Modified nltk-internal imports to import values from the modules wher…

…e they are defined -- e.g., changed "from nltk import FreqDist" to "from nltk.probability import FreqDist". This helps to avoid circular import problems, and will be helpful if we choose to do any lazy importing to speed up nltk import time.

svn/trunk@8144

nltk/app/chartparser_app.py

@@ -46,8 +46,9 @@
 import os.path
 
 from nltk.parse.chart import *
-from nltk import tokenize, Tree, Nonterminal, parse_cfg
-from nltk import in_idle
+from nltk.tree import Tree
+from nltk.grammar import Nonterminal, parse_cfg
+from nltk.util import in_idle
 from nltk.draw.util import *
 from nltk.draw.cfg import CFGEditor
 from nltk.draw.tree import tree_to_treesegment, TreeSegmentWidget

nltk/app/chunkparser_app.py

@@ -22,7 +22,9 @@
 import re
 import random
 
-from nltk import corpus, Tree, chunk, in_idle
+import nltk
+from nltk.tree import Tree
+from nltk.util import in_idle
 from nltk.draw.util import *
 
 class RegexpChunkApp(object):
@@ -268,9 +270,9 @@ def __init__(self, devset_name='conll2000', devset=None,
         # Named development sets:
         if devset is None:
             if devset_name == 'conll2000':
-                devset = corpus.conll2000.chunked_sents('train.txt')#[:100]
+                devset = nltk.corpus.conll2000.chunked_sents('train.txt')#[:100]
             elif devset == 'treebank':
-                devset = corpus.treebank_chunk.chunked_sents()#[:100]
+                devset = nltk.corpus.treebank_chunk.chunked_sents()#[:100]
             else:
                 raise ValueError('Unknown development set %s' % devset_name)
 
@@ -318,7 +320,7 @@ def __init__(self, devset_name='conll2000', devset=None,
         """The index of the next sentence in the development set that
            should be looked at by the eval demon."""
 
-        self._eval_score = chunk.ChunkScore(chunk_node=chunk_node)
+        self._eval_score = nltk.chunk.ChunkScore(chunk_node=chunk_node)
         """The L{ChunkScore <nltk.chunk.ChunkScore>} object that's used
            to keep track of the score of the current grammar on the
            development set."""
@@ -571,7 +573,7 @@ def _eval_demon(self):
                     self._eval_normalized_grammar = None
                     return
             self._eval_index = 0
-            self._eval_score = chunk.ChunkScore(chunk_node=
+            self._eval_score = nltk.chunk.ChunkScore(chunk_node=
                                                 self._chunk_node)
             self._eval_grammar = self.grammar
             self._eval_normalized_grammar = self.normalized_grammar
@@ -824,7 +826,7 @@ def show_trace(self, *e):
             self.devsetbox.insert('end', tagseq+'\n')
             self.devsetbox.tag_add('wrapindent','end -2c linestart','end -2c')
             # Run a partial parser, and extract gold & test chunks
-            chunker = chunk.RegexpChunkParser(rules[:i])
+            chunker = nltk.chunk.RegexpChunkParser(rules[:i])
             test_tree = self._chunkparse(gold_tree.leaves())
             gold_chunks = self._chunks(gold_tree)
             test_chunks = self._chunks(test_tree)
@@ -896,11 +898,11 @@ def _view_history(self, index):
         self.normalized_grammar = self.normalize_grammar(
             self._history[index][0])
         if self.normalized_grammar:
-            rules = [chunk.regexp.RegexpChunkRule.parse(line)
+            rules = [nltk.chunk.regexp.RegexpChunkRule.parse(line)
                      for line in self.normalized_grammar.split('\n')]
         else:
             rules = []
-        self.chunker = chunk.RegexpChunkParser(rules)
+        self.chunker = nltk.chunk.RegexpChunkParser(rules)
         # Show the score.
         self._eval_plot()
         # Update the devset box
@@ -1028,7 +1030,7 @@ def _grammarcheck(self, grammar):
             line = re.sub(r'((\\.|[^#])*)(#.*)?', r'\1', line)
             line = line.strip()
             if line:
-                try: chunk.regexp.RegexpChunkRule.parse(line)
+                try: nltk.chunk.regexp.RegexpChunkRule.parse(line)
                 except ValueError, e:
                     self.grammarbox.tag_add('error', '%s.0' % (lineno+1),
                                             '%s.0 lineend' % (lineno+1))
@@ -1061,7 +1063,7 @@ def update(self, *event):
         try:
             # Note: the normalized grammar has no blank lines.
             if normalized_grammar:
-                rules = [chunk.regexp.RegexpChunkRule.parse(line)
+                rules = [nltk.chunk.regexp.RegexpChunkRule.parse(line)
                          for line in normalized_grammar.split('\n')]
             else:
                 rules = []
@@ -1071,7 +1073,7 @@ def update(self, *event):
             self.chunker = None
             return
 
