phitter.discrete.discrete_distributions package

Submodules

phitter.discrete.discrete_distributions.bernoulli module

class phitter.discrete.discrete_distributions.bernoulli.Bernoulli(parameters=None, discrete_measures=None, init_parameters_examples=False)

Bases: object

Bernoulli distribution - Parameters Bernoulli Distribution: {“p”: *} - https://phitter.io/distributions/discrete/bernoulli

cdf(x)

Cumulative distribution function

Return type:: float | ndarray

central_moments(k)

Parametric central moments. µ’[k] = E[(X - E[X])ᵏ] = ∫(x-µ[k])ᵏ∙f(x) dx

Return type:: float | None

get_parameters(discrete_measures)

Calculate proper parameters of the distribution from sample discrete_measures. The parameters are calculated by formula.

Parameters:: discrete_measures (MEASUREMESTS) – attributes: mean, std, variance, skewness, kurtosis, median, mode, min, max, size, num_bins, data
Returns:: parameters
Return type:: {“p”: *}

property kurtosis: float: Parametric kurtosis

property mean: float: Parametric mean

property median: float: Parametric median

property mode: float: Parametric mode

property name

non_central_moments(k)

Parametric no central moments. µ[k] = E[Xᵏ] = ∫xᵏ∙f(x) dx

Return type:: float | None

property num_parameters: int: Number of parameters of the distribution

parameter_restrictions()

Check parameters restrictions

Return type:: bool

property parameters_example: dict[str, int | float]

pmf(x)

Probability mass function

Return type:: float | ndarray

ppf(u)

Percent point function. Inverse of Cumulative distribution function. If CDF[x] = u => PPF[u] = x

Return type:: float | ndarray

sample(n, seed=None)

Sample of n elements of ditribution

Return type:: ndarray

property skewness: float: Parametric skewness

property standard_deviation: float: Parametric standard deviation

property variance: float: Parametric variance

phitter.discrete.discrete_distributions.binomial module

class phitter.discrete.discrete_distributions.binomial.Binomial(parameters=None, discrete_measures=None, init_parameters_examples=False)

Bases: object

Binomial distribution - Parameters Binomial Distribution: {“n”: *, “p”: *} - https://phitter.io/distributions/discrete/binomial

cdf(x)

Cumulative distribution function

Return type:: float | ndarray

central_moments(k)

Parametric central moments. µ’[k] = E[(X - E[X])ᵏ] = ∫(x-µ[k])ᵏ∙f(x) dx

Return type:: float | None

get_parameters(discrete_measures)

Calculate proper parameters of the distribution from sample discrete_measures. The parameters are calculated by formula.

Parameters:: discrete_measures (MEASUREMESTS) – attributes: mean, std, variance, skewness, kurtosis, median, mode, min, max, size, num_bins, data
Returns:: parameters
Return type:: {“n”: *, “p”: *}

property kurtosis: float: Parametric kurtosis

property mean: float: Parametric mean

property median: float: Parametric median

property mode: float: Parametric mode

property name

non_central_moments(k)

Parametric no central moments. µ[k] = E[Xᵏ] = ∫xᵏ∙f(x) dx

Return type:: float | None

property num_parameters: int: Number of parameters of the distribution

parameter_restrictions()

Check parameters restrictions

Return type:: bool

property parameters_example: dict[str, int | float]

pmf(x)

Probability mass function

Return type:: float | ndarray

ppf(u)

Percent point function. Inverse of Cumulative distribution function. If CDF[x] = u => PPF[u] = x

Return type:: float | ndarray

sample(n, seed=None)

Sample of n elements of ditribution

Return type:: ndarray

property skewness: float: Parametric skewness

property standard_deviation: float: Parametric standard deviation

property variance: float: Parametric variance

phitter.discrete.discrete_distributions.geometric module

class phitter.discrete.discrete_distributions.geometric.Geometric(parameters=None, discrete_measures=None, init_parameters_examples=False)

Bases: object

Geometric distribution - Parameters Geometric Distribution: {“p”: *} - https://phitter.io/distributions/discrete/geometric

cdf(x)

Cumulative distribution function

Return type:: float | ndarray

central_moments(k)

Parametric central moments. µ’[k] = E[(X - E[X])ᵏ] = ∫(x-µ[k])ᵏ∙f(x) dx

Return type:: float | None

get_parameters(discrete_measures)

Calculate proper parameters of the distribution from sample discrete_measures. The parameters are calculated by formula.

