Skip to content

Instantly share code, notes, and snippets.

Embed
What would you like to do?
import pandas as pd
import numpy as np
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.model_selection import train_test_split
from sklearn.naive_bayes import MultinomialNB
data = pd.read_csv("https://raw.githubusercontent.com/amankharwal/SMS-Spam-Detection/master/spam.csv", encoding= 'latin-1')
data = data[["class", "message"]]
x = np.array(data["message"])
y = np.array(data["class"])
cv = CountVectorizer()
X = cv.fit_transform(x) # Fit the Data
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, random_state=42)
clf = MultinomialNB()
clf.fit(X_train,y_train)
predictions = clf.predict(X_test)
# Classification Report
from sklearn.metrics import classification_report
print(classification_report(y_test, predictions))
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment