texts = [
    "The quick brown fox jumps over the lazy dog",
    "Natural language processing is a subfield of artificial intelligence",
    "Machine learning enables computers to learn from data without explicit programming",
    "Deep learning is a branch of machine learning focused on neural networks",
    "Word embeddings capture semantic relationships between words in a text corpus"
]
 
test_txt = "Machine learning is awesome"
 
# Build Vocabulary
vocab = sorted(set(word for sentence in texts for word in sentence.split()))

import numpy as np
word_to_index = {word: idx for idx, word in enumerate(vocab)}
def one_hot_encode(word):
    """Convert a single English word into a one-hot encoded vector."""
    one_hot_vector = np.zeros(len(vocab))
    if word in word_to_index:
        one_hot_vector[word_to_index[word]] = 1  # Set index position to 1
    return one_hot_vector
 
# Example: Encode individual words
example_words = test_txt.split()
one_hot_vectors = {word: one_hot_encode(word) for word in example_words}
 
# Print One-Hot Encodings
for word, vector in one_hot_vectors.items():
    print(f"{word}: {vector}")

Machine: [0. 1. 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.]
learning: [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. 1. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
is: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 1.
 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
awesome: [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.]

import pandas as pd
import numpy as np
from sklearn.preprocessing import OneHotEncoder
 
encoder = OneHotEncoder(sparse_output=False,handle_unknown='ignore')
vocab_np = np.array(vocab).reshape(-1, 1)
encoder.fit(vocab_np)
test_txt_words = np.array(test_txt.lower().split()).reshape(-1, 1)
encoded_words = encoder.transform(test_txt_words)
for word, vector in zip(test_txt_words.flatten(), encoded_words):
    print(f"{word}: {vector}")

machine: [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. 1. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
learning: [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. 1. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
is: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 1.
 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
awesome: [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.]

 
def binary_transform(text):
    """Convert text into a binary vector."""
    output = np.zeros(len(vocab))
    words = set(text.split())  # Tokenize the input
    for i, v in enumerate(vocab):
        output[i] = v in words  # Set 1 if the word exists
    return output
 
print(binary_transform(test_txt))

[0. 1. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 1.
 0. 0. 0. 0. 1. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]

from sklearn.feature_extraction.text import CountVectorizer
import pandas as pd
 
vec = CountVectorizer(binary=True)
vec.fit(texts)
 
df = pd.DataFrame(vec.transform(texts).toarray(), columns=sorted(vec.vocabulary_.keys()))
print(df)

   artificial  between  branch  brown  capture  computers  corpus  data  deep  \
0           0        0       0      1        0          0       0     0     0   
1           1        0       0      0        0          0       0     0     0   
2           0        0       0      0        0          1       0     1     0   
3           0        0       1      0        0          0       0     0     1   
4           0        1       0      0        1          0       1     0     0   
 
   dog  ...  quick  relationships  semantic  subfield  text  the  to  without  \
0    1  ...      1              0         0         0     0    1   0        0   
1    0  ...      0              0         0         1     0    0   0        0   
2    0  ...      0              0         0         0     0    0   1        1   
3    0  ...      0              0         0         0     0    0   0        0   
4    0  ...      0              1         1         0     1    0   0        0   
 
   word  words  
0     0      0  
1     0      0  
2     0      0  
3     0      0  
4     1      1  
 
[5 rows x 43 columns]

print(sorted(vec.vocabulary_.keys()))
print(vec.transform([test_txt]).toarray())

['artificial', 'between', 'branch', 'brown', 'capture', 'computers', 'corpus', 'data', 'deep', 'dog', 'embeddings', 'enables', 'explicit', 'focused', 'fox', 'from', 'in', 'intelligence', 'is', 'jumps', 'language', 'lazy', 'learn', 'learning', 'machine', 'natural', 'networks', 'neural', 'of', 'on', 'over', 'processing', 'programming', 'quick', 'relationships', 'semantic', 'subfield', 'text', 'the', 'to', 'without', 'word', 'words']
[[0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0 1 1 0 0 0 0 0 0 0 0 0 0 0
  0 0 0 0 0 0 0]]

df = pd.DataFrame(vec.transform([test_txt]).toarray(), columns=sorted(vec.vocabulary_.keys()))
print(df)

   artificial  between  branch  brown  capture  computers  corpus  data  deep  \
0           0        0       0      0        0          0       0     0     0   
 
   dog  ...  quick  relationships  semantic  subfield  text  the  to  without  \
0    0  ...      0              0         0         0     0    0   0        0   
 
   word  words  
0     0      0  
 
[1 rows x 43 columns]

from sklearn.feature_extraction.text import CountVectorizer
import pandas as pd
 
vec = CountVectorizer()
vec.fit(texts)
 
df = pd.DataFrame(vec.transform(texts).toarray(), columns=sorted(vec.vocabulary_.keys()))
print(df)

