updated readme, setup.py, and docs in anticipation of 1.1.1 release

rishi-kulkarni · Jun 11, 2021 · 1b41aa6 · 1b41aa6
1 parent cab235d
commit 1b41aa6
Show file tree

Hide file tree

Showing 6 changed files with 41 additions and 27 deletions.
diff --git a/README.md b/README.md
@@ -2,7 +2,7 @@
 
 ## A Hierarchical Resampling Package for Python
 
-Version 1.1
+Version 1.1.1
 
 hierarch is a package for hierarchical resampling (bootstrapping, permutation) of datasets in Python. Because for loops are ultimately intrinsic to cluster-aware resampling, hierarch uses Numba to accelerate many of its key functions.
 

diff --git a/docs/user/confidence.rst b/docs/user/confidence.rst
@@ -65,7 +65,7 @@ confidence interval. ::
 
     from hierarch.stats import confidence_interval
 
-    ha.stats.confidence_interval(
+    confidence_interval(
     data,
     treatment_col=0,
     compare='means',
@@ -84,7 +84,7 @@ Because ha.stats.confidence_interval is based on a hypothesis test, it requires
 the same input parameters as hypothesis_test. However, 
 the new **interval** parameter determines the width of the interval. ::
 
-    ha.stats.confidence_interval(
+    confidence_interval(
     data,
     treatment_col=0,
     compare='means',
@@ -96,7 +96,7 @@ the new **interval** parameter determines the width of the interval. ::
 
     (-0.9086402840632387, 0.25123067872990457)
 
-    ha.stats.confidence_interval(
+    confidence_interval(
     data,
     treatment_col=0,
     compare='means',
@@ -141,7 +141,8 @@ this value. You can test this with the following code. ::
 
     for i in range(loops):
         data = sim.generate()
-        lower, upper = ha.stats.confidence_interval(data, 0, interval=95, bootstraps=100, permutations='all')
+        lower, upper = confidence_interval(data, 0, interval=95, 
+                                           bootstraps=100, permutations='all')
         if lower <= true_difference <= upper:
             coverage += 1
 
@@ -223,7 +224,7 @@ for **compare** when computing a confidence interval. ::
 
     from hierarch.stats import confidence_interval
 
-    ha.stats.confidence_interval(
+    confidence_interval(
     data,
     treatment_col=0,
     compare='corr',
@@ -260,7 +261,8 @@ set up a simulation as above to check the coverage of the 95% confidence interva
 
     for i in range(loops):
         data = datagen.generate()
-        lower, upper = ha.stats.confidence_interval(data, 0, interval=95, bootstraps=100, permutations='all')
+        lower, upper = confidence_interval(data, 0, interval=95, 
+                                           bootstraps=100, permutations='all')
         if lower <= true_difference <= upper:
             coverage += 1
 
@@ -279,7 +281,8 @@ interest. ::
 
     for i in range(loops):
         data = datagen.generate()
-        lower, upper = ha.stats.confidence_interval(data, 0, interval=99, bootstraps=100, permutations='all')
+        lower, upper = confidence_interval(data, 0, interval=99, 
+                                           bootstraps=100, permutations='all')
         if lower <= true_difference <= upper:
             coverage += 1
 

diff --git a/docs/user/hypothesis.rst b/docs/user/hypothesis.rst
@@ -74,7 +74,9 @@ column - in this case, "Condition." Indexing starts at 0, so you input
 treatment_col=0. In this case, there are only 6c3 = 20 ways to permute the 
 treatment labels, so you should specify "all" permutations be used. ::
 
-    p_val = ha.stats.hypothesis_test(data, treatment_col=0, compare='means',
+    from hierarch.stats import hypothesis_test
+
+    p_val = hypothesis_test(data, treatment_col=0, compare='means',
                                      bootstraps=500, permutations='all', 
                                      random_state=1)
 
@@ -84,20 +86,23 @@ treatment labels, so you should specify "all" permutations be used. ::
 
 There are a number of parameters that can be used to modify hypothesis_test. ::
 
-    ha.stats.hypothesis_test(data_array, 
-                            treatment_col, 
-                            compare="means", 
-                            skip=None, 
-                            bootstraps=100, 
-                            permutations=1000, 
-                            kind='weights', 
-                            return_null=False,
-                            random_state=None)
+    hypothesis_test(data_array, 
+                    treatment_col, 
+                    compare="means", 
+                    skip=None, 
+                    bootstraps=100, 
+                    permutations=1000, 
+                    kind='weights', 
+                    return_null=False,
+                    random_state=None)
 
 **compare**: The default "means" assumes that you are testing for a difference in means, so it uses the Welch t-statistic. 
 "corr" uses a studentized covariance based test statistic which gives the same result as the Welch t-statistic for two-sample
 datasets, but can be used on datasets with any number of related treatment groups. For flexibility, hypothesis_test can 
-also take a test statistic function as an argument. 
+also take a test statistic function as an argument.
+
+**alternative** : "two-sided" or "less" or "greater" specifies the alternative hypothesis. "two-sided" conducts
+a two-tailed test, while "less" or "greater" conduct the appropriate one-tailed test.
 
