@rgsoft/stats 1.0.1

package/dist/index.d.cts

@@ -0,0 +1,179 @@
+declare function erf(z: number): number;
+
+interface Distribution {
+    /** Cumulative distribution function: P(X ≤ x) */
+    getAccumulated(x: number): number;
+    /** Expected value (mean) of the distribution */
+    getMean(): number;
+    /** Returns the variance if applicable */
+    getVariance?(): number;
+    /** Returns the standard deviation if applicable */
+    getStdDev?(): number;
+    /** Generate a random value following this distribution */
+    sample(): number;
+}
+
+/**
+ * Represents a continuous probability distribution function (PDF).
+ *
+ * A PDF defines how the probability density of a continuous random variable
+ * is distributed over its domain. This interface provides methods for
+ * evaluating the density, cumulative distribution, and sampling values
+ * from the distribution.
+ *
+ * All implementations should ensure that the total integral of the density
+ * function over its domain equals 1.
+ */
+interface PDF extends Distribution {
+    /**
+     * Evaluates the probability density function (PDF) at a given value `x`.
+     *
+     * @param x - The point at which to evaluate the density.
+     * @returns The probability density at `x`.
+     *
+     * @example
+     * ```ts
+     * const gaussian = new Gaussian(0, 1);
+     * gaussian.density(0); // ≈ 0.3989
+     * ```
+     */
+    density(x: number): number;
+    /**
+     * Computes the quantile (inverse CDF) for a given probability `p`.
+     *
+     * The quantile function returns the value `x` such that `P(X ≤ x) = p`.
+     * Not all distributions have a closed-form quantile function; in such
+     * cases, implementations may use a numerical approximation or omit
+     * this method.
+     *
+     * @param p - The cumulative probability (0 ≤ p ≤ 1).
+     * @returns The value `x` such that the cumulative probability equals `p`.
+     *
+     * @throws If `p` is outside the range [0, 1].
+     *
+     * @example
+     * ```ts
+     * const gaussian = new Gaussian(0, 1);
+     * gaussian.quantile(0.975); // ≈ 1.96
+     * ```
+     */
+    quantile?(p: number): number;
+}
+
+declare class Exponential implements PDF {
+    private readonly mean;
+    private readonly lambda;
+    constructor(mean: number);
+    getAccumulated(x: number): number;
+    sample(): number;
+    getMean(): number;
+    density(x: number): number;
+    getVariance(): number;
+    getStdDev(): number;
+    quantile(p: number): number;
+}
+
+declare class Gaussian implements PDF {
+    readonly mean: number;
+    readonly variance: number;
+    readonly stdDev: number;
+    constructor(mean?: number, variance?: number);
+    getAccumulated(x: number): number;
+    quantile(p: number): number;
+    getMean(): number;
+    sample(): number;
+    density(x: number): number;
+    getVariance(): number;
+    getStdDev(): number;
+}
+
+declare class Uniform implements PDF {
+    readonly min: number;
+    readonly max: number;
+    private readonly diff;
+    constructor(min: number, max: number);
+    getAccumulated(x: number): number;
+    getMean(): number;
+    sample(): number;
+    density(x: number): number;
+    getVariance(): number;
+    getStdDev(): number;
+    quantile(p: number): number;
+}
+
+interface PMF extends Distribution {
+    probability(x: number): number;
+}
+
+declare class Binomial implements PMF {
+    private readonly n;
+    private readonly p;
+    private readonly probabilities;
+    private readonly accumulative;
+    private readonly variance;
+    private readonly stdDev;
+    constructor(n: number, p: number);
+    getAccumulated(x: number): number;
+    sample(): number;
+    getMean(): number;
+    getVariance(): number;
+    getStdDev(): number;
+    probability(x: number): number;
+}
+
+declare class NegativeBinomial implements PMF {
+    private readonly r;
+    private readonly p;
+    private readonly accumulative;
+    private readonly mean;
+    private readonly variance;
+    private readonly stdDev;
+    constructor(r: number, p: number);
+    getAccumulated(x: number): number;
+    getMean(): number;
+    getVariance(): number;
+    getStdDev(): number;
+    sample(): number;
+    probability(x: number): number;
+}
+
+declare class Poisson implements PMF {
+    private readonly l;
+    private readonly accumulative;
+    private readonly mean;
+    private readonly variance;
+    private readonly stdDev;
+    constructor(l: number);
+    getAccumulated(x: number): number;
+    sample(): number;
+    getMean(): number;
+    getVariance(): number;
+    getStdDev(): number;
+    probability(x: number): number;
+}
+
+declare class Stats {
+    private readonly orderedData;
+    private readonly data;
+    private _mean?;
+    private _variance?;
+    private _stdDev?;
+    private _q1?;
+    private _q2?;
+    private _q3?;
+    private _normalized?;
+    private _zScores?;
+    constructor(data: number[]);
+    get mean(): number;
+    get median(): number;
+    get variance(): number;
+    get stdDev(): number;
+    get q1(): number;
+    get q2(): number;
+    get q3(): number;
+    get zScores(): number[];
+    get normalized(): number[];
+    private percentile;
+}
+
+export { Binomial, Exponential, Gaussian, NegativeBinomial, Poisson, Stats, Uniform, erf };

