!pip install --upgrade pip !pip install wordcloud

Spam detection using Machine Learning

Importing Libraries

import pandas as pd import numpy as np import re import collections import nltk from nltk.corpus import stopwords from sklearn.model_selection import train_test_split, cross_val_score from sklearn.feature_extraction.text import CountVectorizer from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score, classification_report import seaborn as sns import matplotlib.pyplot as plt %matplotlib inline #from sklearn.naive_bayes import MultinomialNB # from sklearn.ensemble import RandomForestClassifier # from sklearn.svm import SVC # from sklearn.linear_model import LogisticRegression

Importing Data

#Importing our data df = pd.read_csv('spam.csv')

Looking into data

df.head()

v1object

v2object

ham

Go until jurong point, crazy.. Available only in bugis n great world la e buffet... Cine there got …

ham

Ok lar... Joking wif u oni...

spam

Free entry in 2 a wkly comp to win FA Cup final tkts 21st May 2005. Text FA to 87121 to receive ent…

ham

U dun say so early hor... U c already then say...

ham

Nah I don't think he goes to usf, he lives around here though

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 5572 entries, 0 to 5571
Data columns (total 5 columns):
 #   Column      Non-Null Count  Dtype 
---  ------      --------------  ----- 
 0   v1          5572 non-null   object
 1   v2          5572 non-null   object
 2   Unnamed: 2  50 non-null     object
 3   Unnamed: 3  12 non-null     object
 4   Unnamed: 4  6 non-null      object
dtypes: object(5)
memory usage: 217.8+ KB

df.describe()

v1object

v2object

count

5572

unique

5169

top

ham

Sorry, I'll call later

freq

4825

Data Preprocessing

Getting required columns

df = df[['v1','v2']]

Changing column names

df.columns = ['Label','Text_data']

Creating 'Target' column to have numerical representation of 'Label' column

df['Target'] = df['Label'].map({'spam':1,'ham':0})

Creating 'Text_length' column

df['Text_length'] = df['Text_data'].apply(len)

Labelobject

ham86.6%

spam13.4%

Text_dataobject

Sorry, I'll call later0.5%

I cant pick the phone right now. Pls send a message0.2%

5167 others99.2%

ham

Go until jurong point, crazy.. Available only in bugis n great world la e buffet... Cine there got …

ham

Ok lar... Joking wif u oni...

spam

Free entry in 2 a wkly comp to win FA Cup final tkts 21st May 2005. Text FA to 87121 to receive ent…

ham

U dun say so early hor... U c already then say...

ham

Nah I don't think he goes to usf, he lives around here though

spam

FreeMsg Hey there darling it's been 3 week's now and no word back! I'd like some fun you up for it …

ham

Even my brother is not like to speak with me. They treat me like aids patent.

ham

As per your request 'Melle Melle (Oru Minnaminunginte Nurungu Vettam)' has been set as your callert…

spam

WINNER!! As a valued network customer you have been selected to receivea �900 prize reward! To clai…

spam

Had your mobile 11 months or more? U R entitled to Update to the latest colour mobiles with camera …

df.head()

Labelobject

Text_dataobject

ham

Go until jurong point, crazy.. Available only in bugis n great world la e buffet... Cine there got …

ham

Ok lar... Joking wif u oni...

spam

Free entry in 2 a wkly comp to win FA Cup final tkts 21st May 2005. Text FA to 87121 to receive ent…

ham

U dun say so early hor... U c already then say...

ham

Nah I don't think he goes to usf, he lives around here though

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 5572 entries, 0 to 5571
Data columns (total 4 columns):
 #   Column       Non-Null Count  Dtype 
---  ------       --------------  ----- 
 0   Label        5572 non-null   object
 1   Text_data    5572 non-null   object
 2   Target       5572 non-null   int64 
 3   Text_length  5572 non-null   int64 
dtypes: int64(2), object(2)
memory usage: 174.2+ KB

df.describe()

Targetfloat64

Text_lengthfloat64

count

5572

mean

0.134063173

80.05832735

std

0.3407507549

59.62393672

min

25%

50%

75%

121

max

910

df['Label'].value_counts()

nltk.download('stopwords') stop_words = set(stopwords.words('english'))

print(stop_words)

{'are', 'again', 'she', 'of', 'only', 've', "weren't", 'yourself', 'it', 'so', "she's", 'from', 'is', 'shan', 'those', 'out', 'yourselves', 'were', 'was', "mightn't", 'few', 'and', 'as', 'theirs', 'such', 'my', 'hers', 'a', 'has', 't', 'm', "isn't", 'same', 'all', 'but', 'ourselves', 'be', 'doing', "shouldn't", "don't", 'i', 'y', 'had', 'to', 'now', 'does', 'don', "you'll", 'them', 'that', 'the', 'this', 'we', 'until', 'hasn', 'will', 'having', 'when', 'up', 'against', "shan't", 'am', 'weren', 'over', "needn't", 'own', "aren't", 'mightn', 'further', 'above', 'then', 'hadn', 'no', 'being', 'couldn', 'have', 'why', "hasn't", 'under', 'here', 'your', 'below', 'herself', 'which', 'an', 'itself', 'who', 'both', "it's", "you'd", 'his', 'down', 'or', 'not', 'd', "you've", "haven't", "mustn't", 'than', 'him', 'at', 'more', 'yours', 'themselves', "won't", 'with', 'its', 'can', 'o', 'about', 'if', 'each', 'do', 'these', 'off', 'by', 'ain', 'before', 'how', "wasn't", 'just', 'what', "wouldn't", 'you', 'ours', 'himself', 'isn', 'too', 'her', 'me', 'through', 'did', 'because', 'once', 'our', 'where', 'aren', 'they', 'their', 'needn', "you're", 'didn', 'into', 'doesn', 'most', 'very', "couldn't", 'he', 'wasn', 'some', 'll', "hadn't", "doesn't", 'mustn', 'in', 'on', 'between', 'other', 's', 'wouldn', 'myself', 'haven', "should've", 'won', 'there', 'after', "that'll", 'while', 'for', 'should', 're', 'ma', 'any', 'nor', "didn't", 'shouldn', 'during', 'been', 'whom'}

Cleaning data

def process_text(data): sentence_in_lowercase = data.lower() sentence_with_only_alphanumerics = re.sub(r'[^0-9a-zA-Z]', ' ', sentence_in_lowercase) sentence_removed_of_extra_spaces = re.sub(r'\s+', ' ', sentence_with_only_alphanumerics) processed_sentence = " ".join(word for word in sentence_removed_of_extra_spaces.split() if word not in stop_words) return processed_sentence

df['Cleaned_Text_data'] = df['Text_data'].apply(process_text)

Labelobject

ham86.6%

spam13.4%

Text_dataobject

Sorry, I'll call later0.5%

I cant pick the phone right now. Pls send a message0.2%

5167 others99.2%

ham

Go until jurong point, crazy.. Available only in bugis n great world la e buffet... Cine there got …

ham

Ok lar... Joking wif u oni...

spam

Free entry in 2 a wkly comp to win FA Cup final tkts 21st May 2005. Text FA to 87121 to receive ent…

ham

U dun say so early hor... U c already then say...

ham

Nah I don't think he goes to usf, he lives around here though

spam

FreeMsg Hey there darling it's been 3 week's now and no word back! I'd like some fun you up for it …

ham

Even my brother is not like to speak with me. They treat me like aids patent.

ham

As per your request 'Melle Melle (Oru Minnaminunginte Nurungu Vettam)' has been set as your callert…

spam

WINNER!! As a valued network customer you have been selected to receivea �900 prize reward! To clai…

spam

Had your mobile 11 months or more? U R entitled to Update to the latest colour mobiles with camera …

df['Cleaned_text_length'] = df['Cleaned_Text_data'].apply(len)

Labelobject

ham86.6%

spam13.4%

Text_dataobject

Sorry, I'll call later0.5%

I cant pick the phone right now. Pls send a message0.2%

5167 others99.2%

ham

Go until jurong point, crazy.. Available only in bugis n great world la e buffet... Cine there got …

ham

Ok lar... Joking wif u oni...

spam

Free entry in 2 a wkly comp to win FA Cup final tkts 21st May 2005. Text FA to 87121 to receive ent…

ham

U dun say so early hor... U c already then say...

ham

Nah I don't think he goes to usf, he lives around here though

spam

FreeMsg Hey there darling it's been 3 week's now and no word back! I'd like some fun you up for it …

ham

Even my brother is not like to speak with me. They treat me like aids patent.

ham

As per your request 'Melle Melle (Oru Minnaminunginte Nurungu Vettam)' has been set as your callert…

spam

WINNER!! As a valued network customer you have been selected to receivea �900 prize reward! To clai…

spam

Had your mobile 11 months or more? U R entitled to Update to the latest colour mobiles with camera …

Visualization

plt.figure(figsize=(8,8)) df['Label'].value_counts().plot(kind='pie', labels=['Ham','spam'], autopct='%1.0f%%') plt.title('Ham vs Spam') plt.show()

plt.figure(figsize=(8,8)) plt.grid(True) df['Label'].value_counts().plot(kind='bar') plt.legend = ['ham','spam'] plt.xlabel("Label") plt.ylabel("Count") plt.title("Ham vs Spam") plt.show()

df.hist(bins=40, figsize=(16,10), by='Label', column='Text_length', color=['Green']) plt.show()

sns.countplot(df['Label']) plt.show()

