def PrintSerialCorrelations(dailies):
"""Prints a table of correlations with different lags.
dailies: map from category name to DataFrame of daily prices
"""
filled_dailies = {}
for name, daily in dailies.items():
filled_dailies[name] = FillMissing(daily, span=30)
# print serial correlations for raw price data
for name, filled in filled_dailies.items():
corr = thinkstats2.SerialCorr(filled.ppg, lag=1)
print(name, corr)
rows = []
for lag in [1, 7, 30, 365]:
row = [str(lag)]
for name, filled in filled_dailies.items():
corr = thinkstats2.SerialCorr(filled.resid, lag)
row.append('%.2g' % corr)
rows.append(row)
print(r'\begin{tabular}{|c|c|c|c|}')
print(r'\hline')
print(r'lag & high & medium & low \\ \hline')
for row in rows:
print(' & '.join(row) + r' \\')
print(r'\hline')
print(r'\end{tabular}')
filled = filled_dailies['high']
acf = smtsa.acf(filled.resid, nlags=365, unbiased=True)
print('%0.3f, %0.3f, %0.3f, %0.3f, %0.3f' %
(acf[0], acf[1], acf[7], acf[30], acf[365]))
def TestStatistic(self, data):
"""Computes the test statistic.
data: tuple of xs and ys
"""
series, lag = data
test_stat = abs(thinkstats2.SerialCorr(series, lag))
return test_stat
def TestStatistic(self, data):
""" computes the test statistic
@param: data (tuple) - x and y values
returns
@param: test_stat
"""
series, lag = data
test_stat = abs(thinkstats2.SerialCorr(series, lag))
return test_stat
def main():
all_recs = cyb_records_2.Errors()
all_recs.ReadRecords()
print 'Number of total stats', len(all_recs.records)
clean_recs = clean_events.CleanEvents(all_recs.records)
print 'Number of clean events', len(clean_recs)
errors = CorrErrDist(clean_recs)
print 'Number of dict entries', len(errors)
for key in errors.keys():
print "Error id =", key, "Correlation =", thinkstats2.SerialCorr(
errors.get(key)), "List length =", len(errors.get(key))