Я пытаюсь вычислить Pearson Correlation на основе предоставленной сути здесь . Странно получается ошибка ValueError: all the input array dimensions for the concatenation axis must match exactly, but along dimension 1, the array at index 0 has size 52 and the array at index 1 has size 1 (во фрейме данных 52 записи).
Вот предоставленная функция:
def cor_selector(X, y, num_feats):
cor_list = []
feature_name = X.columns.tolist()
# calculate the correlation with y for each feature
for i in X.columns.tolist():
cor = np.corrcoef(X[i], y)[0, 1] # error happens during the 2nd call to here
cor_list.append(cor)
# replace NaN with 0
cor_list = [0 if np.isnan(i) else i for i in cor_list]
# feature name
cor_feature = X.iloc[:, np.argsort(np.abs(cor_list))[-num_feats:]].columns.tolist()
# feature selection? 0 for not select, 1 for select
cor_support = [True if i in cor_feature else False for i in feature_name]
return cor_support, cor_feature
Вот мой скрипт:
df = pd.read_csv(DATA_CSV) # shape: (52, 5)
X = df[['a', 'b', 'c']]
y = df[['d']]
num_feats = 3
cor_support, cor_feature = cor_selector(X, y, num_feats)
print(str(len(cor_feature)), 'selected features')
Полная трассировка стека:
Traceback (most recent call last):
File "/Applications/PyCharm.app/Contents/plugins/python/helpers/pydev/pydevd.py", line 1438, in _exec
pydev_imports.execfile(file, globals, locals) # execute the script
File "/Applications/PyCharm.app/Contents/plugins/python/helpers/pydev/_pydev_imps/_pydev_execfile.py", line 18, in execfile
exec(compile(contents+"\n", file, 'exec'), glob, loc)
File "/Users/talha/PycharmProjects/covid19/store_data.py", line 275, in <module>
cor_support, cor_feature = cor_selector(X, y, num_feats)
File "/Users/talha/PycharmProjects/covid19/store_data.py", line 254, in cor_selector
cor = np.corrcoef(X[i], y)[0, 1]
File "<__array_function__ internals>", line 6, in corrcoef
File "/Users/talha/.local/share/virtualenvs/covid19-g87yyZJK/lib/python3.7/site-packages/numpy/lib/function_base.py", line 2526, in corrcoef
c = cov(x, y, rowvar)
File "<__array_function__ internals>", line 6, in cov
File "/Users/talha/.local/share/virtualenvs/covid19-g87yyZJK/lib/python3.7/site-packages/numpy/lib/function_base.py", line 2390, in cov
X = np.concatenate((X, y), axis=0)
File "<__array_function__ internals>", line 6, in concatenate