aboutsummaryrefslogtreecommitdiffstats
path: root/resources/tools/presentation/generator_tables.py
blob: 65bf6d562e7fbfa91723e9b63962059e81079d0d (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
# Copyright (c) 2017 Cisco and/or its affiliates.
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at:
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

"""Algorithms to generate tables.
"""


import logging
import csv
import prettytable
import pandas as pd

from string import replace
from math import isnan

from errors import PresentationError
from utils import mean, stdev, relative_change, remove_outliers, find_outliers


def generate_tables(spec, data):
    """Generate all tables specified in the specification file.

    :param spec: Specification read from the specification file.
    :param data: Data to process.
    :type spec: Specification
    :type data: InputData
    """

    logging.info("Generating the tables ...")
    for table in spec.tables:
        try:
            eval(table["algorithm"])(table, data)
        except NameError:
            logging.error("The algorithm '{0}' is not defined.".
                          format(table["algorithm"]))
    logging.info("Done.")


def table_details(table, input_data):
    """Generate the table(s) with algorithm: table_detailed_test_results
    specified in the specification file.

    :param table: Table to generate.
    :param input_data: Data to process.
    :type table: pandas.Series
    :type input_data: InputData
    """

    logging.info("  Generating the table {0} ...".
                 format(table.get("title", "")))

    # Transform the data
    data = input_data.filter_data(table)

    # Prepare the header of the tables
    header = list()
    for column in table["columns"]:
        header.append('"{0}"'.format(str(column["title"]).replace('"', '""')))

    # Generate the data for the table according to the model in the table
    # specification
    job = table["data"].keys()[0]
    build = str(table["data"][job][0])
    try:
        suites = input_data.suites(job, build)
    except KeyError:
        logging.error("    No data available. The table will not be generated.")
        return

    for suite_longname, suite in suites.iteritems():
        # Generate data
        suite_name = suite["name"]
        table_lst = list()
        for test in data[job][build].keys():
            if data[job][build][test]["parent"] in suite_name:
                row_lst = list()
                for column in table["columns"]:
                    try:
                        col_data = str(data[job][build][test][column["data"].
                                       split(" ")[1]]).replace('"', '""')
                        if column["data"].split(" ")[1] in ("vat-history",
                                                            "show-run"):
                            col_data = replace(col_data, " |br| ", "",
                                               maxreplace=1)
                            col_data = " |prein| {0} |preout| ".\
                                format(col_data[:-5])
                        row_lst.append('"{0}"'.format(col_data))
                    except KeyError:
                        row_lst.append("No data")
                table_lst.append(row_lst)

        # Write the data to file
        if table_lst:
            file_name = "{0}_{1}{2}".format(table["output-file"], suite_name,
                                            table["output-file-ext"])
            logging.info("      Writing file: '{}'".format(file_name))
            with open(file_name, "w") as file_handler:
                file_handler.write(",".join(header) + "\n")
                for item in table_lst:
                    file_handler.write(",".join(item) + "\n")

    logging.info("  Done.")


def table_merged_details(table, input_data):
    """Generate the table(s) with algorithm: table_merged_details
    specified in the specification file.

    :param table: Table to generate.
    :param input_data: Data to process.
    :type table: pandas.Series
    :type input_data: InputData
    """

    logging.info("  Generating the table {0} ...".
                 format(table.get("title", "")))

    # Transform the data
    data = input_data.filter_data(table)
    data = input_data.merge_data(data)
    data.sort_index(inplace=True)

    suites = input_data.filter_data(table, data_set="suites")
    suites = input_data.merge_data(suites)

    # Prepare the header of the tables
    header = list()
    for column in table["columns"]:
        header.append('"{0}"'.format(str(column["title"]).replace('"', '""')))

    for _, suite in suites.iteritems():
        # Generate data
        suite_name = suite["name"]
        table_lst = list()
        for test in data.keys():
            if data[test]["parent"] in suite_name:
                row_lst = list()
                for column in table["columns"]:
                    try:
                        col_data = str(data[test][column["data"].
                                       split(" ")[1]]).replace('"', '""')
                        if column["data"].split(" ")[1] in ("vat-history",
                                                            "show-run"):
                            col_data = replace(col_data, " |br| ", "",
                                               maxreplace=1)
                            col_data = " |prein| {0} |preout| ".\
                                format(col_data[:-5])
                        row_lst.append('"{0}"'.format(col_data))
                    except KeyError:
                        row_lst.append("No data")
                table_lst.append(row_lst)

