AmrutaKoshe

#pre-processing of data to remove special characters, hashtags, urls etc
import re
def cleanResume(resumeText):
    resumeText = re.sub('http\S+\s*', ' ', resumeText)  # remove URLs
    resumeText = re.sub('RT|cc', ' ', resumeText)  # remove RT and cc
    resumeText = re.sub('#\S+', '', resumeText)  # remove hashtags
    resumeText = re.sub('@\S+', '  ', resumeText)  # remove mentions
    resumeText = re.sub('[%s]' % re.escape("""!"#$%&'()*+,-./:;<=>[email protected][\]^_`{|}~"""), ' ', resumeText)  # remove punctuations
    resumeText = re.sub(r'[^\x00-\x7f]',r' ', resumeText) 
    resumeText = re.sub('\s+', ' ', resumeText)  # remove extra whitespace

AmrutaKoshe

#tokenize features and labels

import tensorflow as tf
from tensorflow.keras.preprocessing.sequence import pad_sequences
from tensorflow.keras.preprocessing.text import Tokenizer

# Tokenize feature data
vocab_size = 6000
oov_tok = '<>'

AmrutaKoshe

# Tokenize label data 
label_tokenizer = Tokenizer(lower=True)
label_tokenizer.fit_on_texts(labels)

label_index = label_tokenizer.word_index
print(dict(list(label_index.items())))

# Print example label encodings from train and test datasets
train_label_sequences = label_tokenizer.texts_to_sequences(train_labels)

AmrutaKoshe

#Train a sequential model

# Define the neural network
embedding_dim = 64

model = tf.keras.Sequential([
  # Add an Embedding layer expecting input vocab of size 6000, and output embedding dimension of size 64 we set at the top
  tf.keras.layers.Embedding(vocab_size, embedding_dim, input_length=1),
  tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(embedding_dim)),
  #tf.keras.layers.Dense(embedding_dim, activation='relu'),

AmrutaKoshe

# let's create an array containing the previous three examples to predict and use our model to get predictions

to_predict = [test_feature_padded[3],test_feature_padded[8],test_feature_padded[17]]
prediction = model.predict_classes(np.array(to_predict))

AmrutaKoshe

print(test_labels[3])
print(test_labels[8])
print(test_labels[17])

AmrutaKoshe

Name=[]
for file in os.listdir(directory):
    Name+=[file]
print(Name)
print(len(Name))

AmrutaKoshe

Breed = 'dog breed/Akita dog'
import os 
sub_class = os.listdir(Breed)

fig = plt.figure(figsize=(10,5))
for e in range(len(sub_class[:10])):
    plt.subplot(2,5,e+1)
    img = plt.imread(os.path.join(Breed,sub_class[e]))
    plt.imshow(img, cmap=plt.get_cmap('gray'))
    plt.axis('off')

AmrutaKoshe

dataset=[]
testset=[]
count=0

for file in os.listdir(directory):
    path=os.path.join(directory,file)
    t=0
    for im in os.listdir(path):
        image=load_img(os.path.join(path,im), grayscale=False, color_mode='rgb', target_size=(180,180))
        image=img_to_array(image)

AmrutaKoshe

labels1=to_categorical(labels0)
labels=np.array(labels1)

data=np.array(data)
test=np.array(test)