PROJECT NO - 01 : WORLD POPULATION ANALYSIS

In [50]: #Install and Import Necessary Libraries:

pip install plotly

Defaulting to user installation because normal site-packages is not writeable

Requirement already satisfied: plotly in c:\users\user\appdata\local\packages\pythonsoftwarefoundation.python.3.12_qb
z5n2kfra8p0\localcache\local-packages\python312\site-packages (5.23.0)
Requirement already satisfied: tenacity>=6.2.0 in c:\users\user\appdata\local\packages\pythonsoftwarefoundation.pytho
n.3.12_qbz5n2kfra8p0\localcache\local-packages\python312\site-packages (from plotly) (9.0.0)
Requirement already satisfied: packaging in c:\users\user\appdata\local\packages\pythonsoftwarefoundation.python.3.12
_qbz5n2kfra8p0\localcache\local-packages\python312\site-packages (from plotly) (23.2)
Note: you may need to restart the kernel to use updated packages.

In [1]: import pandas as pd

import numpy as np
from matplotlib import pyplot as plt
import seaborn as sns

In [2]: import plotly.express as px

import plotly.subplots as sp
import plotly.graph_objects as go

In [3]: #Data Collection

df=pd.read_csv(r'C:\Users\user\Desktop/world_population.csv')

In [4]: df.head()
Out[4]:
2022 2020 2015 2010 2000 1990
Rank Country/Territory Continent
Population Population Population Population Population Population

0 1 China Asia 1.425887e+09 1.424930e+09 1.393715e+09 1.348191e+09 1.264099e+09 1.153704e+09 9

1 2 India Asia 1.417173e+09 1.396387e+09 1.322867e+09 1.240614e+09 1.059634e+09 8.704522e+08 6

North
2 3 United States 3.382899e+08 3.359420e+08 3.246078e+08 3.111828e+08 2.823986e+08 2.480837e+08 2
America

3 4 Indonesia Asia 2.755013e+08 2.718580e+08 2.590920e+08 2.440162e+08 2.140724e+08 1.821599e+08 1

4 5 Pakistan Asia 2.358249e+08 2.271967e+08 2.109693e+08 1.944545e+08 1.543699e+08 1.154141e+08

In [18]: #Data Preprocessing

df.isnull().sum()
 <class 'pandas.core.frame.DataFrame'>
RangeIndex: 234 entries, 0 to 233
Data columns (total 15 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 Rank 234 non-null int64
1 Country/Territory 234 non-null object
2 Continent 234 non-null object
3 2022 Population 234 non-null int64
4 2020 Population 234 non-null int64
5 2015 Population 234 non-null int64
6 2010 Population 234 non-null int64
7 2000 Population 234 non-null int64
8 1990 Population 234 non-null int64
9 1980 Population 234 non-null int64
10 1970 Population 234 non-null int64
11 Area (km?) 234 non-null int64
12 Density (per km?) 234 non-null float64
13 Growth Rate 234 non-null float64
14 World Population Percentage 234 non-null float64
dtypes: float64(3), int64(10), object(2)
memory usage: 27.6+ KB

In [51]: df.info()
 <class 'pandas.core.frame.DataFrame'>
RangeIndex: 234 entries, 0 to 233
Data columns (total 15 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 Rank 234 non-null int64
1 Country/Territory 234 non-null object
2 Continent 234 non-null object
3 2022 Population 234 non-null float64
4 2020 Population 234 non-null float64
5 2015 Population 234 non-null float64
6 2010 Population 234 non-null float64
7 2000 Population 234 non-null float64
8 1990 Population 234 non-null float64
9 1980 Population 234 non-null float64
10 1970 Population 234 non-null float64
11 Area (km?) 234 non-null int64
12 Density (per km?) 234 non-null float64
13 Growth Rate 234 non-null float64
14 World Population Percentage 234 non-null float64
dtypes: float64(11), int64(2), object(2)
memory usage: 27.6+ KB

In [52]: #Exploratory Data Analysis (EDA)

#check coorelation of dataset
df.corr(numeric_only=True)
Out[52]:
2022 2020 2015 2010 2000 1990 1980 1970 Ar
Rank
Population Population Population Population Population Population Population Population (km

