The Euro on Forex¶

# import libraries and set display options
import pandas as pd
import pprint
pd.options.display.float_format = '{:20,.4f}'.format
pd.set_option('display.max_rows', None)
pd.set_option('display.max_columns', None)
pd.set_option('display.width', 1000)
pd.set_option('display.colheader_justify', 'center')
pd.set_option('display.precision', 3)

# open file
x_rates = pd.read_csv("euro-daily-hist_1999_2020.csv")

# head, tail, and basic info
display(x_rates.head())
display(x_rates.tail())
display(x_rates.info())

# strip brackets and trailing space from country names
# replace remaining space with underscore
x_rates.columns = x_rates.columns.str.replace("[","").str.replace("]","")
x_rates.columns = x_rates.columns.str.rstrip()
x_rates.columns = x_rates.columns.str.replace(" ","_")

# rename columns
x_rates.rename(columns={"Period\\Unit:":"Date",
                        "Chinese_yuan_renminbi":"Chinese_yuan",
                        "UK_pound_sterling":"UK_pound"}, inplace=True)

# convert datetime
x_rates["Date"] = pd.to_datetime(x_rates["Date"])

# resort and reindex
x_rates.sort_values("Date", inplace=True)
x_rates.reset_index(drop=True, inplace=True)

# convert hyphens in currency columns to NaN
import numpy as np
x_rates = x_rates.replace("-", np.nan)

# convert exchange rate values to float
x_rates.iloc[:,1:] = x_rates.iloc[:,1:].astype(float)

# create a euro to dollar dataframe and add 30 day rolling mean column
us_dollar = x_rates[["Date","US_dollar"]].copy()
us_dollar["rolling_mean_30"] = us_dollar["US_dollar"].rolling(30).mean()

# line graph for euro to dollar exchange rate
import matplotlib.pyplot as plt
%matplotlib inline
plt.plot(us_dollar["Date"], us_dollar["rolling_mean_30"])
plt.show()

# create nan group and get dates
nan_dollar_group = us_dollar[us_dollar["US_dollar"].isnull()]
nan_days = nan_dollar_group["Date"]

# line graph showing 30 day rolling mean with and without vertical bars representing null days
plt.figure(figsize=(10,3.75))
plt.subplot(1,2,1)
plt.plot(us_dollar["Date"], us_dollar["rolling_mean_30"])
plt.yticks([])
plt.subplot(1,2,2)
plt.plot(us_dollar["Date"], us_dollar["rolling_mean_30"])
plt.yticks([])
for xc in nan_days:
    plt.axvline(x=xc, color="lightcyan")
plt.suptitle("Euro to US dollar exchange rates, dataset w/ NaN values and corresponding dates in light blue")
plt.show()

# create a dollar to euro dataframe with NaN dates removed
US_dollar_nonull = x_rates[x_rates["US_dollar"].notna()].copy()
US_dollar_nonull["rolling_mean_30"] = US_dollar_nonull["US_dollar"].rolling(30).mean()

# line graph showing 30 day rolling mean with and without NaN dates
plt.figure(figsize=(10,3.75))
plt.subplot(1,2,1)
plt.plot(us_dollar["Date"], us_dollar["rolling_mean_30"])
plt.yticks([])
plt.subplot(1,2,2)
plt.plot(US_dollar_nonull["Date"], US_dollar_nonull["rolling_mean_30"])
plt.yticks([])
plt.suptitle("Euro to US dollar exchange rates, with NaN dates and corresponding dates removed")
plt.show()

# function to build data frame for Euro to other half of trading pair
xchange_list = []
def xchange(column):
    xchange_list.append(column)
    dataset = x_rates[["Date",column]].copy()
    dataset = dataset[dataset[column].notna()]
    dataset["rolling_mean_30"] = dataset[column].rolling(30).mean()
    return dataset

# is there a way to apply this function to all the columns in x_rates?
# one drawback would be having 42 data frames
# but I don't know how else to deal with NaN cells being different for each currency
# i should see if there's a way to add the rolling mean column for each currency

# calling xchange function on four highly traded currencies
us_dollar = xchange("US_dollar")
japanese_yen = xchange("Japanese_yen")
uk_pound = xchange("UK_pound")
australian_dollar = xchange("Australian_dollar")

# line graph showing Euro to each trading pair
plt.figure(figsize=(10,7.5))
plt.subplot(2,2,1)
plt.plot(us_dollar["Date"], us_dollar["rolling_mean_30"])
plt.title("Euro to US dollar")
plt.yticks([])
plt.subplot(2,2,2)
plt.plot(japanese_yen["Date"], japanese_yen["rolling_mean_30"])
plt.title("Euro to Japanese yen")
plt.yticks([])
plt.subplot(2,2,3)
plt.plot(uk_pound["Date"], uk_pound["rolling_mean_30"])
plt.title("Euro to UK pound")
plt.yticks([])
plt.subplot(2,2,4)
plt.plot(australian_dollar["Date"], australian_dollar["rolling_mean_30"])
plt.title("Euro to Australian dollar")
plt.yticks([])
plt.subplots_adjust(hspace=0.3)
plt.show()

# with less code?
# plt.figure(figsize=(10,7.5))
# for i in range(1, 5):
#     plt.subplot(2,2,i)
# plt.show()

# calling xchange function on four least traded currencies
israeli_shekel = xchange("Israeli_shekel")
philippine_peso = xchange("Philippine_peso")
malaysian_ringgit = xchange("Malaysian_ringgit")
romanian_leu = xchange("Romanian_leu")

# line graph showing Euro to each trading pair
plt.figure(figsize=(10,7.5))
plt.subplot(2,2,1)
plt.plot(israeli_shekel["Date"], israeli_shekel["rolling_mean_30"])
plt.title("Euro to Israeli shekel")
plt.yticks([])
plt.subplot(2,2,2)
plt.plot(philippine_peso["Date"], philippine_peso["rolling_mean_30"])
plt.title("Euro to Philippine peso")
plt.yticks([])
plt.subplot(2,2,3)
plt.plot(malaysian_ringgit["Date"], malaysian_ringgit["rolling_mean_30"])
plt.title("Euro to Malaysian ringgit")
plt.yticks([])
plt.subplot(2,2,4)
plt.plot(romanian_leu["Date"], romanian_leu["rolling_mean_30"])
plt.title("Euro to Romanian leu")
plt.yticks([])
plt.subplots_adjust(hspace=0.3)
plt.show()

# function to get log of daily rate
def logarizer(dataset):
    dataset["log_rate"] = np.log(dataset.iloc[:,1]/dataset.iloc[:,1].shift()) # getting the log of the exchange rate
    return dataset["log_rate"]

# function to get overall volatility
volatility_dict = {}
def volatizer(dataset):
    column_headers = list(dataset.columns.values)
    currency_name = column_headers[1]
    volatility = dataset["log_rate"].std()*253**.5 # volatility measured by standard deviation * 253 trading days per year
    volatility = round(volatility, 4)*100
    volatility_dict[currency_name] = volatility

# it would be cool to convert or use xchange_list
# i didn't really think .replace would work
# currency_list = []
# for currency in xchange_list:
#     currency = currency.replace("'","").lower()
#     currency_list.append(currency)
# currency_list
# ['us_dollar',
#  'japanese_yen',
#  'uk_pound',
#  'australian_dollar',
#  'israeli_shekel',
#  'philippine_peso',
#  'malaysian_ringgit',
#  'romanian_leu']

# calling logarizer on all eight currencies
c_list = [us_dollar, japanese_yen, uk_pound, australian_dollar,
          israeli_shekel, philippine_peso, malaysian_ringgit, romanian_leu]
for currency in c_list:
    logarizer(currency)
    
# calling volatizer on all eight currencies
for currency in c_list:
    volatizer(currency)

# line graph showing log exchange rates of each currency
plt.figure(figsize=(10,14))
for i, currency in zip(range(1,9), c_list):
    plt.subplot(4,2,i)
    currency["log_rate"].plot.hist(bins=50)
#     plt.title(currency) # will get ValueError: The truth value of a DataFrame is ambiguous. Use a.empty, a.bool(), a.item(), a.any() or a.all().
plt.show()

# plt.title("Romanian volatility: " + str(romanian_leu["volatility"]) + "%")

volatility_dict

# import geopandas and other libraries
import geopandas as gpd
import seaborn as sns
import os
map_data = gpd.read_file("World_Countries__Generalized_.shp")
map_data["Volatility"] = None
map_data.head()

map_data.shape
# map_data.plot(figsize=(15,13))
# map_data[map_data["COUNTRY"] == "United States"].plot(color = "green")