v1.0.7

src/cophi/__version__.py

@@ -1,3 +1,3 @@
-VERSION = (1, 0, 6)
+VERSION = (1, 0, 7)
 
 __version__ = ".".join(map(str, VERSION))

src/cophi/model.py

@@ -7,6 +7,7 @@
 
 import collections
 import itertools
+import logging
 import math
 import pathlib
 
@@ -18,6 +19,8 @@
 import cophi.utils
 import cophi.complexity
 
+logger = logging.getLogger(__name__)
+
 
 class Textfile:
     """Model class for a Textfile.
@@ -351,8 +354,15 @@ def __init__(self, documents, sparse=False):
         else:
             matrix = pd.DataFrame
         self.documents = documents
-        self.dtm = matrix({document.title: document.bow
-                           for document in self.documents})
+        def count_corpus(documents):
+            corpus = dict()
+            for document in documents:
+                logger.info("Processing '{}'...".format(document.title))
+                corpus[document.title] = document.bow
+            return corpus
+        counts = count_corpus(self.documents)
+        logger.info("Constructing document-term matrix...")
+        self.dtm = matrix(counts)
         self.dtm = self.dtm.T.fillna(0).astype(int)
 
     @staticmethod

src/cophi/utils.py

@@ -22,7 +22,7 @@ def construct_ngrams(tokens, n=2, sep=" "):
     return (sep.join(ngram)
             for ngram in zip(*(itertools.islice(i, token, None)
                              for token, i in enumerate(itertools.tee(tokens,
-                                                                     2)))))
+                                                                     n)))))
 
 
 def find_tokens(document, token_pattern=r"\p{L}+\p{P}?\p{L}+", maximum=None):