BestFit::calculateGoodnessOfFit() - Code Metrics - Inspection of "Merge pull request #4339 from quonly/patch-1" - PHPOffice/PhpSpreadsheet - Measure and Improve Code Quality continuously with Scrutinizer

Passed

Push — master ( 20aac0...5868f8 )

unknown

created 2025-03-12 06:51 UTC

BestFit::calculateGoodnessOfFit() C

↳ Parent: BestFit

Complexity

Conditions	11
Paths	160

Size

Total Lines	51
Code Lines	38

Duplication

Lines	0
Ratio	0 %

Code Coverage

Tests	30
CRAP Score	11.0295

Importance

Changes

Metric	Value
eloc	38
c	0
b	0
f	0
dl	0
loc	51
ccs	30
cts	32
cp	0.9375
rs	6.8166
cc	11
nc	160
nop	8
crap	11.0295

How to fix Long Method Complexity Many Parameters

<?php

namespace PhpOffice\PhpSpreadsheet\Shared\Trend;

abstract class BestFit
{
    /**
     * Indicator flag for a calculation error.
     */
    protected bool $error = false;

    /**
     * Algorithm type to use for best-fit.
     */
    protected string $bestFitType = 'undetermined';

    /**
     * Number of entries in the sets of x- and y-value arrays.
     */
    protected int $valueCount;

    /**
     * X-value dataseries of values.
     *
     * @var float[]
     */
    protected array $xValues = [];

    /**
     * Y-value dataseries of values.
     *
     * @var float[]
     */
    protected array $yValues = [];

    /**
     * Flag indicating whether values should be adjusted to Y=0.
     */
    protected bool $adjustToZero = false;

    /**
     * Y-value series of best-fit values.
     *
     * @var float[]
     */
    protected array $yBestFitValues = [];

    protected float $goodnessOfFit = 1;

    protected float $stdevOfResiduals = 0;

    protected float $covariance = 0;

    protected float $correlation = 0;

    protected float $SSRegression = 0;

    protected float $SSResiduals = 0;

    protected float $DFResiduals = 0;

    protected float $f = 0;

    protected float $slope = 0;

    protected float $slopeSE = 0;

    protected float $intersect = 0;

    protected float $intersectSE = 0;

    protected float $xOffset = 0;

    protected float $yOffset = 0;

    public function getError(): bool
    {
        return $this->error;
    }

    public function getBestFitType(): string
    {
        return $this->bestFitType;
    }

    /**
     * Return the Y-Value for a specified value of X.
     *
     * @param float $xValue X-Value
     *
     * @return float Y-Value
     */
    abstract public function getValueOfYForX(float $xValue): float;

    /**
     * Return the X-Value for a specified value of Y.
     *
     * @param float $yValue Y-Value
     *
     * @return float X-Value
     */
    abstract public function getValueOfXForY(float $yValue): float;

    /**
     * Return the original set of X-Values.
     *
     * @return float[] X-Values
     */
    public function getXValues(): array
    {
        return $this->xValues;
    }

    /**
     * Return the Equation of the best-fit line.
     *
     * @param int $dp Number of places of decimal precision to display
     */
    abstract public function getEquation(int $dp = 0): string;

    /**
     * Return the Slope of the line.
     *
     * @param int $dp Number of places of decimal precision to display
     */
    public function getSlope(int $dp = 0): float
    {
        if ($dp != 0) {
            return round($this->slope, $dp);
        }

        return $this->slope;
    }

    /**
     * Return the standard error of the Slope.
     *
     * @param int $dp Number of places of decimal precision to display
     */
    public function getSlopeSE(int $dp = 0): float
    {
        if ($dp != 0) {
            return round($this->slopeSE, $dp);
        }

        return $this->slopeSE;
    }

    /**
     * Return the Value of X where it intersects Y = 0.
     *
     * @param int $dp Number of places of decimal precision to display
     */
    public function getIntersect(int $dp = 0): float
    {
        if ($dp != 0) {
            return round($this->intersect, $dp);
        }

        return $this->intersect;
    }

    /**
     * Return the standard error of the Intersect.
     *
     * @param int $dp Number of places of decimal precision to display
     */
    public function getIntersectSE(int $dp = 0): float
    {
        if ($dp != 0) {
            return round($this->intersectSE, $dp);
        }

