In [ ]:
#Assignment
In [53]:
import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
In [54]:
df_internet = pd.read_csv('C:\\Users\\MNLVBPV\internet_session.csv',parse_dates = ['start_time'])

df_internet
Out[54]:
name start_time usage_time IP MAC upload download total_transfer seession_break_reason
0 user1 2022-05-10 02:59:32 00:00:36:28 10.55.14.222 48:E7:DA:58:22:E9 15861.76 333168.64 349030.40 Idle-Timeout
1 user1 2022-05-10 18:53:27 00:01:49:56 10.55.2.253 48:E7:DA:58:22:E9 16957.44 212152.32 229109.76 Idle-Timeout
2 user1 2022-05-10 21:20:44 00:01:35:00 10.55.2.253 48:E7:DA:58:22:E9 14080.0 195153.92 209233.92 Idle-Timeout
3 user1 2022-05-11 00:37:42 00:00:26:00 10.55.2.253 48:E7:DA:58:22:E9 5242.88 40806.4 46049.28 Idle-Timeout
4 user1 2022-05-11 02:59:38 00:00:11:52 10.55.2.253 48:E7:DA:58:22:E9 22067.2 10772.48 32839.68 Idle-Timeout
... ... ... ... ... ... ... ... ... ...
4707 user9 2022-11-04 01:11:34 00:06:54:32 10.55.4.189 DA:2F:97:0E:B7:D0 107960.32 2390753.28 2495610.88 Idle-Timeout
4708 user9 2022-11-04 10:26:09 00:00:23:49 10.55.4.59 DA:2F:97:0E:B7:D0 11407.36 209674.24 221081.60 Idle-Timeout
4709 user9 2022-11-04 20:41:42 00:01:24:13 10.55.15.186 DA:2F:97:0E:B7:D0 18995.2 373657.6 392652.80 Idle-Timeout
4710 user9 2022-11-05 00:21:06 00:08:49:43 10.55.4.159 DA:2F:97:0E:B7:D0 46602.24 593766.4 640368.64 Idle-Timeout
4711 user9 2022-11-05 20:55:37 00:01:06:20 10.55.2.33 DA:2F:97:0E:B7:D0 21237.76 298536.96 319774.72 NaN

4712 rows × 9 columns

In [55]:
df_internet.shape
Out[55]:
(4712, 9)
In [56]:
#What is the most frequent internet activity time of the day ?

df_internet['hour'] = pd.to_datetime(df_internet['start_time']).dt.hour
frequent_activity= df_internet['hour'].value_counts().sort_index()
plt.figure(figsize=(18,9))
sns.lineplot(data=frequent_activity)
plt.xticks(np.linspace(start =0,stop =24,num=25))
plt.show()
plt.clf()

<Figure size 432x288 with 0 Axes>
In [62]:
# How often the ip changes ?

base_ip = '48:E7:DA:58:22:E9'
ip_count = 0
for i in range(1,df_internet.shape[0]):
    if df_internet.iloc[i]['IP'] !=base_ip:
        ip_count =+1
        base_ip = df_internet.iloc[i]['IP']
        
print("the ip address changed  " + str(ip_count)  + ' times')

the ip address changed  1 times
In [63]:
# How often the device changed.

base_device = 'download'
device_count = 0
for i in range(1, df_internet.shape[0]):
    if df_internet.iloc[i]['download'] != base_device:
        device_count +=1
        base_device = df_internet.iloc[i]['download']

print('The device changed ' + str(device_count) + ' times') 

The device changed 4710 times
In [64]:
# What is the average usage per hour , per day and per month ?

df_internet.reset_index(inplace=True)

df_internet['day'] = df_internet['start_time'].dt.day
df_internet['month'] = df_internet['start_time'].dt.month

hourly_average = df_internet.groupby('hour').total_transfer.mean()
print('The Average usage per hour is:\n ' +  str(round(hourly_average, 2)))

The Average usage per hour is:
 hour
0     464530.44
1     530880.86
2     431576.11
3     345303.34
4     359809.44
5     275960.91
6     468959.59
7     292886.83
8     366681.92
9     377480.64
10    393259.12
11    309492.45
12    310137.98
13    335270.58
14    472403.71
15    517005.11
16    403919.40
17    525423.69
18    665414.45
19    390839.43
20    355740.06
21    471461.40
22    449600.50
23    407785.08
Name: total_transfer, dtype: float64
In [ ]:
In [ ]:
In [ ]: