{"id":1159456,"date":"2025-01-13T18:53:06","date_gmt":"2025-01-13T10:53:06","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1159456.html"},"modified":"2025-01-13T18:53:09","modified_gmt":"2025-01-13T10:53:09","slug":"python%e5%a6%82%e4%bd%95%e6%8a%8a%e6%95%b0%e6%8d%ae%e5%88%86%e7%bb%84%e8%be%93%e5%87%ba","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1159456.html","title":{"rendered":"python\u5982\u4f55\u628a\u6570\u636e\u5206\u7ec4\u8f93\u51fa"},"content":{"rendered":"

\"python\u5982\u4f55\u628a\u6570\u636e\u5206\u7ec4\u8f93\u51fa\"<\/p>\n

\u5728Python\u4e2d\uff0c\u53ef\u4ee5\u4f7f\u7528\u591a\u79cd\u65b9\u6cd5\u5c06\u6570\u636e\u5206\u7ec4\u8f93\u51fa\uff0c\u5e38\u89c1\u7684\u65b9\u6cd5\u5305\u62ec\u4f7f\u7528\u5b57\u5178\u3001\u4f7f\u7528Pandas\u5e93\u3001\u4f7f\u7528itertools.groupby\u51fd\u6570\u7b49<\/strong>\u3002\u5176\u4e2d\uff0c\u4f7f\u7528\u5b57\u5178\u8fdb\u884c\u5206\u7ec4\u662f\u6bd4\u8f83\u76f4\u89c2\u4e14\u5e38\u7528\u7684\u65b9\u6cd5\u3002\u5b57\u5178\u5141\u8bb8\u6211\u4eec\u5c06\u6570\u636e\u6309\u67d0\u4e2a\u952e\u503c\u8fdb\u884c\u5206\u7ec4<\/strong>\uff0c\u4ece\u800c\u5b9e\u73b0\u6570\u636e\u7684\u5206\u7c7b\u8f93\u51fa\u3002\u4e0b\u9762\u8be6\u7ec6\u5c55\u5f00\u89e3\u91ca\u5982\u4f55\u4f7f\u7528\u5b57\u5178\u8fdb\u884c\u6570\u636e\u5206\u7ec4\u3002<\/p>\n<\/p>\n

\u5047\u8bbe\u6211\u4eec\u6709\u4e00\u7ec4\u6570\u636e\uff0c\u8868\u793a\u4e0d\u540c\u5b66\u751f\u7684\u6210\u7ee9\uff0c\u5305\u62ec\u59d3\u540d\u3001\u79d1\u76ee\u548c\u5206\u6570\u3002\u6211\u4eec\u5e0c\u671b\u6309\u7167\u79d1\u76ee\u5bf9\u8fd9\u4e9b\u6570\u636e\u8fdb\u884c\u5206\u7ec4\u3002\u53ef\u4ee5\u4f7f\u7528\u5b57\u5178\u6765\u5b9e\u73b0\u8fd9\u4e00\u70b9\uff1a<\/p>\n<\/p>\n

# \u793a\u4f8b\u6570\u636e<\/p>\n
data = [<\/p>\n
    {'name': 'Alice', 'subject': 'Math', 'score': 85},<\/p>\n
    {'name': 'Bob', 'subject': 'Math', 'score': 90},<\/p>\n
    {'name': 'Alice', 'subject': 'English', 'score': 92},<\/p>\n
    {'name': 'Bob', 'subject': 'English', 'score': 88},<\/p>\n
    {'name': 'Charlie', 'subject': 'Math', 'score': 95},<\/p>\n
    {'name': 'Charlie', 'subject': 'English', 'score': 85}<\/p>\n
]<\/p>\n
\u4f7f\u7528\u5b57\u5178\u8fdb\u884c\u5206\u7ec4<\/strong><\/h2>\n
grouped_data = {}<\/p>\n
for entry in data:<\/p>\n
    subject = entry['subject']<\/p>\n
    if subject not in grouped_data:<\/p>\n
        grouped_data[subject] = []<\/p>\n
    grouped_data[subject].append(entry)<\/p>\n
\u8f93\u51fa\u5206\u7ec4\u540e\u7684\u6570\u636e<\/strong><\/h2>\n
for subject, entries in grouped_data.items():<\/p>\n
    print(f"Subject: {subject}")<\/p>\n
    for entry in entries:<\/p>\n
        print(entry)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e0a\u8ff0\u4ee3\u7801\u901a\u8fc7\u904d\u5386\u6570\u636e\u5217\u8868\uff0c\u5c06\u6bcf\u4e00\u6761\u6570\u636e\u6309\u79d1\u76ee\u5206\u7ec4\u5230\u5b57\u5178\u4e2d\uff0c\u5e76\u6700\u7ec8\u6253\u5370\u51fa\u5206\u7ec4\u540e\u7684\u6570\u636e\u3002\u8fd9\u79cd\u65b9\u6cd5\u7b80\u5355\u76f4\u89c2\uff0c\u9002\u7528\u4e8e\u6570\u636e\u91cf\u8f83\u5c0f\u6216\u7ed3\u6784\u8f83\u4e3a\u7b80\u5355\u7684\u60c5\u51b5<\/strong>\u3002<\/p>\n<\/p>\n
\n
\u4e00\u3001\u4f7f\u7528\u5b57\u5178\u8fdb\u884c\u6570\u636e\u5206\u7ec4<\/h2>\n<\/p>\n
1\u3001\u57fa\u672c\u5b9e\u73b0<\/h3>\n<\/p>\n
\u5b57\u5178\u662f\u4e00\u79cd\u975e\u5e38\u7075\u6d3b\u7684\u6570\u636e\u7ed3\u6784\uff0c\u9002\u7528\u4e8e\u5404\u79cd\u6570\u636e\u5206\u7ec4\u573a\u666f\u3002\u901a\u8fc7\u5b57\u5178\u7684\u952e\u503c\u5bf9\uff0c\u6211\u4eec\u53ef\u4ee5\u65b9\u4fbf\u5730\u5c06\u6570\u636e\u6309\u67d0\u4e2a\u5b57\u6bb5\u8fdb\u884c\u5206\u7ec4\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u5177\u4f53\u793a\u4f8b\uff0c\u6f14\u793a\u5982\u4f55\u4f7f\u7528\u5b57\u5178\u5bf9\u5b66\u751f\u6210\u7ee9\u6570\u636e\u6309\u79d1\u76ee\u8fdb\u884c\u5206\u7ec4\uff1a<\/p>\n<\/p>\n
# \u793a\u4f8b\u6570\u636e<\/p>\n
data = [<\/p>\n
    {'name': 'Alice', 'subject': 'Math', 'score': 85},<\/p>\n
    {'name': 'Bob', 'subject': 'Math', 'score': 90},<\/p>\n
    {'name': 'Alice', 'subject': 'English', 'score': 92},<\/p>\n
    {'name': 'Bob', 'subject': 'English', 'score': 88},<\/p>\n
    {'name': 'Charlie', 'subject': 'Math', 'score': 95},<\/p>\n
    {'name': 'Charlie', 'subject': 'English', 'score': 85}<\/p>\n
]<\/p>\n
\u4f7f\u7528\u5b57\u5178\u8fdb\u884c\u5206\u7ec4<\/strong><\/h2>\n
grouped_data = {}<\/p>\n
for entry in data:<\/p>\n
    subject = entry['subject']<\/p>\n
    if subject not in grouped_data:<\/p>\n
        grouped_data[subject] = []<\/p>\n
    grouped_data[subject].append(entry)<\/p>\n
\u8f93\u51fa\u5206\u7ec4\u540e\u7684\u6570\u636e<\/strong><\/h2>\n
for subject, entries in grouped_data.items():<\/p>\n
    print(f"Subject: {subject}")<\/p>\n
    for entry in entries:<\/p>\n
        print(entry)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5728\u8fd9\u4e2a\u4f8b\u5b50\u4e2d\uff0c\u6211\u4eec\u9996\u5148\u521b\u5efa\u4e00\u4e2a\u7a7a\u5b57\u5178 grouped_data<\/code>\uff0c\u7136\u540e\u904d\u5386\u6570\u636e\u5217\u8868 data<\/code>\u3002\u5bf9\u4e8e\u6bcf\u4e00\u6761\u6570\u636e\uff0c\u6211\u4eec\u6839\u636e\u5176 subject<\/code> \u5b57\u6bb5\u5c06\u5176\u6dfb\u52a0\u5230\u5b57\u5178\u4e2d\u76f8\u5e94\u7684\u952e\u4e0b\u3002\u6700\u540e\uff0c\u6211\u4eec\u904d\u5386\u5b57\u5178\u5e76\u8f93\u51fa\u5206\u7ec4\u540e\u7684\u6570\u636e\u3002<\/p>\n<\/p>\n
2\u3001\u6269\u5c55\u529f\u80fd<\/h3>\n<\/p>\n
\u4f7f\u7528\u5b57\u5178\u8fdb\u884c\u6570\u636e\u5206\u7ec4\u65f6\uff0c\u6211\u4eec\u8fd8\u53ef\u4ee5\u6269\u5c55\u529f\u80fd\uff0c\u4f8b\u5982\u6309\u591a\u4e2a\u5b57\u6bb5\u8fdb\u884c\u5206\u7ec4\u3001\u7edf\u8ba1\u6bcf\u7ec4\u6570\u636e\u7684\u6570\u91cf\u6216\u6c42\u548c\u3002\u4ee5\u4e0b\u793a\u4f8b\u5c55\u793a\u4e86\u5982\u4f55\u6309\u591a\u4e2a\u5b57\u6bb5\uff08\u5982\u79d1\u76ee\u548c\u59d3\u540d\uff09\u8fdb\u884c\u5206\u7ec4\uff0c\u5e76\u7edf\u8ba1\u6bcf\u7ec4\u6570\u636e\u7684\u6570\u91cf\uff1a<\/p>\n<\/p>\n
from collections import defaultdict<\/p>\n
\u793a\u4f8b\u6570\u636e<\/strong><\/h2>\n
data = [<\/p>\n
    {'name': 'Alice', 'subject': 'Math', 'score': 85},<\/p>\n
    {'name': 'Bob', 'subject': 'Math', 'score': 90},<\/p>\n
    {'name': 'Alice', 'subject': 'English', 'score': 92},<\/p>\n
    {'name': 'Bob', 'subject': 'English', 'score': 88},<\/p>\n
    {'name': 'Charlie', 'subject': 'Math', 'score': 95},<\/p>\n
    {'name': 'Charlie', 'subject': 'English', 'score': 85}<\/p>\n
]<\/p>\n
\u4f7f\u7528\u5b57\u5178\u8fdb\u884c\u5206\u7ec4\uff0c\u5e76\u7edf\u8ba1\u6bcf\u7ec4\u6570\u636e\u7684\u6570\u91cf<\/strong><\/h2>\n
grouped_data = defaultdict(int)<\/p>\n
for entry in data:<\/p>\n
    key = (entry['subject'], entry['name'])<\/p>\n
    grouped_data[key] += 1<\/p>\n
\u8f93\u51fa\u5206\u7ec4\u540e\u7684\u6570\u636e\u53ca\u6570\u91cf<\/strong><\/h2>\n
for key, count in grouped_data.items():<\/p>\n
    subject, name = key<\/p>\n
    print(f"Subject: {subject}, Name: {name}, Count: {count}")<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5728\u8fd9\u4e2a\u4f8b\u5b50\u4e2d\uff0c\u6211\u4eec\u4f7f\u7528 defaultdict<\/code> \u6765\u7b80\u5316\u7edf\u8ba1\u8fc7\u7a0b\uff0c\u5e76\u4e14\u6309 subject<\/code> \u548c name<\/code> \u4e24\u4e2a\u5b57\u6bb5\u8fdb\u884c\u5206\u7ec4\u3002\u6700\u7ec8\u8f93\u51fa\u6bcf\u7ec4\u6570\u636e\u7684\u6570\u91cf\u3002<\/p>\n<\/p>\n
\u4e8c\u3001\u4f7f\u7528Pandas\u8fdb\u884c\u6570\u636e\u5206\u7ec4<\/h2>\n<\/p>\n
1\u3001\u57fa\u672c\u5b9e\u73b0<\/h3>\n<\/p>\n
