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')