bobbert/UNI-PROG3-CW2-MLWP
1
0 Fork 0
mirror of https://github.com/mudabbir-ahmad/UNI-PROG3-CW2-MLWP.git synced 2026-10-08 04:10:20 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
1db5d76e7bf14f8c3156298e192bd8c58d5d7db9
UNI-PROG3-CW2-MLWP/Q1.ipynb
T
bobbert 1db5d76e7b Starting Part E
2026-04-25 14:36:11 +01:00

1102 lines
35 KiB
Plaintext
Raw Blame History

{
"cells": [
{
"metadata": {},
"cell_type": "markdown",
"source": "",
"id": "8a77807f92f26ee"
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2026-04-25T10:00:23.434531Z",
"start_time": "2026-04-25T10:00:23.381273Z"
}
},
"cell_type": "markdown",
"source": [
"## This is the Q1 Notebook!\n",
"\n",
"It's tracked via GitHub! hence the need for this line for the init commit"
],
"id": "193cc36275a60171"
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2026-04-25T13:28:40.486005100Z",
"start_time": "2026-04-25T13:28:40.480384400Z"
}
},
"cell_type": "code",
"source": [
"import pandas as pd\n",
"import numpy as np"
],
"id": "edaea0c939a83b79",
"outputs": [],
"execution_count": 70
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2026-04-25T13:28:40.502729500Z",
"start_time": "2026-04-25T13:28:40.488006Z"
}
},
"cell_type": "code",
"source": "df = pd.read_csv('data/googleplaystore_new.csv')",
"id": "e657e9baacc13e6b",
"outputs": [],
"execution_count": 71
},
{
"metadata": {},
"cell_type": "markdown",
"source": "## Part A\n",
"id": "751a6161e8e12bdd"
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2026-04-25T13:28:40.516572500Z",
"start_time": "2026-04-25T13:28:40.503729900Z"
}
},
"cell_type": "code",
"source": [
"df = df.dropna()\n",
"df = df.drop_duplicates()"
],
"id": "756c92821453bbb3",
"outputs": [],
"execution_count": 72
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2026-04-25T13:28:40.537749600Z",
"start_time": "2026-04-25T13:28:40.517577900Z"
}
},
"cell_type": "code",
"source": "df.head(10)",
"id": "4e1be303d63f47a4",
"outputs": [
{
"data": {
"text/plain": [
" App Category Rating Reviews Size \\\n",
"0 Market Update Helper LIBRARIES_AND_DEMO 4.1 20145 11k \n",
"1 SuperLivePro BUSINESS 4.3 46353 21M \n",
"2 Wifi Connect Library LIBRARIES_AND_DEMO 3.9 58055 41k \n",
"3 Apk Installer LIBRARIES_AND_DEMO 3.8 7750 292k \n",
"4 English speaking texts EDUCATION 4.4 1619 3.0M \n",
"5 Eternal life LIBRARIES_AND_DEMO 5.0 26 2.5M \n",
"6 Dresses Ideas & Fashions +3000 BEAUTY 4.5 473 8.2M \n",
"7 GO Notifier COMMUNICATION 4.2 124346 695k \n",
"8 Prosperity EVENTS 5.0 16 2.3M \n",
"9 NSE Mobile Trading FINANCE 4.1 13868 1.4M \n",
"\n",
" Installs Type Price Content Rating Genres Android Ver \n",
"0 1,000,000+ Free 0 Everyone Libraries & Demo 1.5 and up \n",
"1 1,000,000+ Free 0 Everyone Business 1.5 and up \n",
"2 5,000,000+ Free 0 Everyone Libraries & Demo 1.5 and up \n",
"3 1,000,000+ Free 0 Everyone Libraries & Demo 1.6 and up \n",
"4 1,000,000+ Free 0 Everyone Education 1.6 and up \n",
"5 1,000+ Free 0 Everyone Libraries & Demo 1.6 and up \n",
"6 100,000+ Free 0 Mature 17+ Beauty 1.6 and up \n",
"7 10,000,000+ Free 0 Everyone Communication 2.0 and up \n",
"8 100+ Free 0 Everyone Events 2.0 and up \n",
"9 1,000,000+ Free 0 Everyone Finance 2.1 and up "
],
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>App</th>\n",
" <th>Category</th>\n",
