"""
This python code help you to start the project
Date: 2018-06-30
"""

from __future__ import print_function
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

# Read in the risk-free rate
data = pd.read_csv('nme_R031.28290.20180609114202.01.csv',skiprows=2)
cr = data['Call Rate, Uncollateralized Overnight, Average (Daily)']
ds = data['Name of time-series']
dates = pd.to_datetime(ds, format = '%Y/%m/%d')

n = len(cr)
to_drop = []
for i in range(n):
   if cr[i]  == 'NA    ':
      to_drop.append(i)   

a = cr.drop(to_drop)
dates = dates[a.index]

ra = a.values
nr = len(ra)
raa = np.zeros(nr)
for i in range(nr):
   raa[i] = float(ra[i])

rf = pd.Series(data=raa, index = pd.to_datetime(dates), name = 'rf')
drf = pd.DataFrame({'Date': rf.index, 'rf': rf.values})
drf.index = pd.to_datetime(drf.Date)
drf = drf.drop(['Date'], axis=1)

# Read in all the indexes 
data_all = pd.read_csv('PW_EW_TOPIX.csv')
data_all.index = pd.to_datetime(data_all.Date)
data_all = data_all.drop(['Date'], axis=1)

# Concatenate and align the data
df = pd.concat([drf, data_all], axis=1)
df = df.dropna()

# Re-sample daily into monthly data set
dfm = df.resample('M').last()