Added function docs

kcbo/statistical_tests/beta_binomial_difference.py

@@ -106,4 +106,30 @@ def generate_text_description(self, summary_data):
  return description
 
 def conversion_test(dataframe, groups=None, groupcol='group', successcol='conversions', totalcol='total', samples=100000, **kwargs):
+ """Beta-Binomial model Conversion t_test.py
+
+ Given a dataframe of the form:
+
+ |Group|Successes|Total|
+ |-----|---------|-----|
+ |A | <int>|<int>|
+ |B | <int>|<int>|
+ ...
+
+ Compute estimates of the true proportion of successes and compare proportions from different groups.
+
+
+ Inputs:
+ dataframe -- Pandas dataframe of form above
+ groups -- (optional) list of groups to look at. Excluded looks at all groups
+ groupcol -- string for indexing dataframe column for groups
+ successcol -- string for indexing dataframe column for number of succcesses
+ totalcol -- string for indexing dataframe column for group totals
+
+ Returns:
+ (description, raw_data)
+ description: table describing output data
+ raw_data: dictionary of output data
+
+ """
  return BetaBinomialTest(dataframe, groups, groupcol, successcol, totalcol, samples, **kwargs).summary()

kcbo/statistical_tests/lognormal_comparison_test.py

@@ -137,6 +137,32 @@ def generate_text_description(self, summary_data):
 
 
 def lognormal_comparison_test(dataframe, groups=None, groupcol='group', valuecol='value', **kwargs):
+ """Lognormal Median Comparison
+
+ Given a dataframe of the form:
+
+ |Group |Observed Value|
+ |-------|--------------|
+ |<group>| <float>|
+ ...
+
+ Compute estimates of the difference of medians between groups.
+
+ Note: This test assumes that input comes from distributions with the same variance.
+
+ Inputs:
+ dataframe -- Pandas dataframe of form above
+ groups -- (optional) list of groups to look at. Excluded looks at all groups
+ groupcol -- string for indexing dataframe column for groups
+ valuecol -- string for indexing dataframe column for values of observations
+
+ Returns:
+ (description, raw_data)
+ description: table describing output data
+ raw_data: dictionary of output data
+
+ """
+
  results = LognormalMedianComparison(
  dataframe, groups=None, groupcol='group', valuecol='value', **kwargs)
  return results.summary()

kcbo/statistical_tests/t_test.py

@@ -37,6 +37,7 @@ def initialize_test(self, dataframe, groups=None, groupcol='group', valuecol='va
  self.burns = burns
  self.thin = thin
 
+ self.progress_bar = kwargs.get('progress_bar',False)
  if self.delay_statistic != True:
  local_vars = locals()
  del local_vars['self']
@@ -106,7 +107,7 @@ def run_model(self, key, df=None, groups=None, groupcol=None, valuecol=None, poo
 
  # Generate our MCMC object and run sampler
  mcmc = pm.MCMC(model)
- mcmc.sample(iter=samples, burn=burns, thin=thin, progress_bar=False)
+ mcmc.sample(iter=samples, burn=burns, thin=thin, progress_bar=self.progress_bar)
 
  self.mcmcs[key] = mcmc
  self.complete_key(key)
@@ -197,6 +198,36 @@ def generate_text_description(self, summary_data):
 
 
 def t_test(df, groups=None, groupcol='group', valuecol='value', pooling='default', samples=40000, burns=10000, thin=1, *args, **kwargs):
+ """Bayesian t-Test
+
+ Given a dataframe of the form:
+
+ |Group |Observed Value|
+ |-------|--------------|
+ |<group>| <float>|
+ ...
+
+ Perform pairwise t-Tests on groups
+
+ Inputs:
+ dataframe -- Pandas dataframe of form above
+ groups -- (optional) list of groups to look at. Excluded looks at all groups
+ groupcol -- string for indexing dataframe column for groups
+ valuecol -- string for indexing dataframe column for values of observations
+ pooling -- strategy for using pooled data in test. 
+ * 'default' -- uses pairwise pooled data
+ * 'all' -- uses pooled data from all groups
+ samples -- number of samples to use in MCMC
+ burns -- number of burns to use in MCMC
+ thin -- thinning to use in MCMC
+ progress_bar -- boolean, show progress bar of sampler (PyMC progress bar)
+
+ Returns:
+ (description, raw_data)
+ description: table describing output data
+ raw_data: dictionary of output data
+
+ """
  test = TTest(df, groups, groupcol, valuecol,
  pooling, samples, burns, thin, *args, **kwargs)
  return test.summary()