Pandas\u662fPython\u4e2d\u4e00\u4e2a\u5f3a\u5927\u7684\u6570\u636e\u5904\u7406\u5e93\uff0c\u63d0\u4f9b\u4e86\u8bb8\u591a\u65b9\u4fbf\u7684\u6570\u636e\u64cd\u4f5c\u529f\u80fd\u3002\u4f7f\u7528Pandas\uff0c\u6211\u4eec\u53ef\u4ee5\u66f4\u9ad8\u6548\u5730\u5bf9\u6570\u636e\u8fdb\u884c\u5206\u7ec4\u548c\u5904\u7406\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u793a\u4f8b\uff0c\u6f14\u793a\u5982\u4f55\u4f7f\u7528Pandas\u5bf9\u5b66\u751f\u6210\u7ee9\u6570\u636e\u6309\u79d1\u76ee\u8fdb\u884c\u5206\u7ec4\uff1a<\/p>\n<\/p>\n
import pandas as pd<\/p>\n
\u793a\u4f8b\u6570\u636e<\/strong><\/h2>\n
data = [<\/p>\n
    {'name': 'Alice', 'subject': 'Math', 'score': 85},<\/p>\n
    {'name': 'Bob', 'subject': 'Math', 'score': 90},<\/p>\n
    {'name': 'Alice', 'subject': 'English', 'score': 92},<\/p>\n
    {'name': 'Bob', 'subject': 'English', 'score': 88},<\/p>\n
    {'name': 'Charlie', 'subject': 'Math', 'score': 95},<\/p>\n
    {'name': 'Charlie', 'subject': 'English', 'score': 85}<\/p>\n
]<\/p>\n
\u521b\u5efaDataFrame<\/strong><\/h2>\n
df = pd.DataFrame(data)<\/p>\n
\u6309\u79d1\u76ee\u5206\u7ec4<\/strong><\/h2>\n
grouped = df.groupby('subject')<\/p>\n
\u8f93\u51fa\u5206\u7ec4\u540e\u7684\u6570\u636e<\/strong><\/h2>\n
for subject, group in grouped:<\/p>\n
    print(f"Subject: {subject}")<\/p>\n
    print(group)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5728\u8fd9\u4e2a\u4f8b\u5b50\u4e2d\uff0c\u6211\u4eec\u9996\u5148\u5c06\u6570\u636e\u8f6c\u6362\u4e3a\u4e00\u4e2aPandas DataFrame\uff0c\u7136\u540e\u4f7f\u7528 groupby<\/code> \u65b9\u6cd5\u6309 subject<\/code> \u8fdb\u884c\u5206\u7ec4\u3002\u6700\u540e\uff0c\u6211\u4eec\u904d\u5386\u5206\u7ec4\u5bf9\u8c61\u5e76\u8f93\u51fa\u5206\u7ec4\u540e\u7684\u6570\u636e\u3002<\/p>\n<\/p>\n
2\u3001\u6269\u5c55\u529f\u80fd<\/h3>\n<\/p>\n
Pandas\u63d0\u4f9b\u4e86\u4e30\u5bcc\u7684\u5206\u7ec4\u64cd\u4f5c\u529f\u80fd\uff0c\u5982\u805a\u5408\u3001\u8fc7\u6ee4\u3001\u8f6c\u6362\u7b49\u3002\u4ee5\u4e0b\u793a\u4f8b\u5c55\u793a\u4e86\u5982\u4f55\u5728\u5206\u7ec4\u7684\u57fa\u7840\u4e0a\u8fdb\u884c\u805a\u5408\u64cd\u4f5c\uff0c\u4f8b\u5982\u8ba1\u7b97\u6bcf\u4e2a\u79d1\u76ee\u7684\u5e73\u5747\u5206\u6570\uff1a<\/p>\n<\/p>\n
import pandas as pd<\/p>\n
\u793a\u4f8b\u6570\u636e<\/strong><\/h2>\n
data = [<\/p>\n
    {'name': 'Alice', 'subject': 'Math', 'score': 85},<\/p>\n
    {'name': 'Bob', 'subject': 'Math', 'score': 90},<\/p>\n
    {'name': 'Alice', 'subject': 'English', 'score': 92},<\/p>\n
    {'name': 'Bob', 'subject': 'English', 'score': 88},<\/p>\n
    {'name': 'Charlie', 'subject': 'Math', 'score': 95},<\/p>\n
