Coffee Production Analysis
#Importing key data analysis libraries
import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
#Importing dataset
coffee_production = pd.read_csv("/work/Coffee_production.csv", header=0, delimiter=",")
coffee_production
Countryobject
Angola1.8%
Bolivia (Plurinational State of)1.8%
53 others96.4%
Coffee typeobject
Arabica40%
Robusta27.3%
2 others32.7%
0
Angola
Robusta/Arabica
1
Bolivia (Plurinational State of)
Arabica
2
Brazil
Arabica/Robusta
3
Burundi
Arabica/Robusta
4
Ecuador
Arabica/Robusta
5
Indonesia
Robusta/Arabica
6
Madagascar
Robusta
7
Malawi
Arabica
8
Papua New Guinea
Arabica/Robusta
9
Paraguay
Arabica
#Show the key information of the dataset
print(coffee_production.info())
#Only two columns are data type object and the rest are float64
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 55 entries, 0 to 54
Data columns (total 33 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 Country 55 non-null object
1 Coffee_type 55 non-null object
2 1990/91 55 non-null float64
3 1991/92 55 non-null float64
4 1992/93 55 non-null float64
5 1993/94 55 non-null float64
6 1994/95 55 non-null float64
7 1995/96 55 non-null float64
8 1996/97 55 non-null float64
9 1997/98 55 non-null float64
10 1998/99 55 non-null float64
11 1999/00 55 non-null float64
12 2000/01 55 non-null float64
13 2001/02 55 non-null float64
14 2002/03 55 non-null float64
15 2003/04 55 non-null float64
16 2004/05 55 non-null float64
17 2005/06 55 non-null float64
18 2006/07 55 non-null float64
19 2007/08 55 non-null float64
20 2008/09 55 non-null float64
21 2009/10 55 non-null float64
22 2010/11 55 non-null float64
23 2011/12 55 non-null float64
24 2012/13 55 non-null float64
25 2013/14 55 non-null float64
26 2014/15 55 non-null float64
27 2015/16 55 non-null float64
28 2016/17 55 non-null float64
29 2017/18 55 non-null float64
30 2018/19 55 non-null float64
31 2019/20 55 non-null float64
32 Total_production 55 non-null float64
dtypes: float64(31), object(2)
memory usage: 14.3+ KB
None
#Renaming columns
coffee_production = coffee_production.rename(columns={"Type": "Coffee_type"})
coffee_production
Countryobject
Angola1.8%
Bolivia (Plurinational State of)1.8%
53 others96.4%
Coffee_typeobject
Arabica40%
Robusta27.3%
2 others32.7%
0
Angola
Robusta/Arabica
1
Bolivia (Plurinational State of)
Arabica
2
Brazil
Arabica/Robusta
3
Burundi
Arabica/Robusta
4
Ecuador
Arabica/Robusta
5
Indonesia
Robusta/Arabica
6
Madagascar
Robusta
7
Malawi
Arabica
8
Papua New Guinea
Arabica/Robusta
9
Paraguay
Arabica
Top 5 Robusta Production Countries
--Selecting the top 5 Robusta production countries
SELECT *
FROM coffee_production
WHERE Coffee_type = 'Robusta'
ORDER BY Total_production DESC
LIMIT 5
Countryobject
Coffee_typeobject
0
Côte d'Ivoire
Robusta
1
Madagascar
Robusta
2
Lao People's Democratic Republic
Robusta
3
Guinea
Robusta
4
Togo
Robusta
#Visualizaing what countries have a robusta type of coffee.
