Add implementation of standard deviation on data

inflammation-analysis.py

@@ -26,12 +26,15 @@ def main(args):
     for filename in infiles:
         inflammation_data = models.load_csv(filename)
 
+
         view_data = {
                 'average': models.daily_mean(inflammation_data),
                 'max': models.daily_max(inflammation_data),
-                'min': models.daily_min(inflammation_data)
+                'min': models.daily_min(inflammation_data),
+                **(models.s_dev(inflammation_data))
         }
 
+
         views.visualize(view_data)
 
 

inflammation/compute_data.py

@@ -6,26 +6,72 @@
 import numpy as np
 
 from inflammation import models, views
+from unittest.mock import Mock
+import numpy.testing as npt
 
 
-def analyse_data(data_dir):
-    """Calculate the standard deviation by day between datasets
+class CSVDataSource:
+    def __init__(self,dir_path):
+        self.dir_path = dir_path
 
-    Gets all the inflammation csvs within a directory, works out the mean
-    inflammation value for each day across all datasets, then graphs the
-    standard deviation of these means."""
-    data_file_paths = glob.glob(os.path.join(data_dir, 'inflammation*.csv'))
+    def load_inflammation_data(self):
+        files_of_interest = 'inflammation*.csv'
+        data_file_paths = glob.glob(os.path.join(self.dir_path, files_of_interest))
+
+        if len(data_file_paths) == 0:
+            raise ValueError(f"No inflammation csv's found in path {self.dir_path}")
+
+        data = map(models.load_csv, data_file_paths)
+        return data
+
+
+class JSONDataSource:
+  """
+  Loads all the inflammation JSON's within a specified folder.
+  """
+  def __init__(self, dir_path):
+    self.dir_path = dir_path
+
+  def load_inflammation_data(self):
+    data_file_paths = glob.glob(os.path.join(self.dir_path, 'inflammation*.json'))
     if len(data_file_paths) == 0:
-        raise ValueError(f"No inflammation csv's found in path {data_dir}")
-    data = map(models.load_csv, data_file_paths)
+      raise ValueError(f"No inflammation JSON's found in path {self.dir_path}")
+    data = map(models.load_json, data_file_paths)
+    return list(data)
 
 
+def compute_standard_deviation_by_day(data):
     means_by_day = map(models.daily_mean, data)
     means_by_day_matrix = np.stack(list(means_by_day))
-
+    
     daily_standard_deviation = np.std(means_by_day_matrix, axis=0)
+    return daily_standard_deviation
+
+
+def analyse_data(data_source):
+    """Calculate the standard deviation by day between datasets
+
+    Gets all the inflammation csvs within a directory, works out the mean
+    inflammation value for each day across all datasets, then graphs the
+    standard deviation of these means."""
+
+    data = data_source.load_inflammation_data()
+
+    daily_standard_deviation = compute_standard_deviation_by_day(data)
 
     graph_data = {
         'standard deviation by day': daily_standard_deviation,
     }
-    views.visualize(graph_data)
+
+    return daily_standard_deviation
+    #views.visualize(graph_data)
+
+
+def test_compute_data_mock_source():
+    from inflammation.compute_data import analyse_data
+    data_source = Mock()
+    data_source.load_inflammation_data.return_value = [[[0, 2, 0]], [[0, 1, 0]]]
+
+    result = analyse_data(data_source)
+    npt.assert_array_almost_equal(result, [0, math.sqrt(0.25) ,0])
+

inflammation/example_with_classes.py

@@ -0,0 +1,24 @@
+import math
+
+class Circle:
+    def __init__(self, radius):
+        self.radius = radius
+
+    def get_area(self):
+        return math.pi * self.radius * self.radius
+
+class Rectangle:
+    def __init__(self,width,height):
+        self.width = width
+        self.height = height
+
+    def get_area(self):
+        return self.width * self.height
+
+my_circle = Circle(10)
+your_rectangle = Rectangle(20,30)
+
+shapes = [my_circle, your_rectangle]
+
+for shape in shapes:
+    print(shape.get_area())

inflammation/models.py

@@ -65,4 +65,17 @@ def daily_min(data):
     :returns: An array of minimum values of measurements for each day.
     """
     return np.min(data, axis=0)
-
+
+
+def standard_deviation(data):
+    """Computes and returns standard deviation for data.
+    Input = 2d inflammation data
+    Output = Standard deviation of input data
+    """
+    mmm = np.mean(data, axis=0)
+    devs = []
+    for entry in data:
+        devs.append((entry - mmm) * (entry - mmm))
+
+    standard_deviation2 = sum(devs) / len(data)
+    return {'standard deviation': standard_deviation2}

inflammation/views.py

@@ -1,7 +1,6 @@
 """Module containing code for plotting inflammation data."""
 
