I'm getting this error "AttributeError: 'Word2Vec' object has no attribute 'index2word'" in following code in python. Anyone knows how can I solve it?
Acctually "tfidf_weighted_averaged_word_vectorizer" throws the error. "obli.csv" contains line of sentences.
Thank you.
from feature_extractors import tfidf_weighted_averaged_word_vectorizer
dataset = get_data2()
corpus, labels = dataset.data, dataset.target
corpus, labels = remove_empty_docs(corpus, labels)
# print('Actual class label:', dataset.target_names[labels[10]])
train_corpus, test_corpus, train_labels, test_labels = prepare_datasets(corpus,
labels,
test_data_proportion=0.3)
tfidf_vectorizer, tfidf_train_features = tfidf_extractor(train_corpus)
vocab = tfidf_vectorizer.vocabulary_
tfidf_wv_train_features = tfidf_weighted_averaged_word_vectorizer(corpus=tokenized_train,
tfidf_vectors=tfidf_train_features,
tfidf_vocabulary=vocab,
model=model,
num_features=100)
def get_data2():
obli = pd.read_csv('db/obli.csv').values.ravel().tolist()
cl0 = [0 for x in range(len(obli))]
nonObli = pd.read_csv('db/nonObli.csv').values.ravel().tolist()
cl1 = [1 for x in range(len(nonObli))]
all = obli + nonObli
db = Db(all,cl0 + cl1)
db.data = all
db.target = cl0 + cl1
return db
This is code from chapter 4 of Text Analytics for Python by Dipanjan Sarkar.
index2word in gensim has been moved since that text was published.
Instead of model.index2word you should use model.wv.index2word.
Related
Any help will be highly appreciated
I'm trying to load two lists containing image paths and their corresponding labels. Something like this:
p0 = ['a','b',....] #paths to images .tif format
p1 = [1,2,3,......] #paths to images .tif format
labels = [0,1,1,...] #corresponding labels w.r.t both the lists
I used a tf.data in the following way:
def TFData(p_0, p_1, batch_size, labels=None, is_train=True):
dset = tf.data.Dataset.from_tensor_slices((p_0,p_1))
if labels is not None:
label = tf.data.Dataset.from_tensor_slices(labels)
AUTO = tf.data.experimental.AUTOTUNE
final_dset = tf.data.Dataset.zip((dset, label))
final_dset = final_dset.batch(batch_size, drop_remainder=is_train).prefetch(AUTO)
return final_dset
This returns:
<PrefetchDataset shapes: (((64,), (64,)), (64,)), types: ((tf.string, tf.string), tf.int32)>
My question is how to apply a function to convert the paths to arrays using cv2 as the images are .tif files? such that the result will be:
<PrefetchDataset shapes: (((64,256,256,3), (64,256,256,3)), (64,)), types: ((tf.float64, tf.float64), tf.int32)>
I'm using a dataset.map. However it's throwing error:
def to_array(p_0):
im_1 = cv2.imread(p_0,1)
#im = tfio.experimental.image.decode_tiff(paths)
im_1 = cv2.resize(im_1,(img_w,img_h)) #img_w=img_h=256
im_1 = np.asarray(im_1, dtype=np.float64)
im_1 /= 255
return im_1
def parse_fn(p_0):
[p_0,] = tf.py_function(to_array, [p_0], [tf.float64])
return p_0
def TFData(p_0, p_1, batch_size, labels=None, is_train=True):
dset_1 = tf.data.Dataset.from_tensor_slices(p_0)
dset_1 = dset_1.map(parse_fn)
dset_2 = tf.data.Dataset.from_tensor_slices(p_1)
dset_2 = dset_2.map(parse_fn)
if labels is not None:
label = tf.data.Dataset.from_tensor_slices(labels)
AUTO = tf.data.experimental.AUTOTUNE
final_dset = tf.data.Dataset.zip((dset_1, dset_2, label))
final_dset = final_dset.batch(batch_size, drop_remainder=is_train).prefetch(AUTO)
return final_dset
print(train_data) #where train_data is defined as TFData()
<PrefetchDataset shapes: ((<unknown>, <unknown>), (64,)), types: ((tf.float64, tf.float64), tf.int32)>
This throws an error:
for (t,p),l in train_data.as_numpy_iterator():
print(t)
print(p)
print(l)
print(type(t))
break
SystemError: <built-in function imread> returned NULL without setting an error
[[{{node EagerPyFunc}}]] [Op:IteratorGetNext]
Any help will be highly appreciated
I think your problem is in cv2.imread.
