Stats.stddev_outliers() - Code Metrics - Inspection of "Suppress warning on enabled xdist on or missing st..." - ionelmc/pytest-benchmark - Measure and Improve Code Quality continuously with Scrutinizer

Completed

Pull Request — master (#113)

unknown

created 2018-06-24 10:10 UTC

Stats.stddev_outliers() A

↳ Parent: Stats

Complexity

Conditions

Size

Total Lines

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
cc	4
dl	0
loc	12
rs	9.8
c	0
b	0
f	0

from __future__ import division
from __future__ import print_function

import operator
import statistics
from bisect import bisect_left
from bisect import bisect_right

from .utils import cached_property
from .utils import funcname
from .utils import get_cprofile_functions


class Stats(object):
    fields = (
        "min", "max", "mean", "stddev", "rounds", "median", "iqr", "q1", "q3", "iqr_outliers", "stddev_outliers",
        "outliers", "ld15iqr", "hd15iqr", "ops", "total"
    )

    def __init__(self):
        self.data = []

    def __bool__(self):
        return bool(self.data)

    def __nonzero__(self):
        return bool(self.data)

    def as_dict(self):
        return dict(
            (field, getattr(self, field))
            for field in self.fields
        )

    def update(self, duration):
        self.data.append(duration)

    @cached_property
    def sorted_data(self):
        return sorted(self.data)

    @cached_property
    def total(self):
        return sum(self.data)

    @cached_property
    def min(self):
        return min(self.data)

    @cached_property
    def max(self):
        return max(self.data)

    @cached_property
    def mean(self):
        return statistics.mean(self.data)

    @cached_property
    def stddev(self):
        if len(self.data) > 1:
            return statistics.stdev(self.data)
        else:
            return 0

    @property
    def stddev_outliers(self):
        """
        Count of StdDev outliers: what's beyond (Mean - StdDev, Mean - StdDev)
        """
        count = 0
        q0 = self.mean - self.stddev
        q4 = self.mean + self.stddev
        for val in self.data:
            if val < q0 or val > q4:
                count += 1
        return count

    @cached_property
    def rounds(self):
        return len(self.data)

    @cached_property
    def median(self):
        return statistics.median(self.data)

    @cached_property
    def ld15iqr(self):
        """
        Tukey-style Lowest Datum within 1.5 IQR under Q1.
        """
        if len(self.data) == 1:
            return self.data[0]
        else:
            return self.sorted_data[bisect_left(self.sorted_data, self.q1 - 1.5 * self.iqr)]

    @cached_property
    def hd15iqr(self):
        """
        Tukey-style Highest Datum within 1.5 IQR over Q3.
        """
        if len(self.data) == 1:
            return self.data[0]
        else:
            pos = bisect_right(self.sorted_data, self.q3 + 1.5 * self.iqr)
            if pos == len(self.data):
                return self.sorted_data[-1]
            else:
                return self.sorted_data[pos]

    @cached_property

    def q1(self):
        rounds = self.rounds
        data = self.sorted_data

        # See: https://en.wikipedia.org/wiki/Quartile#Computing_methods
        if rounds == 1:
            return data[0]
        elif rounds % 2:  # Method 3
            n, q = rounds // 4, rounds % 4
            if q == 1:
                return 0.25 * data[n - 1] + 0.75 * data[n]
            else:
                return 0.75 * data[n] + 0.25 * data[n + 1]
        else:  # Method 2
            return statistics.median(data[:rounds // 2])

    @cached_property

    def q3(self):
        rounds = self.rounds
        data = self.sorted_data

        # See: https://en.wikipedia.org/wiki/Quartile#Computing_methods
        if rounds == 1:
            return data[0]
        elif rounds % 2:  # Method 3
            n, q = rounds // 4, rounds % 4
            if q == 1:
                return 0.75 * data[3 * n] + 0.25 * data[3 * n + 1]
            else:
                return 0.25 * data[3 * n + 1] + 0.75 * data[3 * n + 2]
        else:  # Method 2
            return statistics.median(data[rounds // 2:])

    @cached_property
    def iqr(self):
        return self.q3 - self.q1

    @property
    def iqr_outliers(self):
        """
        Count of Tukey outliers: what's beyond (Q1 - 1.5IQR, Q3 + 1.5IQR)
        """
        count = 0
        q0 = self.q1 - 1.5 * self.iqr
        q4 = self.q3 + 1.5 * self.iqr
        for val in self.data:
            if val < q0 or val > q4:
                count += 1
        return count

    @cached_property
    def outliers(self):
        return "%s;%s" % (self.stddev_outliers, self.iqr_outliers)

    @cached_property
    def ops(self):
        if self.total:
            return self.rounds / self.total
        return 0


class Metadata(object):
    def __init__(self, fixture, iterations, options):
        self.name = fixture.name
        self.fullname = fixture.fullname
        self.group = fixture.group
        self.param = fixture.param
        self.params = fixture.params
        self.extra_info = fixture.extra_info
        self.cprofile_stats = fixture.cprofile_stats

        self.iterations = iterations
        self.stats = Stats()
        self.options = options
        self.fixture = fixture

    def __bool__(self):
        return bool(self.stats)

    def __nonzero__(self):
        return bool(self.stats)

    def get(self, key, default=None):
        try:
            return getattr(self.stats, key)
        except AttributeError:
            return getattr(self, key, default)

    def __getitem__(self, key):
        try:
            return getattr(self.stats, key)
        except AttributeError:
            return getattr(self, key)