package/dist/index.d.ts

@@ -0,0 +1,179 @@
+declare function erf(z: number): number;
+
+interface Distribution {
+    /** Cumulative distribution function: P(X ≤ x) */
+    getAccumulated(x: number): number;
+    /** Expected value (mean) of the distribution */
+    getMean(): number;
+    /** Returns the variance if applicable */
+    getVariance?(): number;
+    /** Returns the standard deviation if applicable */
+    getStdDev?(): number;
+    /** Generate a random value following this distribution */
+    sample(): number;
+}
+
+/**
+ * Represents a continuous probability distribution function (PDF).
+ *
+ * A PDF defines how the probability density of a continuous random variable
+ * is distributed over its domain. This interface provides methods for
+ * evaluating the density, cumulative distribution, and sampling values
+ * from the distribution.
+ *
+ * All implementations should ensure that the total integral of the density
+ * function over its domain equals 1.
+ */
+interface PDF extends Distribution {
+    /**
+     * Evaluates the probability density function (PDF) at a given value `x`.
+     *
+     * @param x - The point at which to evaluate the density.
+     * @returns The probability density at `x`.
+     *
+     * @example
+     * ```ts
+     * const gaussian = new Gaussian(0, 1);
+     * gaussian.density(0); // ≈ 0.3989
+     * ```
+     */
+    density(x: number): number;
+    /**
+     * Computes the quantile (inverse CDF) for a given probability `p`.
+     *
+     * The quantile function returns the value `x` such that `P(X ≤ x) = p`.
+     * Not all distributions have a closed-form quantile function; in such
+     * cases, implementations may use a numerical approximation or omit
+     * this method.
+     *
+     * @param p - The cumulative probability (0 ≤ p ≤ 1).
+     * @returns The value `x` such that the cumulative probability equals `p`.
+     *
+     * @throws If `p` is outside the range [0, 1].
+     *
+     * @example
+     * ```ts
+     * const gaussian = new Gaussian(0, 1);
+     * gaussian.quantile(0.975); // ≈ 1.96
+     * ```
+     */
+    quantile?(p: number): number;
+}
+
+declare class Exponential implements PDF {
+    private readonly mean;
+    private readonly lambda;
+    constructor(mean: number);
+    getAccumulated(x: number): number;
+    sample(): number;
+    getMean(): number;
+    density(x: number): number;
+    getVariance(): number;
+    getStdDev(): number;
+    quantile(p: number): number;
+}
+
+declare class Gaussian implements PDF {
+    readonly mean: number;
+    readonly variance: number;
+    readonly stdDev: number;
+    constructor(mean?: number, variance?: number);
+    getAccumulated(x: number): number;
+    quantile(p: number): number;
+    getMean(): number;
+    sample(): number;
+    density(x: number): number;
+    getVariance(): number;
+    getStdDev(): number;
+}
+
+declare class Uniform implements PDF {
+    readonly min: number;
+    readonly max: number;
+    private readonly diff;
+    constructor(min: number, max: number);
+    getAccumulated(x: number): number;
+    getMean(): number;
+    sample(): number;
+    density(x: number): number;
+    getVariance(): number;
+    getStdDev(): number;
+    quantile(p: number): number;
+}
+
+interface PMF extends Distribution {
+    probability(x: number): number;
+}
+
+declare class Binomial implements PMF {
+    private readonly n;
+    private readonly p;
+    private readonly probabilities;
+    private readonly accumulative;
+    private readonly variance;
+    private readonly stdDev;
+    constructor(n: number, p: number);
+    getAccumulated(x: number): number;
+    sample(): number;
+    getMean(): number;
+    getVariance(): number;
+    getStdDev(): number;
+    probability(x: number): number;
+}
+
+declare class NegativeBinomial implements PMF {
+    private readonly r;
+    private readonly p;
+    private readonly accumulative;
+    private readonly mean;
+    private readonly variance;
+    private readonly stdDev;
+    constructor(r: number, p: number);
+    getAccumulated(x: number): number;
+    getMean(): number;
+    getVariance(): number;
+    getStdDev(): number;
+    sample(): number;
+    probability(x: number): number;
+}
+
+declare class Poisson implements PMF {
+    private readonly l;
+    private readonly accumulative;
+    private readonly mean;
+    private readonly variance;
+    private readonly stdDev;
+    constructor(l: number);
+    getAccumulated(x: number): number;
+    sample(): number;
+    getMean(): number;
+    getVariance(): number;
+    getStdDev(): number;
+    probability(x: number): number;
+}
+
+declare class Stats {
+    private readonly orderedData;
+    private readonly data;
+    private _mean?;
+    private _variance?;
+    private _stdDev?;
+    private _q1?;
+    private _q2?;
+    private _q3?;
+    private _normalized?;
+    private _zScores?;
+    constructor(data: number[]);
+    get mean(): number;
+    get median(): number;
+    get variance(): number;
+    get stdDev(): number;
+    get q1(): number;
+    get q2(): number;
+    get q3(): number;
+    get zScores(): number[];
+    get normalized(): number[];
+    private percentile;
+}
+
+export { Binomial, Exponential, Gaussian, NegativeBinomial, Poisson, Stats, Uniform, erf };