diff --git a/data/inflammation-01.json b/data/inflammation-01.json new file mode 100644 index 0000000..9fbcc94 --- /dev/null +++ b/data/inflammation-01.json @@ -0,0 +1,182 @@ +[ + { + "observations": [0,0,1,3,1,2,4,7,8,3,3,3,10,5,7,4,7,7,12,18,6,13,11,11,7,7,4,6,8,8,4,4,5,7,3,4,2,3,0,0] + }, + { + "observations": [0,1,2,1,2,1,3,2,2,6,10,11,5,9,4,4,7,16,8,6,18,4,12,5,12,7,11,5,11,3,3,5,4,4,5,5,1,1,0,1] + }, + { + "observations": [0,1,1,3,3,2,6,2,5,9,5,7,4,5,4,15,5,11,9,10,19,14,12,17,7,12,11,7,4,2,10,5,4,2,2,3,2,2,1,1] + }, + { + "observations": [0,0,2,0,4,2,2,1,6,7,10,7,9,13,8,8,15,10,10,7,17,4,4,7,6,15,6,4,9,11,3,5,6,3,3,4,2,3,2,1] + }, + { + "observations": [0,1,1,3,3,1,3,5,2,4,4,7,6,5,3,10,8,10,6,17,9,14,9,7,13,9,12,6,7,7,9,6,3,2,2,4,2,0,1,1] + }, + { + "observations": [0,0,1,2,2,4,2,1,6,4,7,6,6,9,9,15,4,16,18,12,12,5,18,9,5,3,10,3,12,7,8,4,7,3,5,4,4,3,2,1] + }, + { + "observations": [0,0,2,2,4,2,2,5,5,8,6,5,11,9,4,13,5,12,10,6,9,17,15,8,9,3,13,7,8,2,8,8,4,2,3,5,4,1,1,1] + }, + { + "observations": [0,0,1,2,3,1,2,3,5,3,7,8,8,5,10,9,15,11,18,19,20,8,5,13,15,10,6,10,6,7,4,9,3,5,2,5,3,2,2,1] + }, + { + "observations": [0,0,0,3,1,5,6,5,5,8,2,4,11,12,10,11,9,10,17,11,6,16,12,6,8,14,6,13,10,11,4,6,4,7,6,3,2,1,0,0] + }, + { + "observations": [0,1,1,2,1,3,5,3,5,8,6,8,12,5,13,6,13,8,16,8,18,15,16,14,12,7,3,8,9,11,2,5,4,5,1,4,1,2,0,0] + }, + { + "observations": [0,1,0,0,4,3,3,5,5,4,5,8,7,10,13,3,7,13,15,18,8,15,15,16,11,14,12,4,10,10,4,3,4,5,5,3,3,2,2,1] + }, + { + "observations": [0,1,0,0,3,4,2,7,8,5,2,8,11,5,5,8,14,11,6,11,9,16,18,6,12,5,4,3,5,7,8,3,5,4,5,5,4,0,1,1] + }, + { + "observations": [0,0,2,1,4,3,6,4,6,7,9,9,3,11,6,12,4,17,13,15,13,12,8,7,4,7,12,9,5,6,5,4,7,3,5,4,2,3,0,1] + }, + { + "observations": [0,0,0,0,1,3,1,6,6,5,5,6,3,6,13,3,10,13,9,16,15,9,11,4,6,4,11,11,12,3,5,8,7,4,6,4,1,3,0,0] + }, + { + "observations": [0,1,2,1,1,1,4,1,5,2,3,3,10,7,13,5,7,17,6,9,12,13,10,4,12,4,6,7,6,10,8,2,5,1,3,4,2,0,2,0] + }, + { + "observations": [0,1,1,0,1,2,4,3,6,4,7,5,5,7,5,10,7,8,18,17,9,8,12,11,11,11,14,6,11,2,10,9,5,6,5,3,4,2,2,0] + }, + { + "observations": [0,0,0,0,2,3,6,5,7,4,3,2,10,7,9,11,12,5,12,9,13,19,14,17,5,13,8,11,5,10,9,8,7,5,3,1,4,0,2,1] + }, + { + "observations": [0,0,0,1,2,1,4,3,6,7,4,2,12,6,12,4,14,7,8,14,13,19,6,9,12,6,4,13,6,7,2,3,6,5,4,2,3,0,1,0] + }, + { + "observations": [0,0,2,1,2,5,4,2,7,8,4,7,11,9,8,11,15,17,11,12,7,12,7,6,7,4,13,5,7,6,6,9,2,1,1,2,2,0,1,0] + }, + { + "observations": [0,1,2,0,1,4,3,2,2,7,3,3,12,13,11,13,6,5,9,16,9,19,16,11,8,9,14,12,11,9,6,6,6,1,1,2,4,3,1,1] + }, + { + "observations": [0,1,1,3,1,4,4,1,8,2,2,3,12,12,10,15,13,6,5,5,18,19,9,6,11,12,7,6,3,6,3,2,4,3,1,5,4,2,2,0] + }, + { + "observations": [0,0,2,3,2,3,2,6,3,8,7,4,6,6,9,5,12,12,8,5,12,10,16,7,14,12,5,4,6,9,8,5,6,6,1,4,3,0,2,0] + }, + { + "observations": [0,0,0,3,4,5,1,7,7,8,2,5,12,4,10,14,5,5,17,13,16,15,13,6,12,9,10,3,3,7,4,4,8,2,6,5,1,0,1,0] + }, + { + "observations": [0,1,1,1,1,3,3,2,6,3,9,7,8,8,4,13,7,14,11,15,14,13,5,13,7,14,9,10,5,11,5,3,5,1,1,4,4,1,2,0] + }, + { + "observations": [0,1,1,1,2,3,5,3,6,3,7,10,3,8,12,4,12,9,15,5,17,16,5,10,10,15,7,5,3,11,5,5,6,1,1,1,1,0,2,1] + }, + { + "observations": [0,0,2,1,3,3,2,7,4,4,3,8,12,9,12,9,5,16,8,17,7,11,14,7,13,11,7,12,12,7,8,5,7,2,2,4,1,1,1,0] + }, + { + "observations": [0,0,1,2,4,2,2,3,5,7,10,5,5,12,3,13,4,13,7,15,9,12,18,14,16,12,3,11,3,2,7,4,8,2,2,1,3,0,1,1] + }, + { + "observations": [0,0,1,1,1,5,1,5,2,2,4,10,4,8,14,6,15,6,12,15,15,13,7,17,4,5,11,4,8,7,9,4,5,3,2,5,4,3,2,1] + }, + { + "observations": [0,0,2,2,3,4,6,3,7,6,4,5,8,4,7,7,6,11,12,19,20,18,9,5,4,7,14,8,4,3,7,7,8,3,5,4,1,3,1,0] + }, + { + "observations": [0,0,0,1,4,4,6,3,8,6,4,10,12,3,3,6,8,7,17,16,14,15,17,4,14,13,4,4,12,11,6,9,5,5,2,5,2,1,0,1] + }, + { + "observations": [0,1,1,0,3,2,4,6,8,6,2,3,11,3,14,14,12,8,8,16,13,7,6,9,15,7,6,4,10,8,10,4,2,6,5,5,2,3,2,1] + }, + { + "observations": [0,0,2,3,3,4,5,3,6,7,10,5,10,13,14,3,8,10,9,9,19,15,15,6,8,8,11,5,5,7,3,6,6,4,5,2,2,3,0,0] + }, + { + "observations": [0,1,2,2,2,3,6,6,6,7,6,3,11,12,13,15,15,10,14,11,11,8,6,12,10,5,12,7,7,11,5,8,5,2,5,5,2,0,2,1] + }, + { + "observations": [0,0,2,1,3,5,6,7,5,8,9,3,12,10,12,4,12,9,13,10,10,6,10,11,4,15,13,7,3,4,2,9,7,2,4,2,1,2,1,1] + }, + { + "observations": [0,0,1,2,4,1,5,5,2,3,4,8,8,12,5,15,9,17,7,19,14,18,12,17,14,4,13,13,8,11,5,6,6,2,3,5,2,1,1,1] + }, + { + "observations": [0,0,0,3,1,3,6,4,3,4,8,3,4,8,3,11,5,7,10,5,15,9,16,17,16,3,8,9,8,3,3,9,5,1,6,5,4,2,2,0] + }, + { + "observations": [0,1,2,2,2,5,5,1,4,6,3,6,5,9,6,7,4,7,16,7,16,13,9,16,12,6,7,9,10,3,6,4,5,4,6,3,4,3,2,1] + }, + { + "observations": [0,1,1,2,3,1,5,1,2,2,5,7,6,6,5,10,6,7,17,13,15,16,17,14,4,4,10,10,10,11,9,9,5,4,4,2,1,0,1,0] + }, + { + "observations": [0,1,0,3,2,4,1,1,5,9,10,7,12,10,9,15,12,13,13,6,19,9,10,6,13,5,13,6,7,2,5,5,2,1,1,1,1,3,0,1] + }, + { + "observations": [0,1,1,3,1,1,5,5,3,7,2,2,3,12,4,6,8,15,16,16,15,4,14,5,13,10,7,10,6,3,2,3,6,3,3,5,4,3,2,1] + }, + { + "observations": [0,0,0,2,2,1,3,4,5,5,6,5,5,12,13,5,7,5,11,15,18,7,9,10,14,12,11,9,10,3,2,9,6,2,2,5,3,0,0,1] + }, + { + "observations": [0,0,1,3,3,1,2,1,8,9,2,8,10,3,8,6,10,13,11,17,19,6,4,11,6,12,7,5,5,4,4,8,2,6,6,4,2,2,0,0] + }, + { + "observations": [0,1,1,3,4,5,2,1,3,7,9,