Scribd
Upload
19 views4 pages

Mail Spam

The document discusses building machine learning models to classify email messages as spam or ham. It loads and prepares a dataset, splits it into training and test sets, and trains Naive Bayes, SVM and Random Forest classifiers on the data, evaluating their performance using accuracy scores and cross-validation.

Uploaded by

Sanjay
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
19 views4 pages

Mail Spam

The document discusses building machine learning models to classify email messages as spam or ham. It loads and prepares a dataset, splits it into training and test sets, and trains Naive Bayes, SVM and Random Forest classifiers on the data, evaluating their performance using accuracy scores and cross-validation.

Uploaded by

Sanjay
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 4

MailSpam

April 7, 2024

[1]: import pandas as pd

[2]: df_train=pd.read_csv('/content/drive/MyDrive/email.csv')
df_train.head()

[2]: Category Message


0 ham Go until jurong point, crazy.. Available only …
1 ham Ok lar… Joking wif u oni…
2 spam Free entry in 2 a wkly comp to win FA Cup fina…
3 ham U dun say so early hor… U c already then say…
4 ham Nah I don't think he goes to usf, he lives aro…

[3]: df_train.dtypes

[3]: Category object


Message object
dtype: object

[5]: df_train['spam']=df_train['Category'].apply(lambda x: 1 if x=='spam' else 0)


df_train.head()

[5]: Category Message spam


0 ham Go until jurong point, crazy.. Available only … 0
1 ham Ok lar… Joking wif u oni… 0
2 spam Free entry in 2 a wkly comp to win FA Cup fina… 1
3 ham U dun say so early hor… U c already then say… 0
4 ham Nah I don't think he goes to usf, he lives aro… 0

[6]: df_train.isnull().sum()

[6]: Category 0
Message 0
spam 0
dtype: int64

[7]: from sklearn.model_selection import train_test_split

X=df_train['Message']

1
y=df_train['spam']

X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.2)

[20]: from sklearn import svm


from sklearn.ensemble import RandomForestClassifier
from sklearn.naive_bayes import MultinomialNB
from sklearn import metrics
from sklearn.pipeline import Pipeline
from sklearn.feature_extraction.text import CountVectorizer

clf_NaiveBayes = Pipeline([
('vectorizer', CountVectorizer()),
('classifier', MultinomialNB())
])

clf_rfc = Pipeline([
('vectorizer', CountVectorizer()),
('classifier', RandomForestClassifier())
])

clf_svm = Pipeline([
('vectorizer', CountVectorizer()),
('svm',svm.SVC(kernel='linear',C=100,gamma=0.001))
])

clf_NaiveBayes.fit(X_train,y_train)
y_pred=clf_NaiveBayes.predict(X_test)
acc=metrics.accuracy_score(y_pred,y_test)
cm=metrics.confusion_matrix(y_pred,y_test)
print("Navies Bayes")
print(cm)
print(acc)

clf_svm.fit(X_train,y_train)
y_pred=clf_svm.predict(X_test)
acc_svm=metrics.accuracy_score(y_pred,y_test)
cm_svm=metrics.confusion_matrix(y_pred,y_test)
print("SVM:")
print(cm_svm)
print(acc_svm)

clf_rfc.fit(X_train,y_train)
y_pred=clf_rfc.predict(X_test)
acc_rfc=metrics.accuracy_score(y_pred,y_test)
cm_rfc=metrics.confusion_matrix(y_pred,y_test)
print("Random Forest Classifier:")

2
print(cm_rfc)
print(acc_rfc)

Navies Bayes
[[974 13]
[ 9 119]]
0.9802690582959641
SVM:
[[981 11]
[ 2 121]]
0.9883408071748879
Random Forest Classifier:
[[983 23]
[ 0 109]]
0.979372197309417

[23]: from sklearn.model_selection import cross_val_score

svm_cross_valid=cross_val_score(clf_svm,X_train,y_train,cv=5)
mean_acc_svm=svm_cross_valid.mean()
print(mean_acc_svm)

rfc_cross_valid=cross_val_score(clf_rfc,X_train,y_train,cv=5)
mean_acc_rfc=rfc_cross_valid.mean()
print(mean_acc_rfc)

nb_cross_valid=cross_val_score(clf_NaiveBayes,X_train,y_train,cv=5)
mean_acc_nb=nb_cross_valid.mean()
print(mean_acc_nb)

0.9802599990940799
0.9755489624697399
0.9860931185295907

[37]: from sklearn.model_selection import GridSearchCV

svm_param_grid = {'svm__C': [0.1, 1, 10, 100], 'svm__gamma': [0.1, 0.01, 0.


↪001], 'svm__kernel': ['linear', 'rbf', 'sigmoid', 'poly']}

svm_model_param = GridSearchCV(clf_svm, svm_param_grid,cv=3)


svm_model_param.fit(X_train, y_train)

svm_best_estimator = svm_model_param.best_estimator_

y_pred_svm = svm_best_estimator.predict(X_test)

3
svm_acc_ht = metrics.accuracy_score(y_pred_svm, y_test)

print("SVM Accuracy:", svm_acc_ht)

SVM Accuracy: 0.9883408071748879

[36]: rfc_param_grid = {
'classifier__n_estimators': [100, 200, 300],
'classifier__max_depth': [None, 10, 50],
'classifier__min_samples_split': [2, 5],
'classifier__min_samples_leaf': [1, 2]
}

# Perform RandomizedSearchCV for Random Forest with reduced search space and␣
↪fewer CV folds

rfc_model_param = GridSearchCV(clf_rfc, rfc_param_grid, cv=3, n_jobs=-1)


rfc_model_param.fit(X_train, y_train)

# Get best estimator


rfc_best_estimator = rfc_model_param.best_estimator_

# Make predictions on the test data


y_pred_rfc = rfc_best_estimator.predict(X_test)

# Calculate accuracy
rfc_acc_ht = metrics.accuracy_score(y_pred_rfc, y_test)

print("Random Forest Accuracy:", rfc_acc_ht)

Random Forest Accuracy: 0.9829596412556054

You might also like