More comprehensive excel and csv import, bringing in limits as part o…

…f the headers.

examples/example_data.csv

@@ -1,4 +1,4 @@
-index,value
+index,value (lsl=-2.5 usl=2.5)
 0,2.22733878
 1,-0.59642503
 2,0.38748058

examples/import_from_csv.py

@@ -1,8 +1,11 @@
+import logging
 from manufacturing import import_csv, calc_cpk, show_cpk
 
-data = import_csv('example_data.csv', columnname='value')
+logging.basicConfig(level=logging.INFO)
 
-cpk = calc_cpk(data, upper_spec_limit=2.5, lower_spec_limit=-2.5)
+data = import_csv('example_data.csv', columnname='value (lsl=-2.5 usl=2.5)')
+
+cpk = calc_cpk(**data)
 print(f'cpk = {cpk:.3g}')
 
-show_cpk(data, upper_spec_limit=2.5, lower_spec_limit=-2.5)
+show_cpk(**data)

examples/import_from_excel.py

@@ -1,8 +1,8 @@
 from manufacturing import import_excel, calc_cpk, show_cpk
 
-data = import_excel('example_data.xlsx', columnname='value', skiprows=3)
+data = import_excel('example_data.xlsx', columnname='value (lsl=-2.5 usl=2.5)', skiprows=3)
 
-cpk = calc_cpk(data, upper_spec_limit=2.5, lower_spec_limit=-2.5)
+cpk = calc_cpk(**data)
 print(f'cpk = {cpk:.3g}')
 
-show_cpk(data, upper_spec_limit=2.5, lower_spec_limit=-2.5)
+show_cpk(**data)

manufacturing/__init__.py

@@ -5,4 +5,4 @@
 __all__ = ['calc_cpk', 'show_cpk',
            'import_csv', 'import_excel']
 
-__version__ = '0.2.0'
+__version__ = '0.3.0'

manufacturing/data_import.py

@@ -1,18 +1,53 @@
+import logging
 from pathlib import Path
 import pandas as pd
 
+_logger = logging.getLogger(__name__)
 
-def import_csv(file_path: (str, Path), columnname, **kwargs):
+
+def _parse_col_for_limits(columnname: str):
+    if '(' in columnname and ')' in columnname:
+        _logger.info(f'parentheses detected, loading thresholds')
+        strings = columnname.split('(')[1].replace(')', '')
+        str1, str2 = strings.split(' ')
+
+        if 'lsl' in str1:
+            lsl = float(str1.split('=')[1])
+        elif 'lsl' in str2:
+            lsl = float(str2.split('=')[1])
+        else:
+            lsl = None
+
+        if 'usl' in str1:
+            usl = float(str1.split('=')[1])
+        elif 'usl' in str2:
+            usl = float(str2.split('=')[1])
+        else:
+            usl = None
+    else:
+        lsl, usl = None, None
+
+    return lsl, usl
+
+
+def import_csv(file_path: (str, Path), columnname: str, **kwargs):
     """
     Imports data from a csv file and outputs the specified column of data as a `pandas.Series`
 
     :param file_path: the path to the file on the local file system
     :param columnname: the column name to which the data is associated
     :param kwargs: keyword arguments to be passed directly into `pandas.read_csv()`
-    :return: a pandas series of the data which is to be analyzed
+    :return: a dict containing a pandas series and the limits of the data to be analyzed
     """
     df = pd.read_csv(file_path, **kwargs)
-    return df[columnname]
+
+    lsl, usl = _parse_col_for_limits(columnname)
+
+    return {
+        'data': df[columnname],
+        'lower_spec_limit': lsl,
+        'upper_spec_limit': usl
+    }
 
 
 def import_excel(file_path: (str, Path), columnname, **kwargs):
@@ -25,4 +60,11 @@ def import_excel(file_path: (str, Path), columnname, **kwargs):
     :return: a pandas series of the data which is to be analyzed
     """
     df = pd.read_excel(file_path, **kwargs)
-    return df[columnname]
+
+    lsl, usl = _parse_col_for_limits(columnname)
+
+    return {
+        'data': df[columnname],
+        'lower_spec_limit': lsl,
+        'upper_spec_limit': usl
+    }

readme.md

@@ -2,6 +2,14 @@
 
 To provide analysis tools and metrics useful in manufacturing environments.
 
+# Project Maturity
+
+Every effort is being made to ensure that the results are accurate, but the user is ultimately
+responsible for any resulting analysis.
+
+The API should not be considered stable until v1.0 or greater.  Until then, breaking changes may
+be released as different API options are explored.
+
 # Installation
 
 ## From `setup.py`