'''

Generates a company's beta based on the desired time frame using daily values

Inputs
=========
tic: string
    the company's ticker (as per Yahoo! finance)
start_date: string
    the earliest date to be used
end_date: string
    the last date to be used

Parameters
==========
t_per: string
    time period for regression
mkt_tic: string
    proxt to use for the stock market
df_tic: data frame
    data frame that holds the Yahoo! Finance outputs for the company
df_mkt: data frame
    data frame that holds the Yahoo! Finance outputs for the market proxy
tic_hpr: float
    daily hpr for the stock
mkt_hpr: float
    daily hpr for the market
regress: regression output
    output of the beta regression
beta: float
    company's beta
df: integer
    degress of freedom for the significance tests and CI
beta_se: float
    standard error of the beta result
beta_tval: float
    the t-value based on the degrees of freedom used

Returns
=======
beta : float
    the company's beta
CI_low: float
    the beta's confidence interval's lower bound
CI_high: float
    the beta's confidence interval's upper bound
stat_t: float
    the test statistic for the beta's significance
stat_1per: float
    the critical value for 1 percent significant
stat_5per: float
    the critical value for 5 percent significant

'''

# packages to use for the analysis
import datetime as date
import pandas as pd
import pandas_datareader as web
import statsmodels.api as sm
import statsmodels.formula.apo as smf
from scipy import stats

# derive the inputs from the user
print("What is the company's ticker? (Please use the ticker as per Yahoo! Finance)")
tic = raw_input()

print("What would you like to use as a market proxy: S&P 500 (1) or Russell 3000 (2)")
mrk_tic = raw_input()

if mrk_tic = 1:
    mrk_tic = "GSPC"
elif mrk_tic = 2:
    mrk_tic = "RUA"
else:
    print("Error: please input 1 or 2 for the two options listed prior")

print("Would you like to select a trailing time frame (1) or input custom dates (2)")
t_per = raw_input()

date = {-30, -90, -180, -365, -1095, -1825] # vector of days for reference

print("Please select: one month (1), three months(2), six months(3), one year(4), three year(5), five year(6) ")
t_per = raw_input()
t_per = date[t_per - 1]
end_date = date.today()
start_date = timedelta(days = t_per)

"""
if t_per = 1:
    date = {-30, -90, -180, -365, -1095, -1825] # vector of days for reference
    print("Please select: one month (1), three months(2), six months(3), one year(4), three year(5), five year(6) ")
    t_per = raw_input()
    t_per = date[t_per - 1]
    end_date = date.today()
    start_date = timedelta(days = t_per)
elif t_per = 2:
    print("Please enter the start date (mm/dd/yyyy)")
    start_date = raw_input()
    sd_mm =
    sd_dd =
    sd_yyyy =
    print("Please enter the end date (mm/dd/yyyy)")
    end_date = raw_input()
    ed_mm =
    ed_dd =
    ed_yyyy =
else:
    print("Error: please input 1 or 2 for the two options listed prior")

"""

start_date = date.datetime(sd_yyyy,sd_mm,sd_dd)
end = date.datetime(ed_yyyy,ed_mm,ed_dd)

# retrieve stock prices and calculate returns
df_tic = web.get_data_yahoo(tic, start_date, end_date)
adj_close_tic = df_tic['Adj Close']

for i = 0:len(adj_close_tic) - 1:
    tic_hpr = []
    hpr = (adj_close_tic[i] - adj_close_tic[i + 1]) / adj_close_tic[i + 1]
    tic_hpr.append(hpr)
next i

# retrieve market proxy prices and calculate returns
df_mkt = web.get_data_yahoo(mrk_tic, start_date, end_date)
adj_close_mkt = df_mkt['Adj Close']

for i = 0:len(adj_close_mkt) - 1:
    mkt_hpr = []
    hpr = (adj_close_mkt[i] - adj_close_mkt[i + 1]) / adj_close_mkt[i + 1]
    mkt_hpr.append(hpr)
next i

# regress the stock returns on the market returns
regress = sm.OLS(tic_hpr, mkt_hpr).fit()
beta = regress.params

# find the beta's standard error and compute the 95% CI
beta_se = regress.bse

df = len(tic_hpr) - 1
beta_tval = stats.t.ppf(1-0.025, df)

CI_low = beta - (beta_tval * beta_se)
CI_high = beta + (beta_tval * beta_se)

# find the test statistics
stat_t = regress.tvalues()

stat_5per = stats.t.ppf(1-0.025, df)
stat_1per = stats.t.ppf(1-0.005, df)

# print results
print("Results:")
print("The beta for %s is %d." % (tic, beta))
print("The CI for the beta is %d to %d." % (CI_low, CI_high))
print("The t-stat is %d, which compares to the 5 percent and 1 percent critical values of %d and %d, respectively." % (stat_t, stat_5per, stat_1per))