Created
August 15, 2022 10:57
-
-
Save okanyenigun/1cf0b57782338f0e3b68472b8e7ac738 to your computer and use it in GitHub Desktop.
naive bayes
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import nltk | |
nltk.download('stopwords') | |
import pandas as pd | |
import numpy as np | |
from nltk.corpus import stopwords | |
import string | |
from sklearn.feature_extraction.text import CountVectorizer | |
from sklearn.preprocessing import LabelBinarizer | |
from sklearn.model_selection import train_test_split | |
from sklearn.naive_bayes import MultinomialNB | |
from sklearn.metrics import accuracy_score | |
df = pd.read_csv("spam.csv",encoding='iso8859_14') | |
df.drop(labels=df.columns[2:],axis=1,inplace=True) | |
df.columns=['target','text'] | |
def clean_util(text): | |
punc_rmv = [char for char in text if char not in string.punctuation] | |
punc_rmv = "".join(punc_rmv) | |
stopword_rmv = [w.strip().lower() for w in punc_rmv.split() if w.strip().lower() not in stopwords.words('english')] | |
return " ".join(stopword_rmv) | |
df['text'] = df['text'].apply(clean_util) | |
cv = CountVectorizer() | |
X = cv.fit_transform(df['text']).toarray() | |
lb = LabelBinarizer() | |
y = lb.fit_transform(df['target']).ravel() | |
# Train Test Split | |
X_train, X_test, y_train, y_test = train_test_split(X,y) | |
clf = MultinomialNB(alpha=1) | |
clf.fit(X,y) | |
y_pred = clf.predict(X_test) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment