Python: KeyError

Question

I want to compute the correlation ratio between a nominal and a numeric feature using the following code:

def corr_ratio(values, category_labels):


    # Computes correlation ratio for a given array of values and category_labels
    # Eqn: eta^2 = (sum_x [N_x * (mean(y_x) - mean(y))^2]) / (sum_x [sum_i [(y_xi - mean(y))^2]])
    # values: 1D array
    # category_labels: 1D array
    category_labels = np.array(category_labels)
    values = np.array(values)
    categories = np.unique(category_labels)
    data_dict = {}
    for catname in categories:
        indices = np.where(category_labels == catname)
    data_dict[catname] = values[indices]
    cat_means = {catname: np.mean(data_dict[catname]) for catname in categories}
    overall_mean = np.mean(values)
    nominator = np.sum([len(data_dict[catname]) * (cat_means[catname] - overall_mean) ** 2 for catname in categories])
    denominator = np.sum([(val - overall_mean) ** 2 for catname in categories for val in data_dict[catname]])
    corr_ratio = nominator / denominator
    return corr_ratio


data = {
    'Month': ['August', 'August', 'August', 'August', 'August', 'August', 'August', 'August', 'August', 'August',
              'August', 'August',
              'February', 'February', 'February', 'February', 'February', 'February', 'February', 'February',
              'February', 'February', 'February', 'February'],
    'Day': ['Sunday', 'Monday', 'Tuesday', 'Sunday', 'Monday', 'Tuesday', 'Sunday', 'Monday', 'Tuesday', 'Sunday',
            'Monday', 'Tuesday',
            'Sunday', 'Monday', 'Tuesday', 'Sunday', 'Monday', 'Tuesday', 'Sunday', 'Monday', 'Tuesday', 'Sunday',
            'Monday', 'Tuesday', ],
    'Temperature': [34, 32, 33, 36, 37, 35, 29, 32, 33, 32, 36, 30,
                    19, 22, 21, 17, 15, 14, 19, 20, 22, 20, 19, 18],
    'WorkingHours': [0, 9.5, 8.5, 0, 9, 8.5, 0, 10, 9.5, 0, 8, 8.5,
                     0, 8.5, 9, 0, 9, 9, 0, 10, 8, 0, 8.5, 9.5]}

df = pd.DataFrame(data)

print(corr_ratio(df['Temperature'], df['Day']))

However, the following error is produced. I would appreciate if you could let me know how to resolve it.

    print(corr_ratio(df['Temperature'], df['Day']))
  File "D:/mifs-master_2/MU/learning-from-imbalanced-classes-master/learning-from-imbalanced-classes-master/continuous/Final Logit/logit-final.py", line 383, in corr_ratio
    cat_means = {catname: np.mean(data_dict[catname]) for catname in categories}
  File "D:/mifs-master_2/MU/learning-from-imbalanced-classes-master/learning-from-imbalanced-classes-master/continuous/Final Logit/logit-final.py", line 383, in <dictcomp>
    cat_means = {catname: np.mean(data_dict[catname]) for catname in categories}
KeyError: 'Monday'

Thanks in advance.

taras · Accepted Answer · 2018-09-03 15:33:35Z

1

In this code snippet

for catname in categories:
    indices = np.where(category_labels == catname)
data_dict[catname] = values[indices]

data_dict[catname] assignment happens outside the for loop, so indenting it by one level fixes the issue.

for catname in categories:
    indices = np.where(category_labels == catname)
    data_dict[catname] = values[indices]

answered Sep 3, 2018 at 15:33

taras

6,93510 gold badges46 silver badges54 bronze badges

Sign up to request clarification or add additional context in comments.

1 Comment

ebrahimi Over a year ago

Thanks a lot for your time.

Collectives™ on Stack Overflow

Python: KeyError

1 Answer 1

1 Comment

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

1 Comment

Your Answer

Sign up or log in

Post as a guest

Related