-        self.chunker = chunk.RegexpChunkParser(rules)
+        self.chunker = nltk.chunk.RegexpChunkParser(rules)
         self.grammarbox.tag_remove('error', '1.0', 'end')
         self.grammar_changed = time.time()
         # Display the results

nltk/app/collocations_app.py

@@ -8,7 +8,9 @@
 
 import threading
 
-from nltk import corpus, FreqDist, in_idle
+import nltk
+from nltk.util import in_idle
+from nltk.probability import FreqDist
 from nltk.text import Text as TextDomain
 from nltk.draw.util import *
 
@@ -18,37 +20,37 @@
 _DEFAULT = 'English: Brown Corpus (Humor)'
 _CORPORA = {
             'Catalan: CESS-CAT Corpus':
-                lambda: corpus.cess_cat.words(),
+                lambda: nltk.corpus.cess_cat.words(),
             'English: Brown Corpus':
-                lambda: corpus.brown.words(),
+                lambda: nltk.corpus.brown.words(),
             'English: Brown Corpus (Press)':
-                lambda: corpus.brown.words(categories=['news', 'editorial', 'reviews']),
+                lambda: nltk.corpus.brown.words(categories=['news', 'editorial', 'reviews']),
             'English: Brown Corpus (Religion)':
-                lambda: corpus.brown.words(categories='religion'),
+                lambda: nltk.corpus.brown.words(categories='religion'),
             'English: Brown Corpus (Learned)':
-                lambda: corpus.brown.words(categories='learned'),
+                lambda: nltk.corpus.brown.words(categories='learned'),
             'English: Brown Corpus (Science Fiction)':
-                lambda: corpus.brown.words(categories='science_fiction'),
+                lambda: nltk.corpus.brown.words(categories='science_fiction'),
             'English: Brown Corpus (Romance)':
-                lambda: corpus.brown.words(categories='romance'),
+                lambda: nltk.corpus.brown.words(categories='romance'),
             'English: Brown Corpus (Humor)':
-                lambda: corpus.brown.words(categories='humor'),
+                lambda: nltk.corpus.brown.words(categories='humor'),
             'English: NPS Chat Corpus':
-                lambda: corpus.nps_chat.words(),
+                lambda: nltk.corpus.nps_chat.words(),
             'English: Wall Street Journal Corpus':
-                lambda: corpus.treebank.words(),
+                lambda: nltk.corpus.treebank.words(),
             'Chinese: Sinica Corpus':
-                lambda: corpus.sinica_treebank.words(),
+                lambda: nltk.corpus.sinica_treebank.words(),
             'Dutch: Alpino Corpus':
-                lambda: corpus.alpino.words(),
+                lambda: nltk.corpus.alpino.words(),
             'Hindi: Indian Languages Corpus':
-                lambda: corpus.indian.words(files='hindi.pos'),
+                lambda: nltk.corpus.indian.words(files='hindi.pos'),
             'Portuguese: Floresta Corpus (Portugal)':
-                lambda: corpus.floresta.words(),
+                lambda: nltk.corpus.floresta.words(),
             'Portuguese: MAC-MORPHO Corpus (Brazil)':
-                lambda: corpus.mac_morpho.words(),
+                lambda: nltk.corpus.mac_morpho.words(),
             'Spanish: CESS-ESP Corpus':
-                lambda: corpus.cess_esp.words(),
+                lambda: nltk.corpus.cess_esp.words(),
            }
 
