Last active
January 16, 2020 09:40
-
-
Save ettorerizza/20eba704fc5b0aa831e885494ca0fbb3 to your computer and use it in GitHub Desktop.
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
# Source : https://pythonprogramminglanguage.com/logistic-regression-spam-filter/ | |
# dataset : https://archive.ics.uci.edu/ml/datasets/SMS+Spam+Collection | |
import pandas as pd | |
import numpy as np | |
from sklearn.feature_extraction.text import TfidfVectorizer | |
from sklearn.linear_model.logistic import LogisticRegression | |
from sklearn.model_selection import train_test_split, cross_val_score | |
df = pd.read_csv(r'C:/Users/student/Desktop/spam detect logistic regression python/SMSSpamCollection', delimiter='\t',header=None) | |
X_train_raw, X_test_raw, y_train, y_test = train_test_split(df[1],df[0]) | |
vectorizer = TfidfVectorizer() | |
X_train = vectorizer.fit_transform( X_train_raw ) | |
classifier = LogisticRegression() | |
classifier.fit( X_train, y_train ) | |
text = ['URGENT! Win a prize!', 'Hello, how are you?'] | |
X_test = vectorizer.transform( text ) | |
predictions = classifier.predict( X_test ) | |
print(predictions) | |
""" | |
> ['spam', 'ham'] | |
""" |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment