* Raise exceptions if attempt to access parse, but data is not installed. This partly but not fully addresses Issue #97. Still need exceptions on the various Token attributes that access the parse tree, e.g. token.head, token.lefts, token.rights, etc. Exceptions should be centralized, too.

spacy/lexeme.pyx

@@ -55,6 +55,14 @@ cdef class Lexeme:
     property vector:
         def __get__(self):
             cdef int length = self.vocab.vectors_length
+            if length == 0:
+                raise ValueError(
+                    "Word vectors set to length 0. This may be because the "
+                    "data is not installed. If you haven't already, run"
+                    "\npython -m spacy.en.download all\n"
+                    "to install the data."
+                )
+ 
             repvec_view = <float[:length,]>self.c.repvec
             return numpy.asarray(repvec_view)
 

spacy/tokens/doc.pyx

@@ -232,6 +232,13 @@ cdef class Doc:
     @property
     def noun_chunks(self):
         """Yield spans for base noun phrases."""
+        if not self.is_parsed:
+            raise ValueError(
+                "noun_chunks requires the dependency parse, which "
+                "requires data to be installed. If you haven't done so, run: "
+                "\npython -m spacy.en.download all\n"
+                "to install the data")
+ 
         cdef const TokenC* word
         labels = ['nsubj', 'dobj', 'nsubjpass', 'pcomp', 'pobj', 'attr', 'conj']
         np_deps = [self.vocab.strings[label] for label in labels]
@@ -246,6 +253,12 @@ cdef class Doc:
         """
         Yield a list of sentence Span objects, calculated from the dependency parse.
         """
+        if not self.is_parsed:
+            raise ValueError(
+                "sentence boundary detection requires the dependency parse, which "
+                "requires data to be installed. If you haven't done so, run: "
+                "\npython -m spacy.en.download all\n"
+                "to install the data")
         cdef int i
         start = 0
         for i in range(1, self.length):

spacy/tokens/token.pyx

@@ -131,6 +131,13 @@ cdef class Token:
     property vector:
         def __get__(self):
             cdef int length = self.vocab.vectors_length
+            if length == 0:
+                raise ValueError(
+                    "Word vectors set to length 0. This may be because the "
+                    "data is not installed. If you haven't already, run"
+                    "\npython -m spacy.en.download all\n"
+                    "to install the data."
+                )
             repvec_view = <float[:length,]>self.c.lex.repvec
             return numpy.asarray(repvec_view)