Question

我正在尝试使用Python和IBM Watson Tone Analyzer构建情感分析项目。首先，我使用的是TextBlob，但是现在我必须在同一代码中使用IBM Watson。当我使用TextBlob执行该代码时，它运行良好，但是对于IBM Watson，我遇到了一些问题，因为我是机器学习的新手，所以我根本不知道它是什么。

    #Import library
import tweepy
import pandas as pd
import numpy as np
from watson_developer_cloud import ToneAnalyzerV3
from watson_developer_cloud.tone_analyzer_v3 import ToneInput

#for plotting and virtualization
from IPython.display import display
import matplotlib.pyplot as plt
import seaborn as sns
%matplotlib inline

#Twitter app access keys for @user
#Consume
CONSUMER_KEY    = 'xxxxxxxxxxxxxxxxxxx'
CONSUMER_SECRET = 'xxxxxxxxxxxxxxxxxxx'
#Access
ACCESS_TOKEN  = 'xxxxxxxxxxxxxxxxxxxxxxx'
ACCESS_SECRET = 'xxxxxxxxxxxxxxxxxxxxxxx'

# We import our access keys:
from credentials import *    # This will allow us to use the keys as variables

# API's setup:
def twitter_setup():
    """
    Utility function to setup the Twitter's API
    with our access keys provided.
    """
    # Authentication and access using keys:
    auth = tweepy.OAuthHandler(CONSUMER_KEY, CONSUMER_SECRET)
    auth.set_access_token(ACCESS_TOKEN, ACCESS_SECRET)

    # Return API with authentication:
    api = tweepy.API(auth)
    return api

#Create an extractor object:
extractor = twitter_setup()
#We create tweet list as follows:
searchword = input("Enter the name to search:")
tweets = extractor.user_timeline(screen_name = searchword, count=200)
print("Number of tweets extracted : {}\n".format(len(tweets)))
#most recent tweet
print("3 most recent tweets:\n")
for tweet in tweets[:3]:
    print(tweet.text)
    print()

#Create panda dataframe
data = pd.DataFrame(data=[tweet.text for tweet in tweets], columns=['Tweets'])

#Add relevant data:
data['ID'] = np.array([tweet.id for tweet in tweets])
data['Date'] = np.array([tweet.created_at for tweet in tweets])
data['Likes'] = np.array([tweet.favorite_count for tweet in tweets])
data['Source'] = np.array([tweet.source for tweet in tweets])

#Sentiment asnalysis using watson
service = ToneAnalyzerV3(
         url="https://gateway.watsonplatform.net/tone-analyzer/api",
         username= "9adf63ab-8b6f-457b-a56a-33c25e0997c6",
         password= "qbms20FWWUNB")

#Sentiment Analysis on tweets:
#from textblob import TextBlob
#import re

#Clean tweets:
def clean_tweet(tweet):

    return ' '.join(re.sub("(@[A-Za-z0-9]+)|([^0-9A-Za-z \t])|(\w+:\/\/\S+)", " ", tweet).split())

tone_chat = service.tone_chat(clean_tweet(tweet))

def analize_sentiment(tweet):

    tone_chat = service.tone_chat(clean_tweet(tweet))

#    analysis = TextBlob(clean_tweet(tweet))
#    if analysis.sentiment.polarity > 0:
#       return 1
#    elif analysis.sentiment.polarity == 0:
#        return 0
#   else:
#        return -1

#Create a new column and display the new result:
data['SA'] = np.array(analize_sentiment(tweet) for tweet in data['Tweets']])
display(data.head(10))

#Construct classified list:
positive_tweets = [tweet for index, tweet in enumerate(data['Tweets']) if data['SA'][index] > 0]
neutral_tweets = [tweet for index, tweet in enumerate(data['Tweets']) if data['SA'][index] == 0]
negative_tweets = [tweet for index, tweet in enumerate(data['Tweets']) if data['SA'][index] < 0]

#We print percentages:
print("Percentage of positive tweets: {}%".format(len(positive_tweets)*100/len(data['Tweets'])))
print("Percentage of negative tweets: {}%".format(len(negative_tweets)*100/len(data['Tweets'])))
print("Percentage of neutral tweets: {}%".format(len(neutral_tweets)*100/len(data['Tweets'])))

# Pie chart:
ptweets = len(positive_tweets)*100/len(data['Tweets'])
neutweets = len(neutral_tweets)*100/len(data['Tweets'])
negtweets = len(negative_tweets)*100/len(data['Tweets'])
labels = 'negative','neutral','positive'
sizes = [negtweets,neutweets,ptweets]
cols = ['c','m','r']
plt.pie(sizes,labels=labels,colors=cols,startangle=90,shadow=True,autopct='%1.1f%%')
plt.legend()
plt.title("Overall Sentiment of the people in analzing 200 tweets")
plt.show()

我已经注释了TextBlob的旧代码，因此请忽略它。使用spyder执行它时，出现以下错误：

File "<ipython-input-12-4e56d84102b8>", line 93
    data['SA'] = np.array(analize_sentiment(tweet) for tweet in data['Tweets']])

请帮助我解决此错误，如果有任何错误，请详细提及，因为我可能不明白。

您可以直接在Sypder中运行此代码以重现错误并找出解决方案，请帮帮我。

谢谢

IBM Watson音调分析器

0 个答案: