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

# In[18]:


import pandas as pd
from matplotlib import pyplot as plt
from IPython.display import display
get_ipython().run_line_magic('matplotlib', 'inline')
plt.rcParams['figure.figsize'] = (20.0, 10.0)

rhi_csv = 'tabula-RHI-beneficiaries-non-domestic-individuals-companies.csv'


# In[30]:


df = pd.read_csv(rhi_csv)
df['Date'] = pd.to_datetime(df['Date of\rApplication'], format='%d/%m/%Y')
df['Cash'] = df['Amount of payments\rmade to 28 February\r2017 (£)*'].replace('[£,]','', regex=True).astype(float)
df.drop(['Date of\rApplication','Amount of payments\rmade to 28 February\r2017 (£)*'], axis=1, inplace=True) 
df.rename(columns={'Business or\rInstallation\rLocation':'Postcode', 'Installation\rCapacity\r(kWth)':'Capacity (kWth)','Technology Type':'Type','Name':'Company'}, inplace=True)
display(df.head())
display(df.dtypes)


# In[36]:


df[df.Postcode.isnull()]


# In[37]:


df.Cash.sum()


# In[ ]: