train_set = []
for i in range(len(data_train)):
data1 = data_train.tweet[i]
data2 = data_train.label[i]
train_tup = (data1, data2)
train_set.append(train_tup)
tweet_train_set = [tweet for tweet,label in train_set]
label_train_set = [label for tweet,label in train_set]
## inisialisasi LSF data train ##
train_lsf = []
lsf_train = LSF.LSF(data_train)
for i in range(len(lsf_train)):
lsf1 = lsf_train[i]
lsf2 = lsf_train[i]
lsf_train_tup = (lsf1,lsf2)
train_lsf.append(lsf_train_tup)
train_lsf = np.array(train_lsf)
#%%
## inisialisasi data test ##
test_set = []
for i in range(len(data_testing)):
data3 = data_testing.tweet[i]
# -*- coding: utf-8 -*-
"""
Created on Tue Apr 24 23:33:53 2018
@author: Latifah
"""
import pandas as pd
import LSF
dataset = pd.read_csv("testing_prepros(01).csv", encoding='utf-8')
#%%
score = pd.Series(LSF.LSF(dataset))
#%%
label = []
for i in range(score.shape[0]):
if (score.iloc[i] >= 1):
label.append(int(1))
else:
label.append(int(0))
#%%
from sklearn.metrics import accuracy_score, precision_score, recall_score, confusion_matrix
accuracy = accuracy_score(dataset.label, label) * 100
precision = precision_score(dataset.label, label) * 100
recall = recall_score(dataset.label, label) * 100
confusion_matrix = confusion_matrix(dataset.label, label)
