self.fc(x)
+        x = torch.sigmoid(x)
+        return x
+
+lr_model = LogisticRegressionModel() 
+
+criterion = torch.nn.BCELoss()
+optimizer = torch.optim.SGD(lr_model.parameters(), lr = 0.1)
+
+train_x_tensor = torch.tensor(train_X_data).float()
+train_y_tensor = torch.tensor(train_y).float()
+
+train_dataset = TensorDataset(train_x_tensor, train_y_tensor)
+train_loader = DataLoader(dataset=train_dataset)
+
+dev_x_tensor = torch.tensor(dev_X_data).float()
+dev_y_tensor = torch.tensor(dev_y).float()
+
+dev_dataset = TensorDataset(dev_x_tensor, dev_y_tensor)
+dev_loader = DataLoader(dataset=dev_dataset)
+
+n_epochs = 2
+
+def make_train_step(model, loss_fn, optimizer):
+    def train_step(x, y):
+        model.train()
+        yhat = model(x)
+        loss = loss_fn(yhat, y.unsqueeze(1))
+        loss.backward()
+        optimizer.step()
+        optimizer.zero_grad()  
+        return loss.item()
+    return train_step
+
+train_step = make_train_step(lr_model, criterion, optimizer)
+training_losses = []
+validation_losses = []
+
+for epoch in range(n_epochs):
+    y_pred = []
+    losses = []
+    for x_batch, y_batch in train_loader:
+        loss = train_step(x_batch, y_batch)
+        losses.append(loss)
+    training_loss = np.mean(losses)
+    training_losses.append(training_loss)
+        
+    #Evaluation
+    with torch.no_grad():
+        val_losses = []
+        for x_val, y_val in dev_loader:
+            lr_model.eval()
+            yhat = lr_model(x_val)
+            y_pred.append(int(yhat.item() > 0.5))
+            val_loss = criterion(yhat, y_val.unsqueeze(1))
+            val_losses.append(val_loss.item())
+        validation_loss = np.mean(val_losses)
+        validation_losses.append(validation_loss)
+    print(f"[{epoch+1}] Training loss: {training_loss:.3f}\t Validation loss: {validation_loss:.3f}")
+
+
+score1 = metrics.accuracy_score(dev_y, y_pred)
+print("accuracy:   %0.5f" % score1)
+
+
+file = open('dev-0/out.tsv',"w") 
+for i in y_pred:
+    file.writelines("{}\n".format(i))    
+file.close() 
+
+
+test_X = []
+with open('test-A/in.tsv','r') as test_in_file:
+    for line in test_in_file:
+        test_X.append(get_str_cleaned(line.rstrip('\n')))
+
+test_X_data = pd.DataFrame(test_X)
+test_X_data = test_X_data[test_X_data.columns[0]].apply(document_vector)
+test_x_tensor = torch.tensor(test_X_data).float()
+
+val_y_pred = []
+with torch.no_grad():
+    for x_val in test_x_tensor:
+        lr_model.eval()
+        yhat = lr_model(x_val)
+        val_y_pred.append(int(yhat.item() > 0.5))
+
+file = open('test-A/out.tsv',"w") 
+for i in val_y_pred:
+    file.writelines("{}\n".format(i))    
+file.close()

rozwiazanie.py

@@ -0,0 +1,67 @@
+#import numpy as np
+import gzip
+from sklearn.naive_bayes import MultinomialNB
+from sklearn.feature_extraction.text import TfidfVectorizer, CountVectorizer
+from sklearn import metrics
+
+#df = pd.read_csv('sport-text-classification-ball-ISI-public/train/train.tsv.gz', compression='gzip', header=None, sep='\t', error_bad_lines=False)
+train_X = [] 
+train_y = []
+with gzip.open('train/train.tsv.gz','r') as fin:        
+    for line in fin:
+        sline = line.decode('UTF-8').replace("\n", "").split("\t")
+        train_y.append(sline[0])
+        train_X.append(''.join(sline[1:]))
+
+test_X = []
+with open('dev-0/in.tsv','r') as test_in_file:
+    for line in test_in_file:
+        test_X.append(line.rstrip('\n'))
+
+test_y = []
+with open('dev-0/expected.tsv','r') as test_expected_file:
+    for line in test_expected_file:
+        test_y.append(line.rstrip('\n'))
+
+vectorizer = TfidfVectorizer(lowercase = True)
+X_train_tf = vectorizer.fit_transform(train_X)
+print("n_samples: %d, n_features: %d" % X_train_tf.shape)
+
+X_test_tf = vectorizer.transform(test_X)
+print("n_samples: %d, n_features: %d" % X_test_tf.shape)
+
+naive_bayes_classifier = MultinomialNB()
+naive_bayes_classifier.fit(X_train_tf, train_y)
+
+y_pred = naive_bayes_classifier.predict(X_test_tf)
+
+score1 = metrics.accuracy_score(test_y, y_pred)
+print("accuracy:   %0.3f" % score1)
+
+print(metrics.classification_report(test_y, y_pred,
+                                            target_names=['1', '0']))
+
+print("confusion matrix:")
+print(metrics.confusion_matrix(test_y, y_pred))
+
+print('------------------------------')
+
+file = open('dev-0/out.tsv',"w") 
+for i in y_pred:
+    file.writelines("{}\n".format(i))    
+file.close() 
+
+val_X = []
+with open('test-A/in.tsv','r') as test_in_file:
+    for line in test_in_file:
+        val_X.append(line.rstrip('\n'))
+        
+X_val_tf = vectorizer.transform(val_X)
+print("n_samples: %d, n_features: %d" % X_val_tf.shape)
+
+val_y_pred = naive_bayes_classifier.predict(X_val_tf)
+
+file = open('test-A/out.tsv',"w") 
+for i in val_y_pred:
+    file.writelines("{}\n".format(i))    
+file.close()