Parameters:: discrete_measures (MEASUREMESTS) – attributes: mean, std, variance, skewness, kurtosis, median, mode, min, max, size, num_bins, data
Returns:: parameters
Return type:: {“p”: *}

property kurtosis: float: Parametric kurtosis

property mean: float: Parametric mean

property median: float: Parametric median

property mode: float: Parametric mode

property name

non_central_moments(k)

Parametric no central moments. µ[k] = E[Xᵏ] = ∫xᵏ∙f(x) dx

Return type:: float | None

property num_parameters: int: Number of parameters of the distribution

parameter_restrictions()

Check parameters restrictions

Return type:: bool

property parameters_example: dict[str, int | float]

pmf(x)

Probability mass function

Return type:: float | ndarray

ppf(u)

Percent point function. Inverse of Cumulative distribution function. If CDF[x] = u => PPF[u] = x

Return type:: float | ndarray

sample(n, seed=None)

Sample of n elements of ditribution

Return type:: ndarray

property skewness: float: Parametric skewness

property standard_deviation: float: Parametric standard deviation

property variance: float: Parametric variance

phitter.discrete.discrete_distributions.hypergeometric module

class phitter.discrete.discrete_distributions.hypergeometric.Hypergeometric(parameters=None, discrete_measures=None, init_parameters_examples=False)

Bases: object

Hypergeometric_distribution - Parameters Hypergeometric Distribution: {“N”: *, “K”: *, “n”: *} - https://phitter.io/distributions/discrete/hypergeometric

cdf(x)

Cumulative distribution function

Return type:: float | ndarray

central_moments(k)

Parametric central moments. µ’[k] = E[(X - E[X])ᵏ] = ∫(x-µ[k])ᵏ∙f(x) dx

Return type:: float | None

get_parameters(discrete_measures)

Calculate proper parameters of the distribution from sample discrete_measures. The parameters are calculated by formula.

Parameters:: discrete_measures (MEASUREMESTS) – attributes: mean, std, variance, skewness, kurtosis, median, mode, min, max, size, num_bins, data
Returns:: parameters
Return type:: {“N”: *, “K”: *, “n”: *}

property kurtosis: float: Parametric kurtosis

property mean: float: Parametric mean

property median: float: Parametric median

property mode: float: Parametric mode

property name

non_central_moments(k)

Parametric no central moments. µ[k] = E[Xᵏ] = ∫xᵏ∙f(x) dx

Return type:: float | None

property num_parameters: int: Number of parameters of the distribution

parameter_restrictions()

Check parameters restrictions

Return type:: bool

property parameters_example: dict[str, int | float]

pmf(x)

Probability mass function

Return type:: float | ndarray

ppf(u)

Percent point function. Inverse of Cumulative distribution function. If CDF[x] = u => PPF[u] = x

Return type:: float | ndarray

sample(n, seed=None)

Sample of n elements of ditribution

Return type:: ndarray

property skewness: float: Parametric skewness

property standard_deviation: float: Parametric standard deviation

property variance: float: Parametric variance

phitter.discrete.discrete_distributions.logarithmic module

class phitter.discrete.discrete_distributions.logarithmic.Logarithmic(parameters=None, discrete_measures=None, init_parameters_examples=False)

Bases: object

Logarithmic distribution - Parameters Logarithmic Distribution: {“p”: *} - https://phitter.io/distributions/discrete/logarithmic

cdf(x)

Cumulative distribution function

Return type:: float | ndarray

central_moments(k)

Parametric central moments. µ’[k] = E[(X - E[X])ᵏ] = ∫(x-µ[k])ᵏ∙f(x) dx

Return type:: float | None

get_parameters(discrete_measures)

Calculate proper parameters of the distribution from sample discrete_measures. The parameters are calculated by formula.

Parameters:: discrete_measures (MEASUREMESTS) – attributes: mean, std, variance, skewness, kurtosis, median, mode, min, max, size, num_bins, data
Returns:: parameters
Return type:: {“p”: *}

property kurtosis: float: Parametric kurtosis

property mean: float: Parametric mean

property median: float: Parametric median

property mode: float: Parametric mode

property name

non_central_moments(k)

Parametric no central moments. µ[k] = E[Xᵏ] = ∫xᵏ∙f(x) dx

Return type:: float | None

property num_parameters: int: Number of parameters of the distribution

parameter_restrictions()

Check parameters restrictions

Return type:: bool

property parameters_example: dict[str, int | float]

pmf(x)

Probability mass function

Return type:: float | ndarray

ppf(u)

Percent point function. Inverse of Cumulative distribution function. If CDF[x] = u => PPF[u] = x

Return type:: float | ndarray

sample(n, seed=None)

Sample of n elements of ditribution

Return type:: ndarray

property skewness: float: Parametric skewness

property standard_deviation: float: Parametric standard deviation

property variance: float: Parametric variance

phitter.discrete.discrete_distributions.negative_binomial module

class phitter.discrete.discrete_distributions.negative_binomial.NegativeBinomial(parameters=None, discrete_measures=None, init_parameters_examples=False)

Bases: object

Negative binomial distribution - Parameters NegativeBinomial Distribution: {“r”: *, “p”: *} - https://phitter.io/distributions/discrete/negative_binomial

cdf(x)

Cumulative distribution function

Return type:: float | ndarray

central_moments(k)

Parametric central moments. µ’[k] = E[(X - E[X])ᵏ] = ∫(x-µ[k])ᵏ∙f(x) dx

Return type:: float | None

get_parameters(discrete_measures)

Calculate proper parameters of the distribution from sample discrete_measures. The parameters are calculated by formula.

Parameters:: discrete_measures (MEASUREMESTS) – attributes: mean, std, variance, skewness, kurtosis, median, mode, min, max, size, num_bins, data
Returns:: parameters
Return type:: {“r”: *, “p”: *}

property kurtosis: float: Parametric kurtosis

property mean: float: Parametric mean

property median: float: Parametric median

property mode: float: Parametric mode

property name

non_central_moments(k)

Parametric no central moments. µ[k] = E[Xᵏ] = ∫xᵏ∙f(x) dx

Return type:: float | None

property num_parameters: int: Number of parameters of the distribution

parameter_restrictions()

Check parameters restrictions

Return type:: bool

property parameters_example: dict[str, int | float]

pmf(x)

Probability mass function

Return type:: float | ndarray

ppf(u)

Percent point function. Inverse of Cumulative distribution function. If CDF[x] = u => PPF[u] = x

Return type:: float | ndarray

sample(n, seed=None)

Sample of n elements of ditribution

Return type:: ndarray

property skewness: float: Parametric skewness

property standard_deviation: float: Parametric standard deviation

property variance: float: Parametric variance

phitter.discrete.discrete_distributions.poisson module

class phitter.discrete.discrete_distributions.poisson.Poisson(parameters=None, discrete_measures=None, init_parameters_examples=False)

Bases: object

Poisson distribution - Parameters Poisson Distribution: {“lambda”: *} - https://phitter.io/distributions/discrete/poisson

cdf(x)

Cumulative distribution function

Return type:: float | ndarray

central_moments(k)

Parametric central moments. µ’[k] = E[(X - E[X])ᵏ] = ∫(x-µ[k])ᵏ∙f(x) dx

Return type:: float | None

get_parameters(discrete_measures)

Calculate proper parameters of the distribution from sample discrete_measures. The parameters are calculated by formula.

Parameters:: discrete_measures (MEASUREMESTS) – attributes: mean, std, variance, skewness, kurtosis, median, mode, min, max, size, num_bins, data
Returns:: parameters
Return type:: {“lambda”: *}

property kurtosis: float: Parametric kurtosis

property mean: float: Parametric mean

property median: float: Parametric median

property mode: float: Parametric mode

property name

non_central_moments(k)

Parametric no central moments. µ[k] = E[Xᵏ] = ∫xᵏ∙f(x) dx

Return type:: float | None

property num_parameters: int: Number of parameters of the distribution

parameter_restrictions()

Check parameters restrictions

Return type:: bool

property parameters_example: dict[str, int | float]

pmf(x)

Probability mass function

Return type:: float | ndarray

ppf(u)

Percent point function. Inverse of Cumulative distribution function. If CDF[x] = u => PPF[u] = x

Return type:: float | ndarray

sample(n, seed=None)

Sample of n elements of ditribution

Return type:: ndarray

property skewness: float: Parametric skewness

property standard_deviation: float: Parametric standard deviation

property variance: float: Parametric variance

phitter.discrete.discrete_distributions.uniform module

class phitter.discrete.discrete_distributions.uniform.Uniform(parameters=None, discrete_measures=None, init_parameters_examples=False)

Bases: object

Uniform distribution - Parameters Uniform Distribution: {“a”: *, “b”: *} - https://phitter.io/distributions/discrete/uniform

cdf(x)

Cumulative distribution function

Return type:: float | ndarray

central_moments(k)

Parametric central moments. µ’[k] = E[(X - E[X])ᵏ] = ∫(x-µ[k])ᵏ∙f(x) dx

Return type:: float | None

get_parameters(discrete_measures)

Calculate proper parameters of the distribution from sample discrete_measures. The parameters are calculated by formula.

Parameters:: discrete_measures (MEASUREMESTS) – attributes: mean, std, variance, skewness, kurtosis, median, mode, min, max, size, num_bins, data
Returns:: parameters
Return type:: {“a”: *, “b”: *}

property kurtosis: float: Parametric kurtosis

property mean: float: Parametric mean

property median: float: Parametric median

property mode: float: Parametric mode

property name

non_central_moments(k)

Parametric no central moments. µ[k] = E[Xᵏ] = ∫xᵏ∙f(x) dx

Return type:: float | None

property num_parameters: int: Number of parameters of the distribution

parameter_restrictions()

Check parameters restrictions

Return type:: bool

property parameters_example: dict[str, int | float]

pmf(x)

Probability mass function

Return type:: float | ndarray

ppf(u)

Percent point function. Inverse of Cumulative distribution function. If CDF[x] = u => PPF[u] = x

Return type:: float | ndarray

sample(n, seed=None)

Sample of n elements of ditribution

Return type:: ndarray

property skewness: float: Parametric skewness

property standard_deviation: float: Parametric standard deviation

property variance: float: Parametric variance

phitter.discrete.discrete_distributions package

Submodules

phitter.discrete.discrete_distributions.bernoulli module

phitter.discrete.discrete_distributions.binomial module

phitter.discrete.discrete_distributions.geometric module

phitter.discrete.discrete_distributions.hypergeometric module

phitter.discrete.discrete_distributions.logarithmic module

phitter.discrete.discrete_distributions.negative_binomial module

phitter.discrete.discrete_distributions.poisson module

phitter.discrete.discrete_distributions.uniform module

Module contents