projekt-uma/svm.ipynb

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", encoding='utf-8') as f:
    x_train = f.readlines()


with open("train/expected.tsv", encoding='utf-8') as f:
    y_train = f.readlines()

len(x_train)

289579

np.random.seed(500)

with open("svm/in.tsv", encoding='utf-8') as f:
    x_dev = f.readlines()

len(y_train)

289579

y_train = LabelEncoder().fit_transform(y_train)
y_train

array([2, 0, 0, ..., 0, 0, 1], dtype=int64)

pipeline = make_pipeline(TfidfVectorizer(),svm.SVC())

model = pipeline.fit(x_train, y_train)

prediction = model.predict(x_dev)

np.savetxt("svm/outfull.tsv", prediction, fmt='%d')