    @property
    def has_error(self):
        return self.fixture.has_error

    def as_dict(self, include_data=True, flat=False, stats=True, cprofile=None):
        result = {
            "group": self.group,
            "name": self.name,
            "fullname": self.fullname,
            "params": self.params,
            "param": self.param,
            "extra_info": self.extra_info,
            "options": dict(
                (k, funcname(v) if callable(v) else v) for k, v in self.options.items()
            )
        }
        if self.cprofile_stats:
            cprofile_list = result["cprofile"] = []
            cprofile_functions = get_cprofile_functions(self.cprofile_stats)
            stats_columns = ["cumtime", "tottime", "ncalls", "ncalls_recursion",
                             "tottime_per", "cumtime_per", "function_name"]
            # move column first
            if cprofile is not None:
                stats_columns.remove(cprofile)
                stats_columns.insert(0, cprofile)
            for column in stats_columns:
                cprofile_functions.sort(key=operator.itemgetter(column), reverse=True)
                for cprofile_function in cprofile_functions[:25]:
                    if cprofile_function not in cprofile_list:
                        cprofile_list.append(cprofile_function)
                # if we want only one column or we already have all available functions
                if cprofile is None or len(cprofile_functions) == len(cprofile_list):
                    break
        if stats:
            stats = self.stats.as_dict()
            if include_data:
                stats["data"] = self.stats.data
            stats["iterations"] = self.iterations
            if flat:
                result.update(stats)
            else:
                result["stats"] = stats
        return result

    def update(self, duration):
        self.stats.update(duration / self.iterations)


def normalize_stats(stats):
    if 'ops' not in stats:
        # fill field added in 3.1.0
        stats['ops'] = 1 / stats['mean']
    return stats


1		from __future__ import division
2		from __future__ import print_function
3
4		import operator
5		import statistics
6		from bisect import bisect_left
7		from bisect import bisect_right
8
9		from .utils import cached_property
10		from .utils import funcname
11		from .utils import get_cprofile_functions
12
13
14		class Stats(object):
15		fields = (
16		"min", "max", "mean", "stddev", "rounds", "median", "iqr", "q1", "q3", "iqr_outliers", "stddev_outliers",
17		"outliers", "ld15iqr", "hd15iqr", "ops", "total"
18		)
19
20		def __init__(self):
21		self.data = []
22
23		def __bool__(self):
24		return bool(self.data)
25
26		def __nonzero__(self):
27		return bool(self.data)
28
29		def as_dict(self):
30		return dict(
31		(field, getattr(self, field))
32		for field in self.fields
33		)
34
35		def update(self, duration):
36		self.data.append(duration)
37
38		@cached_property
39		def sorted_data(self):
40		return sorted(self.data)
41
42		@cached_property
43		def total(self):
44		return sum(self.data)
45
46		@cached_property
47		def min(self):
48		return min(self.data)
49
50		@cached_property
51		def max(self):
52		return max(self.data)
53
54		@cached_property
55		def mean(self):
56		return statistics.mean(self.data)
57
58		@cached_property
59		def stddev(self):
60		if len(self.data) > 1:
61		return statistics.stdev(self.data)
62		else:
63		return 0
64
65		@property
66		def stddev_outliers(self):
67		"""
68		Count of StdDev outliers: what's beyond (Mean - StdDev, Mean - StdDev)
69		"""
70		count = 0
71		q0 = self.mean - self.stddev
72		q4 = self.mean + self.stddev
73		for val in self.data:
74		if val < q0 or val > q4:
75		count += 1
76		return count
77
78		@cached_property
79		def rounds(self):
80		return len(self.data)
81
82		@cached_property
83		def median(self):
84		return statistics.median(self.data)
85
86		@cached_property
87		def ld15iqr(self):
88		"""
89		Tukey-style Lowest Datum within 1.5 IQR under Q1.
90		"""
91		if len(self.data) == 1:
92		return self.data[0]
93		else:
94		return self.sorted_data[bisect_left(self.sorted_data, self.q1 - 1.5 * self.iqr)]
95
96		@cached_property
97		def hd15iqr(self):
98		"""
99		Tukey-style Highest Datum within 1.5 IQR over Q3.
100		"""
101		if len(self.data) == 1:
102		return self.data[0]
103		else:
104		pos = bisect_right(self.sorted_data, self.q3 + 1.5 * self.iqr)
105		if pos == len(self.data):
106		return self.sorted_data[-1]
107		else:
108		return self.sorted_data[pos]
109
110	View Code Duplication	@cached_property
		0 ignored issues – show Duplication introduced 2016-05-26 23:02 UTC by Report Bug Copy Issue Report This code seems to be duplicated in your project. Loading history...
111		def q1(self):
112		rounds = self.rounds
113		data = self.sorted_data
114
115		# See: https://en.wikipedia.org/wiki/Quartile#Computing_methods
116		if rounds == 1:
117		return data[0]
118		elif rounds % 2: # Method 3
119		n, q = rounds // 4, rounds % 4
120		if q == 1:
121		return 0.25 * data[n - 1] + 0.75 * data[n]
122		else:
123		return 0.75 * data[n] + 0.25 * data[n + 1]
124		else: # Method 2
125		return statistics.median(data[:rounds // 2])
126
127	View Code Duplication	@cached_property
		0 ignored issues – show Duplication introduced 2016-05-26 23:02 UTC by Report Bug Copy Issue Report This code seems to be duplicated in your project. Loading history...
128		def q3(self):
129		rounds = self.rounds
130		data = self.sorted_data
131
132		# See: https://en.wikipedia.org/wiki/Quartile#Computing_methods
133		if rounds == 1:
134		return data[0]
135		elif rounds % 2: # Method 3
136		n, q = rounds // 4, rounds % 4
137		if q == 1:
138		return 0.75 * data[3 * n] + 0.25 * data[3 * n + 1]
139		else:
140		return 0.25 * data[3 * n + 1] + 0.75 * data[3 * n + 2]
141		else: # Method 2
142		return statistics.median(data[rounds // 2:])
143
144		@cached_property
145		def iqr(self):
146		return self.q3 - self.q1
147
148		@property
149		def iqr_outliers(self):
150		"""
151		Count of Tukey outliers: what's beyond (Q1 - 1.5IQR, Q3 + 1.5IQR)
152		"""
153		count = 0
154		q0 = self.q1 - 1.5 * self.iqr
155		q4 = self.q3 + 1.5 * self.iqr
156		for val in self.data:
157		if val < q0 or val > q4:
158		count += 1
159		return count
160
161		@cached_property
162		def outliers(self):
163		return "%s;%s" % (self.stddev_outliers, self.iqr_outliers)
164
165		@cached_property
166		def ops(self):
167		if self.total:
168		return self.rounds / self.total
169		return 0
170
171
172		class Metadata(object):
173		def __init__(self, fixture, iterations, options):
174		self.name = fixture.name
175		self.fullname = fixture.fullname
176		self.group = fixture.group
177		self.param = fixture.param
178		self.params = fixture.params
179		self.extra_info = fixture.extra_info
180		self.cprofile_stats = fixture.cprofile_stats
181
182		self.iterations = iterations
183		self.stats = Stats()
184		self.options = options
185		self.fixture = fixture
186
187		def __bool__(self):
188		return bool(self.stats)
189
190		def __nonzero__(self):
191		return bool(self.stats)
192
193		def get(self, key, default=None):
194		try:
195		return getattr(self.stats, key)
196		except AttributeError:
197		return getattr(self, key, default)
198
199		def __getitem__(self, key):
200		try:
201		return getattr(self.stats, key)
202		except AttributeError:
203		return getattr(self, key)
204
205		@property
206		def has_error(self):
207		return self.fixture.has_error
208
209		def as_dict(self, include_data=True, flat=False, stats=True, cprofile=None):
210		result = {
211		"group": self.group,
212		"name": self.name,
213		"fullname": self.fullname,
214		"params": self.params,
215		"param": self.param,
216		"extra_info": self.extra_info,
217		"options": dict(
218		(k, funcname(v) if callable(v) else v) for k, v in self.options.items()
219		)
220		}
221		if self.cprofile_stats:
222		cprofile_list = result["cprofile"] = []
223		cprofile_functions = get_cprofile_functions(self.cprofile_stats)
224		stats_columns = ["cumtime", "tottime", "ncalls", "ncalls_recursion",
225		"tottime_per", "cumtime_per", "function_name"]
226		# move column first
227		if cprofile is not None:
228		stats_columns.remove(cprofile)
229		stats_columns.insert(0, cprofile)
230		for column in stats_columns:
231		cprofile_functions.sort(key=operator.itemgetter(column), reverse=True)
232		for cprofile_function in cprofile_functions[:25]:
233		if cprofile_function not in cprofile_list:
234		cprofile_list.append(cprofile_function)
235		# if we want only one column or we already have all available functions
236		if cprofile is None or len(cprofile_functions) == len(cprofile_list):
237		break
238		if stats:
239		stats = self.stats.as_dict()
240		if include_data:
241		stats["data"] = self.stats.data
242		stats["iterations"] = self.iterations
243		if flat:
244		result.update(stats)
245		else:
246		result["stats"] = stats
247		return result
248
249		def update(self, duration):
250		self.stats.update(duration / self.iterations)
251
252
253		def normalize_stats(stats):
254		if 'ops' not in stats:
255		# fill field added in 3.1.0
256		stats['ops'] = 1 / stats['mean']
257		return stats
258

ionelmc / pytest-benchmark

Pull Request — master (#113)

Stats.stddev_outliers() A

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like