/shared-libs/python3.9/py/lib/python3.9/site-packages/seaborn/_decorators.py:36: FutureWarning: Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  warnings.warn(

def plot_top_10_words(data): counter = collections.Counter([word for sentence in data for word in sentence.split()]) most_common_10_words = counter.most_common(15) most_common_10_words_df = pd.DataFrame(most_common_10_words, columns=["Word", "Count"]).sort_values(by="Count") most_common_10_words_df.plot.barh(x = "Word", y = "Count", color="blue", figsize=(15, 20)) plt.title('Top 10 common words') plt.grid(True) plt.xlabel("Count")

Top 10 common words before cleaning data

plot_top_10_words(df["Text_data"])

Top 10 common words after cleaning data

plot_top_10_words(df["Cleaned_Text_data"])

Dividing data so that it can be used later on if required

spam_data = df[df['Label']=='spam'] spam_data.head()

Labelobject

Text_dataobject

spam

Free entry in 2 a wkly comp to win FA Cup final tkts 21st May 2005. Text FA to 87121 to receive ent…

spam

FreeMsg Hey there darling it's been 3 week's now and no word back! I'd like some fun you up for it …

spam

WINNER!! As a valued network customer you have been selected to receivea �900 prize reward! To clai…

spam

Had your mobile 11 months or more? U R entitled to Update to the latest colour mobiles with camera …

spam

SIX chances to win CASH! From 100 to 20,000 pounds txt> CSH11 and send to 87575. Cost 150p/day, 6da…

spam_data

Labelobject

spam100%

Text_dataobject

Please call our customer service representative on FREEPHONE 0808 145 4742 between 9am-11pm as you have WON a guaranteed �1000 cash or �5000 prize!0.5%

HMV BONUS SPECIAL 500 pounds of genuine HMV vouchers to be won. Just answer 4 easy questions. Play Now! Send HMV to 86688 More info:www.100percent-real.com0.4%

651 others99.1%

spam

Free entry in 2 a wkly comp to win FA Cup final tkts 21st May 2005. Text FA to 87121 to receive ent…

spam

FreeMsg Hey there darling it's been 3 week's now and no word back! I'd like some fun you up for it …

spam

WINNER!! As a valued network customer you have been selected to receivea �900 prize reward! To clai…

spam

Had your mobile 11 months or more? U R entitled to Update to the latest colour mobiles with camera …

spam

SIX chances to win CASH! From 100 to 20,000 pounds txt> CSH11 and send to 87575. Cost 150p/day, 6da…

spam

URGENT! You have won a 1 week FREE membership in our �100,000 Prize Jackpot! Txt the word: CLAIM to…

spam

XXXMobileMovieClub: To use your credit, click the WAP link in the next txt message or click here>> …

spam

England v Macedonia - dont miss the goals/team news. Txt ur national team to 87077 eg ENGLAND to 87…

spam

Thanks for your subscription to Ringtone UK your mobile will be charged �5/month Please confirm by …

spam

07732584351 - Rodger Burns - MSG = We tried to call you re your reply to our sms for a free nokia m…

ham_data = df[df['Label']=='ham'] ham_data.head()

Labelobject

Text_dataobject

ham

Go until jurong point, crazy.. Available only in bugis n great world la e buffet... Cine there got …

ham

Ok lar... Joking wif u oni...

ham

U dun say so early hor... U c already then say...

ham

Nah I don't think he goes to usf, he lives around here though

ham

Even my brother is not like to speak with me. They treat me like aids patent.

ham_data

Labelobject

ham100%

Text_dataobject

Sorry, I'll call later0.6%

I cant pick the phone right now. Pls send a message0.2%

4514 others99.1%

ham

Go until jurong point, crazy.. Available only in bugis n great world la e buffet... Cine there got …

ham

Ok lar... Joking wif u oni...

ham

U dun say so early hor... U c already then say...

ham

Nah I don't think he goes to usf, he lives around here though

ham

Even my brother is not like to speak with me. They treat me like aids patent.

ham

As per your request 'Melle Melle (Oru Minnaminunginte Nurungu Vettam)' has been set as your callert…

ham

I'm gonna be home soon and i don't want to talk about this stuff anymore tonight, k? I've cried eno…

ham

I've been searching for the right words to thank you for this breather. I promise i wont take your …

ham

I HAVE A DATE ON SUNDAY WITH WILL!!

ham

Oh k...i'm watching here:)