Rank 1.000000 -0.358361 -0.355854 -0.351222 -0.347461 -0.341057 -0.336152 -0.335246 -0.335379 -0.3837

2022
-0.358361 1.000000 0.999946 0.999490 0.998629 0.994605 0.987228 0.980285 0.973162 0.4534
Population

2020
-0.355854 0.999946 1.000000 0.999763 0.999105 0.995583 0.988724 0.982121 0.975254 0.4549
Population

2015
-0.351222 0.999490 0.999763 1.000000 0.999783 0.997340 0.991594 0.985724 0.979414 0.4582
Population

2010
-0.347461 0.998629 0.999105 0.999783 1.000000 0.998593 0.993929 0.988786 0.983042 0.4619
Population

2000
-0.341057 0.994605 0.995583 0.997340 0.998593 1.000000 0.998336 0.995160 0.990956 0.4739
Population

1990
-0.336152 0.987228 0.988724 0.991594 0.993929 0.998336 1.000000 0.999042 0.996602 0.4867
Population

1980
-0.335246 0.980285 0.982121 0.985724 0.988786 0.995160 0.999042 1.000000 0.999194 0.4981
Population

1970
-0.335379 0.973162 0.975254 0.979414 0.983042 0.990956 0.996602 0.999194 1.000000 0.5099
Population

Area (km?) -0.383774 0.453411 0.454993 0.458240 0.461936 0.473933 0.486764 0.498166 0.509940 1.0000

Density
0.129436 -0.027618 -0.027358 -0.026857 -0.026505 -0.026139 -0.026224 -0.026587 -0.026881 -0.0631
(per km?)
 2022 2020 2015 2010 2000 1990 1980 1970 Ar
Rank
Population Population Population Population Population Population Population Population (km

Growth
-0.224561 -0.020863 -0.025116 -0.032154 -0.037983 -0.050515 -0.062397 -0.072349 -0.081313 -0.0139
Rate

World
Population -0.358464 0.999999 0.999944 0.999487 0.998626 0.994598 0.987218 0.980273 0.973150 0.4532
Percentage

In [53]: #plot a Heatmap Of coorelation matrix

sns.heatmap(df.corr(numeric_only=True))

Out[53]: <Axes: >

In [7]: #Based on coorelations lets plot graphs
#change the data types of columns as per requirement
df[' 2022 Population ']=df[' 2022 Population '].astype(int)
df[' 2015 Population ']=df[' 2015 Population '].astype(int)
df[' 2010 Population ']=df[' 2010 Population '].astype(int)
df[' 2000 Population ']=df[' 2000 Population '].astype(int)
df[' 1990 Population ']=df[' 1990 Population '].astype(int)
df[' 1980 Population ']=df[' 1980 Population '].astype(int)
df[' 1970 Population ']=df[' 1970 Population '].astype(int)
df[' 2020 Population ']=df[' 2020 Population '].astype(int)

In [5]: #plot graph for countries over continents

continent_wise=df.groupby(by='Continent')['Country/Territory'].count()

In [9]: continent_wise

Out[9]: Continent
Africa 57
Asia 50
Europe 50
North America 40
Oceania 23
South America 14
Name: Country/Territory, dtype: int64

In [16]: continents=continent_wise.index
counts=continent_wise.values
sns.set_style('whitegrid')
plt.pie(counts,labels=continents,shadow=True,startangle=90,colors=sns.color_palette('viridis'),autopct=lambda p:f'{in
 plt.title('Continents wise Countries',fontsize=20)

plt.grid(True)
plt.show()

In [8]: #plot graph for population percentage over the continents

 continent_wise_pop=df.groupby(['Continent'])[' 2022 Population '].sum()

In [9]: continent_wise_pop

Out[9]: Continent
Africa 1.426731e+09
Asia 4.721383e+09
Europe 7.431475e+08
North America 6.002961e+08
Oceania 4.503855e+07
South America 4.368166e+08
Name: 2022 Population , dtype: float64

