def __call__(self):
self.tokenize_normalize()
return self.create_embedding()
def convert_to_neg_pos(score):
"""
Apply linear conversion to change into -1 to 1 range.
:param score: float
:return: float
"""
new_value = ((score - 0) / (1 - 0)) * (1 + 1) + -1
return round(new_value, 3)
SentimentScorer_span = sentiment_analysis.SentimentAnalysisSpanish()
SentimentScorer_eng = SentimentIntensityAnalyzer()
def sentiment_score(word_list, lang):
"""
Helper function to calculate sentiment associated with word_list
:param word_list: list of words to score
:param lang: string with en or es
:return sentiment: float with sentiment score for words
"""
SentimentScorer_eng = SentimentIntensityAnalyzer()
if lang == 'es':
sentiment_total = [SentimentScorer_span.sentiment(word) for word in word_list]
sentiment = convert_to_neg_pos(np.mean(sentiment_total))
#libraries
import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
from sentiment_analysis_spanish import sentiment_analysis
import pandas as pd
import numpy as np
from math import sin
from time import time
#source code
initial_time = time()
sentiment = sentiment_analysis.SentimentAnalysisSpanish()
data_cleaning = []
analyzed_data = []
print('Reading data...')
df = pd.read_csv("data/data-test.csv")
file = open("data/list_art_pron.txt", "r", encoding="utf-8")
text = file.read()
art_pron = text.split(",")
print('Removing articles and pronouns...')
for row in df.message:
for art in art_pron:
row = row.replace(' ' + art + ' ', ' ')
data_cleaning.append(row)
print('Sentiment analysis...')
import sys
import src.config.urls as urls
import pandas as pd
import numpy as np
from sentiment_analysis_spanish import sentiment_analysis as s_a
# Initialize variables
sentiment = s_a.SentimentAnalysisSpanish()
def read_files():
try:
df = pd.read_csv(urls.url_csv)
file = open(urls.url_stopword, "r", encoding="utf-8")
text = file.read()
art_pron = text.split(",")
return [df, file, text, art_pron]
except:
print("An exception ocurred in method read_files", sys.exc_info()[0])
def remove_stopwords(df, art_pron):
try:
data_cleansing = []
for row in df.message:
for art in art_pron:
row = row.replace(' ' + art + ' ', ' ')
data_cleansing.append(row)
def __init__(self):
self._model = sentiment_analysis.SentimentAnalysisSpanish()
def analyze(text):
sentiment = sentiment_analysis.SentimentAnalysisSpanish()
result = sentiment.sentiment(text)
return result