[go: up one dir, main page]
Scribd
Upload
16 views2 pages

Exp 8-2

The document demonstrates how to perform one-hot encoding for text data using TensorFlow and scikit-learn. It includes examples of tokenizing text and encoding both words and characters into a binary format. Additionally, it visualizes the one-hot encoding of characters using a heatmap with Seaborn.

Uploaded by

nagallahema2004
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
16 views2 pages

Exp 8-2

The document demonstrates how to perform one-hot encoding for text data using TensorFlow and scikit-learn. It includes examples of tokenizing text and encoding both words and characters into a binary format. Additionally, it visualizes the one-hot encoding of characters using a heatmap with Seaborn.

Uploaded by

nagallahema2004
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

import numpy as np

import seaborn as sns


import matplotlib.pyplot as plt
from tensorflow.keras.preprocessing.text import Tokenizer
from sklearn.preprocessing import OneHotEncoder

# Example text
texts = ["hello world", "machine learning is fun"]

# Tokenizer and one-hot encoding


tokenizer = Tokenizer()
tokenizer.fit_on_texts(texts)
vocabulary = tokenizer.word_index
one_hot = tokenizer.texts_to_matrix(texts, mode='binary')

# One-hot encoding for characters


# Extract characters from the text
characters = sorted(set("".join(texts).replace(" ", ""))) # Remove
spaces and sort unique characters
encoder = OneHotEncoder(sparse_output=False)
char_one_hot = encoder.fit_transform(np.array(characters).reshape(-1,
1))

# Plot heatmap for one-hot encoding of characters


plt.figure(figsize=(8, 5))
sns.heatmap(char_one_hot, annot=True, fmt=".1f", cmap="Blues",
xticklabels=encoder.categories_[0],
yticklabels=characters)
plt.title("One-Hot Encoding for Characters")
plt.xlabel("Character")
plt.ylabel("Position")
plt.show()

You might also like