 from matplotlib import pyplot as plt
-import numpy as np
 
 
 def visualize(data_dict):

tests/test_compute_data.py

@@ -0,0 +1,51 @@
+#! /usr/bin/env python
+
+from pathlib import Path
+import numpy.testing as npt
+import pytest
+from unittest.mock import Mock
+
+
+@pytest.mark.parametrize(
+        "data,expected_output",
+        [
+            ([[[0, 1, 0],[0, 2, 0]]], [0, 0, 0]),
+        ],
+ids=['Two patients in same file'])
+
+def test_compute_standard_deviation_by_day(data,expected_output):
+    from inflammation.compute_data import compute_standard_deviation_by_day
+
+    result = compute_standard_deviation_by_day(data)
+    npt.assert_almost_equal(result,expected_output)
+
+
+def test_analyse_data():
+    from inflammation.compute_data import analyse_data, CSVDataSource
+    path = "data"
+    data_source = CSVDataSource(path)
+    result = analyse_data(data_source)
+
+    npt.assert_almost_equal(result, [0.        , 0.22510286, 0.18157299, 0.1264423 , 0.9495481 ,
+       0.27118211, 0.25104719, 0.22330897, 0.89680503, 0.21573875,
+       1.24235548, 0.63042094, 1.57511696, 2.18850242, 0.3729574 ,
+       0.69395538, 2.52365162, 0.3179312 , 1.22850657, 1.63149639,
+       2.45861227, 1.55556052, 2.8214853 , 0.92117578, 0.76176979,
+       2.18346188, 0.55368435, 1.78441632, 0.26549221, 1.43938417,
+       0.78959769, 0.64913879, 1.16078544, 0.42417995, 0.36019114,
+       0.80801707, 0.50323031, 0.47574665, 0.45197398, 0.22070227])
+
+
+def test_with_mocks():
+    print('Hello')
+    mock_shape1 = Mock()
+    mock_shape1.get_area.return_value = 10
+
+    mock_shape2 = Mock()
+    mock_shape2.get_area.return_value = 20
+
+    shapes = [mock_shape1,mock_shape2]
+
+    for shape in shapes:
+        print(shape.get_area())
+

tests/test_models.py

@@ -3,7 +3,7 @@
 import numpy as np
 import numpy.testing as npt
 import os
-
+import pytest
 
 def test_daily_mean_zeros():
     """Test that mean function works for an array of zeros."""
@@ -37,3 +37,14 @@ def test_load_from_json(tmpdir):
         temp_json_file.write('[{"observations":[1, 2, 3]},{"observations":[4, 5, 6]}]')
     result = load_json(example_path)
     npt.assert_array_equal(result, [[1, 2, 3], [4, 5, 6]])
+
+
+@pytest.mark.parametrize('data, expected_standard_deviation', [
+    ([0, 0, 0], 0.0),
+    ([1.0, 1.0, 1.0], 0),
+    ([0.0, 2.0], 1.0)
+])
+def test_daily_standard_deviation(data, expected_standard_deviation):
+    from inflammation.models import s_dev
+    result_data = s_dev(data)['standard deviation']
+    npt.assert_approx_equal(result_data, expected_standard_deviation)