In [10]: continents=continent_wise_pop.index
population=continent_wise_pop.values
sns.set_style('whitegrid')
explode=[0,0,0,0,1,0]
plt.pie(population,labels=continents,explode=explode,autopct='%1.1f%%',shadow=True)
plt.title('continent wise population percentage',fontsize=20)
#plt.lengend()
plt.show()
In [17]: #lets plot world population over the years
Total_Population=df[[' 2022 Population ',' 2020 Population ',' 2015 Population ',' 2010 Population ',' 2000 Populatio
Total_Population
Out[17]: 2022 Population 7.973413e+09
2020 Population 7.839251e+09
2015 Population 7.424810e+09
2010 Population 6.983785e+09
2000 Population 6.147056e+09
1990 Population 5.314192e+09
1980 Population 4.442400e+09
1970 Population 3.694137e+09
dtype: float64

In [18]: plt.figure(figsize=(15,5))
sns.set_style('whitegrid')
x=Total_Population.values
sns.lineplot(Total_Population,marker="o",ms=7,label=x)
plt.grid(ls='dotted')
plt.title('Total Population over years',fontsize=20)
plt.ylabel('In Billions')
plt.legend(title='Population',fancybox=False)
plt.xlabel('Year')
plt.show()
In [19]: years_population_continent_wise=df.groupby(['Continent'])[[' 2022 Population ',' 2020 Population ',' 2015 Population

In [20]: dff=years_population_continent_wise.transpose()
dff
Out[20]: Continent Asia Africa Europe North America South America Oceania

2022 Population 4.721383e+09 1.426731e+09 743147538.0 600296136.0 436816608.0 45038554.0

2020 Population 4.663087e+09 1.360672e+09 745792196.0 594236593.0 431530043.0 43933426.0

2015 Population 4.458250e+09 1.201102e+09 741535608.0 570383850.0 413134396.0 40403283.0

2010 Population 4.220041e+09 1.055228e+09 735613934.0 542720651.0 393078250.0 37102764.0

2000 Population 3.735090e+09 8.189460e+08 726093423.0 486069584.0 349634282.0 31222778.0

1990 Population 3.210564e+09 6.381506e+08 720320797.0 421266425.0 297146415.0 26743822.0

1980 Population 2.635334e+09 4.815364e+08 692527159.0 368293361.0 241789006.0 22920240.0

1970 Population 2.144906e+09 3.654443e+08 655923991.0 315434606.0 192947156.0 19480270.0

In [21]: plt.figure(figsize=(15,6))
sns.lineplot(dff,marker='*',ms=10)
plt.xlabel('Year')
plt.ylabel('In Billions')
plt.grid(ls='dotted')
plt.title('Continental Population over years',fontsize=20)
plt.show()
In [87]: header_values=years_population_continent_wise.columns

In [88]: header_values

Out[88]: Index([' 2022 Population ', ' 2020 Population ', ' 2015 Population ',
' 2010 Population ', ' 2000 Population ', ' 1990 Population ',
' 1980 Population ', ' 1970 Population '],
dtype='object')
In [22]: #Melt the data as per requirement
df_melted=df.melt(id_vars=['Continent'],value_vars=[' 2022 Population ',' 2020 Population ',' 2015 Population ',' 201

In [17]: df_melted

Out[17]: Continent Year Population

0 Asia 2022 Population 1425887337

1 Asia 2022 Population 1417173173

2 North America 2022 Population 338289857

3 Asia 2022 Population 275501339

4 Asia 2022 Population 235824862

... ... ... ...

1867 North America 1970 Population 11402

1868 South America 1970 Population 2274

1869 Oceania 1970 Population 5185

1870 Oceania 1970 Population 1714

1871 Europe 1970 Population 752

1872 rows × 3 columns

In [34]: #population_by_continent=df_melted.groupby(['Continent'])['Year'].sum().reset_index()
In [35]: #population_by_continent

Out[35]: Continent Year

0 Africa 2022 Population 2022 Population 2022 Popula...

1 Asia 2022 Population 2022 Population 2022 Popula...

2 Europe 2022 Population 2022 Population 2022 Popula...

3 North America 2022 Population 2022 Population 2022 Popula...

4 Oceania 2022 Population 2022 Population 2022 Popula...

5 South America 2022 Population 2022 Population 2022 Popula...

In [24]: fig=px.line(df_melted,x='Year',y='Population',color='Continent',title='Population by continent in years')

fig.show()
 Population by continent in years

1.4B

1.2B

1B
Population

0.8B

0.6B

0.4B

0.2B
In [25]: selected_columns=[' 2022 Population ',' 2020 Population ',' 2015 Population ',' 2010 Population ',' 2000 Population
total_population=df[selected_columns].sum()

