Explore

Python

Libraries Used

import numpy as np

import pandas as pd

⁠

Data Loading

Mount Google Drive

from google.colab import drive

drive.mount('/contentdrive/')

Load Regions Table

# regions table

path='/contentdrive/MyDrive/SQL - Deforestation Porject/DB Files/regions.csv'

regions=pd.read_csv(path)

regions.head()

regions

regions

Afghanistan

AFG

South Asia

Low income

Albania

ALB

Europe & Central Asia

Algeria

DZA

Middle East & North Africa

American Samoa

ASM

East Asia & Pacific

Andorra

AND

Europe & Central Asia

There are no rows in this table

⁠

Load Land Area Table

# land area table

path='/contentdrive/MyDrive/SQL - Deforestation Porject/DB Files/land_area.csv'

land_area=pd.read_csv(path)

land_area.head()

land_area

land_area

There are no rows in this table

⁠

Load Forest Area Table

# forest area table

path='/contentdrive/MyDrive/SQL - Deforestation Porject/DB Files/forest_area.csv'

forest_area=pd.read_csv(path)

forest_area.head()

forest area

forest area

There are no rows in this table

⁠

Data Processing

Merge Tables

# forsetation view table

forestation = regions.merge(land_area, on=["country_code"], how="inner")\

.merge(forest_area, on=["country_code", "year"], how="inner")

Convert Total Area to sq km

# Convert total area to sq km

forestation['total_area_sqkm'] = forestation['total_area_sq_mi'] * 2.59

# Remove total_area_sq_mi column

forestation.drop(columns=["total_area_sq_mi"], inplace=True)

# Remove nulls from the table

forestation = forestation.dropna(subset=["total_area_sqkm", "forest_area_sqkm"])

# Create a new column "forest_area_percent"

forestation['forest_area_percent'] = (forestation['forest_area_sqkm'] / forestation['total_area_sqkm'] * 100).round(2)

Display Forestation Data

forestation.head()

forestation

forestation

There are no rows in this table

⁠

Analysis

Total Forest Area in 1990

# Part 1 .a. What was the total forest area (in sq km) of the world in 1990?

# فلترة الجدول على 1990 & world

World_1990= forestation[(forestation['year'] == 1990) & (forestation['country_name'].str.lower() == 'world')]

# حساب إجمالي مساحة الغابات لعام 1990

total_forest_area_1990 = World_1990['forest_area_sqkm'].sum()

print(total_forest_area_1990)

Total Forest Area in 1990: 41282694.9 sq km

Total Forest Area in 2016

# Part 1 .b. What was the total forest area (in sq km) of the world in 2016?

# فلترة الجدول على 2016 & World

World_2016= forestation[(forestation['year'] == 2016) & (forestation['country_name'].str.lower() == 'world')]

# حساب إجمالي مساحة الغابات لعام 2016

total_forest_area_2016 = World_2016['forest_area_sqkm'].sum()

print(total_forest_area_2016)

Total Forest Area in 2016: 39958245.9 sq km

Change in Forest Area

# Part 1 .c.What was the change (in sq km) in the forest area of the world from 1990 to 2016?

# the change in the forest area from 1990 to 2016

change_in_forest_area = total_forest_area_1990 - total_forest_area_2016

print(change_in_forest_area)

Change in Forest Area: 1324449.0 sq km

Percent Change in Forest Area

# Part 1 .d. What was the percent change in forest area of the world between 1990 and 2016?

# the percent change in the forest area from 1990 to 2016

percent_change_in_forest_area = round((total_forest_area_1990 - total_forest_area_2016)/total_forest_area_1990 * 100,2)

print(percent_change_in_forest_area)

Percent Change in Forest Area: 3.21 %

Closest Country's Total Area to Forest Area Lost

# Part 1 .e. If you compare the amount of forest area lost between 1990 and 2016, to which country's total area in 2016 is it closest to?

