def testCorr(self):
xs = [1, 2, 3]
ys = [3, 4, 5]
cor = correlation.Corr(xs, ys)
self.assertAlmostEquals(cor, 1.0)
xs = [1, 2, 100]
ys = [3, 4, 5]
cor = correlation.Corr(xs, ys)
self.assertAlmostEquals(cor, 0.8703878312633373)
cor = correlation.Corr(xs, xs)
self.assertAlmostEquals(cor, 1.0)
def SpearmanCorr(xs, ys):
"""
斯皮尔曼秩相关系数, 对异常值和变量分布不对称 不敏感
"""
xs_r = ToRanks(xs)
ys_r = ToRanks(ys)
return correlation.Corr(xs_r, ys_r)
def main():
resp = brfss.Respondents()
resp.ReadRecords(data_dir='res')
heights, weights = resp.GetHeightAndWeight()
r1 = Corr(heights, weights)
# 方法2
r2 = correlation.Corr(heights, weights)
print(r1, "vs", r2)
print("E = 1 vs", Corr(heights, heights))
def ComputeCorrelations():
resp = brfss_scatter.Respondents()
resp.ReadRecords()
print('Number of records:', len(resp.records))
heights, weights = resp.GetHeightWeight()
pearson = correlation.Corr(heights, weights)
print('Pearson correlation (weights):', pearson)
log_weights = Log(weights)
pearson = correlation.Corr(heights, log_weights)
print('Pearson correlation (log weights):', pearson)
spearman = correlation.SpearmanCorr(heights, weights)
print('Spearman correlation (weights):', spearman)
inter, slope = correlation.LeastSquares(heights, log_weights)
print('Least squares inter, slope (log weights):', inter, slope)
res = correlation.Residuals(heights, log_weights, inter, slope)
R2 = correlation.CoefDetermination(log_weights, res)
print('Coefficient of determination:', R2)
print('sqrt(R^2):', math.sqrt(R2))
def sim_pearson(perfs, p1, p2):
"""
皮尔逊相关系数(Pearson correlation coefficient)
cov(X, Y) / sigmaX*sigmaY
协方差(X,Y) / X的标准方差*Y的标准方差
"""
shared_items = {}
for item in perfs[p1]:
if item in perfs[p2]:
shared_items[item] = 1
n = len(shared_items)
if n == 0: return 0
# p1, p2共同的影评数据
data_p1 = [perfs[p1][it] for it in shared_items]
data_p2 = [perfs[p2][it] for it in shared_items]
# 计算影评均值
mu_p1 = sum(data_p1) / n
mu_p2 = sum(data_p2) / n
# print(mu_p1, mu_p2)
# 计算标准方差
var_p1 = sum([pow(it-mu_p1, 2) for it in data_p1]) / n
var_p2 = sum([pow(it-mu_p2, 2) for it in data_p2]) / n
# print(var_p1, var_p2)
if var_p1 == 0 or var_p2 == 0: return 0
# 计算协方差
cov = sum([(x-mu_p1)*(y-mu_p2) for x, y in zip(data_p1, data_p2)]) / n
# print(cov)
# 计算皮尔逊相关系数
r = cov / sqrt(var_p1*var_p2)
# ============ thinkstat 方法 ===============
if show:
rr = correlation.Corr(data_p1, data_p2)
print(r, rr)
thinkplot.Clf()
thinkplot.Scatter(data_p1, data_p2)
thinkplot.Show()
return r
def ComputeLeastSquares(ages, weights):
"""Computes least squares fit for ages and weights.
Prints summary statistics.
"""
# compute the correlation between age and weight
print 'Pearson correlation', correlation.Corr(ages, weights)
print 'Spearman correlation', correlation.SpearmanCorr(ages, weights)
# compute least squares fit
inter, slope = correlation.LeastSquares(ages, weights)
print '(inter, slope):', inter, slope
res = correlation.Residuals(ages, weights, inter, slope)
R2 = correlation.CoefDetermination(weights, res)
print 'R^2', R2
print
return inter, slope, R2
def Correlation(self):
"""Computes the correlation between log volumes and rdts."""
vs, rdts = zip(*self.initial_rdt)
lvs = [math.log(v) for v in vs]
return correlation.Corr(lvs, rdts)
def peasson_for_distance(xs, ys):
# 计算皮尔逊相关系数, 返回1-r, 越相近距离越短
r = correlation.Corr(xs, ys)
return 1 - r