In [26]: a=total_population.index.str.replace('Population','')
b=total_population.values

In [27]: plt.figure(figsize=(15,5))
plt.bar(a,b,label=b,color=sns.color_palette('inferno'),width=0.5)
plt.legend(title='Population ')
plt.xlabel('YEAR')
plt.ylabel('POPULATION')
plt.title('YEAR WISE WORLD POPULATION',fontsize=20)
#plt.ylim(0,7)
plt.show()
In [28]: Top_10_by_growthrate=df.sort_values(by='Growth Rate',ascending=False).head(10)
Low_Population_growth_countries=df.sort_values(by='Growth Rate',ascending=False).tail(10)

In [29]: Top_10_by_growthrate
Out[29]:
2022 2020 2015 2010 2000 1990 1980
Rank Country/Territory Continent
Population Population Population Population Population Population Population

134 135 Moldova Europe 3272996.0 3084847.0 3277388.0 3678186.0 4251573.0 4480199.0 4103240.0

36 37 Poland Europe 39857145.0 38428366.0 38553146.0 38597353.0 38504431.0 38064255.0 35521429.0

53 54 Niger Africa 26207977.0 24333639.0 20128124.0 16647543.0 11622665.0 8370647.0 6173177.0

59 60 Syria Asia 22125249.0 20772595.0 19205178.0 22337563.0 16307654.0 12408996.0 8898954.0

115 116 Slovakia Europe 5643453.0 5456681.0 5424444.0 5396424.0 5376690.0 5261305.0 4973883.0

14 15 DR Congo Africa 99010212.0 92853164.0 78656904.0 66391257.0 48616317.0 35987541.0 26708686.0

181 182 Mayotte Africa 326101.0 305587.0 249545.0 211786.0 159215.0 92659.0 52233.0

68 69 Chad Africa 17723315.0 16644701.0 14140274.0 11894727.0 8259137.0 5827069.0 4408230.0

41 42 Angola Africa 35588987.0 33428485.0 28127721.0 23364185.0 16394062.0 11828638.0 8330047.0

58 59 Mali Africa 22593590.0 21224040.0 18112907.0 15529181.0 11239101.0 8945026.0 7372581.0

In [30]: x=Top_10_by_growthrate['Country/Territory']
y=Top_10_by_growthrate['Growth Rate']
plt.figure(figsize=(12,5))
plt.bar(x,y,width=0.5,label=y,color=sns.color_palette('plasma'))
plt.legend(loc=1,title='Growth rate')
plt.title('HIGHESH GROWING COUNTRIES IN THE WORLD',fontsize=20)
plt.ylim(1,1.10)
plt.ylabel('GROWTH RATE')
 plt.xlabel('COUNTRIES')
plt.show()

In [34]: #Low_Population_growth_countries=df.groupby('Country/Territory')['Growth Rate'].sum().sort_values().head(10)

Low_Population_growth_countries
Out[34]:
2022 2020 2015 2010 2000 1990 1980
Rank Country/Territory Continent
Population Population Population Population Population Population Population

129 130 Croatia Europe 4030358 4096868 4254815 4368682 4548434 4873707 4680144

104 105 Serbia Europe 7221365 7358005 7519496 7653748 7935022 7987529 7777010

214 215 Marshall Islands Oceania 41569 43413 49410 53416 54224 46047 31988

Bosnia and
136 137 Europe 3233526 3318407 3524324 3811088 4179350 4494310 4199820
Herzegovina

150 151 Latvia Europe 1850651 1897052 1991955 2101530 2392530 2689391 2572037

140 141 Lithuania Europe 2750055 2820267 2963765 3139019 3599637 3785847 3521206

107 108 Bulgaria Europe 6781953 6979175 7309253 7592273 8097691 8767778 8980606

212 213 American Samoa Oceania 44273 46189 51368 54849 58230 47818 32886

118 119 Lebanon Asia 5489739 5662923 6398940 4995800 4320642 3593700 2963702

37 38 Ukraine Europe 39701739 43909666 44982564 45683020 48879755 51589817 49973920