        return $this->intersectSE;
    }

    /**
     * Return the goodness of fit for this regression.
     *
     * @param int $dp Number of places of decimal precision to return
     */
    public function getGoodnessOfFit(int $dp = 0): float
    {
        if ($dp != 0) {
            return round($this->goodnessOfFit, $dp);
        }

        return $this->goodnessOfFit;
    }

    /**
     * Return the goodness of fit for this regression.
     *
     * @param int $dp Number of places of decimal precision to return
     */
    public function getGoodnessOfFitPercent(int $dp = 0): float
    {
        if ($dp != 0) {
            return round($this->goodnessOfFit * 100, $dp);
        }

        return $this->goodnessOfFit * 100;
    }

    /**
     * Return the standard deviation of the residuals for this regression.
     *
     * @param int $dp Number of places of decimal precision to return
     */
    public function getStdevOfResiduals(int $dp = 0): float
    {
        if ($dp != 0) {
            return round($this->stdevOfResiduals, $dp);
        }

        return $this->stdevOfResiduals;
    }

    /**
     * @param int $dp Number of places of decimal precision to return
     */
    public function getSSRegression(int $dp = 0): float
    {
        if ($dp != 0) {
            return round($this->SSRegression, $dp);
        }

        return $this->SSRegression;
    }

    /**
     * @param int $dp Number of places of decimal precision to return
     */
    public function getSSResiduals(int $dp = 0): float
    {
        if ($dp != 0) {
            return round($this->SSResiduals, $dp);
        }

        return $this->SSResiduals;
    }

    /**
     * @param int $dp Number of places of decimal precision to return
     */
    public function getDFResiduals(int $dp = 0): float
    {
        if ($dp != 0) {
            return round($this->DFResiduals, $dp);
        }

        return $this->DFResiduals;
    }

    /**
     * @param int $dp Number of places of decimal precision to return
     */
    public function getF(int $dp = 0): float
    {
        if ($dp != 0) {
            return round($this->f, $dp);
        }

        return $this->f;
    }

    /**
     * @param int $dp Number of places of decimal precision to return
     */
    public function getCovariance(int $dp = 0): float
    {
        if ($dp != 0) {
            return round($this->covariance, $dp);
        }

        return $this->covariance;
    }

    /**
     * @param int $dp Number of places of decimal precision to return
     */
    public function getCorrelation(int $dp = 0): float
    {
        if ($dp != 0) {
            return round($this->correlation, $dp);
        }

        return $this->correlation;
    }

    /**
     * @return float[]
     */
    public function getYBestFitValues(): array
    {
        return $this->yBestFitValues;
    }

    protected function calculateGoodnessOfFit(float $sumX, float $sumY, float $sumX2, float $sumY2, float $sumXY, float $meanX, float $meanY, bool|int $const): void
    {
        $SSres = $SScov = $SStot = $SSsex = 0.0;
        foreach ($this->xValues as $xKey => $xValue) {
            $bestFitY = $this->yBestFitValues[$xKey] = $this->getValueOfYForX($xValue);

            $SSres += ($this->yValues[$xKey] - $bestFitY) * ($this->yValues[$xKey] - $bestFitY);
            if ($const === true) {
                $SStot += ($this->yValues[$xKey] - $meanY) * ($this->yValues[$xKey] - $meanY);
            } else {
                $SStot += $this->yValues[$xKey] * $this->yValues[$xKey];
            }
            $SScov += ($this->xValues[$xKey] - $meanX) * ($this->yValues[$xKey] - $meanY);
            if ($const === true) {
                $SSsex += ($this->xValues[$xKey] - $meanX) * ($this->xValues[$xKey] - $meanX);
            } else {
                $SSsex += $this->xValues[$xKey] * $this->xValues[$xKey];
            }
        }

        $this->SSResiduals = $SSres;
        $this->DFResiduals = $this->valueCount - 1 - ($const === true ? 1 : 0);

        if ($this->DFResiduals == 0.0) {
            $this->stdevOfResiduals = 0.0;
        } else {
            $this->stdevOfResiduals = sqrt($SSres / $this->DFResiduals);
        }

        if ($SStot == 0.0 || $SSres == $SStot) {
            $this->goodnessOfFit = 1;
        } else {
            $this->goodnessOfFit = 1 - ($SSres / $SStot);
        }

        $this->SSRegression = $this->goodnessOfFit * $SStot;
        $this->covariance = $SScov / $this->valueCount;
        $this->correlation = ($this->valueCount * $sumXY - $sumX * $sumY) / sqrt(($this->valueCount * $sumX2 - $sumX ** 2) * ($this->valueCount * $sumY2 - $sumY ** 2));
        $this->slopeSE = $this->stdevOfResiduals / sqrt($SSsex);
        $this->intersectSE = $this->stdevOfResiduals * sqrt(1 / ($this->valueCount - ($sumX * $sumX) / $sumX2));
        if ($this->SSResiduals != 0.0) {
            if ($this->DFResiduals == 0.0) {
                $this->f = 0.0;
            } else {
                $this->f = $this->SSRegression / ($this->SSResiduals / $this->DFResiduals);
            }
        } else {
            if ($this->DFResiduals == 0.0) {
                $this->f = 0.0;
            } else {
                $this->f = $this->SSRegression / $this->DFResiduals;
            }
        }
    }

    /** @return float|int */
    private function sumSquares(array $values)
    {
        return array_sum(
            array_map(
                fn ($value): float|int => $value ** 2,
                $values
            )
        );
    }

    /**
     * @param float[] $yValues
     * @param float[] $xValues
     */
    protected function leastSquareFit(array $yValues, array $xValues, bool $const): void
    {
        // calculate sums
        $sumValuesX = array_sum($xValues);
        $sumValuesY = array_sum($yValues);
        $meanValueX = $sumValuesX / $this->valueCount;
        $meanValueY = $sumValuesY / $this->valueCount;
        $sumSquaresX = $this->sumSquares($xValues);
        $sumSquaresY = $this->sumSquares($yValues);
        $mBase = $mDivisor = 0.0;
        $xy_sum = 0.0;
        for ($i = 0; $i < $this->valueCount; ++$i) {
            $xy_sum += $xValues[$i] * $yValues[$i];

            if ($const === true) {
                $mBase += ($xValues[$i] - $meanValueX) * ($yValues[$i] - $meanValueY);
                $mDivisor += ($xValues[$i] - $meanValueX) * ($xValues[$i] - $meanValueX);
            } else {
                $mBase += $xValues[$i] * $yValues[$i];
                $mDivisor += $xValues[$i] * $xValues[$i];
            }
        }

        // calculate slope
        $this->slope = $mBase / $mDivisor;

        // calculate intersect
        $this->intersect = ($const === true) ? $meanValueY - ($this->slope * $meanValueX) : 0.0;

        $this->calculateGoodnessOfFit($sumValuesX, $sumValuesY, $sumSquaresX, $sumSquaresY, $xy_sum, $meanValueX, $meanValueY, $const);
    }

    /**
     * Define the regression.
     *
     * @param float[] $yValues The set of Y-values for this regression
     * @param float[] $xValues The set of X-values for this regression
     */
    public function __construct(array $yValues, array $xValues = [])
    {
        //    Calculate number of points
        $yValueCount = count($yValues);
        $xValueCount = count($xValues);

        //    Define X Values if necessary
        if ($xValueCount === 0) {
            $xValues = range(1, $yValueCount);
        } elseif ($yValueCount !== $xValueCount) {
            //    Ensure both arrays of points are the same size
            $this->error = true;
        }

        $this->valueCount = $yValueCount;
        $this->xValues = $xValues;
        $this->yValues = $yValues;
    }
}


