def run(self, observed, expected=None, conditions_list=None,
measure='Measure', alpha=0.05):
"""
"""
chisq, prob, df, expected = _stats.lchisquare(observed, expected)
try:
lnchisq, lnprob, lndf, lnexpected = \
_stats.llnchisquare(observed, expected)
except:
lnchisq, lnprob, lndf, lnexpected = 'nan','nan','nan','nan'
self.observed = observed
self.expected = expected
self.alpha = alpha
if conditions_list == None:
self.conditions_list = []
abc = lambda i : 'ABCDEFGHIJKLMNOPQRSTUVWXYZ'\
[i%26]*(int(math.floor(i/26))+1)
for i in _xrange(len(observed)):
self.conditions_list.append(abc(i))
else:
self.conditions_list = conditions_list
self['chisq'] = chisq
self['p'] = prob
self['df'] = df
self['lnchisq'] = lnchisq
self['lnp'] = lnprob
self['lndf'] = lndf
self['N'] = sum(observed)
self.observed = observed
self.expected = expected
p_observed = [v/float(self['N']) for v in observed]
p_expected = [v/float(self['N']) for v in expected]
p_chisq = sum([(po-pe)**2/pe for po,pe in zip(p_observed,p_expected)])
self['w'] = math.sqrt(p_chisq)
self['lambda'] = p_chisq*self['N']
self['crit_chi2'] = scipy.stats.chi2.ppf((1.-alpha),df)
self['power'] = 1. - ncx2cdf(self['crit_chi2'],df,self['lambda'])
def run(self, row_factor, col_factor, alpha=0.05):
"""
runs a 2-way chi square on the matched data in row_factor
and col_factor.
"""
if len(row_factor) != len(col_factor):
raise Exception('row_factor and col_factor must be equal lengths')
counter = Counter()
row_counter = Counter()
col_counter = Counter()
for r, c in zip(row_factor, col_factor):
counter[(r, c)] += 1.
row_counter[r] += 1.
col_counter[c] += 1.
N = float(sum(counter.values()))
observed = []
expected = []
for r in sorted(row_counter):
observed.append([])
expected.append([])
for c in sorted(col_counter):
observed[-1].append(counter[(r, c)])
expected[-1].append((row_counter[r] * col_counter[c]) / N)
N_r, N_c = len(row_counter), len(col_counter)
df = (N_r - 1) * (N_c - 1)
chisq = sum((o - e)**2 / e
for o, e in zip(_flatten(observed), _flatten(expected)))
prob = _stats.chisqprob(chisq, df)
try:
lnchisq = 2. * sum(
o * math.log(o / e)
for o, e in zip(_flatten(observed), _flatten(expected)))
lnprob = _stats.chisqprob(lnchisq, df)
except:
lnchisq = 'nan'
lnprob = 'nan'
if N_r == N_c == 2:
ccchisq = sum(
(abs(o - e) - 0.5)**2 / e
for o, e in zip(_flatten(observed), _flatten(expected)))
ccprob = _stats.chisqprob(ccchisq, df)
else:
ccchisq = None
ccprob = None
def rprob(r, df):
TINY = 1e-30
t = r * math.sqrt(df / ((1.0 - r + TINY) * (1.0 + r + TINY)))
return _stats.betai(0.5 * df, 0.5, df / (df + t * t))
k = min([N_r, N_c])
cramerV = math.sqrt(chisq / (N * (k - 1)))
cramerV_prob = rprob(cramerV, N - 2)
C = math.sqrt(chisq / (chisq + N))
C_prob = rprob(C, N - 2)
self['chisq'] = chisq
self['p'] = prob
self['df'] = df
self['lnchisq'] = lnchisq
self['lnp'] = lnprob
self['ccchisq'] = ccchisq
self['ccp'] = ccprob
self['N'] = N
self['C'] = C
self['CramerV'] = cramerV
self['CramerV_prob'] = cramerV_prob
self['C'] = C
self['C_prob'] = C_prob
self.counter = counter
self.row_counter = row_counter
self.col_counter = col_counter
self.N_r = N_r
self.N_c = N_c
p_observed = [v / float(self['N']) for v in _flatten(observed)]
p_expected = [v / float(self['N']) for v in _flatten(expected)]
p_chisq = sum([(po - pe)**2 / pe
for po, pe in zip(p_observed, p_expected)])
self['w'] = math.sqrt(p_chisq)
self['lambda'] = p_chisq * self['N']
self['crit_chi2'] = scipy.stats.chi2.ppf((1. - alpha), df)
self['power'] = 1. - ncx2cdf(self['crit_chi2'], df, self['lambda'])
def run(self, row_factor, col_factor, alpha=0.05):
"""
runs a 2-way chi square on the matched data in row_factor
and col_factor.
"""
if len(row_factor) != len(col_factor):
raise Exception('row_factor and col_factor must be equal lengths')
counter = Counter()
row_counter= Counter()
col_counter= Counter()
for r,c in zip(row_factor, col_factor):
counter[(r,c)] += 1.
row_counter[r] += 1.
col_counter[c] += 1.
N = float(sum(counter.values()))
observed = []
expected = []
for r in sorted(row_counter):
observed.append([])
expected.append([])
for c in sorted(col_counter):
observed[-1].append(counter[(r,c)])
expected[-1].append((row_counter[r]*col_counter[c])/N)
N_r, N_c = len(row_counter), len(col_counter)
df = (N_r - 1) * (N_c - 1)
chisq = sum((o-e)**2/e for o,e in
zip(_flatten(observed),_flatten(expected)))
prob = _stats.chisqprob(chisq, df)
try:
lnchisq = 2.*sum(o*math.log(o/e) for o,e in
zip(_flatten(observed),_flatten(expected)))
lnprob = _stats.chisqprob(lnchisq, df)
except:
lnchisq = 'nan'
lnprob = 'nan'
if N_r == N_c == 2:
ccchisq = sum((abs(o-e)-0.5)**2/e for o,e in
zip(_flatten(observed),_flatten(expected)))
ccprob = _stats.chisqprob(ccchisq, df)
else:
ccchisq = None
ccprob = None
def rprob(r,df):
TINY = 1e-30
t = r*math.sqrt(df/((1.0-r+TINY)*(1.0+r+TINY)))
return _stats.betai(0.5*df,0.5,df/(df+t*t))
k = min([N_r, N_c])
cramerV = math.sqrt(chisq/(N*(k-1)))
cramerV_prob = rprob(cramerV, N-2)
C = math.sqrt(chisq/(chisq + N))
C_prob = rprob(C, N-2)
self['chisq'] = chisq
self['p'] = prob
self['df'] = df
self['lnchisq'] = lnchisq
self['lnp'] = lnprob
self['ccchisq'] = ccchisq
self['ccp'] = ccprob
self['N'] = N
self['C'] = C
self['CramerV'] = cramerV
self['CramerV_prob'] = cramerV_prob
self['C'] = C
self['C_prob'] = C_prob
self.counter = counter
self.row_counter = row_counter
self.col_counter = col_counter
self.N_r = N_r
self.N_c = N_c
p_observed = [v/float(self['N']) for v in _flatten(observed)]
p_expected = [v/float(self['N']) for v in _flatten(expected)]
p_chisq = sum([(po-pe)**2/pe for po,pe in zip(p_observed,p_expected)])
self['w'] = math.sqrt(p_chisq)
self['lambda'] = p_chisq*self['N']
self['crit_chi2'] = scipy.stats.chi2.ppf((1.-alpha),df)
self['power'] = 1. - ncx2cdf(self['crit_chi2'],df,self['lambda'])
