1.数据集的获取与处理同logisti回归中所用方法
from utils import process_tweet, lookup
import pdb
from nltk.corpus import stopwords, twitter_samples
import numpy as np
import pandas as pd
import nltk
import string
from nltk.tokenize import TweetTokenizer
from os import getcwd
# get the sets of positive and negative tweets
all_positive_tweets = twitter_samples.strings('positive_tweets.json')
all_negative_tweets = twitter_samples.strings('negative_tweets.json')
# split the data into two pieces, one for training and one for testing (validation set)
test_pos = all_positive_tweets[4000:]
train_pos = all_positive_tweets[:4000]
test_neg = all_negative_tweets[4000:]
train_neg = all_negative_tweets[:4000]
train_x = train_pos + train_neg
test_x = test_pos + test_neg
# avoid assumptions about the length of all_positive_tweets
train_y = np.append(np.ones(len(train_pos)), np.zeros(len(train_neg)))
test_y = np.append(np.ones(len(test_pos)), np.zeros(len(test_neg)))
def process_tweet(tweet):
'''
Input:
tweet: a string containing a tweet
Output:
tweets_clean: a list of words containing the processed tweet
'''
stemmer = PorterStemmer()
stopwords_english = stopwords.words('english')
# remove stock market tickers like $GE
tweet = re.sub(r'\$\w*', '', tweet)
# remove old style retweet text "RT"
tweet = re.sub(r'^RT[\s]+', '', tweet)
# remove hyperlinks
tweet = re.sub(r'https?:\/\/.*[\r\n]*', '', tweet)
# remove hashtags
# only removing the hash # sign from the word
tweet = re.sub(r'#', '', tweet)
# tokenize tweets
tokenizer = TweetTokenizer(preserve_case=False, strip_handles=True,
reduce_len=True)
tweet_tokens = tokenizer.tokenize(tweet)
tweets_clean = []
for word in tweet_tokens:
if (word not in stopwords_english and # remove stopwords