Global Plastic Pollution Analysis

import numpy as np import pandas as pd import seaborn as sns import warnings import matplotlib.pyplot as plt %matplotlib inline warnings.filterwarnings('ignore') sns.set_style('darkgrid')

''' reading dataset ''' df = pd.read_csv('per-capita-plastic-waste-vs-gdp-per-capita.csv')

''' displaying first 5 rows ''' df.head()

''' shape of data ''' df.shape

''' checking null values in data ''' df.isnull().sum()

''' checking percentage of null values in each column ''' for column in df.columns: print("{} has {:.2f}% null values: ".format(column, (df[column].isnull().sum() / len(df)) * 100 )) print("-" * 100)

Entity has 0.00% null values: 
----------------------------------------------------------------------------------------------------
Code has 4.18% null values: 
----------------------------------------------------------------------------------------------------
Year has 0.00% null values: 
----------------------------------------------------------------------------------------------------
Per capita plastic waste (kg/person/day) has 99.61% null values: 
----------------------------------------------------------------------------------------------------
GDP per capita, PPP (constant 2011 international $) has 86.70% null values: 
----------------------------------------------------------------------------------------------------
Total population (Gapminder, HYDE & UN) has 2.67% null values: 
----------------------------------------------------------------------------------------------------
Continent has 99.41% null values: 
----------------------------------------------------------------------------------------------------

''' checking info of data ''' df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 48168 entries, 0 to 48167
Data columns (total 7 columns):
 #   Column                                               Non-Null Count  Dtype  
---  ------                                               --------------  -----  
 0   Entity                                               48168 non-null  object 
 1   Code                                                 46154 non-null  object 
 2   Year                                                 48168 non-null  int64  
 3   Per capita plastic waste (kg/person/day)             186 non-null    float64
 4   GDP per capita, PPP (constant 2011 international $)  6407 non-null   float64
 5   Total population (Gapminder, HYDE & UN)              46883 non-null  float64
 6   Continent                                            285 non-null    object 
dtypes: float64(3), int64(1), object(3)
memory usage: 2.6+ MB

''' renaming column names ''' df.rename(columns={'GDP per capita, PPP (constant 2011 international $)': 'GDP per capita in PPP', 'Total population (Gapminder, HYDE & UN)': 'Total Population', 'Per capita plastic waste (kg/person/day)': 'Waste per person(kg/day)'}, inplace=True)

df.head()

''' removing entities/countries with incomplete/missing data ''' incmp_df_idx = df[(df['Total Population'].isna()) & (df['GDP per capita in PPP'].isna())].index df.drop(incmp_df_idx, inplace=True)

df.head()

df.shape

'''retrieving rows in which year == 2010''' df_2010 = df[df['Year'] == 2010] df_2010 = df_2010.drop(columns='Continent')

df_2010.head()

'''retrieving continent name in which year == 2015''' df_2015 = df[df['Year'] == 2015] df_2010['Continent'] = df_2015['Continent'].values

df_2015.head()

'''dropping rows with missing Continent values using index''' missing_idx = df_2010[df_2010['Continent'].isna()].index df_2010.drop(missing_idx, inplace=True)

''' dropping rows with missing per person waste generation values ''' df_2010 = df_2010[df_2010['Waste per person(kg/day)'].notna()] wa_g = df_2010.reset_index().drop('index', axis=1)

wa_g.head()

''' reading 2nd file ''' df2 = pd.read_csv('per-capita-mismanaged-plastic-waste-vs-gdp-per-capita.csv')

''' displaying first 5 rows of df2 ''' df2.head()

''' renaming columns''' df2.rename(columns={'Per capita mismanaged plastic waste': 'Mismanaged waste per person(kg/day)', 'GDP per capita, PPP (constant 2011 international $)': 'GDP per capita in PPP', 'Total population (Gapminder, HYDE & UN)': 'Total Population'}, inplace=True)

''' dropping Continent column ''' df2.drop('Continent', axis=1, inplace=True)

'''retrieving rows in which year == 2010''' df2_2010 = df2[df2.Year == 2010] df2_2010.head()

''' dropping rows with missing mismanaged waste values ''' df2_2010 = df2_2010[df2_2010['Mismanaged waste per person(kg/day)'].isna() != True] ''' reset index ''' w_m = df2_2010.reset_index().drop('index', axis=1)

w_m.head()

''' merging w_m and wa_g ''' df_plastic_waste = pd.merge(wa_g, w_m, how='inner')

''' displaying data ''' df_plastic_waste.head()

''' converting column names into list ''' df_plastic_waste.columns.tolist() ''' column names ''' col_names = ['Entity','Code','Year','Waste per person(kg/day)','Mismanaged waste per person(kg/day)', 'GDP per capita in PPP','Total Population','Continent'] df_plastic_waste = df_plastic_waste[col_names] '''rounding the values per person''' df_plastic_waste.iloc[:, 3:5] = np.around(df_plastic_waste[['Waste per person(kg/day)', 'Mismanaged waste per person(kg/day)']], decimals=2) ''' changing data type ''' df_plastic_waste['Total Population'] = df_plastic_waste['Total Population'].astype(int)

'''Generating Total waste and Total mismanaged waste by country''' df_plastic_waste['Total waste(kgs/year)'] = ((df_plastic_waste['Waste per person(kg/day)'] * df_plastic_waste['Total Population']) * 365) df_plastic_waste['Total waste mismanaged(kgs/year)'] = ((df_plastic_waste['Mismanaged waste per person(kg/day)'] * df_plastic_waste['Total Population']) * 365)

df_plastic_waste.head()

''' scatter plot graph ''' plt.figure(1, figsize=(12,8)) plt.scatter(df_plastic_waste['GDP per capita in PPP'], df_plastic_waste['Mismanaged waste per person(kg/day)']) plt.title('Waste Mismanaged', loc='center', fontsize=15) plt.ylabel('Mismanaged waste', loc='center', fontsize=15) plt.xlabel('GDP per capita', fontsize=12) sns.regplot(x='GDP per capita in PPP', y='Mismanaged waste per person(kg/day)', data=df_plastic_waste, scatter_kws={'color': '#34568B'}, line_kws={'color': '#650021'}) plt.show()

''' scatter plot ''' plt.figure(2, figsize=(12,8)) plt.scatter(df_plastic_waste['GDP per capita in PPP'], df_plastic_waste['Waste per person(kg/day)']) plt.title('Waste Generated by GDP', loc='center', fontsize=14) plt.ylabel('Waste per person(kg/day)', loc='center', fontsize=12) plt.xlabel('GDP per capita in PPP', fontsize=12) sns.regplot(x=df_plastic_waste['GDP per capita in PPP'], y=df_plastic_waste['Waste per person(kg/day)'], scatter_kws={'color': '#CD212A'}, line_kws={'color': '#380282'}) plt.show()