Pytest Warnings Fix + Open Data Files Update (aimacode#547)

* DataFile Update

* Update learning.py

* Update search.py

* Update test_learning.py

* Update test_text.py

* Add files via upload

* Update text.ipynb

* Update search-4e.ipynb

* Create CONTRIBUTING.md

Author: antmarakis

CONTRIBUTING.md

@@ -74,21 +74,21 @@ Running the Test-Suite
 =====================
 
 The minimal requirement for running the testsuite is ``py.test``.  You can
-install it with::
+install it with:
 
     pip install pytest
 
-Clone this repository::
+Clone this repository:
 
     git clone https://github.com/aimacode/aima-python.git
 
-Fetch the aima-data submodule::
+Fetch the aima-data submodule:
 
     cd aima-python
     git submodule init
     git submodule update
 
-Then you can run the testsuite with::
+Then you can run the testsuite from the `tests` directory with:
 
     py.test
 

learning.py

@@ -4,7 +4,7 @@
     removeall, unique, product, mode, argmax, argmax_random_tie, isclose, gaussian,
     dotproduct, vector_add, scalar_vector_product, weighted_sample_with_replacement,
     weighted_sampler, num_or_str, normalize, clip, sigmoid, print_table,
-    DataFile, sigmoid_derivative
+    open_data, sigmoid_derivative
 )
 
 import copy
@@ -95,7 +95,7 @@ def __init__(self, examples=None, attrs=None, attrnames=None, target=-1,
         if isinstance(examples, str):
             self.examples = parse_csv(examples)
         elif examples is None:
-            self.examples = parse_csv(DataFile(name + '.csv').read())
+            self.examples = parse_csv(open_data(name + '.csv').read())
         else:
             self.examples = examples
         # Attrs are the indices of examples, unless otherwise stated.
@@ -949,7 +949,7 @@ def cross_validation_wrapper(learner, dataset, k=10, trials=1):
     err_val = []
     err_train = []
     size = 1
-    
+
     while True:
         errT, errV = cross_validation(learner, size, dataset, k)
         # Check for convergence provided err_val is not empty

search-4e.ipynb

@@ -346,7 +346,7 @@
    "outputs": [],
    "source": [
     "from search import *\n",
-    "sgb_words = DataFile(\"EN-text/sgb-words.txt\")"
+    "sgb_words = open_data(\"EN-text/sgb-words.txt\")"
    ]
   },
   {

search.py

@@ -6,7 +6,7 @@
 
 from utils import (
     is_in, argmin, argmax, argmax_random_tie, probability, weighted_sampler,
-    memoize, print_table, DataFile, Stack, FIFOQueue, PriorityQueue, name,
+    memoize, print_table, open_data, Stack, FIFOQueue, PriorityQueue, name,
     distance
 )
 
@@ -1044,7 +1044,7 @@ class BoggleFinder:
 
     def __init__(self, board=None):
         if BoggleFinder.wordlist is None:
-            BoggleFinder.wordlist = Wordlist(DataFile("EN-text/wordlist.txt"))
+            BoggleFinder.wordlist = Wordlist(open_data("EN-text/wordlist.txt"))
         self.found = {}
         if board:
             self.set_board(board)

tests/pytest.ini

@@ -0,0 +1,3 @@
+[pytest]
+filterwarnings =
+    ignore::ResourceWarning

tests/test_learning.py

@@ -1,7 +1,7 @@
 import pytest
 import math
 import random
-from utils import DataFile
+from utils import open_data
 from learning import *
 
 
@@ -18,27 +18,31 @@ def test_euclidean():
     distance = euclidean_distance([0, 0, 0], [0, 0, 0])
     assert distance == 0
 
+
 def test_rms_error():
     assert rms_error([2, 2], [2, 2]) == 0
     assert rms_error((0, 0), (0, 1)) == math.sqrt(0.5)
     assert rms_error((1, 0), (0, 1)) ==  1
     assert rms_error((0, 0), (0, -1)) ==  math.sqrt(0.5)
     assert rms_error((0, 0.5), (0, -0.5)) ==  math.sqrt(0.5)
 
+
 def test_manhattan_distance():
     assert manhattan_distance([2, 2], [2, 2]) == 0
     assert manhattan_distance([0, 0], [0, 1]) == 1
     assert manhattan_distance([1, 0], [0, 1]) ==  2
     assert manhattan_distance([0, 0], [0, -1]) ==  1
     assert manhattan_distance([0, 0.5], [0, -0.5]) == 1
 
+
 def test_mean_boolean_error():
     assert mean_boolean_error([1, 1], [0, 0]) == 1
     assert mean_boolean_error([0, 1], [1, 0]) == 1
     assert mean_boolean_error([1, 1], [0, 1]) == 0.5
     assert mean_boolean_error([0, 0], [0, 0]) == 0
     assert mean_boolean_error([1, 1], [1, 1]) == 0
 
