update

program.py

@@ -1,30 +1,24 @@
 import numpy as np
 from sklearn import preprocessing
-from sklearn.naive_bayes import GaussianNB
+from sklearn.naive_bayes import MultinomialNB
+from sklearn.pipeline import make_pipeline
 from sklearn.feature_extraction.text import TfidfVectorizer
+
 le=preprocessing.LabelEncoder()
 
+
 with open("train/in.tsv") as f:
-    data = f.readlines() 
+    X = f.readlines()
-    vectorizer = TfidfVectorizer(ngram_range=(1,2), use_idf = False)
-    vectorizer = TfidfVectorizer()
-    x = vectorizer.fit_transform(data)
-    X=x.toarray()
     with open("train/expected.tsv") as ff:
         Y = ff.readlines() 
         Y= le.fit_transform(Y)
-        with open("dev-0/in.tsv") as d:
+        with open("test-A/in.tsv") as d:
-            fil = d.readlines() 
+            r = d.readlines() 
-            vectorizer = TfidfVectorizer(ngram_range=(1,2), use_idf = False)
+            gnb = make_pipeline(TfidfVectorizer(),MultinomialNB())
-            vectorizer = TfidfVectorizer()
-            r=vectorizer.fit_transform(fil)
-            r=r.toarray()
-            r=r.reshape(-1,1)
-            gnb = GaussianNB()
             model=gnb.fit(X, Y)
-            y_pred=model.predict(X)
+            y_pred=model.predict(r)
-            print(y_pred)
             y_pred=np.array(y_pred)
-            t=np.array2string(y_pred, precision=2, separator='\n',suppress_small=True)
+            np.set_printoptions(threshold=np.inf)
-            f = open("dev-0/out.tsv", "a")
+            t=np.array2string(y_pred.flatten(), precision=2, separator='\n',suppress_small=True)
+            f = open("test-A/out.tsv", "a")
             f.write(t)