Week2 Emojify_v3a key error

Course Q&A Deep Learning Specialization Sequence Models
1

Hello, and thank you for your time to answer. Currently working on Emojify. In " Exercise 1 - sentence_to_avg" at "

Initialize the average word vector, should have the same shape as your word vectors.

avg = np.zeros(word_to_vec_map['of'].shape)" part I cant initilize the avg to a certain shape. I tryed hardcoding but it is not working as said in description. I am trying to write as it is described, trying to get one of the "word_to_vec_map" keys and use it's shape. However even though I can output it, I cant use it in avg

===
for key, value in word_to_vec_map.items():
continue
print (key, value)
print(word_to_vec_map[‘of’])
print(word_to_vec_map[‘of’].shape)
print("===")
# Initialize the average word vector, should have the same shape as your word vectors.
avg = np.zeros(word_to_vec_map[‘of’].shape)

Output:
===
[‘morrocan’, ‘couscous’, ‘is’, ‘my’, ‘favorite’, ‘dish’]

[ 0.70853 0.57088 -0.4716 0.18048 0.54449 0.72603
0.18157 -0.52393 0.10381 -0.17566 0.078852 -0.36216
-0.11829 -0.83336 0.11917 -0.16605 0.061555 -0.012719
-0.56623 0.013616 0.22851 -0.14396 -0.067549 -0.38157
-0.23698 -1.7037 -0.86692 -0.26704 -0.2589 0.1767
3.8676 -0.1613 -0.13273 -0.68881 0.18444 0.0052464
-0.33874 -0.078956 0.24185 0.36576 -0.34727 0.28483
0.075693 -0.062178 -0.38988 0.22902 -0.21617 -0.22562
-0.093918 -0.80375 ]
(50,)

[0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.
0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.
0. 0.]
avg =
[0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.
0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.
0. 0.]

[‘a’, ‘a_nw’, ‘c_w’, ‘a_s’]

After that it gives key error at the avg part. I am stuck and burned out :smiley:

2

Replace [‘of’] with [any_word].

The “any_word” variable is defined specifically for this purpose by some code earlier in the notebook:

# Get a valid word contained in the word_to_vec_map. 
any_word = list(word_to_vec_map.keys())[0]
3

But any_word just prints out “the” in the descriptions didnt they said dont just use “the”

I tryed and now I am getting " Check that you are finding the 4 words" error

4

The reason your method using [‘of’] doesn’t work is because ‘of’ isn’t in the word_to_vec_map that the test case uses. It is only in the exercise example data set.

That’s why you get the “KeyError”

And that’s why the notebook gives you the “any_word” variable to use.

5

The instructions told you to not hard-code any words from the dictionary - so don’t use ‘the’, use the any_word variable, because that’s always going to be the first key in the dictionary.

6

That’s a different error. So there is another issue in your code.

7

I understand thank you, I am still getting “Check that you are finding the 4 words” error but idk if it is related to my first question

8

The “4 words” error means that either you’re not finding the correct words, or you’re not calculating the average correctly.

9

It’s a different problem entirely.

11

I tryed some experiemnts and found out I implemented a part incorrectly, it seem I have an other error, I will try to fix it, thank you for your time, :slight_smile:

2 Likes
12

Doesn’t work for me, what do i do?

13

What exactly doesn’t work for you? Please be specific.

14

TypeError Traceback (most recent call last)
in
1 # BEGIN UNIT TEST
----> 2 avg = sentence_to_avg(“Morrocan couscous is my favorite dish”, word_to_vec_map)
3 print(“avg = \n”, avg)
4
5 def sentence_to_avg_test(target):

in sentence_to_avg(sentence, word_to_vec_map)
31 # Check that word exists in word_to_vec_map
32 if w in words:
—> 33 avg += word_to_vec_map(w)
34
35 #avg += word_to_vec_map.get(w)

TypeError: ‘dict’ object is not callable

15

Hi, I’m getting this error and don’t know how to solve. Please help

16

“word_to_vec_map” is a python dictionary. So you have to access it using square brackets, not parenthesis.

17

hey i’m unable to fix this error.

avg = np.zeros(word_to_vec_map[any_word].shape)
avg += word_to_vec_map[w]

what am i doing wrong?

18

hey i’m unable to fix this error.

avg = np.zeros(word_to_vec_map[any_word].shape)
avg += word_to_vec_map[w]

what am i doing wrong?

1 Like
19

What error are you seeing? You’re just posting some code fragments.

20

the 4 words error only.
avg = np.zeros(word_to_vec_map[any_word].shape)
avg += word_to_vec_map[w]

i have been stuck on this for a while

21

Why do you feel there is a problem with those lines of code?