本文整理汇总了Python中scipy.stats.f.sf方法的典型用法代码示例。如果您正苦于以下问题：Python f.sf方法的具体用法？Python f.sf怎么用？Python f.sf使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类scipy.stats.f的用法示例。
在下文中一共展示了f.sf方法的3个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: __init__
# 需要导入模块: from scipy.stats import f [as 别名]
# 或者: from scipy.stats.f import sf [as 别名]
def __init__(self, t=None, F=None, sd=None, effect=None, df_denom=None,
df_num=None, alpha=0.05, **kwds):
self.effect = effect # Let it be None for F
if F is not None:
self.distribution = 'F'
self.fvalue = F
self.statistic = self.fvalue
self.df_denom = df_denom
self.df_num = df_num
self.dist = fdist
self.dist_args = (df_num, df_denom)
self.pvalue = fdist.sf(F, df_num, df_denom)
elif t is not None:
self.distribution = 't'
self.tvalue = t
self.statistic = t # generic alias
self.sd = sd
self.df_denom = df_denom
self.dist = student_t
self.dist_args = (df_denom,)
self.pvalue = self.dist.sf(np.abs(t), df_denom) * 2
elif 'statistic' in kwds:
# TODO: currently targeted to normal distribution, and chi2
self.distribution = kwds['distribution']
self.statistic = kwds['statistic']
self.tvalue = value = kwds['statistic'] # keep alias
# TODO: for results instance we decided to use tvalues also for normal
self.sd = sd
self.dist = getattr(stats, self.distribution)
self.dist_args = ()
if self.distribution is 'chi2':
self.pvalue = self.dist.sf(self.statistic, df_denom)
else:
"normal"
self.pvalue = self.dist.sf(np.abs(value)) * 2
# cleanup
# should we return python scalar?
self.pvalue = np.squeeze(self.pvalue) 示例2: pvalues
# 需要导入模块: from scipy.stats import f [as 别名]
# 或者: from scipy.stats.f import sf [as 别名]
def pvalues(self):
"""
(array) The p-values associated with the z-statistics of the
coefficients. Note that the coefficients are assumed to have a Normal
distribution.
"""
return norm.sf(np.abs(self.zvalues)) * 2 示例3: __init__
# 需要导入模块: from scipy.stats import f [as 别名]
# 或者: from scipy.stats.f import sf [as 别名]
def __init__(self, statistic, distribution, dist_args, table=None,
pvalues=None):
self.table = table
self.distribution = distribution
self.statistic = statistic
#self.sd = sd
self.dist_args = dist_args
# The following is because I don't know which we want
if table is not None:
self.statistic = table['statistic'].values
self.pvalues = table['pvalue'].values
self.df_constraints = table['df_constraint'].values
if self.distribution == 'F':
self.df_denom = table['df_denom'].values
else:
if self.distribution is 'chi2':
self.dist = stats.chi2
self.df_constraints = self.dist_args[0] # assumes tuple
# using dist_args[0] is a bit dangerous,
elif self.distribution is 'F':
self.dist = stats.f
self.df_constraints, self.df_denom = self.dist_args
else:
raise ValueError('only F and chi2 are possible distribution')
if pvalues is None:
self.pvalues = self.dist.sf(np.abs(statistic), *dist_args)
else:
self.pvalues = pvalues