Email Spam Detection (Binary Classification)
IntermediateHands-On ML Projects for Intermediate Learners
Project 1:
import pandas as pd
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
df = pd.read_csv("emails.csv")
X = CountVectorizer().fit_transform(df["text"])
y = df["label"]
X_train, X_test, y_train, y_test = train_test_split(X, y)
model = LogisticRegression()
model.fit(X_train, y_train)
print("Accuracy:", model.score(X_test, y_test))