def plot_index(index_name, benchmark_name):
# Load Index Data File
index_path = c.path_dict['index']
index_file = c.file_dict['index_r'] % index_name
df = u.read_csv(index_path + index_file)
# Plot Figure
fig, (ax1, ax2, ax3) = plt.subplots(3, sharex=True)
fig.set_size_inches(32, 18)
# Define Font
font = {
'family': 'serif',
'color': 'black',
'weight': 'normal',
'size': 18,
}
# Plot Sub-figure 1
title = '%s vs. %s' % (index_name, benchmark_name)
ax1.set_title(title, fontdict=font)
ax1.set_xlabel('', fontdict=font)
ax1.set_ylabel('Ratio', fontdict=font)
for column in ['ratio', 'b_ratio']:
df.plot(x='date', y=column, ax=ax1)
# Plot Sub-figure 2
title = 'Index %s' % index_name
ax2.set_title(title, fontdict=font)
ax2.set_xlabel('', fontdict=font)
ax2.set_ylabel('Close Price', fontdict=font)
df.plot(x='date', y='index', ax=ax2)
# Plot Sub-figure 3
title = 'Index %s' % benchmark_name
ax3.set_title(title, fontdict=font)
ax3.set_xlabel('', fontdict=font)
ax3.set_ylabel('Close Price', fontdict=font)
df.plot(x='date', y='b_index', ax=ax3)
# Common Format for Both Sub-figures
for ax in [ax1, ax2, ax3]:
ax.grid(True)
fig.autofmt_xdate()
fig.tight_layout()
plt.setp(plt.gca().get_xticklabels(), rotation=30)
plt.show()
# Save Figure
fig_key = 'fig_index'
fig_path = c.path_dict[fig_key]
fig_file = c.file_dict[fig_key] % (index_name + '_' +
u.dateToStr(u.today()))
u.saveFigure(fig, fig_path, fig_file)
def plot_index_series(index_names, series_name, benchmark_name):
# Load Index Data Files
series_path = c.path_dict['index']
series_file = c.file_dict['index_r'] % series_name
df = u.read_csv(series_path + series_file)
# Plot Figure
fig = plt.figure(figsize=(32, 18), dpi=72, facecolor="white")
axes = plt.subplot(111)
axes.cla() # Clear Axes
# Define Font
font = {
'family': 'serif',
'color': 'black',
'weight': 'normal',
'size': 18,
}
# Plot Sub-figure 1
title = '%s vs. %s' % (series_name, benchmark_name)
plt.title(title, fontdict=font)
axes.set_xlabel('', fontdict=font)
axes.set_ylabel('Ratio', fontdict=font)
df.plot(x='date',
y='ratio_benchmark',
ax=axes,
color='grey',
lw=2.0,
ls='--')
index_number = len(index_names)
for i in range(index_number):
index_name = index_names[i]
column = 'ratio_' + index_name
df.plot(x='date', y=column, ax=axes)
# Common Format for Both Sub-figures
axes.grid(True)
fig.autofmt_xdate()
fig.tight_layout()
plt.setp(plt.gca().get_xticklabels(), rotation=30)
plt.show()
# Save Figure
fig_key = 'fig_index'
fig_path = c.path_dict[fig_key]
fig_file = c.file_dict[fig_key] % (series_name + '_' +
u.dateToStr(u.today()))
u.saveFigure(fig, fig_path, fig_file)
def getDailyHFQ(stock_id, is_index, date_start, date_end, time_to_market, incremental):
hfq = None
# For incremental update, use the next day of last update as the date start.
if incremental:
hfq = loadDailyHFQ(stock_id, is_index)
if not u.isNoneOrEmpty(hfq):
hfq.set_index('date',inplace=True)
hfq.sort_index(ascending=True,inplace=True)
last_day = hfq.index[len(hfq)-1]
date_start = u.nextDayFromStr(last_day)
# Check if existing data file is already up-to-date
if date_end < date_start:
return
# Download
if gs.is_debug:
print('Download Daily HFQ: %s, start=%s, end=%s' % (stock_id, u.dateToStr(date_start), u.dateToStr(date_end)))
df = get_daily_hfq(stock_id=stock_id, is_index=is_index, date_start=date_start,
date_end=date_end, time_to_market=time_to_market)
if not u.isNoneOrEmpty(df):
# Default df has 'date' set as index with type pandas.tslib.Timestamp,
# so merged results will contain 00:00:00 along with date.
# With below series of operation, index of df will be converted to type
# str, thus avoid above issue.
df.reset_index(inplace=True)
df['date'] = df['date'].map(lambda x:str(x.date()))
df.set_index('date',inplace=True)
df.sort_index(ascending=True,inplace=True)
# For incremental update, merge data
if incremental:
if (not u.isNoneOrEmpty(df)) and (not u.isNoneOrEmpty(hfq)):
df = hfq.append(df)
# Format Columns
if not u.isNoneOrEmpty(df):
for column in ['open', 'high', 'close', 'low', 'volume', 'amount', 'factor']:
df[column] = df[column].map(lambda x:'%.3f' % float(x))
# Save to CSV File
if not u.isNoneOrEmpty(df):
u.to_csv(df, c.path_dict['lshq'], c.file_dict['lshq'] % u.stockFileName(stock_id, is_index))
def plot_coefficient_price(stock_ids, allprice, postfix, series_name,
benchmark_name):
# If want to debug benchmark only (without stocks), set below flag to True.
debug_benchmark_only = False
# Extract Stock Prices and Normalize Them
row_number = len(allprice)
stock_number = len(stock_ids)
columns = ['date', benchmark_name]
if not debug_benchmark_only:
for i in range(stock_number):
stock_id = u.stockID(stock_ids[i])
columns.append(stock_id)
prices = u.createDataFrame(row_number, columns)
prices['date'] = allprice['date']
prices[benchmark_name] = allprice['close']
if not debug_benchmark_only:
for i in range(stock_number):
stock_id = u.stockID(stock_ids[i])
prices[stock_id] = allprice['close_' + stock_id]
if debug_benchmark_only:
print('Original Price')
print(prices)
# Normalize Price
for i in range(1, len(columns)):
column = columns[i]
prices[column] = normalize_price(prices[column])
if debug_benchmark_only:
print('Normalized Price')
print(prices)
# Calculate Relative Price w.r.t. First Valid Price
for i in range(1, len(columns)):
column = columns[i]
row = -1
for j in range(row_number):
if not np.isnan(prices.ix[j, column]): # Find first valid price
row = j
break
if row != -1:
if debug_benchmark_only:
print('Row =', row)
ref_price = prices.ix[
row,
column] # Need to be cached in the first place as it will be normalized to one later.
for j in range(row, row_number):
cur_price = prices.ix[j, column]
if not np.isnan(cur_price):
prices.ix[
j, column] = 1.0 + (cur_price - ref_price) / ref_price
if debug_benchmark_only:
print('Relative Price')
print(prices)
# Plot Figure
fig = plt.figure(figsize=(32, 18), dpi=72, facecolor="white")
axes = plt.subplot(111)
axes.cla() # Clear Axes
# Define Font
font = {
'family': 'serif',
'color': 'black',
'weight': 'normal',
'size': 18,
}
# Plot Sub-figure 1
title = '%s vs. %s' % (series_name, benchmark_name)
plt.title(title, fontdict=font)
axes.set_xlabel('', fontdict=font)
axes.set_ylabel('Ratio', fontdict=font)
prices.plot(x='date',
y=benchmark_name,
ax=axes,
color='grey',
lw=2.0,
ls='--')
if not debug_benchmark_only:
for i in range(stock_number):
column = u.stockID(stock_ids[i])
prices.plot(x='date', y=column, ax=axes)
# Common Format for Both Sub-figures
axes.grid(True)
fig.autofmt_xdate()
fig.tight_layout()
plt.setp(plt.gca().get_xticklabels(), rotation=30)
plt.show()
# Save Figure
fig_key = 'fig_coef'
fig_path = c.path_dict[fig_key]
fig_name = '_'.join(
[postfix, series_name, 'vs', benchmark_name,
u.dateToStr(u.today())])
fig_file = c.file_dict[fig_key] % fig_name
u.saveFigure(fig, fig_path, fig_file)