# حساب مساحة كل دولة

forestation_2016 = forestation[(forestation['year'] == 2016) & (forestation['country_name'].str.lower() != 'world')]\

[['country_name','total_area_sqkm']].copy()

# حساب الفرق المطلق لكل دولة

forestation_2016['difference'] = abs(change_in_forest_area - forestation_2016['total_area_sqkm'])

# الدولة ذات الفرق الأقل

closest_country = forestation_2016.sort_values('difference',ascending=True).head(1)

print(closest_country)

Closest Country: Peru with a total area of 1,280,000 sq km.

country_name total_area_sqkm difference 4131 Peru 1.280000e+06 44449.0109

⁠

Regional Insights

Percent Forest Area by Region

# Part 2.(Regional Outlook) Create a table that shows the Regions and their percent forest area in 1990 and 2016.

# فلترة الجدول على عام 1990 وعام 2016

forestation_1990_2016 = forestation[forestation['year'].isin([1990, 2016])]

# تجميع البيانات حسب المنطقة والسنة

forestation_1990_2016 = forestation_1990_2016.groupby(['region', 'year'], as_index=False).agg(

total_land_area=('total_area_sqkm', 'sum'),

total_forest_area=('forest_area_sqkm', 'sum'))

# حساب نسبة الغابات

forestation_1990_2016['percent_forest_area'] = round((forestation_1990_2016['total_forest_area'] / forestation_1990_2016['total_land_area']) * 100,2)

# جدول يحتوي على region - year - percent forest area

r_insights=forestation_1990_2016[['region','year','percent_forest_area']]

print(r_insights)

r_insights

r_insights

There are no rows in this table

⁠

the percent forest of the entire world in 2016

# Part 2 .a. What was the percent forest of the entire world in 2016?

World_2016 = r_insights[(r_insights['year'] == 2016) & (r_insights['region'].str.lower() == 'world')]

print(World_2016)

region year percent_forest_area World 2016 31.38

Highest Percent Forest in 2016

# Part 2 .a. What was the percent forest of the entire world in 2016?

World_2016 = r_insights[(r_insights['year'] == 2016) & (r_insights['region'].str.lower() == 'world')]

print(World_2016)

Highest Percent Forest Region in 2016: Latin America & Caribbean with 46.16%.

region year percent_forest_area 5 Latin America & Caribbean 2016 46.16

Lowest Percent Forest in 2016

# Part 2 .a. Which region had the HIGHEST percent forest in 2016?

region_2016 = r_insights[r_insights['year'] == 2016]

highest_region = region_2016.sort_values('percent_forest_area',ascending=False).head(1)

print(highest_region)

Lowest Percent Forest Region in 2016: Middle East & North Africa with 2.07%.

region year percent_forest_area 7 Middle East & North Africa 2016 2.07

the percent forest of the entire world in 1990

# Part 2 .b. What was the percent forest of the entire world in 1990?

World_1990 = r_insights[(r_insights['year'] == 1990) & (r_insights['region'].str.lower() == 'world')]

print(World_1990)

region year percent_forest_area 4 Latin America & Caribbean 1990 51.03

the LOWEST percent forest in 1990

# Part 2 .b.which region had the LOWEST percent forest in 1990?

region_1990 = r_insights[r_insights['year'] == 1990]

lowest_region = region_1990.sort_values('percent_forest_area',ascending=True).head(1)

print(lowest_region)

region year percent_forest_area 6 Middle East & North Africa 1990 1.78

the world DECREASED in forest area from 1990 to 2016

# Part 2 .c.which regions of the world DECREASED in forest area from 1990 to 2016?

# one table for 1990 / another table for 2016

region_1990 =r_insights[(r_insights['year'] == 1990) & (r_insights['region'] != 'World')]

region_2016 =r_insights[(r_insights['year'] == 2016) & (r_insights['region'] != 'World')]

# merge region 1990 & region 2016

merge_regions= region_1990.merge(region_2016, on=["region"], how="left", suffixes=('_1990', '_2016'))

# create a new column(pfa_decrease)

merge_regions['pfa_decrease'] = merge_regions['percent_forest_area_1990'] - merge_regions['percent_forest_area_2016']

# filter by pfa_decrease >0

result=merge_regions[merge_regions['pfa_decrease'] > 0]

print(result[['region','pfa_decrease']])

Want to print your doc?
This is not the way.

Try clicking the ··· in the right corner or using a keyboard shortcut (

CtrlP

) instead.