Python 文本分类错误 - 预期的字符串或类似字节的对象

Question

我正在尝试在 python 中对大型语料库（732,066 条推文）进行文本分类

# Importing the libraries
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

# Importing the dataset
#dataset = pd.read_csv('Restaurant_Reviews.tsv', delimiter = '\t', quoting = 3)

# Importing the dataset
cols = ["text","geocoordinates0","geocoordinates1","grid"]
dataset = pd.read_csv('tweets.tsv', delimiter = '\t', usecols=cols, quoting = 3, error_bad_lines=False, low_memory=False)

# Removing Non-ASCII characters
def remove_non_ascii_1(dataset):
    return ''.join([i if ord(i) < 128 else ' ' for i in dataset])

# Cleaning the texts
import re
import nltk
nltk.download('stopwords')
from nltk.corpus import stopwords
from nltk.stem.porter import PorterStemmer
corpus = []
for i in range(0, 732066):
    review = re.sub('[^a-zA-Z]', ' ', dataset['text'][i])
    review = review.lower()
    review = review.split()
    ps = PorterStemmer()
    review = [ps.stem(word) for word in review if not word in set(stopwords.words('english'))]
    review = ' '.join(review)
    corpus.append(review)

# Creating the Bag of Words model
from sklearn.feature_extraction.text import CountVectorizer
cv = CountVectorizer()
X = cv.fit_transform(corpus).toarray()
y = dataset.iloc[:, 1].values

# Splitting the dataset into the Training set and Test set
from sklearn.cross_validation import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.20, random_state = 0)

# Fitting Naive Bayes to the Training set
from sklearn.naive_bayes import GaussianNB
classifier = GaussianNB()
classifier.fit(X_train, y_train) 

# Predicting the Test set results
y_pred = classifier.predict(X_test)


# Making the Confusion Matrix
from sklearn.metrics import confusion_matrix
cm = confusion_matrix(y_test, y_pred)

# Applying k-Fold Cross Validation
from sklearn.model_selection import cross_val_score
accuracies = cross_val_score(estimator = classifier, X = X_train, y = y_train, cv = 10)
accuracies.mean()
accuracies.std()

这是我得到的错误，我被卡住了，无法继续机器学习文本分类的其余部分

Traceback (most recent call last):

  File "<ipython-input-2-3fac33122b74>", line 2, in <module>
    review = re.sub('[^a-zA-Z]', ' ', dataset['text'][i])

  File "C:\Anaconda3\envs\py35\lib\re.py", line 182, in sub
    return _compile(pattern, flags).sub(repl, string, count)
TypeError: expected string or bytes-like object

提前感谢您的帮助

Answer 1

尝试

str(dataset.loc[df.index[i], 'text'])

这会将它从之前的任何类型转换为 str 对象。