Update app.py

app.py

@@ -1,75 +1,18 @@
 import pandas as pd
-import numpy as np
-
-from dataprep.clean import clean_country
 import plotly.graph_objects as go
 
-gdp_per_capita = pd.read_csv('./data/country_gdp_per_capita_worldbank.csv')
-gdp_per_capita = gdp_per_capita[['Country Name', '2010', '2011', '2012', '2013', '2014', '2015', '2016', '2017', '2018', '2019', '2020']]
-
-usa = pd.read_csv('./data/USAData_RenewableInvestment_2010-2020.csv').set_index('Country')
-
-## read plotly data ##
-
-temp_delta_plotly = pd.read_csv('./data/Annual_Surface_Temperature_Change.csv')
-invest_plotly = pd.read_csv('data/Environmental_Protection_Expenditures.csv')
-gdp_per_capita_plotly = gdp_per_capita.copy()
-
-## prepare data for plotly ##
-
-gdp_per_capita_plotly = gdp_per_capita_plotly.rename(columns={'Country Name': 'Country'})
-
-# look up ISO3 codes for countries
-gdp_per_capita_plotly = clean_country(gdp_per_capita_plotly, "Country", output_format="alpha-3").rename(columns={'Country_clean': 'ISO3'})
-gdp_per_capita_plotly = gdp_per_capita_plotly[['Country', 'ISO3', '2010', '2011', '2012', '2013', '2014', '2015', '2016', '2017', '2018', '2019', '2020']]
-gdp_per_capita_plotly = gdp_per_capita_plotly.rename(columns={'2010': 2010, '2011': 2011, '2012': 2012, '2013': 2013, '2014': 2014, '2015': 2015, '2016': 2016, '2017': 2017, '2018': 2018, '2019': 2019, '2020': 2020})
-
-temp_delta_plotly = temp_delta_plotly[['Country', 'ISO3', 'F2010', 'F2011', 'F2012', 'F2013', 'F2014', 'F2015', 'F2016', 'F2017', 'F2018', 'F2019', 'F2020']]
-temp_delta_plotly = temp_delta_plotly.rename(columns={'F2010': 2010, 'F2011': 2011, 'F2012': 2012, 'F2013': 2013, 'F2014': 2014, 'F2015': 2015, 'F2016': 2016, 'F2017': 2017, 'F2018': 2018, 'F2019': 2019, 'F2020': 2020})
-
-usa2 = usa.copy().reset_index()
-usa2['ISO3'] = 'USA'
-invest_plotly = invest_plotly[invest_plotly['Unit'] == 'Percent of GDP'].fillna(int(0))
-invest_plotly = invest_plotly[['Country', 'ISO3', 'F2010', 'F2011', 'F2012', 'F2013', 'F2014', 'F2015', 'F2016', 'F2017', 'F2018', 'F2019', 'F2020']].reset_index(drop=True)
-invest_plotly = pd.concat([invest_plotly, usa2])
-invest_plotly = invest_plotly.groupby(['ISO3']).agg('sum').reset_index()
-invest_plotly = invest_plotly.rename(columns={'F2010': 2010, 'F2011': 2011, 'F2012': 2012, 'F2013': 2013, 'F2014': 2014, 'F2015': 2015, 'F2016': 2016, 'F2017': 2017, 'F2018': 2018, 'F2019': 2019, 'F2020': 2020})
 
-temp_delta_plotly = temp_delta_plotly.melt(id_vars=['ISO3'], value_vars=[2010, 2011, 2012, 2013, 2014, 2015, 2016, 2017, 2018, 2019, 2020], var_name='Year', value_name='Temp_Change')
-gdp_per_capita_plotly = gdp_per_capita_plotly.melt(id_vars=['ISO3', 'Country'], value_vars=[2010, 2011, 2012, 2013, 2014, 2015, 2016, 2017, 2018, 2019, 2020], var_name='Year', value_name='GDP_Per_Capita')
-invest_plotly = invest_plotly.melt(id_vars=['ISO3'], value_vars=[2010, 2011, 2012, 2013, 2014, 2015, 2016, 2017, 2018, 2019, 2020], var_name='Year', value_name='Investment_Percent')
-
-plotly_data = pd.merge(temp_delta_plotly, invest_plotly, on=['ISO3', 'Year'])
-plotly_data = pd.merge(gdp_per_capita_plotly, plotly_data, on=['ISO3', 'Year'])
-
-# drop all YEMEN data, as there is missing GDP data and no temp_change data
-plotly_data = plotly_data.drop(plotly_data.loc[plotly_data['ISO3']=='YEM'].index)
-
-# drop 2010-2012 data for SOMALIA, as there is no GDP data
-plotly_data = plotly_data.drop(plotly_data.loc[(plotly_data['ISO3']=='SOM') & (plotly_data['Year']<2013)].index)
-
-new_country_data = plotly_data.copy()
-new_country_data = new_country_data.groupby('Country').agg({'Temp_Change': 'mean', 'Investment_Percent': 'mean', 'GDP_Per_Capita': 'mean'})
-new_country_data['Temp_Change'] = new_country_data['Temp_Change'] + .25
-new_country_data = new_country_data.rename(columns={'Temp_Change': 'temp_delta_avg', 'Investment_Percent': 'renew_invest_avg', 'GDP_Per_Capita': 'gdp_per_capita_avg'})
+# read data
+plotly_data = pd.read_csv('plotly_data.csv')
 
+# find countries in G20
 g20 = ['Argentina', 'Australia', 'Brazil', 'Canada', 'China', 'France', 'Germany', 'India', 'Indonesia', 'Italy', 'Japan', 'Republic of Korea', 'Mexico', 'Russia', 'Saudi Arabia', 'South Africa', 'Turkey', 'United Kingdom', 'United States', 'Austria', 'Belgium', 'Bulgaria', 'Croatia', 'Cyprus', 'Czech Republic', 'Denmark', 'Estonia', 'Finland', 'Greece', 'Hungary', 'Ireland', 'Latvia', 'Lithuania', 'Luxembourg', 'Malta', 'Netherlands', 'Poland', 'Portugal', 'Romania', 'Slovakia', 'Slovenia', 'Spain', 'Sweden']
-new_country_data['g20'] = new_country_data.index.isin(g20).tolist()
-
-g20_countries = new_country_data.loc[new_country_data['g20'] == True].index.to_list()
+plotly_data['g20'] = plotly_data['Country'].isin(g20).tolist()
+g20_countries = plotly_data.loc[plotly_data['g20'] == True]['Country'].to_list()
 
 
-plotly_data['Temp_Change'] = plotly_data['Temp_Change'] + .25
-
-p1 = (plotly_data['Investment_Percent'] > 2)
-p2 = (plotly_data['Temp_Change'] < 1.5)
-
-plotly_data['color_code'] = np.where(p1 & p2, '#46725D', "False")
-plotly_data['color_code'] = np.where(p1 & ~p2, '#A46D13', plotly_data['color_code'])
-plotly_data['color_code'] = np.where(~p1 & p2, '#505693', plotly_data['color_code'])
-plotly_data['color_code'] = np.where(~p1 & ~p2, '#9A381D', plotly_data['color_code'])
-
 # make plotly figure
+import plotly.graph_objects as go
 
 dataset = plotly_data.copy()