parsing time series

Author: sarahmish

Makefile

@@ -62,7 +62,7 @@ lint: ## check style with flake8 and isort
 	invoke lint
 
 .PHONY: lint-sigllm
-lint: ## check style with flake8 and isort
+lint-sigllm: ## check style with flake8 and isort
 	flake8 sigllm tests
 	isort -c --recursive sigllm tests
 

setup.py

@@ -12,6 +12,7 @@
     history = history_file.read()
 
 install_requires = [
+    'numpy',
 ]
 
 setup_requires = [

sigllm/data.py

@@ -0,0 +1,63 @@
+# -*- coding: utf-8 -*-
+
+"""
+Data preprocessing module.
+
+This module contains functions to help parse time series into
+text, preparing it for a language model.
+"""
+
+import numpy as np
+
+
+def sig2str(values, sep=',', space=False, decimal=0):
+    """Convert a signal to a string.
+
+    Convert a 1-dimensional time series into text by casting it
+    to integer values then into a string.
+
+    Args:
+        values (numpy.ndarray):
+            A sequence of signal values.
+        sep (str):
+            String to separate each element in values, Default to `","`.
+        space (bool):
+            Whether to add space between each digit in the result. Default to `False`.
+        decimal (int):
+            Number of decimal points to keep from the float representation. Default to `0`.
+
+    Returns:
+        str:
+            Text containing the elements of `values`.
+    """
+    sign = 1 * (values >= 0) - 1 * (values < 0)
+    values = np.abs(values)
+
+    sequence = sign * (values * 10**decimal).astype(int)
+
+    res = sep.join([str(num) for num in sequence])
+    if space:
+        res = ' '.join(res)
+
+    return res
+
+
+def str2sig(text, sep=',', decimal=0):
+    """Convert a text string to a signal.
+
+    Convert a string containing digits into an array of numbers.
+
+    Args:
+        text (str):
+            A string containing signal values.
+        sep (str):
+            String that was used to separate each element in text, Default to `","`.
+        decimal (int):
+            Number of decimal points to shift each element in text to. Default to `0`.
+
+    Returns:
+        numpy.ndarray:
+            A 1-dimensional array containing parsed elements in `text`.
+    """
+    values = np.fromstring(text, dtype=float, sep=sep)
+    return values * 10**(-decimal)

tests/test_data.py

@@ -0,0 +1,95 @@
+# -*- coding: utf-8 -*-
+
+import numpy as np
+from pytest import fixture
+
+from sigllm.data import sig2str, str2sig
+
+
+@fixture
+def integers():
+    return np.array([1, 2, 3, 4, 5, 6, 7, 8, 9])
+
+
+@fixture
+def floats():
+    return np.array([
+        1.283,
+        2.424,
+        3.213,
+        4.583,
+        5.486,
+        6.284,
+        7.297,
+        8.023,
+        9.786
+    ])
+
+
+@fixture
+def text():
+    return '1,2,3,4,5,6,7,8,9'
+
+
+def test_sig2str(integers):
+    expected = '1,2,3,4,5,6,7,8,9'
+
+    result = sig2str(integers)
+
+    assert result == expected
+
+
+def test_sig2str_decimal(integers):
+    expected = '100,200,300,400,500,600,700,800,900'
+
+    result = sig2str(integers, decimal=2)
+
+    assert result == expected
+
+
+def test_sig2str_sep(integers):
+    expected = '1|2|3|4|5|6|7|8|9'
+
+    result = sig2str(integers, sep='|')
+
+    assert result == expected
+
+
+def test_sig2str_space(integers):
+    expected = '1 , 2 , 3 , 4 , 5 , 6 , 7 , 8 , 9'
+
+    result = sig2str(integers, space=True)
+
+    assert result == expected
+
+
+def test_sig2str_float(floats):
+    expected = '1,2,3,4,5,6,7,8,9'
+
+    result = sig2str(floats)
+
+    assert result == expected
+
+
+def test_sig2str_float_decimal(floats):
+    expected = '128,242,321,458,548,628,729,802,978'
+
+    result = sig2str(floats, decimal=2)
+
+    assert result == expected
+
+
+def test_str2sig(text):
+    expected = np.array([1, 2, 3, 4, 5, 6, 7, 8, 9])
+
+    result = str2sig(text)
+
+    np.testing.assert_equal(result, expected)
+
+
+def test_str2sig_decimal(text):
+    expected = np.array([.01, .02, .03, .04, .05, .06, .07, .08, .09])
+
+    result = str2sig(text, decimal=2)
+
+    np.testing.assert_equal(result, expected)

tests/test_sigllm.py

@@ -13,11 +13,9 @@ class TestSigllm(unittest.TestCase):
 
     def setUp(self):
         """Set up test fixtures, if any."""
-        pass
 
     def tearDown(self):
         """Tear down test fixtures, if any."""
-        pass
 
     def test_000_something(self):
         """Test something."""