#!/usr/bin/env python
# coding: utf-8

# In[1]:


get_ipython().run_line_magic('matplotlib', 'inline')
import matplotlib.pyplot as plt
import seaborn as sns
import pandas as pd
import numpy as np
import os
from os.path import join
import sys
import json


# In[2]:


# Load the "autoreload" extension
get_ipython().run_line_magic('load_ext', 'autoreload')

# always reload modules marked with "%aimport"
get_ipython().run_line_magic('autoreload', '1')


# In[4]:


# add the 'src' directory as one where we can import modules
cwd = os.getcwd()
src_dir = join(cwd, os.pardir, 'src')
sys.path.append(src_dir)


# In[26]:


from util.utils import rename_cols


# ## Load data

# In[31]:


#EPA CEMS data
path = join(cwd, '..', 'Data storage', 'Derived data',
            'Monthly EPA emissions 2017-08-31.csv')
epa = pd.read_csv(path)
rename_cols(epa)
epa = epa.groupby(['year', 'month', 'plant id']).sum()


# In[6]:


#EIA facility data
path = join(cwd, '..', 'Data storage',
            'Facility gen fuels and CO2 2017-08-31.zip')
eia_fac = pd.read_csv(path)
rename_cols(eia_fac)
eia_fac = eia_fac.groupby(['year', 'month', 'plant id', 'fuel']).sum()


# ## Find a facility with biomass and CHP

# In[10]:


idx = pd.IndexSlice


# In[37]:


example_eia = eia_fac.loc[idx[2016, 6, 1897, :], :]
example_eia


# In[38]:


example_eia.sum()


# In[23]:


example_eia.to_clipboard()


# In[35]:


example_epa = epa.loc[idx[2016, 6, 1897], :]
example_epa


# ## Adjust CO₂ emissions

# In[39]:


co2_factor = (example_eia.sum()['elec fuel fossil co2 (kg)']
              / example_eia.sum()['all fuel total co2 (kg)'])
co2_factor


# In[40]:


co2_factor * example_epa['co2_mass (kg)']