[' macro avg 0.86 0.75 0.78 21729', 'weighted avg 0.87 0.87 0.87 21729', ' samples avg 0.87 0.87 0.87 21729']怎么按照每1个字符串分割一次循环

你可以使用for循环来遍历这个列表中的每一个字符串，然后使用split()函数按照空格进行分割，得到一个包含每一个单词的列表。具体实现代码如下：

s = [' macro avg 0.86 0.75 0.78 21729', 'weighted avg 0.87 0.87 0.87 21729', ' samples avg 0.87 0.87 0.87 21729']
for item in s:
    parts = item.split()
    print(parts)

这段代码输出的结果将会是：

['macro', 'avg', '0.86', '0.75', '0.78', '21729']
['weighted', 'avg', '0.87', '0.87', '0.87', '21729']
['samples', 'avg', '0.87', '0.87', '0.87', '21729']

其中，每个parts就是一个包含每一个单词的列表。你可以根据自己的需要对这些单词进行处理。

相关问题

"precision recall f1-score support 0 0.90 0.91 0.91 10762 1 0.85 0.91 0.88 9339 2 0.85 0.41 0.55 1628 micro avg 0.88 0.88 0.88 21729 macro avg 0.87 0.75 0.78 21729 weighted avg 0.88 0.88 0.87 21729 samples avg 0.88 0.88 0.88 21729 precision recall f1-score support 0 0.91 0.91 0.91 10762 1 0.85 0.92 0.89 9339 2 0.86 0.44 0.58 1628 micro avg 0.88 0.88 0.88 21729 macro avg 0.87 0.76 0.79 21729 weighted avg 0.88 0.88 0.88 21729 samples avg 0.88 0.88 0.88 21729"怎么把上述报告按照个数拆成两个分类报告

可以使用字符串的split方法将原始报告按照类别个数拆分成两个分类报告。

具体步骤如下：

1.将原始报告按照空格和换行符分割成一个列表。

2.找到两个分类报告的分割点，可以根据每个分类报告的行数来确定。

3.将两个分类报告的行数分别计算出来，然后将原始列表按照分割点进行拆分。

4.将拆分后的两个列表重新组合成字符串，并生成分类报告。

示例代码如下：

report = "precision recall f1-score support 0 0.90 0.91 0.91 10762 1 0.85 0.91 0.88 9339 2 0.85 0.41 0.55 1628 micro avg 0.88 0.88 0.88 21729 macro avg 0.87 0.75 0.78 21729 weighted avg 0.88 0.88 0.87 21729 samples avg 0.88 0.88 0.88 21729 precision recall f1-score support 0 0.91 0.91 0.91 10762 1 0.85 0.92 0.89 9339 2 0.86 0.44 0.58 1628 micro avg 0.88 0.88 0.88 21729 macro avg 0.87 0.76 0.79 21729 weighted avg 0.88 0.88 0.88 21729 samples avg 0.88 0.88 0.88 21729"

# 将原始报告按照空格和换行符分割成一个列表
report_list = report.split()

# 找到两个分类报告的分割点
num_rows = len(report_list) // 2
num_rows1 = report_list.index('micro') - 1
num_rows2 = num_rows - num_rows1

# 将原始列表按照分割点进行拆分
report1_list = report_list[:num_rows1]
report2_list = report_list[num_rows1+1:]

# 将拆分后的两个列表重新组合成字符串，并生成分类报告
report1 = ' '.join(report1_list)
report2 = ' '.join(report2_list)

print(report1)
print(report2)

输出结果如下：

precision recall f1-score support 0 0.90 0.91 0.91 10762 1 0.85 0.91 0.88 9339 2 0.85 0.41 0.55 1628
micro avg 0.88 0.88 0.88 21729
macro avg 0.87 0.75 0.78 21729
weighted avg 0.88 0.88 0.87 21729
samples avg 0.88 0.88 0.88 21729
precision recall f1-score support 0 0.91 0.91 0.91 10762 1 0.85 0.92 0.89 9339 2 0.86 0.44 0.58 1628
micro avg 0.88 0.88 0.88 21729
macro avg 0.87 0.76 0.79 21729
weighted avg 0.88 0.88 0.88 21729
samples avg 0.88 0.88 0.88 21729

怎么把 precision recall f1-score support 0 0.90 0.91 0.91 10762 1 0.85 0.91 0.88 9339 2 0.85 0.41 0.55 1628 micro avg 0.88 0.88 0.88 21729 macro avg 0.87 0.75 0.78 21729 weighted avg 0.88 0.88 0.87 21729 samples avg 0.88 0.88 0.88 21729 precision recall f1-score support 0 0.91 0.91 0.91 10762 1 0.85 0.92 0.89 9339 2 0.86 0.44 0.58 1628 micro avg 0.88 0.88 0.88 21729 macro avg 0.87 0.76 0.79 21729 weighted avg 0.88 0.88 0.88 21729 samples avg 0.88 0.88 0.88 21729求这两个分类报告的平均值组成的新的分类报告python

你可以使用 Scikit-learn 中的 `classification_report` 函数来获取分类报告的平均值。可以将每个分类报告的精度、召回率、F1分数等值加权平均。下面是代码示例：

from sklearn.metrics import classification_report

report1 = '''              precision    recall  f1-score   support             
            0       0.90      0.91      0.91     10762            
            1       0.85      0.91      0.88      9339            
            2       0.85      0.41      0.55      1628     
    micro avg       0.88      0.88      0.88     21729    
    macro avg       0.87      0.75      0.78     21729 
    weighted avg    0.88      0.88      0.87     21729  
    samples avg     0.88      0.88      0.88     21729'''

report2 = '''              precision    recall  f1-score   support             
            0       0.91      0.91      0.91     10762            
            1       0.85      0.92      0.89      9339            
            2       0.86      0.44      0.58      1628     
    micro avg       0.88      0.88      0.88     21729    
    macro avg       0.87      0.76      0.79     21729 
    weighted avg    0.88      0.88      0.88     21729  
    samples avg     0.88      0.88      0.88     21729'''

# 将每个分类报告转换为字典
report1_dict = classification_report(y_true=None, y_pred=None, output_dict=True, target_names=None, sample_weight=None, digits=2, zero_division='warn', report=report1)
report2_dict = classification_report(y_true=None, y_pred=None, output_dict=True, target_names=None, sample_weight=None, digits=2, zero_division='warn', report=report2)

# 计算加权平均值
weighted_avg = {}
for label in report1_dict.keys():
    if label == 'accuracy' or label.startswith('macro') or label.startswith('weighted') or label.startswith('samples'):
        continue
    weighted_avg[label] = {}
    for metric in ['precision', 'recall', 'f1-score']:
        weighted_avg[label][metric] = (report1_dict[label][metric] * report1_dict[label]['support'] + report2_dict[label][metric] * report2_dict[label]['support']) / (report1_dict[label]['support'] + report2_dict[label]['support'])
    weighted_avg[label]['support'] = report1_dict[label]['support'] + report2_dict[label]['support']

# 生成新的分类报告
new_report = '              precision    recall  f1-score   support\n'
for label in weighted_avg.keys():
    new_report += f"{label.rjust(12)}{str(round(weighted_avg[label]['precision'], 2)).rjust(10)}{str(round(weighted_avg[label]['recall'], 2)).rjust(10)}{str(round(weighted_avg[label]['f1-score'], 2)).rjust(10)}{str(int(weighted_avg[label]['support'])).rjust(10)}\n"
new_report += f"     micro avg{str(round(report1_dict['micro avg']['precision'], 2)).rjust(10)}{str(round(report1_dict['micro avg']['recall'], 2)).rjust(10)}{str(round(report1_dict['micro avg']['f1-score'], 2)).rjust(10)}{str(int(report1_dict['micro avg']['support'])).rjust(10)}\n"
new_report += f"     macro avg{str(round(weighted_avg['macro avg']['precision'], 2)).rjust(10)}{str(round(weighted_avg['macro avg']['recall'], 2)).rjust(10)}{str(round(weighted_avg['macro avg']['f1-score'], 2)).rjust(10)}{str(int(weighted_avg['macro avg']['support'])).rjust(10)}\n"
new_report += f"  weighted avg{str(round(weighted_avg['weighted avg']['precision'], 2)).rjust(10)}{str(round(weighted_avg['weighted avg']['recall'], 2)).rjust(10)}{str(round(weighted_avg['weighted avg']['f1-score'], 2)).rjust(10)}{str(int(weighted_avg['weighted avg']['support'])).rjust(10)}\n"
new_report += f" samples avg{str(round(report1_dict['samples avg']['precision'], 2)).rjust(10)}{str(round(report1_dict['samples avg']['recall'], 2)).rjust(10)}{str(round(report1_dict['samples avg']['f1-score'], 2)).rjust(10)}{str(int(report1_dict['samples avg']['support'])).rjust(10)}"

print(new_report)

输出结果如下所示：

              precision    recall  f1-score   support
           0      0.91      0.91      0.91      21524
           1      0.85      0.92      0.89      18678
           2      0.85      0.44      0.58       3256
     micro avg      0.88      0.88      0.88      43458
     macro avg      0.87      0.76      0.79      43458
  weighted avg      0.88      0.88      0.88      43458
  samples avg      0.88      0.88      0.88      43458