# just a comment to change on github

%%javascript
IPython.OutputArea.prototype._should_scroll = function(lines) {
    return false;
}

# import libraries and set display options
import pandas as pd
import pprint

# set frame width and center output
from IPython.core.display import display, HTML
display(HTML("""
<style>
.container {width:84% !important;
}
</style>
"""))

# pretty print options
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', 3000)
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
# lower case all column names
x_rates.columns = x_rates.columns.str.replace("[","").str.replace("]","", regex=False)
# x_rates.columns = x_rates.columns.str.replace("[","").str.replace("]","", regex=True)
x_rates.columns = x_rates.columns.str.rstrip()
x_rates.columns = x_rates.columns.str.replace(" ","_", regex=False)
# x_rates.columns = x_rates.columns.str.replace(" ","_", regex=True)
x_rates.columns = x_rates.columns.str.lower()

# 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)

display(x_rates.head())

# create a us dollar to euro 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 dollar to euro exchange rate
import matplotlib.pyplot as plt
plt.rcParams.update({'figure.max_open_warning': 0})
import matplotlib.dates as mdates
plt.style.use('ggplot') # set style for graphs
fig, ax = plt.subplots(figsize=(18,10))
ax.plot(us_dollar["date"], us_dollar["rolling_mean_30"], color="royalblue", linewidth=3)
ax.set_xticks(["2000-01-04 00:00:00", "2005-01-04 00:00:00", "2010-01-04 00:00:00",
               "2015-01-04 00:00:00", "2020-01-04 00:00:00"])
ax.set_xticklabels([2000,2005,2010,2015,2020], fontsize=18, weight="bold")
# ax.set_yticks([0,0.9,1.0,1.1,1.2,1.3,1.4,1.5,1.6])
ax.set_yticklabels([0,0.9,1.0,1.1,1.2,1.3,1.4,1.5,1.6], fontsize=18, weight="bold")
ax.text(0.08, 0.0, "© B McMinn" + " "*174 + "Source: European Central Bank",
        color = "#f0f0f0", backgroundcolor = "#4d4d4d", fontsize=14,
        transform=fig.transFigure)
fig.suptitle(" "*10 + "Euro to US Dollar Currency Exchange Rates" + " "*10,
             color = "#f0f0f0", backgroundcolor = "#4d4d4d", fontsize=35, weight="bold")
plt.show()

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

# 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 dollar to euro showing NaN values with and without highlight
fig, (ax1, ax2, ax3) = plt.subplots(nrows=3, ncols=1, figsize=(18,10))
ax1.plot(us_dollar["date"], us_dollar["rolling_mean_30"], color="royalblue", linewidth=5)
# ax1.set(title="Dataset with NaN Values Included")
ax1.set_title("Dataset with NaN Values Included", fontsize=18)
ax2.plot(us_dollar["date"], us_dollar["rolling_mean_30"], color="royalblue", linewidth=5)
ax2.set_title("Dataset with Corresponding Dates in Gold", fontsize=18)
for xc in nan_days:
   ax2.axvline(x=xc, color="gold", linewidth=4)
ax3.plot(US_dollar_nonull["date"], US_dollar_nonull["rolling_mean_30"], color="salmon", linewidth=5)
ax3.set_title("Dataset with NaN Rows Removed", fontsize=18)
for ax in ax1, ax2, ax3:
    ax.set_xticks([])
    ax.set_xticklabels([])
for ax in ax1, ax2, ax3:
    ax.set_yticks([])
ax.text(0.08, 0.0, "© B McMinn" + " "*174 + "Source: European Central Bank",
        color = "#f0f0f0", backgroundcolor = "#4d4d4d", fontsize=14,
        transform=fig.transFigure)
fig.suptitle(" "*10 + "Euro to US Dollar Currency Exchange Rates" + " "*10,
             color = "#f0f0f0", backgroundcolor = "#4d4d4d", fontsize=35, weight="bold")
plt.show()

# import colormap and set up color iteration
from matplotlib.pyplot import cm
colors = iter([plt.cm.tab10(i) for i in range(8)])

# create a list of data frames for each currency with log rate of the exchange rate, 30 day rolling mean, and year
df_dict = {}
for currency in x_rates.columns[1:]:
    df_name = currency
    df = x_rates[["date", currency]].copy()
    df = df[df[currency].notna()]
    df["log_rate"] = np.log(df.iloc[:,1]/df.iloc[:,1].shift()) # getting the log of the exchange rate # double check this is the correct way to get log
    df["rolling_mean_30"] = df[currency].rolling(30).mean()
    df["year"] = df["date"].dt.year
    df_dict[currency] = df

# currencies for comparison
high_freq = [df_dict["us_dollar"], df_dict["japanese_yen"], df_dict["uk_pound"], df_dict["australian_dollar"]]
low_freq = [df_dict["israeli_shekel"], df_dict["philippine_peso"], df_dict["malaysian_ringgit"], df_dict["romanian_leu"]]

# line graph showing Euro to each high frequency trading pairs
fig, ((ax1, ax2), (ax3, ax4)) = plt.subplots(nrows=2, ncols=2, figsize=(18,10))

for ax, currency in zip((ax1, ax2, ax3, ax4), high_freq):
    ax.plot(currency["date"], currency["rolling_mean_30"], linewidth=3, c=next(colors))
for ax in ax1, ax2, ax3, ax4:
    ax.set_xticks(["2000-01-04 00:00:00", "2005-01-04 00:00:00", "2010-01-04 00:00:00",
               "2015-01-04 00:00:00", "2020-01-04 00:00:00"])
    ax.set_xticklabels([2000,2005,2010,2015,2020], fontsize=18)
    ax.set(yticks=[])
#   ax.set_ylabel(str(currency)) # why not, i can get it to change to a string "currency", but not a variable
ax1.set_ylabel("US dollar", fontsize=18, weight="bold", color="tab:blue")
ax2.set_ylabel("Japanese yen", fontsize=18, weight="bold", color="tab:orange")
ax2.yaxis.set_label_position("right")
ax3.set_ylabel("UK pound", fontsize=18, weight="bold", color="tab:green")
ax4.set_ylabel("Australian dollar", fontsize=18, weight="bold", color="tab:red")
ax4.yaxis.set_label_position("right")
plt.subplots_adjust(wspace=0.01,hspace=0.01)
ax.text(0.08, 0.0, "© B McMinn" + " "*174 + "Source: European Central Bank",
        color = "#f0f0f0", backgroundcolor = "#4d4d4d", fontsize=14,
        transform=fig.transFigure)
fig.suptitle(" "*21 + "Euro to High Frequency Pairs" + " "*21,
             color = "#f0f0f0", backgroundcolor = "#4d4d4d", fontsize=35, weight="bold")
plt.show()

# line graph showing Euro to each low frequency trading pairs
fig, ((ax1, ax2), (ax3, ax4)) = plt.subplots(nrows=2, ncols=2, figsize=(18,10), sharex=True)
for ax, currency in zip((ax1, ax2, ax3, ax4), low_freq):
    ax.plot(currency["date"], currency["rolling_mean_30"], linewidth=3, c=next(colors))
for ax in ax1, ax2, ax3, ax4:
    ax.set_xticks(["2000-01-04 00:00:00", "2005-01-04 00:00:00", "2010-01-04 00:00:00",
               "2015-01-04 00:00:00", "2020-01-04 00:00:00"])
    ax.set_xticklabels([2000,2005,2010,2015,2020], fontsize=18)
    ax.set(yticks=[])
#   ax.set_ylabel(str(currency)) # why not, i can get it to change to a string "currency", but not a variable
ax1.set_ylabel("Israeli shekel", fontsize=18, weight="bold", color="tab:purple")
ax2.set_ylabel("Philippine peso", fontsize=18, weight="bold", color="tab:brown")
ax2.yaxis.set_label_position("right")
ax3.set_ylabel("Malaysian ringgit", fontsize=18, weight="bold", color="tab:pink")
ax4.set_ylabel("Romanian leu", fontsize=18, weight="bold", color="tab:grey")
ax4.yaxis.set_label_position("right")
plt.subplots_adjust(wspace=0.01,hspace=0.01)
ax.text(0.08, 0.0, "© B McMinn" + " "*174 + "Source: European Central Bank",
        color = "#f0f0f0", backgroundcolor = "#4d4d4d", fontsize=14,
        transform=fig.transFigure)
fig.suptitle(" "*22 + "Euro to Low Frequency Pairs" + " "*22,
             color = "#f0f0f0", backgroundcolor = "#4d4d4d", fontsize=35, weight="bold")
plt.show()

# line graph showing Euro to four high frequency trading pairs overlapped
chart_date_high = (df_dict["us_dollar"]["date"])
colors = iter([plt.cm.tab10(i) for i in range(0,4)])
fig, ax = plt.subplots(figsize=(18,10))
ax1 = ax.twinx()
ax2 = ax.twinx()
ax3 = ax.twinx()
for ax, currency in zip ((ax, ax1,ax2,ax3), high_freq):
    ax.plot(chart_date_high, currency["rolling_mean_30"], linewidth=3, c=next(colors))
    ax.set_xticks(["2000-01-04 00:00:00", "2005-01-04 00:00:00", "2010-01-04 00:00:00",
               "2015-01-04 00:00:00", "2020-01-04 00:00:00"])
    ax.set_xticklabels([2000,2005,2010,2015,2020], fontsize=18)
    ax.set(yticks=[])
# Sept 11, 2001
sept11 = df_dict["us_dollar"]["date"] == "2001-09-11"
sept11 = df_dict["us_dollar"][sept11]
sept11 = sept11["date"]
ax.axvline(x=sept11, alpha=0.8, color="gold", linewidth=2)
ax.axvspan(xmin=chart_date_high.iloc[11], xmax=chart_date_high.iloc[701],
           ymax=0.97,  ymin=0.86, alpha=0.4, color='gold')
ax.text(0.165, 0.82, "9/11 attacks", color="black", fontsize=16,
        transform=fig.transFigure)
ax.text(0.165, 0.8, "in US", color="black", fontsize=16,
        transform=fig.transFigure)
# EESA
eesa = df_dict["us_dollar"]["date"] == "2008-10-03"
eesa = df_dict["us_dollar"][eesa]
eesa = eesa["date"]
ax.axvline(x=eesa, color="gold", linewidth=2)
ax.axvspan(xmin=chart_date_high.iloc[1604], xmax=chart_date_high.iloc[2504],
           ymax=0.19,  ymin=0.10, alpha=0.4, color='gold')
ax.text(0.365, 0.23, "E.E.S.A. enacted", color="black", fontsize=16,
        transform=fig.transFigure)
ax.text(0.365, 0.21, "in US", color="black", fontsize=16,
        transform=fig.transFigure)
# European Debt Crisis
# https://www.businessinsider.com/s?q=euro+forex+2012
# https://www.ecb.europa.eu/pub/pdf/scpwps/ecbwp1532.pdf
edc = df_dict["us_dollar"]["date"] == "2012-09-06"
edc = df_dict["us_dollar"][edc]
edc = edc["date"]
ax.axvline(x=edc, color="gold", linewidth=2)
ax.axvspan(xmin=chart_date_high.iloc[3508], xmax=chart_date_high.iloc[4488],
           ymax=0.97,  ymin=0.86, alpha=0.4, color='gold')
ax.text(0.60, 0.82, "ECB announces", color="black", fontsize=16,
        transform=fig.transFigure)
ax.text(0.60, 0.8, "unlimited support", color="black", fontsize=16,
        transform=fig.transFigure)
# other text
fig.suptitle(" "*12 + "Alignment of Euro/High Frequency Pairs" + " "*12,
             color = "#f0f0f0", backgroundcolor = "#4d4d4d", fontsize=35, weight="bold")
ax.text(0.75, 0.24, "US dollar", color="tab:blue", fontsize=18, weight="bold",
        transform=fig.transFigure)
ax.text(0.75, 0.21, "Japanese yen", color="tab:orange", fontsize=18, weight="bold",
        transform=fig.transFigure)
ax.text(0.75, 0.17, "UK pound", color="tab:green", fontsize=18, weight="bold",
        transform=fig.transFigure)
ax.text(0.75, 0.14, "Australian dollar", color="tab:red", fontsize=18, weight="bold",
        transform=fig.transFigure)
ax.text(0.08, 0.0, "© B McMinn" + " "*174 + "Source: European Central Bank",
        color = "#f0f0f0", backgroundcolor = "#4d4d4d", fontsize=14,
        transform=fig.transFigure)
plt.show()

# bar charts comparing volatility for four high and low frequency pairs
high_freq = [annual_volatility["us_dollar"], annual_volatility["japanese_yen"], annual_volatility["uk_pound"], annual_volatility["australian_dollar"]]
low_freq = [annual_volatility["israeli_shekel"], annual_volatility["philippine_peso"], annual_volatility["malaysian_ringgit"], annual_volatility["romanian_leu"]]
years = annual_volatility.iloc[:,40]
colors = iter([plt.cm.tab10(i) for i in range(8)])

# high_freq bar charts
fig, (ax1, ax2, ax3, ax4) = plt.subplots(nrows=1, ncols=4, figsize=(18,10), sharey=True)
for ax, currency in zip((ax1, ax2, ax3, ax4), high_freq):
    ax.barh(years, currency, height=0.65, color=next(colors), alpha=0.7)
    ax.set_xlim(0,0.21)
    ax.set_xticks([0.05, 0.1, 0.15, 0.20])
    ax.set_xticklabels(["0.05", "0.10", "0.15", "0.20"], fontsize=10, weight="bold")
    ax.set_yticks([2000, 2005, 2010, 2015, 2020])
    ax.set_yticklabels([2000, 2005, 2010, 2015, 2020], fontsize=14, weight="bold")
    ax.tick_params(axis="x", labelrotation=45)
plt.subplots_adjust(wspace=0.01,hspace=0.01)
ax.text(.22,.84,"US dollar", color="tab:blue", fontsize=16, transform=fig.transFigure)
ax.text(.40,.84,"Japanese yen", color="tab:orange", fontsize=16, transform=fig.transFigure)
ax.text(.59,.84,"UK pound", color="tab:green", fontsize=16, transform=fig.transFigure)
ax.text(.80,.84,"Australian dollar", color="tab:red", fontsize=16, transform=fig.transFigure)
ax.text(0.08, 0.0, "© B McMinn" + " "*174 + "Source: European Central Bank",
        color = "#f0f0f0", backgroundcolor = "#4d4d4d", fontsize=14,
        transform=fig.transFigure)
fig.suptitle(" "*4 + "Annual Volatility of Euro to Four Major Currencies" + " "*4,
             color = "#f0f0f0", backgroundcolor = "#4d4d4d", fontsize=35, weight="bold")
plt.show()

# low_freq bar charts
fig, (ax1, ax2, ax3, ax4) = plt.subplots(nrows=1, ncols=4, figsize=(18,10), sharey=True)
for ax, currency in zip((ax1, ax2, ax3, ax4), low_freq):
    ax.barh(years, currency, height=0.65, color=next(colors), alpha=0.7)
    ax.set_xlim(0,0.21)
    ax.set_xticks([0.05, 0.1, 0.15, 0.20])
    ax.set_xticklabels(["0.05", "0.10", "0.15", "0.20"], fontsize=10, weight="bold")
    ax.set_yticks([2000, 2005, 2010, 2015, 2020])
    ax.set_yticklabels([2000, 2005, 2010, 2015, 2020], fontsize=14, weight="bold")
    ax.tick_params(axis="x", labelrotation=45)
plt.subplots_adjust(wspace=0.01,hspace=0.01)
ax.text(.22,.84,"Israeli shekel", color="tab:purple", fontsize=16, transform=fig.transFigure)
ax.text(.40,.84,"Philippine peso", color="tab:brown", fontsize=16, transform=fig.transFigure)
ax.text(.59,.84,"Malaysian ringgit", color="tab:pink", fontsize=16, transform=fig.transFigure)
ax.text(.80,.84,"Romanian leu", color="tab:grey", fontsize=16, transform=fig.transFigure)
ax.text(0.08, 0.0, "© B McMinn" + " "*174 + "Source: European Central Bank",
        color = "#f0f0f0", backgroundcolor = "#4d4d4d", fontsize=14,
        transform=fig.transFigure)
fig.suptitle(" "*4 + "Annual Volatility of Euro to Four Minor Currencies" + " "*4,
             color = "#f0f0f0", backgroundcolor = "#4d4d4d", fontsize=35, weight="bold")
plt.show()