关于python：使用cv.fit_transform（corpus）.toarray（）的内存错误

Memory error using cv.fit_transform(corpus).toarray()

enter image description here 如果有人能帮助cv.fit_Transform(corpus.toarray()处理大小约为732066x<140(tweets)的语料库，我将不胜感激。文本已被清除，以减少功能和维度，但我一直得到下面的错误

我就是这样开始的

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57

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

# 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]', ' ', str(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[:, 3].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()

下面是输出错误：

X = cv.fit_transform(corpus).toarray() Traceback (most recent call
last):

File"", line 1, in
X = cv.fit_transform(corpus).toarray()

File
"C:\Anaconda3\envs\py35\lib\site-packages\scipy\sparse\compressed.py",
line 920, in toarray
return self.tocoo(copy=False).toarray(order=order, out=out)

File
"C:\Anaconda3\envs\py35\lib\site-packages\scipy\sparse\coo.py",
line 252, in toarray
B = self._process_toarray_args(order, out)

File
"C:\Anaconda3\envs\py35\lib\site-packages\scipy\sparse\base.py",
line 1009, in _process_toarray_args
return np.zeros(self.shape, dtype=self.dtype, order=order)

MemoryError

多谢了！

ps:删除arraylist并使用@kumar建议的multinomianb后，现在出现以下错误：

1
2
3

from sklearn.naive_bayes import MultinomialNB
classifier = MultinomialNB()
classifier.fit(X_train, y_train)

Traceback (most recent call last):

File"", line 1, in
classifier.fit(X_train, y_train)

File
"C:\Anaconda3\envs\py35\lib\site-packages\sklearn
aive_bayes.py",
line 566, in fit
Y = labelbin.fit_transform(y)

File
"C:\Anaconda3\envs\py35\lib\site-packages\sklearn\base.py",
line 494, in fit_transform
return self.fit(X, **fit_params).transform(X)

File
"C:\Anaconda3\envs\py35\lib\site-packages\sklearn\preprocessing\label.py",
line 296, in fit
self.y_type_ = type_of_target(y)

File
"C:\Anaconda3\envs\py35\lib\site-packages\sklearn\utils\multiclass.py",
line 275, in type_of_target
if (len(np.unique(y)) > 2) or (y.ndim >= 2 and len(y[0]) > 1):

File
"C:\Anaconda3\envs\py35\lib\site-packages
umpy\lib\arraysetops.py",
line 198, in unique
ar.sort()

TypeError: unorderable types: str() > float()