1		<?php
2
3		namespace PhpOffice\PhpSpreadsheet\Shared\Trend;
4
5		abstract class BestFit
6		{
7		/**
8		* Indicator flag for a calculation error.
9		*/
10		protected bool $error = false;
11
12		/**
13		* Algorithm type to use for best-fit.
14		*/
15		protected string $bestFitType = 'undetermined';
16
17		/**
18		* Number of entries in the sets of x- and y-value arrays.
19		*/
20		protected int $valueCount;
21
22		/**
23		* X-value dataseries of values.
24		*
25		* @var float[]
26		*/
27		protected array $xValues = [];
28
29		/**
30		* Y-value dataseries of values.
31		*
32		* @var float[]
33		*/
34		protected array $yValues = [];
35
36		/**
37		* Flag indicating whether values should be adjusted to Y=0.
38		*/
39		protected bool $adjustToZero = false;
40
41		/**
42		* Y-value series of best-fit values.
43		*
44		* @var float[]
45		*/
46		protected array $yBestFitValues = [];
47
48		protected float $goodnessOfFit = 1;
49
50		protected float $stdevOfResiduals = 0;
51
52		protected float $covariance = 0;
53
54		protected float $correlation = 0;
55
56		protected float $SSRegression = 0;
57
58		protected float $SSResiduals = 0;
59
60		protected float $DFResiduals = 0;
61
62		protected float $f = 0;
63
64		protected float $slope = 0;
65
66		protected float $slopeSE = 0;
67
68		protected float $intersect = 0;
69
70		protected float $intersectSE = 0;
71
72		protected float $xOffset = 0;
73
74		protected float $yOffset = 0;
75
76		public function getError(): bool
77		{
78		return $this->error;
79		}
80
81	1	public function getBestFitType(): string
82		{
83	1	return $this->bestFitType;
84		}
85
86		/**
87		* Return the Y-Value for a specified value of X.
88		*
89		* @param float $xValue X-Value
90		*
91		* @return float Y-Value
92		*/
93		abstract public function getValueOfYForX(float $xValue): float;
94
95		/**
96		* Return the X-Value for a specified value of Y.
97		*
98		* @param float $yValue Y-Value
99		*
100		* @return float X-Value
101		*/
102		abstract public function getValueOfXForY(float $yValue): float;
103
104		/**
105		* Return the original set of X-Values.
106		*
107		* @return float[] X-Values
108		*/
109	3	public function getXValues(): array
110		{
111	3	return $this->xValues;
112		}
113
114		/**
115		* Return the Equation of the best-fit line.
116		*
117		* @param int $dp Number of places of decimal precision to display
118		*/
119		abstract public function getEquation(int $dp = 0): string;
120
121		/**
122		* Return the Slope of the line.
123		*
124		* @param int $dp Number of places of decimal precision to display
125		*/
126	42	public function getSlope(int $dp = 0): float
127		{
128	42	if ($dp != 0) {
129	2	return round($this->slope, $dp);
130		}
131
132	42	return $this->slope;
133		}
134
135		/**
136		* Return the standard error of the Slope.
137		*
138		* @param int $dp Number of places of decimal precision to display
139		*/
140	3	public function getSlopeSE(int $dp = 0): float
141		{
142	3	if ($dp != 0) {
143		return round($this->slopeSE, $dp);
144		}
145
146	3	return $this->slopeSE;
147		}
148
149		/**
150		* Return the Value of X where it intersects Y = 0.
151		*
152		* @param int $dp Number of places of decimal precision to display
153		*/
154	41	public function getIntersect(int $dp = 0): float
155		{
156	41	if ($dp != 0) {
157	2	return round($this->intersect, $dp);
158		}
159
160	41	return $this->intersect;
161		}
162
163		/**
164		* Return the standard error of the Intersect.
165		*
166		* @param int $dp Number of places of decimal precision to display
167		*/
168	2	public function getIntersectSE(int $dp = 0): float
169		{
170	2	if ($dp != 0) {
171		return round($this->intersectSE, $dp);
172		}
173
174	2	return $this->intersectSE;
175		}
176
177		/**
178		* Return the goodness of fit for this regression.
179		*
180		* @param int $dp Number of places of decimal precision to return
181		*/
182	10	public function getGoodnessOfFit(int $dp = 0): float
183		{
184	10	if ($dp != 0) {
185	3	return round($this->goodnessOfFit, $dp);
186		}
187
188	10	return $this->goodnessOfFit;
189		}
190
191		/**
192		* Return the goodness of fit for this regression.
193		*
194		* @param int $dp Number of places of decimal precision to return
195		*/
196		public function getGoodnessOfFitPercent(int $dp = 0): float
197		{
198		if ($dp != 0) {
199		return round($this->goodnessOfFit * 100, $dp);
200		}
201
202		return $this->goodnessOfFit * 100;
203		}
204
205		/**
206		* Return the standard deviation of the residuals for this regression.
207		*
208		* @param int $dp Number of places of decimal precision to return
209		*/
210	6	public function getStdevOfResiduals(int $dp = 0): float
211		{
212	6	if ($dp != 0) {
213		return round($this->stdevOfResiduals, $dp);
214		}
215
216	6	return $this->stdevOfResiduals;
217		}
218
219		/**
220		* @param int $dp Number of places of decimal precision to return
221		*/
222	3	public function getSSRegression(int $dp = 0): float
223		{
224	3	if ($dp != 0) {
225		return round($this->SSRegression, $dp);
226		}
227
228	3	return $this->SSRegression;
229		}
230
231		/**
232		* @param int $dp Number of places of decimal precision to return
233		*/
234	3	public function getSSResiduals(int $dp = 0): float
235		{
236	3	if ($dp != 0) {
237		return round($this->SSResiduals, $dp);
238		}
239
240	3	return $this->SSResiduals;
241		}
242
243		/**
244		* @param int $dp Number of places of decimal precision to return
245		*/
246	3	public function getDFResiduals(int $dp = 0): float
247		{
248	3	if ($dp != 0) {
249		return round($this->DFResiduals, $dp);
250		}
251
252	3	return $this->DFResiduals;
253		}
254
255		/**
256		* @param int $dp Number of places of decimal precision to return
257		*/
258	3	public function getF(int $dp = 0): float
259		{
260	3	if ($dp != 0) {
261		return round($this->f, $dp);
262		}
263
264	3	return $this->f;
265		}
266
267		/**
268		* @param int $dp Number of places of decimal precision to return
269		*/
270	4	public function getCovariance(int $dp = 0): float
271		{
272	4	if ($dp != 0) {
273		return round($this->covariance, $dp);
274		}
275
276	4	return $this->covariance;
277		}
278
279		/**
280		* @param int $dp Number of places of decimal precision to return
281		*/
282	3	public function getCorrelation(int $dp = 0): float
283		{
284	3	if ($dp != 0) {
285		return round($this->correlation, $dp);
286		}
287
288	3	return $this->correlation;
289		}
290
291		/**
292		* @return float[]
293		*/
294		public function getYBestFitValues(): array
295		{
296		return $this->yBestFitValues;
297		}
298
299	40	protected function calculateGoodnessOfFit(float $sumX, float $sumY, float $sumX2, float $sumY2, float $sumXY, float $meanX, float $meanY, bool\|int $const): void
300		{
301	40	$SSres = $SScov = $SStot = $SSsex = 0.0;
302	40	foreach ($this->xValues as $xKey => $xValue) {
303	40	$bestFitY = $this->yBestFitValues[$xKey] = $this->getValueOfYForX($xValue);
304
305	40	$SSres += ($this->yValues[$xKey] - $bestFitY) * ($this->yValues[$xKey] - $bestFitY);
306	40	if ($const === true) {
307	35	$SStot += ($this->yValues[$xKey] - $meanY) * ($this->yValues[$xKey] - $meanY);
308		} else {
309	5	$SStot += $this->yValues[$xKey] * $this->yValues[$xKey];
310		}
311	40	$SScov += ($this->xValues[$xKey] - $meanX) * ($this->yValues[$xKey] - $meanY);
312	40	if ($const === true) {
313	35	$SSsex += ($this->xValues[$xKey] - $meanX) * ($this->xValues[$xKey] - $meanX);
314		} else {
315	5	$SSsex += $this->xValues[$xKey] * $this->xValues[$xKey];
316		}
317		}
318
319	40	$this->SSResiduals = $SSres;
320	40	$this->DFResiduals = $this->valueCount - 1 - ($const === true ? 1 : 0);
321
322	40	if ($this->DFResiduals == 0.0) {
323	1	$this->stdevOfResiduals = 0.0;
324		} else {
325	39	$this->stdevOfResiduals = sqrt($SSres / $this->DFResiduals);
326		}
327
328	40	if ($SStot == 0.0 \|\| $SSres == $SStot) {
329		$this->goodnessOfFit = 1;
330		} else {
331	40	$this->goodnessOfFit = 1 - ($SSres / $SStot);
332		}
333
334	40	$this->SSRegression = $this->goodnessOfFit * $SStot;
335	40	$this->covariance = $SScov / $this->valueCount;
336	40	$this->correlation = ($this->valueCount * $sumXY - $sumX * $sumY) / sqrt(($this->valueCount * $sumX2 - $sumX ** 2) * ($this->valueCount * $sumY2 - $sumY ** 2));
337	40	$this->slopeSE = $this->stdevOfResiduals / sqrt($SSsex);
338	40	$this->intersectSE = $this->stdevOfResiduals * sqrt(1 / ($this->valueCount - ($sumX * $sumX) / $sumX2));
339	40	if ($this->SSResiduals != 0.0) {
340	28	if ($this->DFResiduals == 0.0) {
341		$this->f = 0.0;
342		} else {
343	28	$this->f = $this->SSRegression / ($this->SSResiduals / $this->DFResiduals);
344		}
345		} else {
346	12	if ($this->DFResiduals == 0.0) {
347	1	$this->f = 0.0;
348		} else {
349	11	$this->f = $this->SSRegression / $this->DFResiduals;
350		}
351		}
352		}
353
354		/** @return float\|int */
355	40	private function sumSquares(array $values)
356		{
357	40	return array_sum(
358	40	array_map(
359	40	fn ($value): float\|int => $value ** 2,
360	40	$values
361	40	)
362	40	);
363		}
364
365		/**
366		* @param float[] $yValues
367		* @param float[] $xValues
368		*/
369	40	protected function leastSquareFit(array $yValues, array $xValues, bool $const): void
370		{
371		// calculate sums
372	40	$sumValuesX = array_sum($xValues);
373	40	$sumValuesY = array_sum($yValues);
374	40	$meanValueX = $sumValuesX / $this->valueCount;
375	40	$meanValueY = $sumValuesY / $this->valueCount;
376	40	$sumSquaresX = $this->sumSquares($xValues);
377	40	$sumSquaresY = $this->sumSquares($yValues);
378	40	$mBase = $mDivisor = 0.0;
379	40	$xy_sum = 0.0;
380	40	for ($i = 0; $i < $this->valueCount; ++$i) {
381	40	$xy_sum += $xValues[$i] * $yValues[$i];
382
383	40	if ($const === true) {
384	35	$mBase += ($xValues[$i] - $meanValueX) * ($yValues[$i] - $meanValueY);
385	35	$mDivisor += ($xValues[$i] - $meanValueX) * ($xValues[$i] - $meanValueX);
386		} else {
387	5	$mBase += $xValues[$i] * $yValues[$i];
388	5	$mDivisor += $xValues[$i] * $xValues[$i];
389		}
390		}
391
392		// calculate slope
393	40	$this->slope = $mBase / $mDivisor;
394
395		// calculate intersect
396	40	$this->intersect = ($const === true) ? $meanValueY - ($this->slope * $meanValueX) : 0.0;
397
398	40	$this->calculateGoodnessOfFit($sumValuesX, $sumValuesY, $sumSquaresX, $sumSquaresY, $xy_sum, $meanValueX, $meanValueY, $const);
399		}
400
401		/**
402		* Define the regression.
403		*
404		* @param float[] $yValues The set of Y-values for this regression
405		* @param float[] $xValues The set of X-values for this regression
406		*/
407	40	public function __construct(array $yValues, array $xValues = [])
408		{
409		// Calculate number of points
410	40	$yValueCount = count($yValues);
411	40	$xValueCount = count($xValues);
412
413		// Define X Values if necessary
414	40	if ($xValueCount === 0) {
415		$xValues = range(1, $yValueCount);
416	40	} elseif ($yValueCount !== $xValueCount) {
417		// Ensure both arrays of points are the same size
418		$this->error = true;
419		}
420
421	40	$this->valueCount = $yValueCount;
422	40	$this->xValues = $xValues;
423	40	$this->yValues = $yValues;
424		}
425		}
426

PHPOffice / PhpSpreadsheet

Push — master ( 20aac0...5868f8 )

BestFit::calculateGoodnessOfFit() C

Complexity

Size

Duplication

Code Coverage

Importance

How to fix Long Method Complexity Many Parameters

Long Method

Many Parameters

Duplication Side-by-Side

Filter issues like