Have you checked outside the functions to see if it is reading and plotting the data accordingly?
Please, try with -1 instead:
im_1 = cv2.imread(p_0,-1)
def convert_data_to_examples(train, test, review, sentiment):
train_InputExamples = train.apply(lambda x: InputExample(guid=None, # Globally unique ID for bookkeeping, unused in this case
text_a = x[review],
label = x[sentiment]), axis = 1)
validation_InputExamples = test.apply(lambda x: InputExample(guid=None, # Globally unique ID for bookkeeping, unused in this case
text_a = x[review],
label = x[sentiment]), axis = 1,)
return train_InputExamples, validation_InputExamples
train_InputExamples, validation_InputExamples = convert_data_to_examples(train, test, 'review', 'sentiment')
NameError: name 'InputExample' is not defined
After running this part of code its gives error. Please tell me how to solve this error.
from transformers import InputExample
I have implemented sequence to sequence model with attention layer if I 300000 data points I'm not getting any error if I use all of my data points I'm getting following error model.fit
TypeError: Expected int32, got None of type 'NoneType' instead.
what would be the reason for this?
the code before model.fit is
class encoder_decoder(tf.keras.Model):
def __init__(self,embedding_size,encoder_inputs_length,output_length,vocab_size,output_vocab_size,score_fun,units):
super(encoder_decoder,self).__init__()
self.vocab_size = vocab_size
self.enc_units = units
self.embedding_size = embedding_size
self.encoder_inputs_length = encoder_inputs_length
self.output_length = output_length
self.lstm_output = 0
self.state_h = 0
self.state_c = 0
self.output_vocab_size = output_vocab_size
self.dec_units = units
self.score_fun = score_fun
self.att_units = units
self.encoder=Encoder(self.vocab_size,self.embedding_size,self.enc_units,self.encoder_inputs_length)
self.decoder = Decoder(self.output_vocab_size, self.embedding_size, self.output_length, self.dec_units ,self.score_fun ,self.att_units)
# self.dense = Dense(self.output_vocab_size,activation = "softmax")
def call(self,data):
input,output = data[0],data[1]
encoder_hidden = self.encoder.initialize_states(input.shape[0])
encoder_output,encoder_hidden,encoder_cell = self.encoder(input,encoder_hidden)
decoder_hidden = encoder_hidden
decoder_cell =encoder_cell
decoder_output = self.decoder(output,encoder_output,decoder_hidden,decoder_cell)
return decoder_output
Inside the call function I'm initializing states for the encoder where I'm getting
the number of rows from input using the following line of code
encoder_hidden = self.encoder.initialize_states(input.shape[0])
If I print input, I'm getting shape as (None,55)
That's the reason I'm getting this error.
Here my total number data points is 330614 when I use all my data I getting this
error, when I use only 330000 data points I'm getting this error,
if I print batch inside def method I'm getting shape as (64,55)
Please find my below code for creating dataset for my sequence to sequence model
the function to reprocess the data and the function to create the dataset
and a function the load the dataset
def preprocess_sentence(w):
# w = unicode_to_ascii(w.lower().strip())
w = re.sub(r"([?.!,¿])", r" \1 ", w)
w = re.sub(r'[" "]+', " ", w)
w = re.sub(r"[^a-zA-Z?.!,¿]+", " ", w)
w = w.strip()
w = '<start> ' + w + ' <end>'
return w
def create_dataset(path, num_examples):
lines = io.open(path, encoding='UTF-8').read().strip().split('\n')
# lines1 = lines[330000:]
# lines = lines[0:323386]+lines1
word_pairs = [[preprocess_sentence(w) for w in l.split('\t')] for l in lines[:num_examples]]
word_pairs = [[i[0],i[1]] for i in word_pairs]
return zip(*word_pairs)
def tokenize(lang):
lang_tokenizer = tf.keras.preprocessing.text.Tokenizer(
filters='')
lang_tokenizer.fit_on_texts(lang)
tensor = lang_tokenizer.texts_to_sequences(lang)
tensor = tf.keras.preprocessing.sequence.pad_sequences(tensor,padding='post')
return tensor, lang_tokenizer
def load_dataset(path, num_examples=None):
# creating cleaned input, output pairs
targ_lang, inp_lang = create_dataset(path, num_examples)
input_tensor, inp_lang_tokenizer = tokenize(inp_lang)
target_tensor, targ_lang_tokenizer = tokenize(targ_lang)
return input_tensor, target_tensor, inp_lang_tokenizer, targ_lang_tokenizer,targ_lang,inp_lang
# Try experimenting with the size of that dataset
num_examples = None
input_tensor, target_tensor, inp_lang, targ_lang,targ_lang_text,inp_lang_text = load_dataset(path, num_examples)
# Calculate max_length of the target tensors
max_length_targ, max_length_inp = target_tensor.shape[1], input_tensor.shape[1]
max_length_targ,max_length_inp
input_tensor_train, input_tensor_val, target_tensor_train, target_tensor_val = train_test_split(input_tensor, target_tensor, test_size=0.2)
the shape of datasets as follows
shape of input train (269291, 55)
shape of target train (269291, 53)
shape of input test (67323, 55)
shape of target test (67323, 53)
You can share the code block before the model.fit.