" <th>Rating</th>\n",
" <th>Reviews</th>\n",
" <th>Size</th>\n",
" <th>Installs</th>\n",
" <th>Type</th>\n",
" <th>Price</th>\n",
" <th>Content Rating</th>\n",
" <th>Genres</th>\n",
" <th>Android Ver</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Market Update Helper</td>\n",
" <td>LIBRARIES_AND_DEMO</td>\n",
" <td>4.1</td>\n",
" <td>20145</td>\n",
" <td>11k</td>\n",
" <td>1,000,000+</td>\n",
" <td>Free</td>\n",
" <td>0</td>\n",
" <td>Everyone</td>\n",
" <td>Libraries &amp; Demo</td>\n",
" <td>1.5 and up</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>SuperLivePro</td>\n",
" <td>BUSINESS</td>\n",
" <td>4.3</td>\n",
" <td>46353</td>\n",
" <td>21M</td>\n",
" <td>1,000,000+</td>\n",
" <td>Free</td>\n",
" <td>0</td>\n",
" <td>Everyone</td>\n",
" <td>Business</td>\n",
" <td>1.5 and up</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>Wifi Connect Library</td>\n",
" <td>LIBRARIES_AND_DEMO</td>\n",
" <td>3.9</td>\n",
" <td>58055</td>\n",
" <td>41k</td>\n",
" <td>5,000,000+</td>\n",
" <td>Free</td>\n",
" <td>0</td>\n",
" <td>Everyone</td>\n",
" <td>Libraries &amp; Demo</td>\n",
" <td>1.5 and up</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>Apk Installer</td>\n",
" <td>LIBRARIES_AND_DEMO</td>\n",
" <td>3.8</td>\n",
" <td>7750</td>\n",
" <td>292k</td>\n",
" <td>1,000,000+</td>\n",
" <td>Free</td>\n",
" <td>0</td>\n",
" <td>Everyone</td>\n",
" <td>Libraries &amp; Demo</td>\n",
" <td>1.6 and up</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>English speaking texts</td>\n",
" <td>EDUCATION</td>\n",
" <td>4.4</td>\n",
" <td>1619</td>\n",
" <td>3.0M</td>\n",
" <td>1,000,000+</td>\n",
" <td>Free</td>\n",
" <td>0</td>\n",
" <td>Everyone</td>\n",
" <td>Education</td>\n",
" <td>1.6 and up</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>Eternal life</td>\n",
" <td>LIBRARIES_AND_DEMO</td>\n",
" <td>5.0</td>\n",
" <td>26</td>\n",
" <td>2.5M</td>\n",
" <td>1,000+</td>\n",
" <td>Free</td>\n",
" <td>0</td>\n",
" <td>Everyone</td>\n",
" <td>Libraries &amp; Demo</td>\n",
" <td>1.6 and up</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>Dresses Ideas &amp; Fashions +3000</td>\n",
" <td>BEAUTY</td>\n",
" <td>4.5</td>\n",
" <td>473</td>\n",
" <td>8.2M</td>\n",
" <td>100,000+</td>\n",
" <td>Free</td>\n",
" <td>0</td>\n",
" <td>Mature 17+</td>\n",
" <td>Beauty</td>\n",
" <td>1.6 and up</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>GO Notifier</td>\n",
" <td>COMMUNICATION</td>\n",
" <td>4.2</td>\n",
" <td>124346</td>\n",
" <td>695k</td>\n",
" <td>10,000,000+</td>\n",
" <td>Free</td>\n",
" <td>0</td>\n",
" <td>Everyone</td>\n",
" <td>Communication</td>\n",
" <td>2.0 and up</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>Prosperity</td>\n",
" <td>EVENTS</td>\n",
" <td>5.0</td>\n",
" <td>16</td>\n",
" <td>2.3M</td>\n",
" <td>100+</td>\n",
" <td>Free</td>\n",
" <td>0</td>\n",
" <td>Everyone</td>\n",
" <td>Events</td>\n",
" <td>2.0 and up</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>NSE Mobile Trading</td>\n",
" <td>FINANCE</td>\n",
" <td>4.1</td>\n",
" <td>13868</td>\n",
" <td>1.4M</td>\n",
" <td>1,000,000+</td>\n",
" <td>Free</td>\n",
" <td>0</td>\n",
" <td>Everyone</td>\n",
" <td>Finance</td>\n",
" <td>2.1 and up</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