In [46]: x=Low_Population_growth_countries['Country/Territory']
y=Low_Population_growth_countries['Growth Rate']
plt.figure(figsize=(16,5))
plt.bar(x,y,label=y,color=sns.color_palette('magma'))
plt.title('SLOWEST GROWING COUNTRIES',fontsize=20)
plt.legend(title='Growth Rate')
plt.xlabel('COUNTRY')
 plt.ylabel('GROWTH RATE')
plt.ylim(0,1.2)
plt.xlim(-0.5,10)
plt.show()

In [30]: df.columns

Out[30]: Index(['Rank', 'Country/Territory', 'Continent', ' 2022 Population ',

' 2020 Population ', ' 2015 Population ', ' 2010 Population ',
' 2000 Population ', ' 1990 Population ', ' 1980 Population ',
' 1970 Population ', 'Area (km?)', 'Density (per km?)', 'Growth Rate',
'World Population Percentage'],
dtype='object')
In [33]: Top_10_Populated_countries_in_1970=df.groupby('Country/Territory')[' 1970 Population '].sum().sort_values(ascending=F

In [34]: Top_10_Populated_countries_in_1970

Out[34]: Country/Territory
China 822534450.0
India 557501301.0
United States 200328340.0
Russia 130093010.0
Indonesia 115228394.0
Japan 105416839.0
Brazil 96369875.0
Germany 78294583.0
Bangladesh 67541860.0
Pakistan 59290872.0
Name: 1970 Population , dtype: float64

In [41]: x=Top_10_Populated_countries_in_1970.index
y=Top_10_Populated_countries_in_1970.values
plt.figure(figsize=(12,5))
plt.bar(x,y,label=y,color=sns.color_palette('magma'))
plt.title('MOST POPULATED COUNTRIES in 1970',fontsize=20)
plt.legend(title='POPULATION')
plt.xlabel('COUNTRY')
plt.ylabel('In Billions')
plt.show()
In [38]: Top_10_Populated_countries_in_2022=df.groupby('Country/Territory')[' 2022 Population '].sum().sort_values(ascending=F

In [47]: x=Top_10_Populated_countries_in_2022.index
y=Top_10_Populated_countries_in_2022.values
plt.figure(figsize=(12,6))
#c=sns.color_palette('cividis')
plt.bar(x,y,label=y,color=sns.color_palette('cividis'))
plt.title('MOST POPULATED COUNTRIES in 2022',fontsize=20)
plt.xlabel('COUNTRY')
plt.ylabel('In Billions')
plt.legend(title='Population')
plt.show()
In [69]: df[df['Country/Territory']=='Vatican City']
Out[69]:
2022 2020 2015 2010 2000 1990 1980
Rank Country/Territory Continent
Population Population Population Population Population Population Population

233 234 Vatican City Europe 510 520 564 596 651 700 733

In [44]: Area=df.groupby('Country/Territory')['Area (km?)'].sum().sort_values(ascending=False).head(10)

Area

Out[44]: Country/Territory
Russia 17098242
Canada 9984670
China 9706961
United States 9372610
Brazil 8515767
Australia 7692024
India 3287590
Argentina 2780400
Kazakhstan 2724900
Algeria 2381741
Name: Area (km?), dtype: int64

In [49]: plt.figure(figsize=(10,6))
#sns.despine(Area)
x=Area.index
y=Area.values
plt.bar(x,y,label=y,color=sns.color_palette('Greens'))
plt.title('LARGEST COUNTRIES IN THE WORLD',fontsize=20)
plt.legend(title='AREA')
plt.xlabel('COUNTRY')
plt.ylabel('Square Kilometers')
#plt.legend(labels=[17098242, 9984670,9706961,9372610,8515767,7692024,3287590,2780400,2724900,2381741])

plt.show()
In [48]: df.columns

Out[48]: Index(['Rank', 'Country/Territory', 'Continent', ' 2022 Population ',

' 2020 Population ', ' 2015 Population ', ' 2010 Population ',
' 2000 Population ', ' 1990 Population ', ' 1980 Population ',
' 1970 Population ', 'Area (km?)', 'Density (per km?)', 'Growth Rate',
'World Population Percentage'],
dtype='object')

