我编写了一个程序,该程序接收包含推文和标签的Twitter数据(0
代表中立情绪,1
代表消极情绪)并预测该推文所属的类别。
该程序在训练和测试集上效果很好。但是我在对字符串应用预测函数时遇到问题。我不确定该怎么做。
在调用预报函数之前,我曾尝试以清理数据集的方式清理字符串,但是返回的值格式错误。
import numpy as np
import pandas as pd
from nltk.corpus import stopwords
from nltk.stem.porter import PorterStemmer
ps = PorterStemmer()
import re
#Loading dataset
dataset = pd.read_csv('tweet.csv')
#List to hold cleaned tweets
clean_tweet = []
#Cleaning tweets
for i in range(len(dataset)):
tweet = re.sub('[^a-zA-Z]', ' ', dataset['tweet'][i])
tweet = re.sub('@[\w]*',' ',dataset['tweet'][i])
tweet = tweet.lower()
tweet = tweet.split()
tweet = [ps.stem(token) for token in tweet if not token in set(stopwords.words('english'))]
tweet = ' '.join(tweet)
clean_tweet.append(tweet)
from sklearn.feature_extraction.text import CountVectorizer
cv = CountVectorizer(max_features = 3000)
X = cv.fit_transform(clean_tweet)
X = X.toarray()
y = dataset.iloc[:, 1].values
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y)
from sklearn.naive_bayes import GaussianNB
n_b = GaussianNB()
n_b.fit(X_train, y_train)
y_pred = n_b.predict(X_test)
some_tweet = "this is a mean tweet" # How to apply predict function to this string
答案 0 :(得分:1)
在新字符串上使用cv.transform([cleaned_new_tweet])
,将新的Tweet转换为现有的文档术语矩阵。这样将以正确的形状返回Tweet。
答案 1 :(得分:1)
.predict()
期望list
中的strings
。因此,您需要将some_tweet
添加到list
中。例如。 new_tweet = ["this is a mean tweet"]
您的代码中有一些问题,我曾尝试为您解决...
import numpy as np
import pandas as pd
from nltk.corpus import stopwords
from nltk.stem.porter import PorterStemmer
ps = PorterStemmer()
import re
#Loading dataset
dataset = pd.read_csv('tweet.csv')
# Define cleaning function
# You can define it once as a function so it can be easily re-used else where
def clean_tweet(tweet: str):
tweet = re.sub('[^a-zA-Z]', ' ', dataset['tweet'][i])
tweet = re.sub('@[\w]*', ' ', tweet) #BUG: you need to pass the tweet you modified here instead of the original tweet again
tweet = tweet.lower()
tweet = tweet.split()
tweet = [ps.stem(token) for token in tweet if not token in set(stopwords.words('english'))]
tweet = ' '.join(tweet)
return tweet
#List to hold cleaned tweets and labels
X = [clean_tweet(tweet) for tweet in dataset['tweet']] # you can create your X directly with your new function
y = dataset.iloc[:, 1].values
# Define a single model
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.naive_bayes import GaussianNB
from sklearn.pipeline import Pipeline
# Use Pipeline as your classifier, this way you don't need to keep calling a transform and fit all the time.
classifier = Pipeline(
[
('cv', CountVectorizer(max_features=300)),
('n_b', GaussianNB())
]
)
# Before you trained your CountVectorizer BEFORE splitting into train/test. That is a biiig mistake.
# First you split to train/split and then you train all the steps of your model.
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y)
# Here you train all steps of your Pipeline in one go.
classifier.fit(X_train, y_train)
y_pred = classifier.predict(X_test)
# Predicting new tweets
some_tweet = "this is a mean tweet"
some_tweet = clean_tweet(some_tweet) # re-use your clean function
predicted = classifier.predict([some_tweet]) # put the tweet inside a list!!!!