]
},
"execution_count": 73,
"metadata": {},
"output_type": "execute_result"
}
],
"execution_count": 73
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2026-04-25T13:14:34.819448Z",
"start_time": "2026-04-25T13:14:34.807334900Z"
}
},
"cell_type": "markdown",
"source": "## Part B",
"id": "5e0e0e76635904b6"
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2026-04-25T13:28:40.562150300Z",
"start_time": "2026-04-25T13:28:40.543751400Z"
}
},
"cell_type": "code",
"source": [
"# 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*\n",
"def parse_size(size_str):\n",
" if isinstance(size_str, str):\n",
" if size_str.endswith('M'):\n",
" return float(size_str[:-1]) * 1024 * 1024\n",
" elif size_str.endswith('k'):\n",
" return float(size_str[:-1]) * 1024\n",
" return size_str"
],
"id": "c15cb7f9831e0f81",
"outputs": [],
"execution_count": 74
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2026-04-25T13:28:40.568463900Z",
"start_time": "2026-04-25T13:28:40.563149700Z"
}
},
"cell_type": "code",
"source": "df['Size in bytes'] = df['Size'].apply(parse_size)",
"id": "c76da70de24ddc72",
"outputs": [],
"execution_count": 75
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2026-04-25T13:28:50.368129Z",
"start_time": "2026-04-25T13:28:50.352002600Z"
}
},
"cell_type": "code",
"source": "df[['Size', 'Size in bytes']].head(10)",
"id": "73784ad66975e81f",
"outputs": [
{
"data": {
"text/plain": [
" Size Size in bytes\n",
"0 11k 11264.0\n",
"1 21M 22020096.0\n",
"2 41k 41984.0\n",
"3 292k 299008.0\n",
"4 3.0M 3145728.0\n",
"5 2.5M 2621440.0\n",
"6 8.2M 8598323.2\n",
"7 695k 711680.0\n",
"8 2.3M 2411724.8\n",
"9 1.4M 1468006.4"
],
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Size</th>\n",
" <th>Size in bytes</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>11k</td>\n",
" <td>11264.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>21M</td>\n",
" <td>22020096.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>41k</td>\n",
" <td>41984.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>292k</td>\n",
" <td>299008.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>3.0M</td>\n",
" <td>3145728.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>2.5M</td>\n",
" <td>2621440.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>8.2M</td>\n",
" <td>8598323.2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>695k</td>\n",
" <td>711680.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>2.3M</td>\n",
" <td>2411724.8</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>1.4M</td>\n",
" <td>1468006.4</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
]
},
"execution_count": 81,
"metadata": {},
"output_type": "execute_result"
}
],
"execution_count": 81
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2026-04-25T13:28:40.608697900Z",
"start_time": "2026-04-25T13:28:40.593237200Z"
}
},
"cell_type": "code",
"source": "print(11*1024) # Just checking the kb and mb conversion happened properly, by checking 2 of the values manually.",
"id": "7ac34d8bc88327a1",
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"11264\n"
]
}
],
"execution_count": 77
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2026-04-25T13:28:40.639521100Z",
"start_time": "2026-04-25T13:28:40.619210900Z"
}
},
