efficient Term Document Matrix with NLTK
An Alternative approach using tokens and Data Frame
import nltk
comment #nltk.download() to get toenize
from urllib import request
url = "http://www.gutenberg.org/files/2554/2554-0.txt"
response = request.urlopen(url)
raw = response.read().decode('utf8')
type(raw)
tokens = nltk.word_tokenize(raw)
type(tokens)
tokens[1:10]
['Project',
'Gutenberg',
'EBook',
'of',
'Crime',
'and',
'Punishment',
',',
'by']
tokens2=pd.DataFrame(tokens)
tokens2.columns=['Words']
tokens2.head()
Words
0 The
1 Project
2 Gutenberg
3 EBook
4 of
tokens2.Words.value_counts().head()
, 16178
. 9589
the 7436
and 6284
to 5278
I know the OP wanted to create a tdm in NLTK, but the textmining
package (pip install textmining
) makes it dead simple:
import textmining
# Create some very short sample documents
doc1 = 'John and Bob are brothers.'
doc2 = 'John went to the store. The store was closed.'
doc3 = 'Bob went to the store too.'
# Initialize class to create term-document matrix
tdm = textmining.TermDocumentMatrix()
# Add the documents
tdm.add_doc(doc1)
tdm.add_doc(doc2)
tdm.add_doc(doc3)
# Write matrix file -- cutoff=1 means words in 1+ documents are retained
tdm.write_csv('matrix.csv', cutoff=1)
# Instead of writing the matrix, access its rows directly
for row in tdm.rows(cutoff=1):
print row
Output:
['and', 'the', 'brothers', 'to', 'are', 'closed', 'bob', 'john', 'was', 'went', 'store', 'too']
[1, 0, 1, 0, 1, 0, 1, 1, 0, 0, 0, 0]
[0, 2, 0, 1, 0, 1, 0, 1, 1, 1, 2, 0]
[0, 1, 0, 1, 0, 0, 1, 0, 0, 1, 1, 1]
Alternatively, one can use pandas and sklearn [source]:
import pandas as pd
from sklearn.feature_extraction.text import CountVectorizer
docs = ['why hello there', 'omg hello pony', 'she went there? omg']
vec = CountVectorizer()
X = vec.fit_transform(docs)
df = pd.DataFrame(X.toarray(), columns=vec.get_feature_names())
print(df)
Output:
hello omg pony she there went why
0 1 0 0 0 1 0 1
1 1 1 1 0 0 0 0
2 0 1 0 1 1 1 0
Thanks to Radim and Larsmans. My objective was to have a DTM like the one you get in R tm. I decided to use scikit-learn and partly inspired by this blog entry. This the code I came up with.
I post it here in the hope that someone else will find it useful.
import pandas as pd
from sklearn.feature_extraction.text import CountVectorizer
def fn_tdm_df(docs, xColNames = None, **kwargs):
''' create a term document matrix as pandas DataFrame
with **kwargs you can pass arguments of CountVectorizer
if xColNames is given the dataframe gets columns Names'''
#initialize the vectorizer
vectorizer = CountVectorizer(**kwargs)
x1 = vectorizer.fit_transform(docs)
#create dataFrame
df = pd.DataFrame(x1.toarray().transpose(), index = vectorizer.get_feature_names())
if xColNames is not None:
df.columns = xColNames
return df
to use it on a list of text in a directory
DIR = 'C:/Data/'
def fn_CorpusFromDIR(xDIR):
''' functions to create corpus from a Directories
Input: Directory
Output: A dictionary with
Names of files ['ColNames']
the text in corpus ['docs']'''
import os
Res = dict(docs = [open(os.path.join(xDIR,f)).read() for f in os.listdir(xDIR)],
ColNames = map(lambda x: 'P_' + x[0:6], os.listdir(xDIR)))
return Res
to create the dataframe
d1 = fn_tdm_df(docs = fn_CorpusFromDIR(DIR)['docs'],
xColNames = fn_CorpusFromDIR(DIR)['ColNames'],
stop_words=None, charset_error = 'replace')