from pandas import *
import numpy as np
from libraries.settings import *
from scipy.stats.stats import pearsonr
import itertools
创建随机样本数据:
df = DataFrame(np.random.random((5, 5)), columns=['gene_' + chr(i + ord('a')) for i in range(5)])
print(df)
gene_a gene_b gene_c gene_d gene_e
0 0.471257 0.854139 0.781204 0.678567 0.697993
1 0.292909 0.046159 0.250902 0.064004 0.307537
2 0.422265 0.646988 0.084983 0.822375 0.713397
3 0.113963 0.016122 0.227566 0.206324 0.792048
4 0.357331 0.980479 0.157124 0.560889 0.973161
correlations = {}
columns = df.columns.tolist()
for col_a, col_b in itertools.combinations(columns, 2):
correlations[col_a + '__' + col_b] = pearsonr(df.loc[:, col_a], df.loc[:, col_b])
result = DataFrame.from_dict(correlations, orient='index')
result.columns = ['PCC', 'p-value']
print(result.sort_index())
PCC p-value
gene_a__gene_b 0.461357 0.434142
gene_a__gene_c 0.177936 0.774646
gene_a__gene_d -0.854884 0.064896
gene_a__gene_e -0.155440 0.802887
gene_b__gene_c -0.575056 0.310455
gene_b__gene_d -0.097054 0.876621
gene_b__gene_e 0.061175 0.922159
gene_c__gene_d -0.633302 0.251381
gene_c__gene_e -0.771120 0.126836
gene_d__gene_e 0.531805 0.356315
>使用获取DataFrame列的唯一组合
itertools.combination(iterable,r)
>使用scipy.stats.stats.personr迭代这些组合并计算成对相关性
>将结果(PCC和p值元组)添加到字典中
>从字典构建DataFrame
然后,您还可以保存result.to_csv().您可能会发现使用MultiIndex(包含每列名称的两列)而不是成对关联的已创建名称会很方便.