"cell_type": "code",
"source": "print((21*1024)*1024) # Ideally this is the same as doing the calculation without the ( ) but just incase!",
"id": "f72b05042c5a16fa",
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"22020096\n"
]
}
],
"execution_count": 78
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2026-04-25T13:28:40.656738800Z",
"start_time": "2026-04-25T13:28:40.641523100Z"
}
},
"cell_type": "code",
"source": "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.",
"id": "dcaf54123ea0d75d",
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"1468006.4\n"
]
}
],
"execution_count": 79
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2026-04-25T13:28:40.678521Z",
"start_time": "2026-04-25T13:28:40.656738800Z"
}
},
"cell_type": "code",
"source": "df.head(10)",
"id": "3e1112ae100d010c",
"outputs": [
{
"data": {
"text/plain": [
" App Category Rating Reviews Size \\\n",
"0 Market Update Helper LIBRARIES_AND_DEMO 4.1 20145 11k \n",
"1 SuperLivePro BUSINESS 4.3 46353 21M \n",
"2 Wifi Connect Library LIBRARIES_AND_DEMO 3.9 58055 41k \n",
"3 Apk Installer LIBRARIES_AND_DEMO 3.8 7750 292k \n",
"4 English speaking texts EDUCATION 4.4 1619 3.0M \n",
"5 Eternal life LIBRARIES_AND_DEMO 5.0 26 2.5M \n",
"6 Dresses Ideas & Fashions +3000 BEAUTY 4.5 473 8.2M \n",
"7 GO Notifier COMMUNICATION 4.2 124346 695k \n",
"8 Prosperity EVENTS 5.0 16 2.3M \n",
"9 NSE Mobile Trading FINANCE 4.1 13868 1.4M \n",
"\n",
" Installs Type Price Content Rating Genres Android Ver \\\n",
"0 1,000,000+ Free 0 Everyone Libraries & Demo 1.5 and up \n",
"1 1,000,000+ Free 0 Everyone Business 1.5 and up \n",
"2 5,000,000+ Free 0 Everyone Libraries & Demo 1.5 and up \n",
"3 1,000,000+ Free 0 Everyone Libraries & Demo 1.6 and up \n",
"4 1,000,000+ Free 0 Everyone Education 1.6 and up \n",
"5 1,000+ Free 0 Everyone Libraries & Demo 1.6 and up \n",
"6 100,000+ Free 0 Mature 17+ Beauty 1.6 and up \n",
"7 10,000,000+ Free 0 Everyone Communication 2.0 and up \n",
"8 100+ Free 0 Everyone Events 2.0 and up \n",
"9 1,000,000+ Free 0 Everyone Finance 2.1 and up \n",
"\n",
" Size in bytes \n",
"0 11264.0 \n",
"1 22020096.0 \n",
"2 41984.0 \n",
"3 299008.0 \n",
"4 3145728.0 \n",
"5 2621440.0 \n",
"6 8598323.2 \n",
"7 711680.0 \n",
"8 2411724.8 \n",
"9 1468006.4 "
],
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>App</th>\n",
" <th>Category</th>\n",
" <th>Rating</th>\n",
" <th>Reviews</th>\n",
" <th>Size</th>\n",
" <th>Installs</th>\n",
" <th>Type</th>\n",
" <th>Price</th>\n",
" <th>Content Rating</th>\n",
" <th>Genres</th>\n",
" <th>Android Ver</th>\n",
" <th>Size in bytes</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Market Update Helper</td>\n",
" <td>LIBRARIES_AND_DEMO</td>\n",
" <td>4.1</td>\n",
" <td>20145</td>\n",
" <td>11k</td>\n",
" <td>1,000,000+</td>\n",
" <td>Free</td>\n",
" <td>0</td>\n",
" <td>Everyone</td>\n",
" <td>Libraries &amp; Demo</td>\n",
" <td>1.5 and up</td>\n",
" <td>11264.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>SuperLivePro</td>\n",
" <td>BUSINESS</td>\n",
" <td>4.3</td>\n",
" <td>46353</td>\n",
" <td>21M</td>\n",
" <td>1,000,000+</td>\n",
" <td>Free</td>\n",
" <td>0</td>\n",
" <td>Everyone</td>\n",
" <td>Business</td>\n",
" <td>1.5 and up</td>\n",
" <td>22020096.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>Wifi Connect Library</td>\n",
" <td>LIBRARIES_AND_DEMO</td>\n",
" <td>3.9</td>\n",
" <td>58055</td>\n",
" <td>41k</td>\n",
" <td>5,000,000+</td>\n",
" <td>Free</td>\n",
" <td>0</td>\n",
" <td>Everyone</td>\n",
" <td>Libraries &amp; Demo</td>\n",
" <td>1.5 and up</td>\n",
" <td>41984.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>Apk Installer</td>\n",
" <td>LIBRARIES_AND_DEMO</td>\n",
" <td>3.8</td>\n",
" <td>7750</td>\n",
" <td>292k</td>\n",
" <td>1,000,000+</td>\n",
" <td>Free</td>\n",
" <td>0</td>\n",
" <td>Everyone</td>\n",
" <td>Libraries &amp; Demo</td>\n",
" <td>1.6 and up</td>\n",
" <td>299008.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>English speaking texts</td>\n",
" <td>EDUCATION</td>\n",
" <td>4.4</td>\n",
" <td>1619</td>\n",
" <td>3.0M</td>\n",
" <td>1,000,000+</td>\n",
" <td>Free</td>\n",
" <td>0</td>\n",
" <td>Everyone</td>\n",
" <td>Education</td>\n",
" <td>1.6 and up</td>\n",
" <td>3145728.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>Eternal life</td>\n",
" <td>LIBRARIES_AND_DEMO</td>\n",
" <td>5.0</td>\n",
" <td>26</td>\n",
" <td>2.5M</td>\n",
" <td>1,000+</td>\n",
" <td>Free</td>\n",
" <td>0</td>\n",
" <td>Everyone</td>\n",
" <td>Libraries &amp; Demo</td>\n",
" <td>1.6 and up</td>\n",
" <td>2621440.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>Dresses Ideas &amp; Fashions +3000</td>\n",
" <td>BEAUTY</td>\n",
" <td>4.5</td>\n",
" <td>473</td>\n",
" <td>8.2M</td>\n",
" <td>100,000+</td>\n",
" <td>Free</td>\n",
" <td>0</td>\n",
" <td>Mature 17+</td>\n",
" <td>Beauty</td>\n",
" <td>1.6 and up</td>\n",
" <td>8598323.2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>GO Notifier</td>\n",
" <td>COMMUNICATION</td>\n",
" <td>4.2</td>\n",
" <td>124346</td>\n",
" <td>695k</td>\n",
" <td>10,000,000+</td>\n",
" <td>Free</td>\n",
" <td>0</td>\n",
" <td>Everyone</td>\n",
" <td>Communication</td>\n",
" <td>2.0 and up</td>\n",
" <td>711680.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>Prosperity</td>\n",
" <td>EVENTS</td>\n",
" <td>5.0</td>\n",
" <td>16</td>\n",
" <td>2.3M</td>\n",
" <td>100+</td>\n",
" <td>Free</td>\n",
" <td>0</td>\n",
" <td>Everyone</td>\n",
" <td>Events</td>\n",
" <td>2.0 and up</td>\n",
" <td>2411724.8</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>NSE Mobile Trading</td>\n",
" <td>FINANCE</td>\n",
" <td>4.1</td>\n",
" <td>13868</td>\n",
" <td>1.4M</td>\n",
" <td>1,000,000+</td>\n",
" <td>Free</td>\n",
" <td>0</td>\n",
" <td>Everyone</td>\n",
" <td>Finance</td>\n",
" <td>2.1 and up</td>\n",
" <td>1468006.4</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
]
},
"execution_count": 80,
"metadata": {},
"output_type": "execute_result"
}
],
"execution_count": 80
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2026-04-25T13:28:40.682532800Z",
"start_time": "2026-04-25T13:28:40.678521Z"
}
},
"cell_type": "markdown",
"source": "# Part C",
"id": "9883e69704d0a69e"
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2026-04-25T13:29:54.733479400Z",
"start_time": "2026-04-25T13:29:54.718136700Z"
}
},
"cell_type": "code",
"source": "df['Numeric_installs'] = df['Installs'].str.replace('+', '').str.replace(',', '').astype(int)",
"id": "c8d4f46526918c20",
"outputs": [],
"execution_count": 82
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2026-04-25T13:30:07.364394100Z",
"start_time": "2026-04-25T13:30:07.347101500Z"
}
},
"cell_type": "code",
"source": "df.head(10)",
"id": "cffd24a82d242352",
"outputs": [
{
"data": {
"text/plain": [
" App Category Rating Reviews Size \\\n",
"0 Market Update Helper LIBRARIES_AND_DEMO 4.1 20145 11k \n",
"1 SuperLivePro BUSINESS 4.3 46353 21M \n",
"2 Wifi Connect Library LIBRARIES_AND_DEMO 3.9 58055 41k \n",
"3 Apk Installer LIBRARIES_AND_DEMO 3.8 7750 292k \n",
"4 English speaking texts EDUCATION 4.4 1619 3.0M \n",
"5 Eternal life LIBRARIES_AND_DEMO 5.0 26 2.5M \n",
"6 Dresses Ideas & Fashions +3000 BEAUTY 4.5 473 8.2M \n",
"7 GO Notifier COMMUNICATION 4.2 124346 695k \n",
"8 Prosperity EVENTS 5.0 16 2.3M \n",
"9 NSE Mobile Trading FINANCE 4.1 13868 1.4M \n",
"\n",
" Installs Type Price Content Rating Genres Android Ver \\\n",
"0 1,000,000+ Free 0 Everyone Libraries & Demo 1.5 and up \n",
"1 1,000,000+ Free 0 Everyone Business 1.5 and up \n",
"2 5,000,000+ Free 0 Everyone Libraries & Demo 1.5 and up \n",
"3 1,000,000+ Free 0 Everyone Libraries & Demo 1.6 and up \n",
"4 1,000,000+ Free 0 Everyone Education 1.6 and up \n",
"5 1,000+ Free 0 Everyone Libraries & Demo 1.6 and up \n",
"6 100,000+ Free 0 Mature 17+ Beauty 1.6 and up \n",
"7 10,000,000+ Free 0 Everyone Communication 2.0 and up \n",
"8 100+ Free 0 Everyone Events 2.0 and up \n",
"9 1,000,000+ Free 0 Everyone Finance 2.1 and up \n",
"\n",
" Size in bytes Numeric_installs \n",
"0 11264.0 1000000 \n",
"1 22020096.0 1000000 \n",
"2 41984.0 5000000 \n",
"3 299008.0 1000000 \n",
"4 3145728.0 1000000 \n",
"5 2621440.0 1000 \n",
"6 8598323.2 100000 \n",
"7 711680.0 10000000 \n",
"8 2411724.8 100 \n",
"9 1468006.4 1000000 "
],
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>App</th>\n",
" <th>Category</th>\n",
" <th>Rating</th>\n",
" <th>Reviews</th>\n",
" <th>Size</th>\n",
" <th>Installs</th>\n",
" <th>Type</th>\n",
" <th>Price</th>\n",
" <th>Content Rating</th>\n",
" <th>Genres</th>\n",
" <th>Android Ver</th>\n",
" <th>Size in bytes</th>\n",
" <th>Numeric_installs</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Market Update Helper</td>\n",
" <td>LIBRARIES_AND_DEMO</td>\n",
" <td>4.1</td>\n",
" <td>20145</td>\n",
" <td>11k</td>\n",
" <td>1,000,000+</td>\n",
" <td>Free</td>\n",
" <td>0</td>\n",
" <td>Everyone</td>\n",
" <td>Libraries &amp; Demo</td>\n",
" <td>1.5 and up</td>\n",
" <td>11264.0</td>\n",
" <td>1000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>SuperLivePro</td>\n",
" <td>BUSINESS</td>\n",
" <td>4.3</td>\n",
" <td>46353</td>\n",
" <td>21M</td>\n",
" <td>1,000,000+</td>\n",
" <td>Free</td>\n",
" <td>0</td>\n",
" <td>Everyone</td>\n",
" <td>Business</td>\n",
" <td>1.5 and up</td>\n",
" <td>22020096.0</td>\n",
" <td>1000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>Wifi Connect Library</td>\n",
" <td>LIBRARIES_AND_DEMO</td>\n",
" <td>3.9</td>\n",
" <td>58055</td>\n",
" <td>41k</td>\n",
" <td>5,000,000+</td>\n",
" <td>Free</td>\n",
" <td>0</td>\n",
" <td>Everyone</td>\n",
" <td>Libraries &amp; Demo</td>\n",
" <td>1.5 and up</td>\n",
" <td>41984.0</td>\n",
" <td>5000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>Apk Installer</td>\n",
" <td>LIBRARIES_AND_DEMO</td>\n",
" <td>3.8</td>\n",
" <td>7750</td>\n",
" <td>292k</td>\n",
" <td>1,000,000+</td>\n",
" <td>Free</td>\n",
" <td>0</td>\n",
" <td>Everyone</td>\n",
" <td>Libraries &amp; Demo</td>\n",
" <td>1.6 and up</td>\n",
" <td>299008.0</td>\n",
" <td>1000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>English speaking texts</td>\n",
" <td>EDUCATION</td>\n",
" <td>4.4</td>\n",
" <td>1619</td>\n",
" <td>3.0M</td>\n",
" <td>1,000,000+</td>\n",
" <td>Free</td>\n",
" <td>0</td>\n",
" <td>Everyone</td>\n",
" <td>Education</td>\n",
" <td>1.6 and up</td>\n",
" <td>3145728.0</td>\n",
" <td>1000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>Eternal life</td>\n",
" <td>LIBRARIES_AND_DEMO</td>\n",
" <td>5.0</td>\n",
" <td>26</td>\n",
" <td>2.5M</td>\n",
" <td>1,000+</td>\n",
" <td>Free</td>\n",
" <td>0</td>\n",
" <td>Everyone</td>\n",
" <td>Libraries &amp; Demo</td>\n",
" <td>1.6 and up</td>\n",
" <td>2621440.0</td>\n",
" <td>1000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>Dresses Ideas &amp; Fashions +3000</td>\n",
" <td>BEAUTY</td>\n",
" <td>4.5</td>\n",
" <td>473</td>\n",
" <td>8.2M</td>\n",
" <td>100,000+</td>\n",
" <td>Free</td>\n",
" <td>0</td>\n",
" <td>Mature 17+</td>\n",
" <td>Beauty</td>\n",
" <td>1.6 and up</td>\n",
" <td>8598323.2</td>\n",
" <td>100000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>GO Notifier</td>\n",
" <td>COMMUNICATION</td>\n",
" <td>4.2</td>\n",
" <td>124346</td>\n",
" <td>695k</td>\n",
" <td>10,000,000+</td>\n",
" <td>Free</td>\n",
" <td>0</td>\n",
" <td>Everyone</td>\n",
" <td>Communication</td>\n",
" <td>2.0 and up</td>\n",
" <td>711680.0</td>\n",
" <td>10000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>Prosperity</td>\n",
" <td>EVENTS</td>\n",
" <td>5.0</td>\n",
" <td>16</td>\n",
" <td>2.3M</td>\n",
" <td>100+</td>\n",
" <td>Free</td>\n",
" <td>0</td>\n",
" <td>Everyone</td>\n",
" <td>Events</td>\n",
" <td>2.0 and up</td>\n",
" <td>2411724.8</td>\n",
" <td>100</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>NSE Mobile Trading</td>\n",
" <td>FINANCE</td>\n",
" <td>4.1</td>\n",
" <td>13868</td>\n",
" <td>1.4M</td>\n",
" <td>1,000,000+</td>\n",
" <td>Free</td>\n",
" <td>0</td>\n",
" <td>Everyone</td>\n",
" <td>Finance</td>\n",
" <td>2.1 and up</td>\n",
" <td>1468006.4</td>\n",
" <td>1000000</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
]
},
"execution_count": 83,
"metadata": {},
"output_type": "execute_result"
}
],
"execution_count": 83
},
{
"metadata": {},
"cell_type": "markdown",
"source": "## Part D",
"id": "1818d3183dae5398"
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2026-04-25T13:35:48.441535100Z",
"start_time": "2026-04-25T13:35:48.421909700Z"
}
},
"cell_type": "code",
"source": "df.to_csv('data/googleplaystore_new_new.csv', index=False)",
"id": "5a99edb9f8b29b12",
"outputs": [],
"execution_count": 88
},
{
"metadata": {},
"cell_type": "markdown",
"source": "# Part E",
"id": "5372c799c0b2662"
},
{
"metadata": {},
"cell_type": "code",
"outputs": [],
"execution_count": null,
"source": "",
"id": "8cc741d5b19eaa62"
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 2
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython2",
"version": "2.7.6"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
Reference in new issue View Git Blame Copy Permalink