Naive Bayes

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


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")])
# INSPECT the dataframe
data.head()

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

print(f'first target: {targets[:1]}\n')
print(f'counts: {counts}\n')
print(f'get_feature_names_out: {vectorizer.get_feature_names_out()}\n')
print(f'first 5 feature names...: {vectorizer.get_feature_names_out()[:5]}')
print(counts.toarray())

classifier = MultinomialNB()
classifier.fit(counts, targets)

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

for idx, exampleText in enumerate(examples):
    # print(f'Text: {exampleText} is probably a {predictions[exampleIdx]}')
    print(f'{predictions[idx]}\t"{exampleText}"')