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

#Show the key information of the dataset print(coffee_production.info()) #Only two columns are data type object and the rest are float64

#Renaming columns coffee_production = coffee_production.rename(columns={"Type": "Coffee_type"}) coffee_production

--Selecting the top 5 Robusta production countries SELECT * FROM coffee_production WHERE Coffee_type = 'Robusta' ORDER BY Total_production DESC LIMIT 5

#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()

-- Selecting the top 5 Arabica Production Countries SELECT * FROM coffee_production WHERE Coffee_type ='Arabica' ORDER BY Total_production DESC LIMIT 5

#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()

SELECT * FROM coffee_production WHERE Coffee_type ='Robusta/Arabica' ORDER BY Total_production DESC LIMIT 5

#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()

SELECT * FROM coffee_production WHERE Coffee_type ='Arabica/Robusta' ORDER BY Total_production DESC LIMIT 5

#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()