In [105… densely_Populated=df.groupby('Country/Territory')['Density (per km?)'].sum().sort_values(ascending=False).head(10)

In [106… densely_Populated

Out[106… Country/Territory
Macau 23172.2667
Monaco 18234.5000
Singapore 8416.4634
Hong Kong 6783.3922
Gibraltar 5441.5000
Bahrain 1924.4876
Maldives 1745.9567
Malta 1687.6139
Sint Maarten 1299.2647
Bermuda 1188.5926
Name: Density (per km?), dtype: float64

In [145… plt.figure(figsize=(10,6))
b=densely_Populated.values
a=densely_Populated.index
plt.bar(a,b,label=b,color=sns.color_palette('husl'))
plt.legend(title='Density (per km?)')
plt.ylabel('DENSITY')
plt.xlabel('COUNTRY')
plt.title('MOST DENSELY POPULATED COUNTRIES')
plt.show()
In [155… b=densely_Populated.values
a=densely_Populated.index
fig=go.Figure(data=[go.Bar(x=a,y=b)])
fig.update_layout(title='bar')
bar

20k

15k

10k

5k
In [147… low_densely_Populated=df.groupby('Country/Territory')['Density (per km?)'].sum().sort_values().head(10)

In [148… low_densely_Populated

Out[148… Country/Territory
Greenland 0.0261
Falkland Islands 0.3105
Western Sahara 2.1654
Mongolia 2.1727
Namibia 3.1092
Australia 3.4032
Iceland 3.6204
French Guiana 3.6459
Guyana 3.7621
Suriname 3.7727
Name: Density (per km?), dtype: float64

In [153… plt.figure(figsize=(14,4))
x=low_densely_Populated.index
y=low_densely_Populated.values
plt.bar(x,y,label=y,color=sns.color_palette('viridis'))
plt.title('LOW DENSELY POPULATED COUNTRIES')
plt.legend(title='Density (per km?)')
plt.xlabel('DENSITY')
plt.ylabel('COUNTRY')
#plt.xlim(-1,10)
plt.show()
In [21]: features=[' 1970 Population ' ,' 2020 Population ']
for feature in features:
fig = px.choropleth(df,
locations='Country/Territory',
locationmode='country names',
color=feature,
hover_name='Country/Territory',
template='plotly_white',
title = feature)
fig.show()
1970 Population
2020 Population
PROJECT NO - 02 : SUPERMART GROCERY SALES - RETAIL ANALYSIS

In [1]: #Install and Import Necessary Libraries:

import pandas as pd
import numpy as np
import seaborn as sns
import plotly.express as px
from matplotlib import pyplot as plt

In [2]: #Data Collection

df=pd.read_csv(r'C:\Users\user\Desktop\Supermart Grocery Sal

In [7]: df.head()

Out[7]: Order Customer Sub Order

Category City R
ID Name Category Date

Oil & 2017-

0 OD1 Harish Masalas Vellore
Masala 11-08

Health 2017-
1 OD2 Sudha Beverages Krishnagiri
Drinks 11-08

Food Atta & 2017-

2 OD3 Hussain Perambalur
Grains Flour 06-12

Fruits & Fresh 2016-

3 OD4 Jackson Dharmapuri
Veggies Vegetables 10-11

Food Organic 2016-

4 OD5 Ridhesh Ooty
Grains Staples 10-11

In [3]: #Data Preprocessing

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 9994 entries, 0 to 9993
Data columns (total 11 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 Order ID 9994 non-null object
1 Customer Name 9994 non-null object
2 Category 9994 non-null object
3 Sub Category 9994 non-null object
4 City 9994 non-null object
5 Order Date 9994 non-null object
6 Region 9994 non-null object
7 Sales 9994 non-null int64
8 Discount 9994 non-null float64
9 Profit 9994 non-null float64
10 State 9994 non-null object
dtypes: float64(2), int64(1), object(8)
memory usage: 859.0+ KB

In [5]: df.isnull().sum()
Out[5]: Order ID 0
Customer Name 0
Category 0
Sub Category 0
City 0
Order Date 0
Region 0
Sales 0
Discount 0
Profit 0
State 0
dtype: int64

