raport addeed

.~lock.Raport.docx#

@@ -0,0 +1 @@
+,tomasz,tomasz-HP-EliteBook-8570p,06.07.2021 12:52,file:///home/tomasz/.config/libreoffice/4;

svm.py

@@ -0,0 +1,33 @@
+import pandas as pd
+import numpy as np
+from nltk.tokenize import word_tokenize
+from nltk import pos_tag
+from nltk.corpus import stopwords
+from nltk.stem import WordNetLemmatizer
+from sklearn.preprocessing import LabelEncoder
+from collections import defaultdict
+from nltk.corpus import wordnet as wn
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn import model_selection, naive_bayes, svm
+from sklearn.metrics import accuracy_score
+from sklearn.pipeline import make_pipeline
+
+with open("train/in.tsv") as f:
+    x_train = f.readlines()
+
+with open("train/expected.tsv") as f:
+    y_train = f.readlines()
+
+with open("dev-0/in.tsv") as f:
+    x_dev = f.readlines()
+
+y_train = LabelEncoder().fit_transform(y_train)
+y_train
+
+pipeline = make_pipeline(TfidfVectorizer(),svm.SVC())
+
+model = pipeline.fit(x_train, y_train)
+
+prediction = model.predict(x_dev)
+
+np.savetxt("svm/out.tsv", prediction, fmt='%d')

wyniki.txt

@@ -1,14 +1,20 @@
 Bayes:
 Likelihood	0.0000
 Accuracy	0.7367
-F1.0	0.4367
+F1.0		0.4367
 Precision	0.8997
-Recall	0.2883
+Recall		0.2883
 
 Logistic Regression:
 Likelihood	0.0000
 Accuracy	0.7523
-F1.0	0.6143
+F1.0		0.6143
 Precision	0.6842
-Recall	0.5573
+Recall		0.5573
 
+SVM:
+Likelihood	0.0000
+Accuracy	0.8249
+F1.0		0.7355
+Precision	0.7905
+Recall		0.6876