File size: 5,360 Bytes
ca1226e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import re
import os
import numpy as np

# Load dataset
df = pd.read_csv('mail_data.csv', names=['Category', 'Message'], header=None, skiprows=1)

# Basic info
print("Dataset Shape:", df.shape)
print("\nValue Counts:\n", df['Category'].value_counts())
print("\nMissing Values:\n", df.isnull().sum())

# Add message length
df['Length'] = df['Message'].apply(len)

# Visualizations
plt.figure(figsize=(18, 10))

# 1. Class Distribution
plt.subplot(3, 2, 1)
sns.countplot(x='Category', data=df)
plt.title('Class Distribution (Spam vs Ham)')

# 2. Message Length Distribution
plt.subplot(3, 2, 2)
sns.histplot(data=df, x='Length', hue='Category', bins=50, kde=True)
plt.title('Message Length Distribution')

# Sample messages
print("\nSample Ham:")
print(df[df['Category'] == 'ham']['Message'].iloc[0])
print("\nSample Spam:")
print(df[df['Category'] == 'spam']['Message'].iloc[0])

#Let's check if there are other characteristic in our text data that separates spam from ham

#Word counts (how often different words are used)
def get_word_count(messages_series: pd.Series)->tuple:
    word_list = []
    for message in messages_series:
        clean_msg = re.sub("[\.|\?|,|\!]+", "", message).lower()
        clean_msg = re.sub("\ \ +", " ", clean_msg).split(" ")
        clean_msg = [word for word in clean_msg if word!=""]
        word_list+=clean_msg

    word_count = pd.Series(word_list).value_counts(normalize=True)
    return word_count

spam_word_count = get_word_count(df[df['Category'] == 'spam']['Message'])
ham_word_count = get_word_count(df[df['Category'] == 'ham']['Message'])

#TODO: Compare the words frequencies to find the ones used more often in spam emails compared to ham emails.

words_list = list(set(spam_word_count.index)&set(ham_word_count.index))
wordcount_distance_spam_ham = []
for i in words_list:
    if i in spam_word_count:
        spam_count_i = spam_word_count[i]
    else:
        spam_count_i = 0
    if i in ham_word_count:
        ham_count_i = ham_word_count[i]
    else:
        ham_count_i = 0
    wordcount_distance_spam_ham.append((ham_count_i-spam_count_i))
wordcount_distance_spam_ham = pd.Series(wordcount_distance_spam_ham, index=words_list)
wordcount_distance_spam_ham = wordcount_distance_spam_ham.sort_values(ascending=False)
print("Words more often found in normal emails than spam emails")
print(wordcount_distance_spam_ham[0:10]) #Words more often present in Ham emails
print("words more often found in spam emails than normal emails")
print(wordcount_distance_spam_ham[-10:]) #Words more often present in spam emails

#Mail Words length (numbers of words used in the message) 
def get_word_len(messages_series: pd.Series)->tuple:
    word_len_list = []
    for message in messages_series:
        clean_msg = re.sub("[\.|\?|,|\!|0-9|]+", "", message).lower()
        clean_msg = re.sub("\ \ +", " ", clean_msg).split(" ")
        clean_msg = [word for word in clean_msg if word!=""]
        word_len_list.append(len(clean_msg))

    len_count = pd.Series(word_len_list)
    return len_count

df['word_len'] = get_word_len(df['Message'])

plt.subplot(3, 2, 3)
sns.histplot(data=df, x='word_len', hue='Category', bins=50, kde=True)
plt.title('Word count Distribution')

#Mail Words length (numbers of words used in the message) 
def get_word_len2(messages_series: pd.Series)->tuple:
    word_len_list = []
    for message in messages_series:
        clean_msg = re.sub("[\.|\?|,|\!|0-9]+", "", message).lower()
        clean_msg = re.sub("\ \ +", " ", clean_msg).split(" ")
        clean_msg = [word for word in clean_msg if word!=""]
        total_word_length = 0
        if len(clean_msg)>0:
            for word in clean_msg:
                total_word_length += len(word)
            avg_word_len = total_word_length/len(clean_msg) 
            word_len_list.append(avg_word_len)
        else:
            word_len_list.append(0)

    len_count = pd.Series(word_len_list)
    return len_count

df['avg_word_len'] = get_word_len2(df['Message'])

plt.subplot(3, 2, 4)
sns.histplot(data=df, x='avg_word_len', hue='Category', bins=50, kde=True)
plt.title('Word length Distribution')

#Mail Words length (numbers of words used in the message) 
def get_avg_sentence_len(messages_series: pd.Series)->tuple:
    word_len_list = []
    avg_sentence_len = []
    for message in messages_series:
        clean_msg = re.sub("\ \ +", " ", message).split(" ")
        sentence_number = 1
        sentence_finished = False
        total_word_length = 0
        for word in clean_msg:
            total_word_length += 1
            if ("." in word) or ("?" in word) or ("!" in word):
                sentence_finished = True
            else:
                if sentence_finished:
                    sentence_number+=1
                    sentence_finished=False
        if total_word_length > 0:
            avg_sentence_len.append(total_word_length/sentence_number)
    avg_sentence_len = pd.Series(avg_sentence_len)
    return avg_sentence_len

df['avg_sentence_len'] = get_avg_sentence_len(df['Message'])

plt.subplot(3, 2, 5)
sns.histplot(data=df, x='avg_sentence_len', hue='Category', bins=50, kde=True)
plt.title('Sentence length Distribution')



plt.tight_layout()
plt.savefig('eda_plots.png')
print("\nEDA plots saved to eda_plots.png")