    {'name': 'Charlie', 'subject': 'English', 'score': 85}<\/p>\n
]<\/p>\n
\u521b\u5efaDataFrame<\/strong><\/h2>\n
df = pd.DataFrame(data)<\/p>\n
\u6309\u79d1\u76ee\u5206\u7ec4\uff0c\u5e76\u8ba1\u7b97\u5e73\u5747\u5206\u6570<\/strong><\/h2>\n
grouped = df.groupby('subject')['score'].mean()<\/p>\n
\u8f93\u51fa\u5206\u7ec4\u540e\u7684\u5e73\u5747\u5206\u6570<\/strong><\/h2>\n
print(grouped)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5728\u8fd9\u4e2a\u4f8b\u5b50\u4e2d\uff0c\u6211\u4eec\u4f7f\u7528 groupby<\/code> \u65b9\u6cd5\u6309 subject<\/code> \u5206\u7ec4\uff0c\u5e76\u4f7f\u7528 mean<\/code> \u65b9\u6cd5\u8ba1\u7b97\u6bcf\u4e2a\u79d1\u76ee\u7684\u5e73\u5747\u5206\u6570\u3002\u6700\u7ec8\u8f93\u51fa\u6bcf\u4e2a\u79d1\u76ee\u7684\u5e73\u5747\u5206\u6570\u3002<\/p>\n<\/p>\n
3\u3001\u9ad8\u7ea7\u529f\u80fd<\/h3>\n<\/p>\n
Pandas\u8fd8\u63d0\u4f9b\u4e86\u8bb8\u591a\u9ad8\u7ea7\u529f\u80fd\uff0c\u5982\u591a\u7ea7\u7d22\u5f15\u3001\u5206\u7ec4\u540e\u7684\u6570\u636e\u8f6c\u6362\u7b49\u3002\u4ee5\u4e0b\u793a\u4f8b\u5c55\u793a\u4e86\u5982\u4f55\u4f7f\u7528\u591a\u7ea7\u7d22\u5f15\u8fdb\u884c\u5206\u7ec4\uff0c\u5e76\u5728\u5206\u7ec4\u540e\u7684\u6570\u636e\u4e0a\u5e94\u7528\u81ea\u5b9a\u4e49\u51fd\u6570\uff1a<\/p>\n<\/p>\n
import pandas as pd<\/p>\n
\u793a\u4f8b\u6570\u636e<\/strong><\/h2>\n
data = [<\/p>\n
    {'name': 'Alice', 'subject': 'Math', 'score': 85},<\/p>\n
    {'name': 'Bob', 'subject': 'Math', 'score': 90},<\/p>\n
    {'name': 'Alice', 'subject': 'English', 'score': 92},<\/p>\n
    {'name': 'Bob', 'subject': 'English', 'score': 88},<\/p>\n
    {'name': 'Charlie', 'subject': 'Math', 'score': 95},<\/p>\n
    {'name': 'Charlie', 'subject': 'English', 'score': 85}<\/p>\n
]<\/p>\n
\u521b\u5efaDataFrame<\/strong><\/h2>\n
df = pd.DataFrame(data)<\/p>\n
\u6309\u79d1\u76ee\u548c\u59d3\u540d\u8fdb\u884c\u591a\u7ea7\u7d22\u5f15\u5206\u7ec4<\/strong><\/h2>\n
grouped = df.groupby(['subject', 'name'])<\/p>\n
\u81ea\u5b9a\u4e49\u51fd\u6570\uff0c\u8ba1\u7b97\u5206\u6570\u7684\u6807\u51c6\u5316\u5206\u6570<\/strong><\/h2>\n
def standardize(x):<\/p>\n
    return (x - x.mean()) \/ x.std()<\/p>\n
\u5728\u5206\u7ec4\u540e\u7684\u6570\u636e\u4e0a\u5e94\u7528\u81ea\u5b9a\u4e49\u51fd\u6570<\/strong><\/h2>\n
standardized_scores = grouped['score'].apply(standardize)<\/p>\n
\u8f93\u51fa\u6807\u51c6\u5316\u540e\u7684\u5206\u6570<\/strong><\/h2>\n
