akash-ch2812

# compute length of vocabulary and maximum length of a caption (for padding)
vocab_len = len(tokenizer.word_counts) + 1
print(f"Vocabulary length - {vocab_len}")

max_caption_len = max([len(x.split(" ")) for x in all_captions])
print(f"Maximum length of caption - {max_caption_len}")

akash-ch2812

from keras.preprocessing.sequence import pad_sequences
from keras.utils import to_categorical

# generator function to generate inputs for model
def create_trianing_data(captions, images, tokenizer, max_caption_length, vocab_len, photos_per_batch):
    
    X1, X2, y = list(), list(), list()
    n=0
   
    # loop through every image

akash-ch2812

import keras

def create_model(max_caption_length, vocab_length):
    
    # sub network for handling the image feature part
    input_layer1 = keras.Input(shape=(18432))
    feature1 = keras.layers.Dropout(0.2)(input_layer1)
    feature2 = keras.layers.Dense(max_caption_length*4, activation='relu')(feature1)
    feature3 = keras.layers.Dense(max_caption_length*4, activation='relu')(feature2)
    feature4 = keras.layers.Dense(max_caption_length*4, activation='relu')(feature3)

akash-ch2812

# create word embeddings
import spacy
nlp = spacy.load('en_core_web_lg')

# create word embeddings
embedding_dimension = 300
embedding_matrix = np.zeros((vocab_len, embedding_dimension))

# travel through every word in vocabulary and get its corresponding vector
for word, index in tokenizer.word_index.items():

akash-ch2812

# get training data
train_data = create_trianing_data(train_image_captions, train_image_features, tokenizer, max_caption_len, vocab_length, 32)

# initialize model
model = create_model(max_caption_len, vocab_len)

steps_per_epochs = len(train_image_captions)//32

# compile model
model.compile(optimizer='adam', loss='categorical_crossentropy')

akash-ch2812

import matplotlib.pyplot as plt
import seaborn as sns
from PIL import Image
%matplotlib inline

# method for generating captions
def generate_captions(model, image, tokenizer.word_index, max_caption_length, tokenizer.index_word):
    
    # input is <start>
    input_text = '<start>'

akash-ch2812

import spacy
import PyPDF2

# spacy english model (large)
nlp = spacy.load('en_core_web_lg')

# method for reading a pdf file
def readPdfFile(filename, folder_name):
    
    # storing path of PDF-Documents folder

akash-ch2812

# convert keywords to vector
def createKeywordsVectors(keyword, nlp):
    doc = nlp(keyword)  # convert to document object

    return doc.vector


# method to find cosine similarity
def cosineSimilarity(vect1, vect2):
    # return cosine distance

akash-ch2812

from spacy.matcher import PhraseMatcher
from scipy import spatial

# method for searching keyword from the text
def search_for_keyword(keyword, doc_obj, nlp):
    phrase_matcher = PhraseMatcher(nlp.vocab)
    phrase_list = [nlp(keyword)]
    phrase_matcher.add("Text Extractor", None, *phrase_list)

    matched_items = phrase_matcher(doc_obj)

akash-ch2812

import pandas as pd
import numpy as np

from sklearn.model_selection import train_test_split
from sklearn.preprocessing import MinMaxScaler
from sklearn.linear_model import LogisticRegression

from sklearn.metrics import classification_report, confusion_matrix, accuracy_score

# load dataset