Implementation

Training and Testing set split

X = df['Cleaned_Text_data'] y = df['Target']

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=0)

X_train.shape

X_test.shape

cv = CountVectorizer().fit(X_train)

training_set = cv.transform(X_train) training_set

testing_set = cv.transform(X_test) testing_set

Trying with multiple models

def provide_classification_report(model): model.fit(training_set,y_train) y_pred = model.predict(testing_set) print('Classification Report\n') print(classification_report(y_test, y_pred)) print('\n Accuracy',accuracy_score(y_test, y_pred)) print('\n Precision',precision_score(y_test, y_pred)) print('\n Recall',recall_score(y_test, y_pred)) print('\n F1 score',f1_score(y_test, y_pred))

from sklearn.linear_model import LogisticRegression model = LogisticRegression() provide_classification_report(model)

Classification Report

              precision    recall  f1-score   support

           0       0.97      1.00      0.99      1196
           1       1.00      0.84      0.91       197

    accuracy                           0.98      1393
   macro avg       0.99      0.92      0.95      1393
weighted avg       0.98      0.98      0.98      1393


 Accuracy 0.9777458722182341

 Precision 1.0

 Recall 0.8426395939086294

 F1 score 0.9146005509641872

from sklearn.naive_bayes import MultinomialNB model = MultinomialNB() provide_classification_report(model)

Classification Report

              precision    recall  f1-score   support

           0       0.99      1.00      0.99      1196
           1       0.98      0.94      0.96       197

    accuracy                           0.99      1393
   macro avg       0.98      0.97      0.98      1393
weighted avg       0.99      0.99      0.99      1393


 Accuracy 0.9885139985642498

 Precision 0.9788359788359788

 Recall 0.9390862944162437

 F1 score 0.9585492227979275

from sklearn.svm import SVC model = SVC(C=3) provide_classification_report(model)

Classification Report

              precision    recall  f1-score   support

           0       0.98      1.00      0.99      1196
           1       0.99      0.88      0.93       197

    accuracy                           0.98      1393
   macro avg       0.99      0.94      0.96      1393
weighted avg       0.98      0.98      0.98      1393


 Accuracy 0.9820531227566404

 Precision 0.9942528735632183

 Recall 0.8781725888324873

 F1 score 0.9326145552560647

from sklearn.tree import DecisionTreeClassifier model = DecisionTreeClassifier() provide_classification_report(model)

Classification Report

              precision    recall  f1-score   support

           0       0.97      0.99      0.98      1196
           1       0.94      0.83      0.88       197

    accuracy                           0.97      1393
   macro avg       0.95      0.91      0.93      1393
weighted avg       0.97      0.97      0.97      1393


 Accuracy 0.9676956209619526

 Precision 0.9367816091954023

 Recall 0.8274111675126904

 F1 score 0.8787061994609165

from sklearn.ensemble import RandomForestClassifier model = RandomForestClassifier() provide_classification_report(model)

Classification Report

              precision    recall  f1-score   support

           0       0.97      1.00      0.99      1196
           1       1.00      0.82      0.90       197

    accuracy                           0.97      1393
   macro avg       0.99      0.91      0.94      1393
weighted avg       0.97      0.97      0.97      1393


 Accuracy 0.9741564967695621

 Precision 1.0

 Recall 0.817258883248731

 F1 score 0.899441340782123

from sklearn.neighbors import KNeighborsClassifier model = KNeighborsClassifier() provide_classification_report(model)

Classification Report

              precision    recall  f1-score   support

           0       0.90      1.00      0.95      1196
           1       1.00      0.33      0.50       197

    accuracy                           0.91      1393
   macro avg       0.95      0.66      0.72      1393
weighted avg       0.91      0.91      0.88      1393


 Accuracy 0.905240488155061

 Precision 1.0

 Recall 0.3299492385786802

 F1 score 0.4961832061068702

Creating a pandas data frame having scores of all above models

results = pd.DataFrame({'Model':['LogisticRegression','MultinomialNB','SVC','DecisionTreeClassifier','RandomForestClassifier','KNeighborsClassifier'], 'Accuracy':[0.98, 0.98, 0.98, 0.96, 0.97, 0.90], 'Precision':[1.0, 0.97, 0.99, 0.94, 1.0, 1.0], 'Recall':[0.84, 0.93, 0.87, 0.82, 0.81, 0.32], 'F1 score':[0.91, 0.95, 0.93, 0.87, 0.89, 0.49]})

results

Modelobject

Accuracyfloat64

MultinomialNB

0.98

SVC

0.98

LogisticRegression

0.98

RandomForestClassifier

0.97

DecisionTreeClassifier

0.96

KNeighborsClassifier

0.9