        # Write the data to file
        if table_lst:
            file_name = "{0}_{1}{2}".format(table["output-file"], suite_name,
                                            table["output-file-ext"])
            logging.info("      Writing file: '{}'".format(file_name))
            with open(file_name, "w") as file_handler:
                file_handler.write(",".join(header) + "\n")
                for item in table_lst:
                    file_handler.write(",".join(item) + "\n")

    logging.info("  Done.")


def table_performance_improvements(table, input_data):
    """Generate the table(s) with algorithm: table_performance_improvements
    specified in the specification file.

    :param table: Table to generate.
    :param input_data: Data to process.
    :type table: pandas.Series
    :type input_data: InputData
    """

    def _write_line_to_file(file_handler, data):
        """Write a line to the .csv file.

        :param file_handler: File handler for the csv file. It must be open for
         writing text.
        :param data: Item to be written to the file.
        :type file_handler: BinaryIO
        :type data: list
        """

        line_lst = list()
        for item in data:
            if isinstance(item["data"], str):
                # Remove -?drdisc from the end
                if item["data"].endswith("drdisc"):
                    item["data"] = item["data"][:-8]
                line_lst.append(item["data"])
            elif isinstance(item["data"], float):
                line_lst.append("{:.1f}".format(item["data"]))
            elif item["data"] is None:
                line_lst.append("")
        file_handler.write(",".join(line_lst) + "\n")

    logging.info("  Generating the table {0} ...".
                 format(table.get("title", "")))

    # Read the template
    file_name = table.get("template", None)
    if file_name:
        try:
            tmpl = _read_csv_template(file_name)
        except PresentationError:
            logging.error("  The template '{0}' does not exist. Skipping the "
                          "table.".format(file_name))
            return None
    else:
        logging.error("The template is not defined. Skipping the table.")
        return None

    # Transform the data
    data = input_data.filter_data(table)

    # Prepare the header of the tables
    header = list()
    for column in table["columns"]:
        header.append(column["title"])

    # Generate the data for the table according to the model in the table
    # specification
    tbl_lst = list()
    for tmpl_item in tmpl:
        tbl_item = list()
        for column in table["columns"]:
            cmd = column["data"].split(" ")[0]
            args = column["data"].split(" ")[1:]
            if cmd == "template":
                try:
                    val = float(tmpl_item[int(args[0])])
                except ValueError:
                    val = tmpl_item[int(args[0])]
                tbl_item.append({"data": val})
            elif cmd == "data":
                jobs = args[0:-1]
                operation = args[-1]
                data_lst = list()
                for job in jobs:
                    for build in data[job]:
                        try:
                            data_lst.append(float(build[tmpl_item[0]]
                                                  ["throughput"]["value"]))
                        except (KeyError, TypeError):
                            # No data, ignore
                            continue
                if data_lst:
                    tbl_item.append({"data": (eval(operation)(data_lst)) /
                                             1000000})
                else:
                    tbl_item.append({"data": None})
            elif cmd == "operation":
                operation = args[0]
                try:
                    nr1 = float(tbl_item[int(args[1])]["data"])
                    nr2 = float(tbl_item[int(args[2])]["data"])
                    if nr1 and nr2:
                        tbl_item.append({"data": eval(operation)(nr1, nr2)})
                    else:
                        tbl_item.append({"data": None})
                except (IndexError, ValueError, TypeError):
                    logging.error("No data for {0}".format(tbl_item[0]["data"]))
                    tbl_item.append({"data": None})
                    continue
            else:
                logging.error("Not supported command {0}. Skipping the table.".
                              format(cmd))
                return None
        tbl_lst.append(tbl_item)

