Get startedGet started for free

Assigning roles using spaCy's parser

In this exercise you'll use spaCy's powerful syntax parser to assign roles to the entities in your users' messages. To do this, you'll define two functions, find_parent_item() and assign_colors(). In doing so, you'll use a parse tree to assign roles, similar to how Alan did in the video.

Recall that you can access the ancestors of a word using its .ancestors attribute.

This exercise is part of the course

Building Chatbots in Python

View Course

Exercise instructions

  • Create a spacy document called doc by passing the message "let's see that jacket in red and some blue jeans" to the nlp object.
  • In the find_parent_item(word) function, iterate over the ancestors of each word until an entity_type() of "item" is found.
  • In the assign_colors(doc) function, iterate over the doc until an entity_type of "color" is found. Then, find the parent item of this word.
  • Pass in the spacy document to the assign_colors() function.

Hands-on interactive exercise

Have a go at this exercise by completing this sample code.

# Create the document
doc = ____

# Iterate over parents in parse tree until an item entity is found
def find_parent_item(word):
    # Iterate over the word's ancestors
    for parent in ____:
        # Check for an "item" entity
        if entity_type(____) == "____":
            return parent.text
    return None

# For all color entities, find their parent item
def assign_colors(doc):
    # Iterate over the document
    for word in ____:
        # Check for "color" entities
        if entity_type(word) == "____":
            # Find the parent
            item =  ____
            print("item: {0} has color : {1}".format(item, word))

# Assign the colors
____
Edit and Run Code