NoneType error is indicating that the final array which is passed to the model is for some reason empty. You can add print statements at previous steps to understand where along the way your array became empty.
Compare the scenario to the case where you are taking all your data points so that you can understand where the array is changing and how it is handled prior to passing it through model.fit.
I am trying to follow a kaggle kernel for BERT implementation :
https://www.kaggle.com/hiromoon166/save-bert-fine-tuning-model
But i am not able to select target variables. I have to select multiple target variables as my y variable as it is a multi-label classification.
This is the line of code i am stuck on:
train_lines, train_labels = train_df['comment_text'].values, train_df.target.values
def convert_lines(example, max_seq_length,tokenizer):
max_seq_length -=2
all_tokens = []
longer = 0
for i in range(example.shape[0]):
tokens_a = tokenizer.tokenize(example[i])
if len(tokens_a)>max_seq_length:
tokens_a = tokens_a[:max_seq_length]
longer += 1
one_token = tokenizer.convert_tokens_to_ids(["[CLS]"]+tokens_a+["[SEP]"])+[0] * (max_seq_length - len(tokens_a))
all_tokens.append(one_token)
print(longer)
return np.array(all_tokens)
nb_epochs=1
bsz = 32
dict_path = os.path.join(BERT_PRETRAINED_DIR, 'vocab.txt')
tokenizer = tokenization.FullTokenizer(vocab_file=dict_path, do_lower_case=True)
print('build tokenizer done')
train_df = pd.read_csv('../input/jigsaw-unintended-bias-in-toxicity-classification/train.csv')
train_df = train_df.sample(frac=0.01,random_state = 42)
#train_df['comment_text'] = train_df['comment_text'].replace({r'\s+$': '', r'^\s+': ''}, regex=True).replace(r'\n', ' ', regex=True)
train_lines, train_labels = train_df['comment_text'].values, train_df.target.values
print('sample used',train_lines.shape)
token_input = convert_lines(train_lines,maxlen,tokenizer)
seg_input = np.zeros((token_input.shape[0],maxlen))
mask_input = np.ones((token_input.shape[0],maxlen))
print(token_input.shape)
print(seg_input.shape)
print(mask_input.shape)
print('begin training')
model3.fit([token_input, seg_input, mask_input],train_labels,batch_size=bsz,epochs=nb_epochs)
Please help me understand how to select target variables here?
I want to create a dataset(data.npy) that has the same format as cifar10. The sample omniglot dataset contains
data = [0001_01.png,0001_02.png,0001_03.png,0001_04.png,0002_01.png,0002_02.png,0002_03.png]
class_name,filename = data[0].split('_')
Each file is append with class.There are 1600 classes and each class has 20 samples. The expected dataset(data.npy) shape is (1600,20,784)
But the shape i got is (1,20,784). Below given is the snippet
classes = []
examples = []
prev = files[0].split('_')[0]
for f in files:
cur_id = f.split('_')[0]
cur_pic = misc.imresize(misc.imread('new_data/' + f),[28,28])
cur_pic = (np.float32(cur_pic)/255).flatten()
if prev == cur_id:
examples.append(cur_pic)
else:
classes.append(examples)
examples = [cur_pic]
prev = cur_id
np.save('data',np.asarray(classes))
Any suggestions would be greatly helpful. The above code is taken from https://github.com/zergylord/oneshot