 class CollocationsView:

nltk/app/concordance_app.py

@@ -10,7 +10,8 @@
 import re
 import threading
 
-from nltk import corpus, in_idle
+import nltk
+from nltk.util import in_idle
 from nltk.draw.util import *
 
 WORD_OR_TAG = '[^/ ]+'
@@ -27,53 +28,53 @@
 _DEFAULT = 'English: Brown Corpus (Humor, simplified)'
 _CORPORA = {
             'Catalan: CESS-CAT Corpus (simplified)':
-                lambda: corpus.cess_cat.tagged_sents(simplify_tags=True),
+                lambda: nltk.corpus.cess_cat.tagged_sents(simplify_tags=True),
             'English: Brown Corpus':
-                lambda: corpus.brown.tagged_sents(),
+                lambda: nltk.corpus.brown.tagged_sents(),
             'English: Brown Corpus (simplified)':
-                lambda: corpus.brown.tagged_sents(simplify_tags=True),
+                lambda: nltk.corpus.brown.tagged_sents(simplify_tags=True),
             'English: Brown Corpus (Press, simplified)':
-                lambda: corpus.brown.tagged_sents(categories=['news', 'editorial', 'reviews'], simplify_tags=True),
+                lambda: nltk.corpus.brown.tagged_sents(categories=['news', 'editorial', 'reviews'], simplify_tags=True),
             'English: Brown Corpus (Religion, simplified)':
-                lambda: corpus.brown.tagged_sents(categories='religion', simplify_tags=True),
+                lambda: nltk.corpus.brown.tagged_sents(categories='religion', simplify_tags=True),
             'English: Brown Corpus (Learned, simplified)':
-                lambda: corpus.brown.tagged_sents(categories='learned', simplify_tags=True),
+                lambda: nltk.corpus.brown.tagged_sents(categories='learned', simplify_tags=True),
             'English: Brown Corpus (Science Fiction, simplified)':
-                lambda: corpus.brown.tagged_sents(categories='science_fiction', simplify_tags=True),
+                lambda: nltk.corpus.brown.tagged_sents(categories='science_fiction', simplify_tags=True),
             'English: Brown Corpus (Romance, simplified)':
-                lambda: corpus.brown.tagged_sents(categories='romance', simplify_tags=True),
+                lambda: nltk.corpus.brown.tagged_sents(categories='romance', simplify_tags=True),
             'English: Brown Corpus (Humor, simplified)':
-                lambda: corpus.brown.tagged_sents(categories='humor', simplify_tags=True),
+                lambda: nltk.corpus.brown.tagged_sents(categories='humor', simplify_tags=True),
             'English: NPS Chat Corpus':
-                lambda: corpus.nps_chat.tagged_posts(),
+                lambda: nltk.corpus.nps_chat.tagged_posts(),
             'English: NPS Chat Corpus (simplified)':
-                lambda: corpus.nps_chat.tagged_posts(simplify_tags=True),
