Merge pull request #20 from edx/vik/rename

Rename, strip out statsd

.gitignore

@@ -8,5 +8,6 @@ _build/
 build/
 dist/
 machine_learning.egg-info/
+ease.egg-info/
 *.egg
 

docs/conf.py

@@ -20,7 +20,7 @@ import sys, os
 # documentation root, use os.path.abspath to make it absolute, like shown here.
 sys.path.append(os.path.abspath('.'))
 sys.path.append(os.path.abspath('../'))
-sys.path.append(os.path.abspath('../machine-learning'))
+sys.path.append(os.path.abspath('../ease'))
 sys.path.append(os.path.abspath('../../'))
 
 # -- General configuration -----------------------------------------------------

docs/installation/installation_overview.rst

@@ -4,7 +4,7 @@ Installation Overview
 
 Notes on how to install:
 
-1. cd DIRECTORY_YOU_INSTALLED_TO.  Make sure that you install to the folder machine-learning!
+1. cd DIRECTORY_YOU_INSTALLED_TO.  Make sure that you install to the folder ease!
 2. sudo apt-get update
 3. sudo apt-get upgrade gcc
 4. sudo xargs -a apt-packages.txt apt-get install

docs/overview/description.rst

@@ -2,7 +2,7 @@
 Description
 ===============================================
 
-The ML repo allows anyone to use machine-learning based automated classification.  This automated classification can work on both free text (essays, content, etc), and on numeric values.
+The ML repo allows anyone to use machine learning based automated classification.  This automated classification can work on both free text (essays, content, etc), and on numeric values.
 
 Let's say that you have 10000 user reviews for 15 books (ie "I loved this!", "I didn't like it.", and so on). What you really want to do is use the user reviews to get an aggregate score for each book that indicates how well-received it is. But, in your haste to collect the data, you forgot to get scores from the users.  In this case, the text of the user reviews is your predictor, and the score that you want to collect from each user for each book is the target variable.
 

machine_learning/create.py → ease/create.py

@@ -5,7 +5,6 @@ Functions that create a machine learning model from training data
 import os
 import sys
 import logging
-from statsd import statsd
 import numpy
 
 #Define base path and add to sys path
@@ -23,7 +22,6 @@ import predictor_extractor
 #Make a log
 log = logging.getLogger(__name__)
 
-@statsd.timed('open_ended_assessment.machine_learning.creator.time')
 def create(text,score,prompt_string):
     """
     Creates a machine learning model from input text, associated scores, a prompt, and a path to the model
@@ -75,10 +73,6 @@ def create(text,score,prompt_string):
         results['errors'].append(msg)
         log.exception(msg)
 
-    #Count number of successful/unsuccessful creations
-    statsd.increment("open_ended_assessment.machine_learning.creator_count",
-        tags=["success:{0}".format(results['success'])])
-
     return results
 
 
@@ -125,8 +119,4 @@ def create_generic(numeric_values, textual_values, target, algorithm = util_func
         results['errors'].append(msg)
         log.exception(msg)
 
-        #Count number of successful/unsuccessful creations
-    statsd.increment("open_ended_assessment.machine_learning.creator_count",
-        tags=["success:{0}".format(results['success'])])
-
     return results
\ No newline at end of file

machine_learning/grade.py → ease/grade.py

@@ -7,7 +7,6 @@ import pickle
 import os
 import numpy
 import logging
-from statsd import statsd
 
 #Append sys to base path to import the following modules
 base_path = os.path.dirname(__file__)
@@ -26,7 +25,6 @@ import math
 
 log = logging.getLogger(__name__)
 
-@statsd.timed('open_ended_assessment.machine_learning.grader.time')
 def grade(grader_data,submission):
     """
     Grades a specified submission using specified models
@@ -105,10 +103,6 @@ def grade(grader_data,submission):
         #If error, success is False.
         results['success']=False
 
-    #Count number of successful/unsuccessful gradings
-    statsd.increment("open_ended_assessment.machine_learning.grader_count",
-        tags=["success:{0}".format(results['success'])])
-
     return results
 
 def grade_generic(grader_data, numeric_features, textual_features):
@@ -152,10 +146,6 @@ def grade_generic(grader_data, numeric_features, textual_features):
         #If there is an error getting confidence, it is not a show-stopper, so just log
         log.exception("Problem generating confidence value")
 
-        #Count number of successful/unsuccessful gradings
-    statsd.increment("open_ended_assessment.machine_learning.grader_count",
-        tags=["success:{0}".format(results['success'])])
-
     if not has_error:
         results['success'] = True
 

requirements.txt

 boto==2.6.0
 coverage==3.5.3
-dogstatsd-python==0.2
 lxml==3.0.1
 mock==0.8.0
 nltk==2.0.3

setup.py

@@ -4,9 +4,9 @@ with open('requirements.txt') as f:
     required = f.read().splitlines()
 
 setup(
-    name = "machine-learning",
+    name = "ease",
     version = "0.1",
-    packages=['machine_learning', 'machine_learning.external_code', 'machine_learning.data', 'machine_learning.external_code.fisher'],
+    packages=['ease', 'ease.external_code', 'ease.data', 'ease.external_code.fisher'],
     package_data = {
         '': ['*.txt', '*.rst', '*.p'],
         },
@@ -15,6 +15,6 @@ setup(
     description = "Machine learning based automated text classification for essay scoring.",
     license = "AGPL",
     keywords = "ml machine learning nlp essay education",
-    url = "https://github.com/edx/machine-learning",
+    url = "https://github.com/edx/ease",
     include_package_data = True,
     )
\ No newline at end of file