all_total_production = Coffee_Robusta['Total_production'].sum()
#New column: Percentage of Total Production
Coffee_Robusta['Production_Percentage'] = Coffee_Robusta['Total_production']/all_total_production*100
#Creating a list for countries and production percentage
production_percentage = Coffee_Robusta['Production_Percentage']
Countries = Coffee_Robusta['Country']
#Color palette
color_palete = sns.color_palette('dark')
#Pie chart
plt.pie(production_percentage, labels=Countries, colors=color_palete, autopct='%.0f%%')
plt.title("Top 5 Robusta Production Countries")
plt.show()
Top 5 Arabica Production Countries
-- Selecting the top 5 Arabica Production Countries
SELECT *
FROM coffee_production
WHERE Coffee_type ='Arabica'
ORDER BY Total_production DESC
LIMIT 5
Countryobject
Coffee_typeobject
0
Colombia
Arabica
1
Ethiopia
Arabica
2
Honduras
Arabica
3
Peru
Arabica
4
Costa Rica
Arabica
#Visualizaing what countries have a arabica type of coffee.
all_total_arabica_production = df_coffee_arabica['Total_production'].sum()
#New column: Percentage of Total Production
df_coffee_arabica['Production_Percentage'] = df_coffee_arabica['Total_production']/all_total_arabica_production*100
#Creating a list for countries and production percentage
production_percentage_arabica = df_coffee_arabica['Production_Percentage']
Countries_arabica = df_coffee_arabica['Country']
#Color paletter
color_palete = sns.color_palette('dark')
#Pie chart
plt.pie(production_percentage_arabica, labels=Countries_arabica, colors=color_palete, autopct='%.0f%%')
plt.title("Top 5 Arabica Production Countries")
plt.show()
Top 5 Robusta/Arabica Production Countries
SELECT *
FROM coffee_production
WHERE Coffee_type ='Robusta/Arabica'
ORDER BY Total_production DESC
LIMIT 5
Countryobject
Coffee_typeobject
0
Viet Nam
Robusta/Arabica
1
Indonesia
Robusta/Arabica
2
India
Robusta/Arabica
3
Uganda
Robusta/Arabica
4
Thailand
Robusta/Arabica
#Visualizaing what countries have a robusta/arabica type of coffee.
all_total_robusta_arabica_production = df_robusta_arabica_coffee['Total_production'].sum()
#New column: Percentage of Total Production
df_robusta_arabica_coffee['Production_Percentage'] = df_robusta_arabica_coffee['Total_production']/all_total_robusta_arabica_production*100
#Creating a list for countries and production percentage
production_percentage_robusta_arabica = df_robusta_arabica_coffee['Production_Percentage']
Countries_robusta_arabica = df_robusta_arabica_coffee['Country']
#Color paletter
color_palete = sns.color_palette('dark')
#Pie chart
plt.pie(production_percentage_robusta_arabica, labels=Countries_robusta_arabica, colors=color_palete, autopct='%.0f%%')
plt.title("Top 5 Robusta/Arabica Production Countries")
plt.show()
Top 5 Arabica/Robusta Production Countries
SELECT *
FROM coffee_production
WHERE Coffee_type ='Arabica/Robusta'
ORDER BY Total_production DESC
LIMIT 5
Countryobject
Coffee_typeobject
0
Brazil
Arabica/Robusta
1
Mexico
Arabica/Robusta
2
Guatemala
Arabica/Robusta
3
Ecuador
Arabica/Robusta
4
Papua New Guinea
Arabica/Robusta
#Visualizaing what countries have a arabica/robusta type of coffee.
all_total_arabica_robusta_production = df_arabica_robusta['Total_production'].sum()
#New column: Percentage of Total Production
df_arabica_robusta['Production_Percentage'] = df_arabica_robusta['Total_production']/all_total_arabica_robusta_production*100
#Creating a list for countries and production percentage
production_percentage_arabica_robusta = df_arabica_robusta['Production_Percentage']
Countries_arabica_robusta = df_arabica_robusta['Country']
#Color paletter
color_palete = sns.color_palette('dark')
#Pie chart
plt.pie(production_percentage_arabica_robusta, labels=Countries_arabica_robusta, colors=color_palete,autopct='%.0f%%')
plt.title("Top 5 Arabica/Robusta Production Countries")
plt.show()