+                lambda: nltk.corpus.nps_chat.tagged_posts(simplify_tags=True),
             'English: Wall Street Journal Corpus':
-                lambda: corpus.treebank.tagged_sents(),
+                lambda: nltk.corpus.treebank.tagged_sents(),
             'English: Wall Street Journal Corpus (simplified)':
-                lambda: corpus.treebank.tagged_sents(simplify_tags=True),
+                lambda: nltk.corpus.treebank.tagged_sents(simplify_tags=True),
             'Chinese: Sinica Corpus':
-                lambda: corpus.sinica_treebank.tagged_sents(),
+                lambda: nltk.corpus.sinica_treebank.tagged_sents(),
             'Chinese: Sinica Corpus (simplified)':
-                lambda: corpus.sinica_treebank.tagged_sents(simplify_tags=True),
+                lambda: nltk.corpus.sinica_treebank.tagged_sents(simplify_tags=True),
             'Dutch: Alpino Corpus':
-                lambda: corpus.alpino.tagged_sents(),
+                lambda: nltk.corpus.alpino.tagged_sents(),
             'Dutch: Alpino Corpus (simplified)':
-                lambda: corpus.alpino.tagged_sents(simplify_tags=True),
+                lambda: nltk.corpus.alpino.tagged_sents(simplify_tags=True),
             'Hindi: Indian Languages Corpus':
-                lambda: corpus.indian.tagged_sents(files='hindi.pos'),
+                lambda: nltk.corpus.indian.tagged_sents(files='hindi.pos'),
             'Hindi: Indian Languages Corpus (simplified)':
-                lambda: corpus.indian.tagged_sents(files='hindi.pos', simplify_tags=True),
+                lambda: nltk.corpus.indian.tagged_sents(files='hindi.pos', simplify_tags=True),
             'Portuguese: Floresta Corpus (Portugal)':
-                lambda: corpus.floresta.tagged_sents(),
+                lambda: nltk.corpus.floresta.tagged_sents(),
             'Portuguese: Floresta Corpus (Portugal, simplified)':
-                lambda: corpus.floresta.tagged_sents(simplify_tags=True),
+                lambda: nltk.corpus.floresta.tagged_sents(simplify_tags=True),
             'Portuguese: MAC-MORPHO Corpus (Brazil)':
-                lambda: corpus.mac_morpho.tagged_sents(),
+                lambda: nltk.corpus.mac_morpho.tagged_sents(),
             'Portuguese: MAC-MORPHO Corpus (Brazil, simplified)':
-                lambda: corpus.mac_morpho.tagged_sents(simplify_tags=True),
+                lambda: nltk.corpus.mac_morpho.tagged_sents(simplify_tags=True),
             'Spanish: CESS-ESP Corpus (simplified)':
-                lambda: corpus.cess_esp.tagged_sents(simplify_tags=True),
+                lambda: nltk.corpus.cess_esp.tagged_sents(simplify_tags=True),
            }
 
