Merge 2bdcab3 into 388d017

sci_analysis/analysis/__init__.py

@@ -8,7 +8,7 @@
 from .stats import VectorStatistics, GroupStatistics, GroupStatisticsStacked, CategoricalStatistics
 
 
-def determine_analysis_type(data, other=None, groups=None, labels=None):
+def determine_analysis_type(data, other=None, groups=None, labels=None, order=None, dropna=None):
     """Attempts to determine the type of data and returns the corresponding sci_analysis Data object.
 
     Parameters
@@ -21,6 +21,10 @@ def determine_analysis_type(data, other=None, groups=None, labels=None):
         The group names to include if data is determined to be a Vector.
     labels : array-like or None
         The sequence of data point labels.
+    order : array-like
+        The order that categories in sequence should appear.
+    dropna : bool
+        Remove all occurances of numpy NaN.
 
     Returns
     -------
@@ -61,10 +65,10 @@ def determine_analysis_type(data, other=None, groups=None, labels=None):
                 else:
                     return Vector(data, labels=labels)
         else:
-            return Categorical(data)
+            return Categorical(data, order=order, dropna=dropna)
 
 
-def analyse(xdata, ydata=None, groups=None, labels=None, **kwargs):
+def analyse(xdata, ydata=None, groups=None, labels=None, alpha=0.05, order=None, dropna=None, **kwargs):
     """
     Alias for analyze.
 
@@ -80,6 +84,10 @@ def analyse(xdata, ydata=None, groups=None, labels=None, **kwargs):
         The sequence of data point labels.
     alpha : float
         The sensitivity to use for hypothesis tests.
+    order : array-like
+        The order that categories in sequence should appear.
+    dropna : bool
+        Remove all occurances of numpy NaN.
 
     Returns
     -------
@@ -97,10 +105,10 @@ def analyse(xdata, ydata=None, groups=None, labels=None, **kwargs):
     xdata : dict(array-like(num)), ydata : None --- Location Test(unstacked)
     xdata : array-like(num), ydata : None, groups : array-like --- Location Test(stacked)
     """
-    return analyze(xdata, ydata=ydata, groups=groups, labels=labels, **kwargs)
+    return analyze(xdata, ydata=ydata, groups=groups, labels=labels, alpha=alpha, order=order, dropna=dropna, **kwargs)
 
 
-def analyze(xdata, ydata=None, groups=None, labels=None, alpha=0.05, **kwargs):
+def analyze(xdata, ydata=None, groups=None, labels=None, alpha=0.05, order=None, dropna=None, **kwargs):
     """
     Automatically performs a statistical analysis based on the input arguments.
 
@@ -116,6 +124,10 @@ def analyze(xdata, ydata=None, groups=None, labels=None, alpha=0.05, **kwargs):
         The sequence of data point labels.
     alpha : float
         The sensitivity to use for hypothesis tests.
+    order : array-like
+        The order that categories in sequence should appear.
+    dropna : bool
+        Remove all occurances of numpy NaN.
 
     Returns
     -------
@@ -190,9 +202,9 @@ def analyze(xdata, ydata=None, groups=None, labels=None, alpha=0.05, **kwargs):
         return tested if debug else None
 
     if ydata is not None:
-        _data = determine_analysis_type(xdata, other=ydata, groups=groups, labels=labels)
+        _data = determine_analysis_type(xdata, other=ydata, groups=groups, labels=labels, order=order, dropna=dropna)
     else:
-        _data = determine_analysis_type(xdata, groups=groups, labels=labels)
+        _data = determine_analysis_type(xdata, groups=groups, labels=labels, order=order, dropna=dropna)
 
     if is_vector(_data) and not _data.other.empty:
         # Correlation and Linear Regression
@@ -273,8 +285,10 @@ def analyze(xdata, ydata=None, groups=None, labels=None, alpha=0.05, **kwargs):
             return tested if debug else None
         else:
             tested.append('Frequencies')
+            if labels is None:
+                labels = True
 
             # Show the histogram and stats
-            GraphFrequency(_data, **kwargs)
+            GraphFrequency(_data, labels=labels, **kwargs)
             CategoricalStatistics(xdata, **kwargs)
             return tested if debug else None

sci_analysis/test/test_analyze.py

@@ -486,6 +486,33 @@ def test_142_stacked_oneway_missing_groups(self):
                                  save_to='{}test_analyze_142'.format(self.save_path)),
                          ['Stacked Oneway', 'TTest'])
 
+    def test_143_categorical_ordered(self):
+        input_array = ['one', 'two', 'one', 'three', 'one', 'three', 'three', 'one']
+        self.assertEqual(analyze(
+            input_array,
+            order=['one', 'two', 'three'],
+            debug=True,
+            save_to='{}test_analyze_143'.format(self.save_path)
+        ), ['Frequencies'])
+
+    def test_144_categorical_no_labels(self):
+        input_array = ['one', 'two', 'one', 'three', 'one', 'three', 'three', 'one']
+        self.assertEqual(analyze(
+            input_array,
+            labels=False,
+            debug=True,
+            save_to='{}test_analyze_144'.format(self.save_path)
+        ), ['Frequencies'])
+
+    def test_145_categorical_with_grid(self):
+        input_array = ['one', 'two', 'one', 'three', 'one', 'three', 'three', 'one']
+        self.assertEqual(analyze(
+            input_array,
+            grid=True,
+            debug=True,
+            save_to='{}test_analyze_145'.format(self.save_path)
+        ), ['Frequencies'])
+
 
 if __name__ == '__main__':
     unittest.main()