我正在寻找一个函数,它以两个列表作为输入,并返回Pearson相关系数和相关性的显著性。
def corr(data1, data2):
"data1 & data2 should be NumPy arrays."
mean1 = data1.mean()
mean2 = data2.mean()
std1 = data1.std()
std2 = data2.std()
#corr = ((data1-mean1)*(data2-mean2)).mean()/(std1*std2)
corr = ((data1*data2).mean()-mean1*mean2)/(std1*std2)
return corr
def manual_pearson(a,b):
"""
Accepts two arrays of equal length, and computes correlation coefficient.
Numerator is the sum of product of (a - a_avg) and (b - b_avg),
while denominator is the product of a_std and b_std multiplied by
length of array.
"""
a_avg, b_avg = np.average(a), np.average(b)
a_stdev, b_stdev = np.std(a), np.std(b)
n = len(a)
denominator = a_stdev * b_stdev * n
numerator = np.sum(np.multiply(a-a_avg, b-b_avg))
p_coef = numerator/denominator
return p_coef
def get_pearson_corelation(self, first_feature_vector=[], second_feature_vector=[], length_of_featureset=0):
indexed_feature_dict = {}
if first_feature_vector == [] or second_feature_vector == [] or length_of_featureset == 0:
raise ValueError("Empty feature vectors or zero length of featureset in get_pearson_corelation")
sum_a = sum(value for index, value in first_feature_vector)
sum_b = sum(value for index, value in second_feature_vector)
avg_a = float(sum_a) / length_of_featureset
avg_b = float(sum_b) / length_of_featureset
mean_sq_error_a = sqrt((sum((value - avg_a) ** 2 for index, value in first_feature_vector)) + ((
length_of_featureset - len(first_feature_vector)) * ((0 - avg_a) ** 2)))
mean_sq_error_b = sqrt((sum((value - avg_b) ** 2 for index, value in second_feature_vector)) + ((
length_of_featureset - len(second_feature_vector)) * ((0 - avg_b) ** 2)))
covariance_a_b = 0
# Calculate covariance for the sparse vectors
for tuple in first_feature_vector:
if len(tuple) != 2:
raise ValueError("Invalid feature frequency tuple in featureVector: %s") % (tuple,)
indexed_feature_dict[tuple[0]] = tuple[1]
count_of_features = 0
for tuple in second_feature_vector:
count_of_features += 1
if len(tuple) != 2:
raise ValueError("Invalid feature frequency tuple in featureVector: %s") % (tuple,)
if tuple[0] in indexed_feature_dict:
covariance_a_b += ((indexed_feature_dict[tuple[0]] - avg_a) * (tuple[1] - avg_b))
del (indexed_feature_dict[tuple[0]])
else:
covariance_a_b += (0 - avg_a) * (tuple[1] - avg_b)
for index in indexed_feature_dict:
count_of_features += 1
covariance_a_b += (indexed_feature_dict[index] - avg_a) * (0 - avg_b)
# Adjust covariance with rest of vector with 0 value
covariance_a_b += (length_of_featureset - count_of_features) * -avg_a * -avg_b
if mean_sq_error_a == 0 or mean_sq_error_b == 0:
return -1
else:
return float(covariance_a_b) / (mean_sq_error_a * mean_sq_error_b)
def test_get_get_pearson_corelation(self):
vector_a = [(1, 1), (2, 2), (3, 3)]
vector_b = [(1, 1), (2, 5), (3, 7)]
self.assertAlmostEquals(self.sim_calculator.get_pearson_corelation(vector_a, vector_b, 3), 0.981980506062, 3, None, None)
vector_a = [(1, 1), (2, 2), (3, 3)]
vector_b = [(1, 1), (2, 5), (3, 7), (4, 14)]
self.assertAlmostEquals(self.sim_calculator.get_pearson_corelation(vector_a, vector_b, 5), -0.0137089240555, 3, None, None)
statistics.correlation
)直接在标准库中提供:from statistics import correlation
# a = [15, 12, 8, 8, 7, 7, 7, 6, 5, 3]
# b = [10, 25, 17, 11, 13, 17, 20, 13, 9, 15]
correlation(a, b)
# 0.1449981545806852
# Given (possibly random) variables, X and Y, and a correlation direction,
# returns:
# (r, p),
# where r is the Pearson correlation coefficient, and p is the probability
# that there is no correlation in the given direction.
#
# direction:
# if positive, p is the probability that there is no positive correlation in
# the population sampled by X and Y
# if negative, p is the probability that there is no negative correlation
# if 0, p is the probability that there is no correlation in either direction
def probabilityNotCorrelated(X, Y, direction=0):
x = len(X)
if x != len(Y):
raise ValueError("variables not same len: " + str(x) + ", and " + \
str(len(Y)))
if x < 6:
raise ValueError("must have at least 6 samples, but have " + str(x))
(corr, prb_2_tail) = stats.pearsonr(X, Y)
if not direction:
return (corr, prb_2_tail)
prb_1_tail = prb_2_tail / 2
if corr * direction > 0:
return (corr, prb_1_tail)
return (corr, 1 - prb_1_tail)
http://www.tradinggeeks.net/2015/08/calculating-correlation-in-python/
相关性 - 用于衡量两个不同变量之间的相似度
from scipy.stats import pearsonr
# final_data is the dataframe with n set of columns
pearson_correlation = final_data.corr(method='pearson')
pearson_correlation
# Print correlation of n*n column
from scipy.stats import spearmanr
# final_data is the dataframe with n set of columns
spearman_correlation = final_data.corr(method='spearman')
spearman_correlation
# Print correlation of n*n column
kendall_correlation=final_data.corr(method='kendall')
kendall_correlation
def correlation_score(y_true, y_pred):
"""Scores the predictions according to the competition rules.
It is assumed that the predictions are not constant.
Returns the average of each sample's Pearson correlation coefficient"""
y2 = y_pred.copy()
y2 -= y2.mean(axis=0); y2 /= y2.std(axis=0)
y1 = y_true.copy();
y1 -= y1.mean(axis=0); y1 /= y1.std(axis=0)
c = (y1*y2).mean().mean()# Correlation for rescaled matrices is just matrix product and average
return c
def pearson(x,y):
n=len(x)
vals=range(n)
sumx=sum([float(x[i]) for i in vals])
sumy=sum([float(y[i]) for i in vals])
sumxSq=sum([x[i]**2.0 for i in vals])
sumySq=sum([y[i]**2.0 for i in vals])
pSum=sum([x[i]*y[i] for i in vals])
# Calculating Pearson correlation
num=pSum-(sumx*sumy/n)
den=((sumxSq-pow(sumx,2)/n)*(sumySq-pow(sumy,2)/n))**.5
if den==0: return 0
r=num/den
return r