6,10,5,8,15,11,12,15,6,12,16,6,4,14,3,12,9,6,11,5,8,5,5,6,1,2,1,2,0] + }, + { + "observations": [0,0,1,3,1,4,3,6,7,8,5,7,11,3,6,11,6,10,6,19,18,14,6,10,7,9,8,5,8,3,10,2,5,1,5,4,2,1,0,1] + }, + { + "observations": [0,1,1,3,3,4,4,6,3,4,9,9,7,6,8,15,12,15,6,11,6,18,5,14,15,12,9,8,3,6,10,6,8,7,2,5,4,3,1,1] + }, + { + "observations": [0,1,2,2,4,3,1,4,8,9,5,10,10,3,4,6,7,11,16,6,14,9,11,10,10,7,10,8,8,4,5,8,4,4,5,2,4,1,1,0] + }, + { + "observations": [0,0,2,3,4,5,4,6,2,9,7,4,9,10,8,11,16,12,15,17,19,10,18,13,15,11,8,4,7,11,6,7,6,5,1,3,1,0,0,0] + }, + { + "observations": [0,1,1,3,1,4,6,2,8,2,10,3,11,9,13,15,5,15,6,10,10,5,14,15,12,7,4,5,11,4,6,9,5,6,1,1,2,1,2,1] + }, + { + "observations": [0,0,1,3,2,5,1,2,7,6,6,3,12,9,4,14,4,6,12,9,12,7,11,7,16,8,13,6,7,6,10,7,6,3,1,5,4,3,0,0] + }, + { + "observations": [0,0,1,2,3,4,5,7,5,4,10,5,12,12,5,4,7,9,18,16,16,10,15,15,10,4,3,7,5,9,4,6,2,4,1,4,2,2,2,1] + }, + { + "observations": [0,1,2,1,1,3,5,3,6,3,10,10,11,10,13,10,13,6,6,14,5,4,5,5,9,4,12,7,7,4,7,9,3,3,6,3,4,1,2,0] + }, + { + "observations": [0,1,2,2,3,5,2,4,5,6,8,3,5,4,3,15,15,12,16,7,20,15,12,8,9,6,12,5,8,3,8,5,4,1,3,2,1,3,1,0] + }, + { + "observations": [0,0,0,2,4,4,5,3,3,3,10,4,4,4,14,11,15,13,10,14,11,17,9,11,11,7,10,12,10,10,10,8,7,5,2,2,4,1,2,1] + }, + { + "observations": [0,0,2,1,1,4,4,7,2,9,4,10,12,7,6,6,11,12,9,15,15,6,6,13,5,12,9,6,4,7,7,6,5,4,1,4,2,2,2,1] + }, + { + "observations": [0,1,2,1,1,4,5,4,4,5,9,7,10,3,13,13,8,9,17,16,16,15,12,13,5,12,10,9,11,9,4,5,5,2,2,5,1,0,0,1] + }, + { + "observations": [0,0,1,3,2,3,6,4,5,7,2,4,11,11,3,8,8,16,5,13,16,5,8,8,6,9,10,10,9,3,3,5,3,5,4,5,3,3,0,1] + }, + { + "observations": [0,1,1,2,2,5,1,7,4,2,5,5,4,6,6,4,16,11,14,16,14,14,8,17,4,14,13,7,6,3,7,7,5,6,3,4,2,2,1,1] + }, + { + "observations": [0,1,1,1,4,1,6,4,6,3,6,5,6,4,14,13,13,9,12,19,9,10,15,10,9,10,10,7,5,6,8,6,6,4,3,5,2,1,1,1] + }, + { + "observations": [0,0,0,1,4,5,6,3,8,7,9,10,8,6,5,12,15,5,10,5,8,13,18,17,14,9,13,4,10,11,10,8,8,6,5,5,2,0,2,0] + }, + { + "observations": [0,0,1,0,3,2,5,4,8,2,9,3,3,10,12,9,14,11,13,8,6,18,11,9,13,11,8,5,5,2,8,5,3,5,4,1,3,1,1,0] + } +] diff --git a/inflammation-analysis.py b/inflammation-analysis.py index 1ca0132..e156431 100644 --- a/inflammation-analysis.py +++ b/inflammation-analysis.py @@ -2,8 +2,10 @@ """Software for managing and analysing patients' inflammation data in our imaginary hospital.""" import argparse +import os from inflammation import models, views +from inflammation.compute_data import analyse_data def main(args): @@ -18,6 +20,10 @@ def main(args): InFiles = [args.infiles] + if args.full_data_analysis: + analyse_data(os.path.dirname(InFiles[0])) + return + for filename in InFiles: inflammation_data = models.load_csv(filename) @@ -34,6 +40,8 @@ def main(args): nargs='+', help='Input CSV(s) containing inflammation series for each patient') + parser.add_argument('--full-data-analysis', action='store_true', dest='full_data_analysis') + args = parser.parse_args() main(args) diff --git a/inflammation/compute_data.py b/inflammation/compute_data.py new file mode 100644 index 0000000..f8da7a6 --- /dev/null +++ b/inflammation/compute_data.py @@ -0,0 +1,31 @@ +"""Module containing mechanism for calculating standard deviation between datasets. +""" + +import glob +import os +import numpy as np + +from inflammation import models, views + + +def analyse_data(data_dir): + """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_file_paths = glob.glob(os.path.join(data_dir, 'inflammation*.csv')) + 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) + + + 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) + + graph_data = { + 'standard deviation by day': daily_standard_deviation, + } + views.visualize(graph_data) diff --git a/inflammation/models.py b/inflammation/models.py index 4f3c337..9e3528e 100644 --- a/inflammation/models.py +++ b/inflammation/models.py @@ -7,6 +7,7 @@ and each column represents a single day across all patients. """ +import json import numpy as np @@ -17,6 +18,27 @@ def load_csv(filename): """ return np.loadtxt(fname=filename, delimiter=',') +def load_json(filename): + """Load a numpy array from a JSON document. + + Expected format: + [ + { + observations: [0, 1] + }, + { + observations: [0, 2] + } + ] + + :param filename: Filename of CSV to load + + """ + with open(filename, 'r', encoding='utf-8') as file: + data_as_json = json.load(file) + return [np.array(entry['observations']) for entry in data_as_json] + + def daily_mean(data): """Calculate the daily mean of a 2d inflammation data array.""" diff --git a/tests/test_models.py b/tests/test_models.py index 295e32c..292d00c 100644 --- a/tests/test_models.py +++ b/tests/test_models.py @@ -2,6 +2,7 @@ import numpy as np import numpy.testing as npt +import os def test_daily_mean_zeros(): @@ -29,3 +30,10 @@ def test_daily_mean_integers(): # Need to use Numpy testing functions to compare arrays npt.assert_array_equal(daily_mean(test_input), test_result) +def test_load_from_json(tmpdir): + from inflammation.models import load_json + example_path = os.path.join(tmpdir, 'example.json') + with open(example_path, 'w') as temp_json_file: + 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]])