In [7]: #Exploratory Data Analysis (EDA)

#check coorelation of dataset
df.corr(numeric_only=True)

Out[7]: order order

Sales Discount Profit
day month

Sales 1.000000 -0.005512 0.605349 0.000179 -0.009518 0

Discount -0.005512 1.000000 0.000017 0.003022 0.002068 -0

Profit 0.605349 0.000017 1.000000 0.010742 0.003184 -0

order
0.000179 0.003022 0.010742 1.000000 -0.033562 -0
day

order
-0.009518 0.002068 0.003184 -0.033562 1.000000 -0
month

order
0.007542 -0.018778 -0.006401 -0.017458 -0.020183 1
year

In [12]: #plot a Heatmap Of coorelation matrix

sns.heatmap(df.corr(numeric_only=True))

Out[12]: <Axes: >

In [12]: #Based on coorelations lets plot graphs
sales_by_category=df.groupby('Category')['Sales'].sum().sort

In [7]: sales_by_category

Out[7]: Category
Eggs, Meat & Fish 2267401
Snacks 2237546
Food Grains 2115272
Bakery 2112281
Fruits & Veggies 2100727
Beverages 2085313
Oil & Masala 2038442
Name: Sales, dtype: int64

In [103… x=sales_by_category.index
y=sales_by_category.values
plt.figure(figsize=(15,6))
plt.bar(x,y,label=y,color=sns.color_palette('plasma'),width=
plt.legend(title='Sales',loc=0)
plt.title('CATEGORY WISE SALES',fontsize=20)
plt.grid(axis='y')
plt.xlabel('CATEGORY',fontsize=14)
plt.ylim(0,3390000)
plt.ylabel("SALES",fontsize=14)
plt.show()
In [7]: city_wise_sales=df.groupby('City')['Sales'].sum().sort_value

In [8]: city_wise_sales

Out[8]: City
Trichy 541403
Nagercoil 551435
Dharmapuri 571553
Dindigul 575631
Theni 579553
Viluppuram 581274
Namakkal 598530
Ooty 599292
Virudhunagar 606820
Madurai 617836
Name: Sales, dtype: int64

In [78]: x=city.index
y=city.values
c=sns.color_palette('inferno')
plt.figure(figsize=(15,6))
plt.barh(x,y,label=y,color=sns.color_palette('inferno'))
plt.title('Top cities with high Sales',fontsize=20)
plt.xlabel('CITY',fontsize=14)
plt.ylabel('SALES',fontsize=14)
plt.grid(axis='x')
plt.xlim(0,900000)
plt.legend(title='Sales',loc=0)
#plt.xticks(rotation=45)
plt.show()
 In [5]: df['Order Date']=pd.to_datetime(df['Order Date'])

C:\Users\user\AppData\Local\Temp\ipykernel_6768\1722919639.p
y:1: UserWarning: Could not infer format, so each element wil
l be parsed individually, falling back to `dateutil`. To ensu
re parsing is consistent and as-expected, please specify a fo
rmat.
df['Order Date']=pd.to_datetime(df['Order Date'])

In [6]: df['order day']=df['Order Date'].dt.day

df['order month']=df['Order Date'].dt.month
df['order year']=df['Order Date'].dt.year

In [137… month_sales=df.groupby('order month')['Sales'].sum()

month_sales

Out[137… order month

1 577972
2 456102
3 1053980
4 998453
5 1086920
6 1057808
7 1089385
8 1046807
9 2064266
10 1243289
11 2193924
12 2088076
Name: Sales, dtype: int64

In [146… x=month_sales.index
y=month_sales.values
explode=[0,0,0,0,0,0,0,0,0,0,0,0]
plt.pie(y,labels=x,explode=explode,shadow=True,autopct='%1.1
plt.title('MONTH WISE SALES')

plt.show()
In [ ]: x=month_sales.index
y=month_sales.values
plt.bar

In [17]: year_sales=df.groupby('order year')['Sales'].sum().sort_valu

year_sales

Out[17]: order year

2018 4977512
2017 3871912
2016 3131959
2015 2975599
Name: Sales, dtype: int64

In [17]: year_sales=df.groupby('order year')['Sales'].sum().sort_valu

year_sales

Out[17]: order year

2018 4977512
2017 3871912
2016 3131959
2015 2975599
Name: Sales, dtype: int64

In [24]: x=year_sales.index
y=year_sales.values

plt.pie(y,labels=x,shadow=True,autopct='%1.1f%%',colors=sns.
plt.title('YEAR WISE SALES')
 plt.show()