venv/bin/activate

@@ -0,0 +1,76 @@
+# This file must be used with "source bin/activate" *from bash*
+# you cannot run it directly
+
+deactivate () {
+    # reset old environment variables
+    if [ -n "${_OLD_VIRTUAL_PATH:-}" ] ; then
+        PATH="${_OLD_VIRTUAL_PATH:-}"
+        export PATH
+        unset _OLD_VIRTUAL_PATH
+    fi
+    if [ -n "${_OLD_VIRTUAL_PYTHONHOME:-}" ] ; then
+        PYTHONHOME="${_OLD_VIRTUAL_PYTHONHOME:-}"
+        export PYTHONHOME
+        unset _OLD_VIRTUAL_PYTHONHOME
+    fi
+
+    # This should detect bash and zsh, which have a hash command that must
+    # be called to get it to forget past commands.  Without forgetting
+    # past commands the $PATH changes we made may not be respected
+    if [ -n "${BASH:-}" -o -n "${ZSH_VERSION:-}" ] ; then
+        hash -r
+    fi
+
+    if [ -n "${_OLD_VIRTUAL_PS1:-}" ] ; then
+        PS1="${_OLD_VIRTUAL_PS1:-}"
+        export PS1
+        unset _OLD_VIRTUAL_PS1
+    fi
+
+    unset VIRTUAL_ENV
+    if [ ! "$1" = "nondestructive" ] ; then
+    # Self destruct!
+        unset -f deactivate
+    fi
+}
+
+# unset irrelevant variables
+deactivate nondestructive
+
+VIRTUAL_ENV="/home/sl6391/python-intermediate-inflammation/venv"
+export VIRTUAL_ENV
+
+_OLD_VIRTUAL_PATH="$PATH"
+PATH="$VIRTUAL_ENV/bin:$PATH"
+export PATH
+
+# unset PYTHONHOME if set
+# this will fail if PYTHONHOME is set to the empty string (which is bad anyway)
+# could use `if (set -u; : $PYTHONHOME) ;` in bash
+if [ -n "${PYTHONHOME:-}" ] ; then
+    _OLD_VIRTUAL_PYTHONHOME="${PYTHONHOME:-}"
+    unset PYTHONHOME
+fi
+
+if [ -z "${VIRTUAL_ENV_DISABLE_PROMPT:-}" ] ; then
+    _OLD_VIRTUAL_PS1="${PS1:-}"
+    if [ "x(venv) " != x ] ; then
+	PS1="(venv) ${PS1:-}"
+    else
+    if [ "`basename \"$VIRTUAL_ENV\"`" = "__" ] ; then
+        # special case for Aspen magic directories
+        # see http://www.zetadev.com/software/aspen/
+        PS1="[`basename \`dirname \"$VIRTUAL_ENV\"\``] $PS1"
+    else
+        PS1="(`basename \"$VIRTUAL_ENV\"`)$PS1"
+    fi
+    fi
+    export PS1
+fi
+
+# This should detect bash and zsh, which have a hash command that must
+# be called to get it to forget past commands.  Without forgetting
+# past commands the $PATH changes we made may not be respected
+if [ -n "${BASH:-}" -o -n "${ZSH_VERSION:-}" ] ; then
+    hash -r
+fi

venv/bin/activate.csh

@@ -0,0 +1,37 @@
+# This file must be used with "source bin/activate.csh" *from csh*.
+# You cannot run it directly.
+# Created by Davide Di Blasi <davidedb@gmail.com>.
+# Ported to Python 3.3 venv by Andrew Svetlov <andrew.svetlov@gmail.com>
+
+alias deactivate 'test $?_OLD_VIRTUAL_PATH != 0 && setenv PATH "$_OLD_VIRTUAL_PATH" && unset _OLD_VIRTUAL_PATH; rehash; test $?_OLD_VIRTUAL_PROMPT != 0 && set prompt="$_OLD_VIRTUAL_PROMPT" && unset _OLD_VIRTUAL_PROMPT; unsetenv VIRTUAL_ENV; test "\!:*" != "nondestructive" && unalias deactivate'
+
+# Unset irrelevant variables.
+deactivate nondestructive
+
+setenv VIRTUAL_ENV "/home/sl6391/python-intermediate-inflammation/venv"
+
+set _OLD_VIRTUAL_PATH="$PATH"
+setenv PATH "$VIRTUAL_ENV/bin:$PATH"
+
+
+set _OLD_VIRTUAL_PROMPT="$prompt"
+
+if (! "$?VIRTUAL_ENV_DISABLE_PROMPT") then
+    if ("venv" != "") then
+        set env_name = "venv"
+    else
+        if (`basename "VIRTUAL_ENV"` == "__") then
+            # special case for Aspen magic directories
+            # see http://www.zetadev.com/software/aspen/
+            set env_name = `basename \`dirname "$VIRTUAL_ENV"\``
+        else
+            set env_name = `basename "$VIRTUAL_ENV"`
+        endif
+    endif
+    set prompt = "[$env_name] $prompt"
+    unset env_name
+endif
+
+alias pydoc python -m pydoc
+
+rehash