+
 def test_mean_error():
     assert mean_error([2, 2], [2, 2]) == 0
     assert mean_error([0, 0], [0, 1]) == 0.5
@@ -53,7 +57,7 @@ def test_exclude():
 
 
 def test_parse_csv():
-    Iris = DataFile('iris.csv').read()
+    Iris = open_data('iris.csv').read()
     assert parse_csv(Iris)[0] == [5.1, 3.5, 1.4, 0.2, 'setosa']
 
 

tests/test_text.py

@@ -3,11 +3,11 @@
 import random
 
 from text import *
-from utils import isclose, DataFile
+from utils import isclose, open_data
 
 
 def test_text_models():
-    flatland = DataFile("EN-text/flatland.txt").read()
+    flatland = open_data("EN-text/flatland.txt").read()
     wordseq = words(flatland)
     P1 = UnigramTextModel(wordseq)
     P2 = NgramTextModel(2, wordseq)
@@ -141,7 +141,7 @@ def test_char_models():
 
 
 def test_viterbi_segmentation():
-    flatland = DataFile("EN-text/flatland.txt").read()
+    flatland = open_data("EN-text/flatland.txt").read()
     wordseq = words(flatland)
     P = UnigramTextModel(wordseq)
     text = "itiseasytoreadwordswithoutspaces"
@@ -158,20 +158,20 @@ def test_shift_encoding():
 
 
 def test_shift_decoding():
-    flatland = DataFile("EN-text/flatland.txt").read()
+    flatland = open_data("EN-text/flatland.txt").read()
     ring = ShiftDecoder(flatland)
     msg = ring.decode('Kyzj zj r jvtivk dvjjrxv.')
 
     assert msg == 'This is a secret message.'
 
 
 def test_permutation_decoder():
-    gutenberg = DataFile("EN-text/gutenberg.txt").read()
-    flatland = DataFile("EN-text/flatland.txt").read()
-    
+    gutenberg = open_data("EN-text/gutenberg.txt").read()
+    flatland = open_data("EN-text/flatland.txt").read()
+
     pd = PermutationDecoder(canonicalize(gutenberg))
     assert pd.decode('aba') in ('ece', 'ete', 'tat', 'tit', 'txt')
-    
+
     pd = PermutationDecoder(canonicalize(flatland))
     assert pd.decode('aba') in ('ded', 'did', 'ece', 'ele', 'eme', 'ere', 'eve', 'eye', 'iti', 'mom', 'ses', 'tat', 'tit')
 
@@ -183,7 +183,7 @@ def test_rot13_encoding():
 
 
 def test_rot13_decoding():
-    flatland = DataFile("EN-text/flatland.txt").read()
+    flatland = open_data("EN-text/flatland.txt").read()
     ring = ShiftDecoder(flatland)
     msg = ring.decode(rot13('Hello, world!'))
 

text.ipynb

@@ -24,7 +24,7 @@
    "outputs": [],
    "source": [
     "from text import *\n",
-    "from utils import DataFile"
+    "from utils import open_data"
    ]
   },
   {
@@ -84,7 +84,7 @@
     }
    ],
    "source": [
-    "flatland = DataFile(\"EN-text/flatland.txt\").read()\n",
+    "flatland = open_data(\"EN-text/flatland.txt\").read()\n",
     "wordseq = words(flatland)\n",
     "\n",
     "P1 = UnigramTextModel(wordseq)\n",
@@ -186,7 +186,7 @@
     }
    ],
    "source": [
-    "flatland = DataFile(\"EN-text/flatland.txt\").read()\n",
+    "flatland = open_data(\"EN-text/flatland.txt\").read()\n",
     "wordseq = words(flatland)\n",
     "P = UnigramTextModel(wordseq)\n",
     "text = \"itiseasytoreadwordswithoutspaces\"\n",
@@ -358,7 +358,7 @@
     }
    ],
    "source": [
-    "flatland = DataFile(\"EN-text/flatland.txt\").read()\n",
+    "flatland = open_data(\"EN-text/flatland.txt\").read()\n",
     "decoder = ShiftDecoder(flatland)\n",
     "\n",
     "decoded_message = decoder.decode(ciphertext)\n",

utils.py

@@ -383,20 +383,13 @@ def print_table(table, header=None, sep='   ', numfmt='{}'):
             str(x), j)(size) for (j, size, x) in zip(justs, sizes, row)))
 
 
-def AIMAFile(components, mode='r'):
-    """Open a file based at the AIMA root directory."""
+def open_data(name, mode='r'):
     aima_root = os.path.dirname(__file__)
-
-    aima_file = os.path.join(aima_root, *components)
+    aima_file = os.path.join(aima_root, *['aima-data', name])
 
     return open(aima_file)
 
 
-def DataFile(name, mode='r'):
-    "Return a file in the AIMA /aima-data directory."
-    return AIMAFile(['aima-data', name], mode)
-
-
 # ______________________________________________________________________________
 # Expressions