Scribd Logo
Upload

Welcome to Scribd!

  • 5 views

    Bayesian Methods

    Uploaded by

    pedropinto8400
    The document discusses Bayesian methods and naive Bayes classification. It shows how to use scikit-learn to build a naive Bayes classifier to classify text messages as spam or ham. The classifier is trained on a dataset of pre-classified emails and is then able to accurately predict the class of new text examples.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    Bayesian Methods

    Uploaded by

    pedropinto8400
    5 views3 pages
    The document discusses Bayesian methods and naive Bayes classification. It shows how to use scikit-learn to build a naive Bayes classifier to classify text messages as spam or ham. The classifier is trained on a dataset of pre-classified emails and is then able to accurately predict the class of new text examples.

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    The document discusses Bayesian methods and naive Bayes classification. It shows how to use scikit-learn to build a naive Bayes classifier to classify text messages as spam or ham. The classifier is trained on a dataset of pre-classified emails and is then able to accurately predict the class of new text examples.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    5 views3 pages

    Bayesian Methods

    Uploaded by

    pedropinto8400
    The document discusses Bayesian methods and naive Bayes classification. It shows how to use scikit-learn to build a naive Bayes classifier to classify text messages as spam or ham. The classifier is trained on a dataset of pre-classified emails and is then able to accurately predict the class of new text examples.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 3

    Bayesian Methods

    March 18, 2024

    0.1 Teorema de Bayes


    • P(A|B) = (P(A)*P(B|A)) / P(B), onde P(A|B) é a chance de A acontecer, dado B.
    • Exemplo de um detector de spam:
    – “Qual seria a chance de um email ser spam se conter a palavra ‘free’ em seu texto?”.
    – P(Spam | Free) = (P(Spam)*P(Free | Spam)) / P(Free)
    • Scikit-learn permite trabalhar de forma fácil com isto.
    • O “CountVectorizer” permite-nos com que operemos com várias palavras de uma vez só e
    MultinomialNB faz todo o trabalho “pesado” de Naive Bayes.

    0.2 Naive Bayes (jeito fácil)


    [4]: import os
    import io
    import numpy
    import pandas as pd
    from pandas import DataFrame
    from sklearn.feature_extraction.text import CountVectorizer
    from sklearn.naive_bayes import MultinomialNB

    def readFiles(path):
    for root, dirnames, filenames in os.walk(path):
    for filename in filenames:
    path = os.path.join(root, filename)

    inBody = False
    lines = []
    f = io.open(path, 'r', encoding='latin1')
    for line in f:
    if inBody:
    lines.append(line)
    elif line == '\n':
    inBody = True
    f.close()
    message = '\n'.join(lines)
    yield path, message

    1
    def dataFrameFromDirectory(path, classification):
    rows = []
    index = []
    for filename, message in readFiles(path):
    rows.append({'message': message, 'class': classification})
    index.append(filename)

    return DataFrame(rows, index=index)

    data = DataFrame({'message': [], 'class': []})

    data = pd.concat([data, dataFrameFromDirectory("emails/spam", "spam")]);


    data = pd.concat([data, dataFrameFromDirectory("emails/ham", "ham")])

    [14]: data.head()

    [14]: message \
    emails/spam/00217.43b4ef3d9c56cf42be9c37b546a19e78 <html><xbody>\n\n<hr width =
    "100%">\n\n<cente…
    emails/spam/00328.73c1a9f83d3b1247522c26eb6d74c215 \n\n Socijalisticka
    partija Srbije, pred…
    emails/spam/00408.22230b84aee00e439ae1938e025d5005 \n\n<html>\n\n<body
    bgcolor="#FFFFFF">\n\n<TAB…
    emails/spam/00383.1aa9a8211d1de540d6e3852e230e5a9d
    <html>\n\n<head>\n\n<title>FREE* Liz Claiborne…
    emails/spam/00390.ce19abc8034db9e6b435d494a91db87a This message is in MIME
    format. Since your mai…

    class
    emails/spam/00217.43b4ef3d9c56cf42be9c37b546a19e78 spam
    emails/spam/00328.73c1a9f83d3b1247522c26eb6d74c215 spam
    emails/spam/00408.22230b84aee00e439ae1938e025d5005 spam
    emails/spam/00383.1aa9a8211d1de540d6e3852e230e5a9d spam
    emails/spam/00390.ce19abc8034db9e6b435d494a91db87a spam

    [8]: vectorizer = CountVectorizer()


    counts = vectorizer.fit_transform(data['message'].values)

    classifier = MultinomialNB()
    targets = data['class'].values
    classifier.fit(counts, targets)

    [8]: MultinomialNB()

    [11]: examples = ['Free Viagra now!!!', "Hi Bob, how about a game of golf tomorrow?"]
    example_counts = vectorizer.transform(examples)
    predictions = classifier.predict(example_counts)

    2
    predictions

    [11]: array(['spam', 'ham'], dtype='<U4')

    Acima é possível ver que o modelo consegue classificar as frases acima de forma correta.

    You might also like