   artificial  between  branch  brown  capture  computers  corpus  data  deep  \
0           0        0       0      1        0          0       0     0     0   
1           1        0       0      0        0          0       0     0     0   
2           0        0       0      0        0          1       0     1     0   
3           0        0       1      0        0          0       0     0     1   
4           0        1       0      0        1          0       1     0     0   
 
   dog  ...  quick  relationships  semantic  subfield  text  the  to  without  \
0    1  ...      1              0         0         0     0    2   0        0   
1    0  ...      0              0         0         1     0    0   0        0   
2    0  ...      0              0         0         0     0    0   1        1   
3    0  ...      0              0         0         0     0    0   0        0   
4    0  ...      0              1         1         0     1    0   0        0   
 
   word  words  
0     0      0  
1     0      0  
2     0      0  
3     0      0  
4     1      1  
 
[5 rows x 43 columns]

from sklearn.feature_extraction.text import TfidfVectorizer
 
vec = TfidfVectorizer()
vec.fit(texts)
 
df = pd.DataFrame(vec.transform(texts).toarray(), columns=sorted(vec.vocabulary_.keys()))
print(df)

   artificial   between    branch     brown   capture  computers    corpus  \
0     0.00000  0.000000  0.000000  0.301511  0.000000   0.000000  0.000000   
1     0.37007  0.000000  0.000000  0.000000  0.000000   0.000000  0.000000   
2     0.00000  0.000000  0.000000  0.000000  0.000000   0.311561  0.000000   
3     0.00000  0.000000  0.307781  0.000000  0.000000   0.000000  0.000000   
4     0.00000  0.316228  0.000000  0.000000  0.316228   0.000000  0.316228   
 
       data      deep       dog  ...     quick  relationships  semantic  \
0  0.000000  0.000000  0.301511  ...  0.301511       0.000000  0.000000   
1  0.000000  0.000000  0.000000  ...  0.000000       0.000000  0.000000   
2  0.311561  0.000000  0.000000  ...  0.000000       0.000000  0.000000   
3  0.000000  0.307781  0.000000  ...  0.000000       0.000000  0.000000   
4  0.000000  0.000000  0.000000  ...  0.000000       0.316228  0.316228   
 
   subfield      text       the        to   without      word     words  
0   0.00000  0.000000  0.603023  0.000000  0.000000  0.000000  0.000000  
1   0.37007  0.000000  0.000000  0.000000  0.000000  0.000000  0.000000  
2   0.00000  0.000000  0.000000  0.311561  0.311561  0.000000  0.000000  
3   0.00000  0.000000  0.000000  0.000000  0.000000  0.000000  0.000000  
4   0.00000  0.316228  0.000000  0.000000  0.000000  0.316228  0.316228  
 
[5 rows x 43 columns]

df = pd.DataFrame(vec.transform([test_txt]).toarray(), columns=sorted(vec.vocabulary_.keys()))
print(df)

   artificial  between  branch  brown  capture  computers  corpus  data  deep  \
0         0.0      0.0     0.0    0.0      0.0        0.0     0.0   0.0   0.0   
 
   dog  ...  quick  relationships  semantic  subfield  text  the   to  \
0  0.0  ...    0.0            0.0       0.0       0.0   0.0  0.0  0.0   
 
   without  word  words  
0      0.0   0.0    0.0  
 
[1 rows x 43 columns]

Openness: 72/100
Conscientiousness: 85/100
Extraversion: 38/100
Agreeableness: 65/100
Neuroticism: 47/100

import gensim
 
word2vec_model = gensim.models.KeyedVectors.load_word2vec_format(
    "GoogleNews-vectors-negative300.bin", binary=True
)
 
print("Word2Vec (King):", word2vec_model["king"][:10])  # First 10 values

Word2Vec (King): [ 0.12597656  0.02978516  0.00860596  0.13964844 -0.02563477 -0.03613281
  0.11181641 -0.19824219  0.05126953  0.36328125]

print("Word2Vec (Queen):", word2vec_model["Queen"][:10])  # First 10 values

Word2Vec (Queen): [-0.22070312 -0.17480469 -0.10498047  0.2578125   0.16210938 -0.13085938
 -0.16699219  0.07373047 -0.07226562  0.02404785]

import numpy as np
 
# Load GloVe embeddings
glove_embeddings = {}
with open("glove.6B.100d.txt", "r", encoding="utf-8") as f:
    for line in f:
        values = line.split()
        word = values[0]
        vector = np.asarray(values[1:], dtype="float32")
        glove_embeddings[word] = vector
 
print("GloVe 'king':", glove_embeddings["king"][:10])  # Show first 10 values

GloVe 'king': [-0.32307 -0.87616  0.21977  0.25268  0.22976  0.7388  -0.37954 -0.35307
 -0.84369 -1.1113 ]