In [3]: sales_by_product=df.groupby('Sub Category')['Sales'].sum().s

sales_by_product

Out[3]: Sub Category

Health Drinks 1051439
Soft Drinks 1033874
Cookies 768213
Breads & Buns 742586
Noodles 735435
Chocolates 733898
Masalas 697480
Cakes 685612
Biscuits 684083
Spices 672876
Name: Sales, dtype: int64

In [4]: x=sales_by_product.index
y=sales_by_product.values
plt.figure(figsize=(15,6))
plt.bar(x,y,label=y,color=sns.color_palette('plasma'),width=
plt.legend(title='Sales',loc=0)
plt.title('sales by product',fontsize=20)
plt.grid(axis='y')
plt.xlabel('PRODUCT',fontsize=14)
plt.ylim(0,1750000)
plt.ylabel("SALES",fontsize=14)
plt.show()
In [8]: df.groupby('Customer Name')['Profit'].sum().sort_values(asce

Out[8]: Customer Name

Arutra 87572.40
Vidya 86725.64
Krithika 85633.03
Akash 82121.26
Surya 80996.85
Name: Profit, dtype: float64

In [14]: day_sales=df.groupby('order day')['Sales'].sum().sort_values

day_sales

Out[14]: order day

21 591670
20 586485
2 571073
3 564417
5 555101
26 550222
8 535192
11 533791
23 531681
9 526866
Name: Sales, dtype: int64

In [9]: le=LabelEncoder()

In [45]: #df['Sub Category']=le.fit_transform(df['Sub Category'])

#df['City']=le.fit_transform(df['City'])
#df['Region']=le.fit_transform(df['Region'])
#df['order month']=le.fit_transform(df['order month'])

In [22]: target=df['Sales']

In [27]: y_pred=lr.predict(x_test)

In [24]: x_train,x_test,y_train,y_test=train_test_split(features,targ

In [31]: mse=mean_squared_error(y_test,y_pred)
r2=r2_score(y_test,y_pred)
In [25]: scaler=StandardScaler()
x_train=scaler.fit_transform(x_train)
x_test=scaler.fit_transform(x_test)

In [26]: lr=LinearRegression()
lr.fit(x_train,y_train)

Out[26]: ▾ LinearRegression i ?

LinearRegression()

In [32]: print(mse,r2)

2199.6894915749735 0.9933977767041029

In [21]: features=df.drop(columns=['Order ID','Customer Name','Order

In [37]: plt.figure(figsize=(8, 6))

plt.scatter(y_test, y_pred)
plt.plot([min(y_test), max(y_test)], [min(y_test),
max(y_test)], color='red')
plt.title('Actual vs Predicted Sales')
plt.xlabel('Actual Sales')
plt.ylabel('Predicted Sales')
plt.show()

In [11]: df.corr(numeric_only=True)
Out[11]: order order
Sales Discount Profit
day month

Sales 1.000000 -0.005512 0.605349 0.000179 -0.009518 0

Discount -0.005512 1.000000 0.000017 0.003022 0.002068 -0

Profit 0.605349 0.000017 1.000000 0.010742 0.003184 -0

order
0.000179 0.003022 0.010742 1.000000 -0.033562 -0
day

order
-0.009518 0.002068 0.003184 -0.033562 1.000000 -0
month

order
0.007542 -0.018778 -0.006401 -0.017458 -0.020183 1
year

In [36]: plt.scatter(y_test,y_pred)
plt.plot([min(y_test), max(y_test)], [min(y_test),
max(y_test)], color='red')

Out[36]: [<matplotlib.lines.Line2D at 0x20d9835b350>]

In [8]: df.columns

Out[8]: Index(['Order ID', 'Customer Name', 'Category', 'Sub Catego

ry', 'City',
'Order Date', 'Region', 'Sales', 'Discount', 'Profi
t', 'State',
'order day', 'order month', 'order year'],
dtype='object')

In [ ]: