def __init__(self, list_of_factors, list_of_data_sets):
self.list_of_means = []
for i in range(len(list_of_factors)):
data = list_of_data_sets[i]
self.list_of_means.append(statchar.aritmetic_mean(data))
all_elements = []
for i in range(len(list_of_factors)):
all_elements += list_of_data_sets[i]
self.grand_mean = statchar.aritmetic_mean(all_elements)
self.estimated_effects = []
for i in range(len(list_of_factors)):
mean = self.list_of_means[i]
self.estimated_effects.append(mean-self.grand_mean)
# DF- degrees of freedom
self.DFtreat = len(list_of_factors) - 1
self.DFtot = len(all_elements) - 1
self.DFres = (self.DFtot-self.DFtreat)
# sum of squares
self.SStreat = statchar.SStreat(list_of_data_sets,
self.estimated_effects)
self.SSres = statchar.SSres(list_of_data_sets, self.list_of_means)
self.SStot = statchar.SStot(list_of_data_sets, self.grand_mean)
# mean squares
self.MStreat = self.SStreat/self.DFtreat
self.MSres = self.SSres/self.DFres
self.F = self.MStreat/self.MSres
def confidence_interval(data, percentile, number_of_tails):
"""
Computes confidence interval for the
mean of the given data covering the probability given by the
variable percentile.
* data specifies the given data.
* precentile gives the probability that the mean of the data is in
the confidence interval.
* number_of_tails gives the number of tails of the normal distribution
to be considered.
"""
square = math.pow(len(data), 0.5)
mean = statchar.aritmetic_mean(data)
std_dev = statchar.std_dev_corrected(data)
dist = distributions.NormalDistribution(0, 1)
if number_of_tails == 2:
alfa = (1-percentile)/2
c = distributions.find_percentile(1-alfa, dist.cdf)
left = mean - c*std_dev/square
right = mean + c*std_dev/square
return left, right
elif number_of_tails == 1:
alfa = percentile
c = distributions.find_percentile(alfa, dist.cdf)
SEM = statchar.std_error_of_mean(data)
left = mean
right = mean + c*SEM/square
return right
def __init__(self, regressand_vector_matrix, regressor_matrix):
self.regressand_vector_matrix = regressand_vector_matrix
self.regressor_matrix = regressor_matrix
f = linregression.add_to_matrix_for_intercept
# Add intercept for improved performance of the model
self.regressor_matrix_for_intecept = f(regressor_matrix)
self.coeficents = linregression.coeficents_estimation(
regressand_vector_matrix, regressor_matrix)
self.mean = statchar.aritmetic_mean(regressand_vector_matrix.matrix[0])
self.SStot = statchar.SS_with_mean(regressand_vector_matrix.matrix[0],
self.mean)
fi = []
for element in regressor_matrix.matrix:
fi.append(LinearRegression.predict(self,
matrices.Matrix([element])))
self.SSreg = statchar.SS_with_mean(fi, self.mean)
self.SSres = statchar.SS_abstract(fi,
regressand_vector_matrix.matrix[0])
self.R_squared = self.SSreg/self.SStot
n = len(regressand_vector_matrix.matrix[0])
p = len(regressor_matrix.matrix[0])
A = n - 1
B = n - p - 1
self.adjusted_R_squared = 1-(1-self.R_squared)*(A/B)