 class ConcordanceSearchView(object):

nltk/app/rdparser_app.py

@@ -68,8 +68,9 @@
 
 import string
 
-from nltk import parse, tokenize, Tree, in_idle
-
+import nltk
+from nltk.tree import Tree
+from nltk.util import in_idle
 from nltk.draw.util import *
 from nltk.draw.tree import *
 from nltk.draw.cfg import *
@@ -86,7 +87,7 @@ class RecursiveDescentApp(object):
     """
     def __init__(self, grammar, sent, trace=0):
         self._sent = sent
-        self._parser = parse.SteppingRecursiveDescentParser(grammar, trace)
+        self._parser = nltk.parse.SteppingRecursiveDescentParser(grammar, trace)
 
         # Set up the main window.
         self._top = Tk()
@@ -866,7 +867,7 @@ def app():
     Create a recursive descent parser demo, using a simple grammar and
     text.
     """    
-    from nltk import parse_cfg
+    from nltk.grammar import parse_cfg
     grammar = parse_cfg("""
     # Grammatical productions.
         S -> NP VP

nltk/app/srparser_app.py

@@ -77,8 +77,8 @@
 
 import string
 
-from nltk import parse, tokenize, in_idle
-
+import nltk
+from nltk.util import in_idle
 from nltk.draw.util import *
 from nltk.draw.tree import *
 from nltk.draw.cfg import CFGEditor
@@ -92,11 +92,11 @@ class ShiftReduceApp(object):
     can shift tokens onto the stack, and can perform reductions on the
     top elements of the stack.  A "step" button simply steps through
     the parsing process, performing the operations that
-    C{parse.ShiftReduceParser} would use.
+    C{nltk.parse.ShiftReduceParser} would use.
     """
     def __init__(self, grammar, sent, trace=0):
         self._sent = sent
-        self._parser = parse.SteppingShiftReduceParser(grammar, trace)
+        self._parser = nltk.parse.SteppingShiftReduceParser(grammar, trace)
 
         # Set up the main window.
         self._top = Tk()
@@ -382,7 +382,7 @@ def _redraw(self):
         # Draw the stack.
         stackx = 5
         for tok in self._parser.stack():
-            if isinstance(tok, parse.Tree):
+            if isinstance(tok, Tree):
                 attribs = {'tree_color': '#4080a0', 'tree_width': 2,
                            'node_font': self._boldfont,
                            'node_color': '#006060',
@@ -685,7 +685,7 @@ def _animate_reduce_frame(self, frame, widgets, dy):
             for widget in widgets:
                 self._cframe.remove_widget(widget)
             tok = self._parser.stack()[-1]
-            if not isinstance(tok, parse.Tree): raise ValueError()
+            if not isinstance(tok, Tree): raise ValueError()
             label = TextWidget(self._canvas, str(tok.node), color='#006060',
                                font=self._boldfont)
             widget = TreeSegmentWidget(self._canvas, label, widgets,
@@ -708,7 +708,7 @@ def _animate_reduce_frame(self, frame, widgets, dy):
 #
 #             # Make a new one.
 #             tok = self._parser.stack()[-1]
-#             if isinstance(tok, parse.Tree):
+#             if isinstance(tok, Tree):
 #                 attribs = {'tree_color': '#4080a0', 'tree_width': 2,
 #                            'node_font': bold, 'node_color': '#006060',
 #                            'leaf_color': '#006060', 'leaf_font':self._font}
@@ -772,7 +772,7 @@ def app():
     text. 
     """
 
-    from nltk import Nonterminal, Production, ContextFreeGrammar
+    from nltk.grammar import Nonterminal, Production, ContextFreeGrammar
     nonterminals = 'S VP NP PP P N Name V Det'
     (S, VP, NP, PP, P, N, Name, V, Det) = [Nonterminal(s)
                                            for s in nonterminals.split()]

nltk/book.py

@@ -3,7 +3,8 @@
 from nltk.corpus import gutenberg, genesis, inaugural,\
        nps_chat, webtext, treebank, wordnet
 from nltk.text import Text
-from nltk import FreqDist, bigrams
+from nltk.probability import FreqDist
+from nltk.util import bigrams
 from nltk.misc import babelize_shell
 
 print "*** Introductory Examples for the NLTK Book ***"

nltk/chunk/regexp.py

@@ -9,7 +9,7 @@
 import re
 import types
 
-from nltk import Tree
+from nltk.tree import Tree
 
 from nltk.chunk.api import *
 from nltk.chunk.util import *
@@ -967,7 +967,6 @@ def _notrace_apply(self, chunkstr):
             rule.apply(chunkstr)
 
     def parse(self, chunk_struct, trace=None):
-        from nltk import Tree
         """
         @type chunk_struct: C{Tree}
         @param chunk_struct: the chunk structure to be (further) chunked
@@ -1224,8 +1223,8 @@ def demo_eval(chunkparser, text):
         evaluation.
     @type text: C{string}
     """
-
-    from nltk import chunk, Tree
+    from nltk import chunk
+    from nltk.tree import Tree
 
     # Evaluate our chunk parser.
     chunkscore = chunk.ChunkScore()