DataReordering

#Bhavesh recommended we put things for ML model by parameter (type of gas) rather than year

import pandas as pd
import numpy as np
df = pd.DataFrame()

for k in range (2000, 2001):
    m = pd.read_excel('/Users/rishishah/Downloads/extracted_data_' + str(k) + '.xlsx')
    df = pd.concat([df, m])

m = pd.read_excel('/Users/rishishah/Downloads/extracted_data_2001-2.xlsx')
df = pd.concat([df, m])

for k in range (2002, 2023):
    m = pd.read_excel('/Users/rishishah/Downloads/extracted_data_' + str(k) + '.xlsx')
    df = pd.concat([df, m])


df['Year'] = np.nan
df = df.drop(columns = 'Unnamed: 0')

#delete all null rows
df = df.dropna(how='all')

years = []
for i in range (2000, 2023):
    for j in range (1, 37):
        years.append(i)

df['Year'] = years

# Set the display option to show all columns
pd.set_option('display.max_columns', None)

#Now, to separate the 4 parameters into 4 excel files
cMonoxideRows = df[df['Gases'] == 'Carbon monoxide']
OzoneRows = df[df['Gases'] == 'Ozone']
sDioxideRows = df[df['Gases'] == 'Sulfur dioxide']
NDioxideRows = df[(df['Gases'] != 'Carbon monoxide') & (df['Gases'] != 'Ozone') & (df['Gases'] != 'Sulfur dioxide')]

cMonoxideRows.to_excel('CarbonMonoxideFile.xlsx')
OzoneRows.to_excel('OzoneFile.xlsx')
sDioxideRows.to_excel('SulfurDioxideFile.xlsx')
NDioxideRows.to_excel('NitrogenDioxideFile.xlsx')