    # Sort the table according to the relative change
    tbl_lst.sort(key=lambda rel: rel[-1]["data"], reverse=True)

    # Create the tables and write them to the files
    file_names = [
        "{0}_ndr_top{1}".format(table["output-file"], table["output-file-ext"]),
        "{0}_pdr_top{1}".format(table["output-file"], table["output-file-ext"]),
        "{0}_ndr_low{1}".format(table["output-file"], table["output-file-ext"]),
        "{0}_pdr_low{1}".format(table["output-file"], table["output-file-ext"])
    ]

    for file_name in file_names:
        logging.info("    Writing the file '{0}'".format(file_name))
        with open(file_name, "w") as file_handler:
            file_handler.write(",".join(header) + "\n")
            for item in tbl_lst:
                if isinstance(item[-1]["data"], float):
                    rel_change = round(item[-1]["data"], 1)
                else:
                    rel_change = item[-1]["data"]
                if "ndr_top" in file_name \
                        and "ndr" in item[0]["data"] \
                        and rel_change >= 10.0:
                    _write_line_to_file(file_handler, item)
                elif "pdr_top" in file_name \
                        and "pdr" in item[0]["data"] \
                        and rel_change >= 10.0:
                    _write_line_to_file(file_handler, item)
                elif "ndr_low" in file_name \
                        and "ndr" in item[0]["data"] \
                        and rel_change < 10.0:
                    _write_line_to_file(file_handler, item)
                elif "pdr_low" in file_name \
                        and "pdr" in item[0]["data"] \
                        and rel_change < 10.0:
                    _write_line_to_file(file_handler, item)

    logging.info("  Done.")


def _read_csv_template(file_name):
    """Read the template from a .csv file.

    :param file_name: Name / full path / relative path of the file to read.
    :type file_name: str
    :returns: Data from the template as list (lines) of lists (items on line).
    :rtype: list
    :raises: PresentationError if it is not possible to read the file.
    """

    try:
        with open(file_name, 'r') as csv_file:
            tmpl_data = list()
            for line in csv_file:
                tmpl_data.append(line[:-1].split(","))
        return tmpl_data
    except IOError as err:
        raise PresentationError(str(err), level="ERROR")


def table_performance_comparison(table, input_data):
    """Generate the table(s) with algorithm: table_performance_comparison
    specified in the specification file.

    :param table: Table to generate.
    :param input_data: Data to process.
    :type table: pandas.Series
    :type input_data: InputData
    """

    logging.info("  Generating the table {0} ...".
                 format(table.get("title", "")))

    # Transform the data
    data = input_data.filter_data(table)

    # Prepare the header of the tables
    try:
        header = ["Test case",
                  "{0} Throughput [Mpps]".format(table["reference"]["title"]),
                  "{0} stdev [Mpps]".format(table["reference"]["title"]),
                  "{0} Throughput [Mpps]".format(table["compare"]["title"]),
                  "{0} stdev [Mpps]".format(table["compare"]["title"]),
                  "Change [%]"]
        header_str = ",".join(header) + "\n"
    except (AttributeError, KeyError) as err:
        logging.error("The model is invalid, missing parameter: {0}".
                      format(err))
        return

    # Prepare data to the table:
    tbl_dict = dict()
    for job, builds in table["reference"]["data"].items():
        for build in builds:
            for tst_name, tst_data in data[job][str(build)].iteritems():
                if tbl_dict.get(tst_name, None) is None:
                    name = "{0}-{1}".format(tst_data["parent"].split("-")[0],
                                            "-".join(tst_data["name"].
                                                     split("-")[1:]))
                    tbl_dict[tst_name] = {"name": name,
                                          "ref-data": list(),
                                          "cmp-data": list()}
                try:
                    tbl_dict[tst_name]["ref-data"].\
                        append(tst_data["throughput"]["value"])
                except TypeError:
                    pass  # No data in output.xml for this test

    for job, builds in table["compare"]["data"].items():
        for build in builds:
            for tst_name, tst_data in data[job][str(build)].iteritems():
                try:
                    tbl_dict[tst_name]["cmp-data"].\
                        append(tst_data["throughput"]["value"])
                except KeyError:
                    pass
                except TypeError:
                    tbl_dict.pop(tst_name, None)

    tbl_lst = list()
    for tst_name in tbl_dict.keys():
        item = [tbl_dict[tst_name]["name"], ]
        if tbl_dict[tst_name]["ref-data"]:
            data_t = remove_outliers(tbl_dict[tst_name]["ref-data"],
                                     table["outlier-const"])
            item.append(round(mean(data_t) / 1000000, 2))
            item.append(round(stdev(data_t) / 1000000, 2))
        else:
            item.extend([None, None])
        if tbl_dict[tst_name]["cmp-data"]:
            data_t = remove_outliers(tbl_dict[tst_name]["cmp-data"],
                                     table["outlier-const"])
            item.append(round(mean(data_t) / 1000000, 2))
            item.append(round(stdev(data_t) / 1000000, 2))
        else:
            item.extend([None, None])
        if item[1] is not None and item[3] is not None:
            item.append(int(relative_change(float(item[1]), float(item[3]))))
        if len(item) == 6:
            tbl_lst.append(item)

    # Sort the table according to the relative change
    tbl_lst.sort(key=lambda rel: rel[-1], reverse=True)

    # Generate tables:
    # All tests in csv:
    tbl_names = ["{0}-ndr-1t1c-full{1}".format(table["output-file"],
                                               table["output-file-ext"]),
                 "{0}-ndr-2t2c-full{1}".format(table["output-file"],
                                               table["output-file-ext"]),
                 "{0}-ndr-4t4c-full{1}".format(table["output-file"],
                                               table["output-file-ext"]),
                 "{0}-pdr-1t1c-full{1}".format(table["output-file"],
                                               table["output-file-ext"]),
                 "{0}-pdr-2t2c-full{1}".format(table["output-file"],
                                               table["output-file-ext"]),
                 "{0}-pdr-4t4c-full{1}".format(table["output-file"],
                                               table["output-file-ext"])
                 ]
    for file_name in tbl_names:
        logging.info("      Writing file: '{0}'".format(file_name))
        with open(file_name, "w") as file_handler:
            file_handler.write(header_str)
            for test in tbl_lst:
                if (file_name.split("-")[-3] in test[0] and    # NDR vs PDR
                        file_name.split("-")[-2] in test[0]):  # cores
                    test[0] = "-".join(test[0].split("-")[:-1])
                    file_handler.write(",".join([str(item) for item in test]) +
                                       "\n")

    # All tests in txt:
    tbl_names_txt = ["{0}-ndr-1t1c-full.txt".format(table["output-file"]),
                     "{0}-ndr-2t2c-full.txt".format(table["output-file"]),
                     "{0}-ndr-4t4c-full.txt".format(table["output-file"]),
                     "{0}-pdr-1t1c-full.txt".format(table["output-file"]),
                     "{0}-pdr-2t2c-full.txt".format(table["output-file"]),
                     "{0}-pdr-4t4c-full.txt".format(table["output-file"])
                     ]

    for i, txt_name in enumerate(tbl_names_txt):
        txt_table = None
        logging.info("      Writing file: '{0}'".format(txt_name))
        with open(tbl_names[i], 'rb') as csv_file:
            csv_content = csv.reader(csv_file, delimiter=',', quotechar='"')
            for row in csv_content:
                if txt_table is None:
                    txt_table = prettytable.PrettyTable(row)
                else:
                    txt_table.add_row(row)
            txt_table.align["Test case"] = "l"
        with open(txt_name, "w") as txt_file:
            txt_file.write(str(txt_table))

    # Selected tests in csv:
    input_file = "{0}-ndr-1t1c-full{1}".format(table["output-file"],
                                               table["output-file-ext"])
    with open(input_file, "r") as in_file:
        lines = list()
        for line in in_file:
            lines.append(line)

    output_file = "{0}-ndr-1t1c-top{1}".format(table["output-file"],
                                               table["output-file-ext"])
    logging.info("      Writing file: '{0}'".format(output_file))
    with open(output_file, "w") as out_file:
        out_file.write(header_str)
        for i, line in enumerate(lines[1:]):
            if i == table["nr-of-tests-shown"]:
                break
            out_file.write(line)

    output_file = "{0}-ndr-1t1c-bottom{1}".format(table["output-file"],
                                                  table["output-file-ext"])
    logging.info("      Writing file: '{0}'".format(output_file))
    with open(output_file, "w") as out_file:
        out_file.write(header_str)
        for i, line in enumerate(lines[-1:0:-1]):
            if i == table["nr-of-tests-shown"]:
                break
            out_file.write(line)

    input_file = "{0}-pdr-1t1c-full{1}".format(table["output-file"],
                                               table["output-file-ext"])
    with open(input_file, "r") as in_file:
        lines = list()
        for line in in_file:
            lines.append(line)

    output_file = "{0}-pdr-1t1c-top{1}".format(table["output-file"],
                                               table["output-file-ext"])
    logging.info("      Writing file: '{0}'".format(output_file))
    with open(output_file, "w") as out_file:
        out_file.write(header_str)
        for i, line in enumerate(lines[1:]):
            if i == table["nr-of-tests-shown"]:
                break
            out_file.write(line)

    output_file = "{0}-pdr-1t1c-bottom{1}".format(table["output-file"],
                                                  table["output-file-ext"])
    logging.info("      Writing file: '{0}'".format(output_file))
    with open(output_file, "w") as out_file:
        out_file.write(header_str)
        for i, line in enumerate(lines[-1:0:-1]):
            if i == table["nr-of-tests-shown"]:
                break
            out_file.write(line)


def table_performance_trending_dashboard(table, input_data):
    """Generate the table(s) with algorithm: table_performance_comparison
    specified in the specification file.

    :param table: Table to generate.
    :param input_data: Data to process.
    :type table: pandas.Series
    :type input_data: InputData
    """

    logging.info("  Generating the table {0} ...".
                 format(table.get("title", "")))

    # Transform the data
    data = input_data.filter_data(table)

    # Prepare the header of the tables
    header = ["Test case",
              "Thput trend [Mpps]",
              "Change [Mpps]",
              "Change [%]",
              "Anomaly"]
    header_str = ",".join(header) + "\n"

    # Prepare data to the table:
    tbl_dict = dict()
    for job, builds in table["data"].items():
        for build in builds:
            for tst_name, tst_data in data[job][str(build)].iteritems():
                if tbl_dict.get(tst_name, None) is None:
                    name = "{0}-{1}".format(tst_data["parent"].split("-")[0],
                                            "-".join(tst_data["name"].
                                                     split("-")[1:]))
                    tbl_dict[tst_name] = {"name": name,
                                          "data": list()}
                try:
                    tbl_dict[tst_name]["data"]. \
                        append(tst_data["result"]["throughput"])
                except (TypeError, KeyError):
                    pass  # No data in output.xml for this test

    tbl_lst = list()
    for tst_name in tbl_dict.keys():
        if len(tbl_dict[tst_name]["data"]) > 2:
            pd_data = pd.Series(tbl_dict[tst_name]["data"])
            win_size = pd_data.size \
                if pd_data.size < table["window"] else table["window"]
            # Test name:
            name = tbl_dict[tst_name]["name"]
            # Throughput trend:
            trend = list(pd_data.rolling(window=win_size, min_periods=2).
                         median())[-2]
            # Anomaly:
            t_data, _ = find_outliers(pd_data)
            last = list(t_data)[-1]
            t_stdev = list(t_data.rolling(window=win_size, min_periods=2).
                         std())[-2]
            if isnan(last):
                anomaly = "outlier"
            elif last < (trend - 3 * t_stdev):
                anomaly = "regression"
            elif last > (trend + 3 * t_stdev):
                anomaly = "progression"
            else:
                anomaly = "normal"

            if not isnan(last) and not isnan(trend):
                # Change:
                change = round(float(last - trend) / 1000000, 2)
                # Relative change:
                rel_change = int(relative_change(float(trend), float(last)))

                tbl_lst.append([name,
                                round(float(last) / 1000000, 2),
                                change,
                                rel_change,
                                anomaly])

    # Sort the table according to the relative change
    tbl_lst.sort(key=lambda rel: rel[-2], reverse=True)

    file_name = "{0}.{1}".format(table["output-file"], table["output-file-ext"])

    logging.info("      Writing file: '{0}'".format(file_name))
    with open(file_name, "w") as file_handler:
        file_handler.write(header_str)
        for test in tbl_lst:
            file_handler.write(",".join([str(item) for item in test]) + '\n')

    txt_file_name = "{0}.txt".format(table["output-file"])
    txt_table = None
    logging.info("      Writing file: '{0}'".format(txt_file_name))
    with open(file_name, 'rb') as csv_file:
        csv_content = csv.reader(csv_file, delimiter=',', quotechar='"')
        for row in csv_content:
            if txt_table is None:
                txt_table = prettytable.PrettyTable(row)
            else:
                txt_table.add_row(row)
        txt_table.align["Test case"] = "l"
    with open(txt_file_name, "w") as txt_file:
        txt_file.write(str(txt_table))