 **skip**: indicates the indices of columns that should be skipped in the bootstrapping procedure. 
 
@@ -228,6 +233,8 @@ treatment 2 represents a slight difference and treatment 4 represents a large di
 There are six total comparisons that can be made, which can be performed automatically
 using multi_sample_test as follows. ::
 
+    from hierarch.stats import multi_sample_test
+
     multi_sample_test(data, treatment_col=0, hypotheses="all",
                     correction=None, bootstraps=1000,
                     permutations="all", random_state=111)

diff --git a/docs/user/overview.rst b/docs/user/overview.rst
@@ -51,5 +51,7 @@ Here is the sort of data that hierarch is designed to perform hypothesis tests o
 
 The code to perform a hierarchical permutation t-test on this dataset looks like::
 
-    hierarch.stats.hypothesis_test(data, treatment_col=0,
-                                   bootstraps=1000, permutations='all')
+    from hierarch.stats import hypothesis_test
+
+    hypothesis_test(data, treatment_col=0,
+                    bootstraps=1000, permutations='all')
diff --git a/docs/user/power.rst b/docs/user/power.rst
@@ -91,11 +91,13 @@ permutations (though this is overkill in the 2, 3, 3 case) on each
 of 100 simulated datasets and prints the fraction of them that return 
 a significant result, assuming a p-value cutoff of 0.05. ::
 
+    from hierarch.stats import hypothesis_test
+
     pvalues = []
     loops = 100
     for i in range(loops):
         data = sim.generate()
-        pvalues.append(ha.stats.hypothesis_test(data, 0, bootstraps=500, permutations=100))
+        pvalues.append(hypothesis_test(data, 0, bootstraps=500, permutations=100))
         
     print(np.less(pvalues, 0.05).sum() / loops) 
 
@@ -111,7 +113,7 @@ you determine the column 1 sample size that achieves at least 80% power. ::
     loops = 100
     for i in range(loops):
         data = sim.generate()
-        pvalues.append(ha.stats.hypothesis_test(data, 0, bootstraps=500, permutations=100))
+        pvalues.append(hypothesis_test(data, 0, bootstraps=500, permutations=100))
         
     print(np.less(pvalues, 0.05).sum() / loops)
 
@@ -134,7 +136,7 @@ achieved with an experimental design that makes more column 2 measurements. ::
     loops = 100
     for i in range(loops):
         data = sim.generate()
-        pvalues.append(ha.stats.hypothesis_test(data, 0, bootstraps=500, permutations=100))
+        pvalues.append(hypothesis_test(data, 0, bootstraps=500, permutations=100))
         
     print(np.less(pvalues, 0.05).sum() / loops)
 
@@ -154,7 +156,7 @@ only 30 column 2 samples. ::
     loops = 100
     for i in range(loops):
         data = sim.generate()
-        pvalues.append(ha.stats.hypothesis_test(data, 0, bootstraps=500, permutations=100))
+        pvalues.append(hypothesis_test(data, 0, bootstraps=500, permutations=100))
         
     print(np.less(pvalues, 0.05).sum() / loops)
     
@@ -180,7 +182,7 @@ the error for an event that happens 5% probability is +/- 2%, but at
     loops = 1000
     for i in range(loops):
         data = sim.generate()
-        pvalues.append(ha.stats.hypothesis_test(data, 0, bootstraps=500, permutations=100))
+        pvalues.append(hypothesis_test(data, 0, bootstraps=500, permutations=100))
         
     print(np.less(pvalues, 0.05).sum() / loops)
 

diff --git a/setup.py b/setup.py
@@ -5,7 +5,7 @@
 
 setuptools.setup(
     name="hierarch",
-    version="1.1.0",
+    version="1.1.1",
     author="Rishi Kulkarni",
     author_email="[email protected]",
     description="Hierarchical hypothesis testing library",