UNI-PROG3-CW2-MLWP/Q1.ipynb

This is the Q1 Notebook!

It's tracked via GitHub! hence the need for this line for the init commit

In [70]:

import pandas as pd
import numpy as np

In [71]:

df = pd.read_csv('data/googleplaystore_new.csv')

Part A

In [72]:

df = df.dropna()
df = df.drop_duplicates()

In [73]:

df.head(10)

Out [73]:

	App	Category	Rating	Reviews	Size	Installs	Type	Price	Content Rating	Genres	Android Ver
0	Market Update Helper	LIBRARIES_AND_DEMO	4.1	20145	11k	1,000,000+	Free	0	Everyone	Libraries & Demo	1.5 and up
1	SuperLivePro	BUSINESS	4.3	46353	21M	1,000,000+	Free	0	Everyone	Business	1.5 and up
2	Wifi Connect Library	LIBRARIES_AND_DEMO	3.9	58055	41k	5,000,000+	Free	0	Everyone	Libraries & Demo	1.5 and up
3	Apk Installer	LIBRARIES_AND_DEMO	3.8	7750	292k	1,000,000+	Free	0	Everyone	Libraries & Demo	1.6 and up
4	English speaking texts	EDUCATION	4.4	1619	3.0M	1,000,000+	Free	0	Everyone	Education	1.6 and up
5	Eternal life	LIBRARIES_AND_DEMO	5.0	26	2.5M	1,000+	Free	0	Everyone	Libraries & Demo	1.6 and up
6	Dresses Ideas & Fashions +3000	BEAUTY	4.5	473	8.2M	100,000+	Free	0	Mature 17+	Beauty	1.6 and up
7	GO Notifier	COMMUNICATION	4.2	124346	695k	10,000,000+	Free	0	Everyone	Communication	2.0 and up
8	Prosperity	EVENTS	5.0	16	2.3M	100+	Free	0	Everyone	Events	2.0 and up
9	NSE Mobile Trading	FINANCE	4.1	13868	1.4M	1,000,000+	Free	0	Everyone	Finance	2.1 and up

Part B

In [74]:

# Getting the column for size, checking if it's ending with an M or a k and converting the Mb to kb with 1024* and then again from kb to just b by another 1024*
def parse_size(size_str):
    if isinstance(size_str, str):
        if size_str.endswith('M'):
            return float(size_str[:-1]) * 1024 * 1024
        elif size_str.endswith('k'):
            return float(size_str[:-1]) * 1024
    return size_str

In [75]:

df['Size in bytes'] = df['Size'].apply(parse_size)

In [81]:

df[['Size', 'Size in bytes']].head(10)

Out [81]:

	Size	Size in bytes
0	11k	11264.0
1	21M	22020096.0
2	41k	41984.0
3	292k	299008.0
4	3.0M	3145728.0
5	2.5M	2621440.0
6	8.2M	8598323.2
7	695k	711680.0
8	2.3M	2411724.8
9	1.4M	1468006.4

In [77]:

print(11*1024) # Just checking the kb and mb conversion happened properly, by checking 2 of the values manually.

11264

In [78]:

print((21*1024)*1024) # Ideally this is the same as doing the calculation without the ( ) but just incase!

22020096

In [79]:

print(1.4*1024*1024) # This one seemed odd... Checked on an online converted to double-check but turns out the 0.4 bytes shows up there too.

1468006.4

In [80]:

df.head(10)

Out [80]:

	App	Category	Rating	Reviews	Size	Installs	Type	Price	Content Rating	Genres	Android Ver	Size in bytes
0	Market Update Helper	LIBRARIES_AND_DEMO	4.1	20145	11k	1,000,000+	Free	0	Everyone	Libraries & Demo	1.5 and up	11264.0
1	SuperLivePro	BUSINESS	4.3	46353	21M	1,000,000+	Free	0	Everyone	Business	1.5 and up	22020096.0
2	Wifi Connect Library	LIBRARIES_AND_DEMO	3.9	58055	41k	5,000,000+	Free	0	Everyone	Libraries & Demo	1.5 and up	41984.0
3	Apk Installer	LIBRARIES_AND_DEMO	3.8	7750	292k	1,000,000+	Free	0	Everyone	Libraries & Demo	1.6 and up	299008.0
4	English speaking texts	EDUCATION	4.4	1619	3.0M	1,000,000+	Free	0	Everyone	Education	1.6 and up	3145728.0
5	Eternal life	LIBRARIES_AND_DEMO	5.0	26	2.5M	1,000+	Free	0	Everyone	Libraries & Demo	1.6 and up	2621440.0
6	Dresses Ideas & Fashions +3000	BEAUTY	4.5	473	8.2M	100,000+	Free	0	Mature 17+	Beauty	1.6 and up	8598323.2
7	GO Notifier	COMMUNICATION	4.2	124346	695k	10,000,000+	Free	0	Everyone	Communication	2.0 and up	711680.0
8	Prosperity	EVENTS	5.0	16	2.3M	100+	Free	0	Everyone	Events	2.0 and up	2411724.8
9	NSE Mobile Trading	FINANCE	4.1	13868	1.4M	1,000,000+	Free	0	Everyone	Finance	2.1 and up	1468006.4

Part C

In [82]:

df['Numeric_installs'] = df['Installs'].str.replace('+', '').str.replace(',', '').astype(int)

In [83]:

df.head(10)

Out [83]:

	App	Category	Rating	Reviews	Size	Installs	Type	Price	Content Rating	Genres	Android Ver	Size in bytes	Numeric_installs
0	Market Update Helper	LIBRARIES_AND_DEMO	4.1	20145	11k	1,000,000+	Free	0	Everyone	Libraries & Demo	1.5 and up	11264.0	1000000
1	SuperLivePro	BUSINESS	4.3	46353	21M	1,000,000+	Free	0	Everyone	Business	1.5 and up	22020096.0	1000000
2	Wifi Connect Library	LIBRARIES_AND_DEMO	3.9	58055	41k	5,000,000+	Free	0	Everyone	Libraries & Demo	1.5 and up	41984.0	5000000
3	Apk Installer	LIBRARIES_AND_DEMO	3.8	7750	292k	1,000,000+	Free	0	Everyone	Libraries & Demo	1.6 and up	299008.0	1000000
4	English speaking texts	EDUCATION	4.4	1619	3.0M	1,000,000+	Free	0	Everyone	Education	1.6 and up	3145728.0	1000000
5	Eternal life	LIBRARIES_AND_DEMO	5.0	26	2.5M	1,000+	Free	0	Everyone	Libraries & Demo	1.6 and up	2621440.0	1000
6	Dresses Ideas & Fashions +3000	BEAUTY	4.5	473	8.2M	100,000+	Free	0	Mature 17+	Beauty	1.6 and up	8598323.2	100000
7	GO Notifier	COMMUNICATION	4.2	124346	695k	10,000,000+	Free	0	Everyone	Communication	2.0 and up	711680.0	10000000
8	Prosperity	EVENTS	5.0	16	2.3M	100+	Free	0	Everyone	Events	2.0 and up	2411724.8	100
9	NSE Mobile Trading	FINANCE	4.1	13868	1.4M	1,000,000+	Free	0	Everyone	Finance	2.1 and up	1468006.4	1000000

Part D

In [88]:

df.to_csv('data/googleplaystore_new_new.csv', index=False)

Part E

In [ ]: