def make_report(title, ordered_cities):
def make_detail_line(city):
return {
'city': city,
'median_price': median_prices[city],
'median_price_index': median_prices_indices[city],
'n_trades': n_trades[city],
'n_trades_index': n_trades_indices[city],
}
c = ColumnsTable((
('city', 30, '%30s', ('', '', '', '', '', 'City'), 'city name'),
('median_price', 7, '%7.0f', ('', '', '', '', 'median', 'price'),
'median price in city'),
('median_price_index', 7, '%7.2f', ('median', 'price', '/',
'overall', 'median', 'price'),
'median price as fraction of overall median price'),
('n_trades', 7, '%7.0f', ('', '', '', '', 'number', 'trades'),
'number of trades across all months'),
('n_trades_index', 7, '%7.2f', ('number', 'trades', '/ ',
'overall', 'median', 'trades'),
'median number trades as fraction of overall median number of trades'
),
))
for city in ordered_cities:
c.append_detail(**make_detail_line(city))
c.append_legend(40)
r = Report()
r.append(title)
r.append(' ')
for line in c.iterlines():
r.append(line)
return r
class ChartCDReport(object):
def __init__(self, column_definitions, test):
self._column_definitions = column_definitions
self._test = test
self._report = Report()
cd = self._column_definitions.defs_for_columns(
'validation_month',
'rank',
'median_absolute_error',
'median_price',
'model',
'n_months_back',
'max_depth',
'n_estimators',
'max_features',
'learning_rate',
'alpha',
'l1_ratio',
'units_X',
'units_y',
)
self._ct = ColumnsTable(columns=cd, verbose=True)
self._header()
def append(self, line):
self._report.append(line)
def write(self, path):
self._ct.append_legend()
for line in self._ct.iterlines():
self._report.append(line)
if self._test:
self._report.append('** TESTING: DISCARD')
self._report.write(path)
def _header(self):
self._report.append(
'Median Absolute Error (MAE) by month for best-performing models and their hyperparameters'
)
self._report.append(' ')
def append_detail(self, **kwds):
with_spaces = {
k:
(None if self._column_definitions.replace_by_spaces(k, v) else v)
for k, v in kwds.iteritems()
}
self._ct.append_detail(**with_spaces)
def make_table_stats(data, control, in_report_p):
'return Report with statistics for years and months that obey the filter'
r = Report()
r.append('Prices by Month')
r.append('')
ct = ColumnsTable((
('year', 4, '%4d', (' ', ' ', 'year'), 'year of transaction'),
('month', 5, '%5d', (' ', ' ', 'month'), 'month of transaction'),
('mean_price', 6, '%6.0f', (' ', ' mean', 'price'),
'mean price in dollars'),
('median_price', 6, '%6.0f', (' ', 'median', 'price'),
'median price in dollars'),
('mean_price_ratio', 6, '%6.3f', (' mean', ' price', ' ratio'),
'ratio of price in current month to prior month'),
('median_price_ratio', 6, '%6.3f', ('median', ' price', ' ratio'),
'ratio of price in current month to prior month'),
('number_trades', 6, '%6d', ('number', 'of', 'trades'),
'number of trades in the month'),
))
prior_mean_price = None
prior_median_price = None
for year in (2003, 2004, 2005, 2006, 2007, 2008, 2009):
for month in (1, 2, 3) if year == 2009 else (1, 2, 3, 4, 5, 6, 7, 8, 9,
10, 11, 12):
if in_report_p(year, month):
selected = data.month == Month(year, month)
prices = data[selected].price
mean_price = prices.mean()
median_price = prices.median()
number_trades = len(prices)
ct.append_detail(
year=year,
month=month,
mean_price=mean_price,
median_price=median_price,
mean_price_ratio=None if prior_mean_price is None else
mean_price / prior_mean_price,
median_price_ratio=None if prior_median_price is None else
median_price / prior_median_price,
number_trades=number_trades,
)
prior_mean_price = mean_price
prior_median_price = median_price
ct.append_legend()
for line in ct.iterlines():
r.append(line)
return r
class ChartEReport(object):
def __init__(self, k, ensemble_weighting, column_definitions, test):
self._column_definitions = column_definitions
self._test = test
self._report = Report()
self._header(k, ensemble_weighting)
cd = self._column_definitions.defs_for_columns(
'validation_month',
'model',
'n_months_back',
'n_estimators',
'max_features',
'max_depth',
'learning_rate',
'rank',
'weight',
'mae_validation',
'mae_query',
'mae_ensemble',
)
self._ct = ColumnsTable(columns=cd, verbose=True)
def write(self, path):
self._ct.append_legend()
for line in self._ct.iterlines():
self._report.append(line)
if self._test:
self._report.append('** TESTING: DISCARD')
self._report.write(path)
def detail_line(self, **kwds):
with_spaces = {
k:
(None if self._column_definitions.replace_by_spaces(k, v) else v)
for k, v in kwds.iteritems()
}
self._ct.append_detail(**with_spaces)
def _header(self, k, ensemble_weighting):
self._report.append(
'Performance of Best Models Separately and as an Ensemble')
self._report.append(' ')
self._report.append('Considering Best K = %d models' % k)
self._report.append('Ensemble weighting: %s' % ensemble_weighting)
class ChartHReport(object):
def __init__(self, k, validation_month, ensemble_weighting,
column_definitions, test):
self._column_definitions = column_definitions
self._report = Report()
self._test = test
self._header(k, validation_month, ensemble_weighting)
cd = self._column_definitions.defs_for_columns(
'description',
'mae_validation',
'mae_query',
'mare_validation',
'mare_query',
)
self._ct = ColumnsTable(columns=cd, verbose=True)
def write(self, path):
self._ct.append_legend()
for line in self._ct.iterlines():
self._report.append(line)
if self._test:
self._report.append('** TESTING: DISCARD')
self._report.write(path)
def detail_line(self, **kwds):
with_spaces = {
k:
(None if self._column_definitions.replace_by_spaces(k, v) else v)
for k, v in kwds.iteritems()
}
self._ct.append_detail(**with_spaces)
def preformatted_line(self, line):
print line
self._ct.append_line(line)
def _header(self, k, validation_month, ensemble_weighting):
self._report.append(
'Performance of Best Models Separately and as an Ensemble')
self._report.append(' ')
self._report.append('Considering Best K = %d models' % k)
self._report.append('For validation month %s' % validation_month)
self._report.append('Ensemble weighting: %s' % ensemble_weighting)
class ChartFReport(object):
def __init__(self, k, ensemble_weighting, column_definitions, test):
self._column_definitions = column_definitions
self._test = test
self._report = Report()
self._header(k, ensemble_weighting)
cd = self._column_definitions.defs_for_columns(
'validation_month',
'mae_index0',
'mae_ensemble',
'mae_best_next_month',
'median_price',
'fraction_median_price_next_month_index0',
'fraction_median_price_next_month_ensemble',
'fraction_median_price_next_month_best',
)
self._ct = ColumnsTable(columns=cd, verbose=True)
def write(self, path):
self._ct.append_legend()
for line in self._ct.iterlines():
self._report.append(line)
if self._test:
self._report.append('** TESTING: DISCARD')
self._report.write(path)
def detail_line(self, **kwds):
with_spaces = {
k:
(None if self._column_definitions.replace_by_spaces(k, v) else v)
for k, v in kwds.iteritems()
}
self._ct.append_detail(**with_spaces)
def _header(self, k, ensemble_weighting):
self._report.append(
'Comparison of Errors of Ensemble and Best Model That Know the Future'
)
self._report.append(' ')
self._report.append('Considering Best K = %d models' % k)
self._report.append('Ensemble weighting: %s' % ensemble_weighting)
class ChartBReport(object):
def __init__(self, validation_month, k, column_definitions, test):
self._report = Report()
self._header(validation_month, k)
self._column_definitions = column_definitions
self._test = test
cd = self._column_definitions.defs_for_columns(
'median_absolute_error',
'model',
'n_months_back',
'max_depth',
'n_estimators',
'max_features',
'learning_rate',
)
self._ct = ColumnsTable(columns=cd, verbose=True)
def _header(self, validation_month, k):
def a(line):
self._report.append(line)
a('MAE for %d best-performing models and their hyperparameters' % k)
a('Validation month: %s' % validation_month)
a(' ')
def append_detail(self, **kwds):
# replace NaN with None
with_spaces = {
k:
(None if self._column_definitions.replace_by_spaces(k, v) else v)
for k, v in kwds.iteritems()
}
self._ct.append_detail(**with_spaces)
def write(self, path):
self._ct.append_legend()
for line in self._ct.iterlines():
self._report.append(line)
if self._test:
self._report.append('**TESTING: DISCARD')
self._report.write(path)
def make_chart_stats(data, control, filter_f):
'return Report with statistics for years and months that obey the filter'
r = Report()
r.append('Prices by Month')
r.append('')
ct = ColumnsTable((
('year', 4, '%4d', (' ', ' ', 'year'), 'year of transaction'),
('month', 5, '%5d', (' ', ' ', 'month'), 'month of transaction'),
('mean_price', 6, '%6.0f', (' ', ' mean', 'price'), 'mean price in dollars'),
('median_price', 6, '%6.0f', (' ', 'median', 'price'), 'median price in dollars'),
('mean_price_ratio', 6, '%6.3f', (' mean', ' price', ' ratio'), 'ratio of price in current month to prior month'),
('median_price_ratio', 6, '%6.3f', ('median', ' price', ' ratio'), 'ratio of price in current month to prior month'),
('number_trades', 6, '%6d', ('number', 'of', 'trades'), 'number of trades in the month'),
))
prior_mean_price = None
prior_median_price = None
for year in xrange(2003, 2010):
for month in xrange(1, 13):
if filter_f(year, month):
value = data[make_reduction_key(year, month)]
mean_price = value['mean']
median_price = value['median']
number_trades = value['count']
ct.append_detail(
year=year,
month=month,
mean_price=mean_price,
median_price=median_price,
mean_price_ratio=None if prior_mean_price is None else mean_price / prior_mean_price,
median_price_ratio=None if prior_median_price is None else median_price / prior_median_price,
number_trades=number_trades,
)
prior_mean_price = mean_price
prior_median_price = median_price
ct.append_legend()
for line in ct.iterlines():
r.append(line)
return r