print(standardized_scores)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5728\u8fd9\u4e2a\u4f8b\u5b50\u4e2d\uff0c\u6211\u4eec\u4f7f\u7528 groupby<\/code> \u65b9\u6cd5\u6309 subject<\/code> \u548c name<\/code> \u8fdb\u884c\u591a\u7ea7\u7d22\u5f15\u5206\u7ec4\uff0c\u5e76\u5b9a\u4e49\u4e00\u4e2a\u81ea\u5b9a\u4e49\u51fd\u6570 standardize<\/code> \u6765\u8ba1\u7b97\u5206\u6570\u7684\u6807\u51c6\u5316\u5206\u6570\u3002\u6700\u540e\uff0c\u6211\u4eec\u5728\u5206\u7ec4\u540e\u7684\u6570\u636e\u4e0a\u5e94\u7528\u8fd9\u4e2a\u81ea\u5b9a\u4e49\u51fd\u6570\uff0c\u5e76\u8f93\u51fa\u6807\u51c6\u5316\u540e\u7684\u5206\u6570\u3002<\/p>\n<\/p>\n
\u4e09\u3001\u4f7f\u7528itertools.groupby\u8fdb\u884c\u6570\u636e\u5206\u7ec4<\/h2>\n<\/p>\n
1\u3001\u57fa\u672c\u5b9e\u73b0<\/h3>\n<\/p>\n
itertools.groupby<\/code> \u662fPython\u6807\u51c6\u5e93\u4e2d\u7684\u4e00\u4e2a\u51fd\u6570\uff0c\u9002\u7528\u4e8e\u5bf9\u6392\u5e8f\u540e\u7684\u6570\u636e\u8fdb\u884c\u5206\u7ec4\u3002\u5b83\u7684\u4f7f\u7528\u8981\u6c42\u6570\u636e\u662f\u6309\u7167\u9700\u8981\u5206\u7ec4\u7684\u952e\u8fdb\u884c\u6392\u5e8f\u7684\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u793a\u4f8b\uff0c\u6f14\u793a\u5982\u4f55\u4f7f\u7528 itertools.groupby<\/code> \u5bf9\u5b66\u751f\u6210\u7ee9\u6570\u636e\u6309\u79d1\u76ee\u8fdb\u884c\u5206\u7ec4\uff1a<\/p>\n<\/p>\n
import itertools<\/p>\n
\u793a\u4f8b\u6570\u636e<\/strong><\/h2>\n
data = [<\/p>\n
    {'name': 'Alice', 'subject': 'Math', 'score': 85},<\/p>\n
    {'name': 'Bob', 'subject': 'Math', 'score': 90},<\/p>\n
    {'name': 'Alice', 'subject': 'English', 'score': 92},<\/p>\n
    {'name': 'Bob', 'subject': 'English', 'score': 88},<\/p>\n
    {'name': 'Charlie', 'subject': 'Math', 'score': 95},<\/p>\n
    {'name': 'Charlie', 'subject': 'English', 'score': 85}<\/p>\n
]<\/p>\n
\u6392\u5e8f\u6570\u636e<\/strong><\/h2>\n
data.sort(key=lambda x: x['subject'])<\/p>\n
\u4f7f\u7528itertools.groupby\u8fdb\u884c\u5206\u7ec4<\/strong><\/h2>\n
grouped = itertools.groupby(data, key=lambda x: x['subject'])<\/p>\n
\u8f93\u51fa\u5206\u7ec4\u540e\u7684\u6570\u636e<\/strong><\/h2>\n
for subject, group in grouped:<\/p>\n
    print(f"Subject: {subject}")<\/p>\n
    for entry in group:<\/p>\n
        print(entry)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5728\u8fd9\u4e2a\u4f8b\u5b50\u4e2d\uff0c\u6211\u4eec\u9996\u5148\u5bf9\u6570\u636e\u6309 subject<\/code> \u5b57\u6bb5\u8fdb\u884c\u6392\u5e8f\uff0c\u7136\u540e\u4f7f\u7528 itertools.groupby<\/code> \u8fdb\u884c\u5206\u7ec4\u3002\u6700\u540e\uff0c\u904d\u5386\u5206\u7ec4\u5bf9\u8c61\u5e76\u8f93\u51fa\u5206\u7ec4\u540e\u7684\u6570\u636e\u3002<\/p>\n<\/p>\n
2\u3001\u6269\u5c55\u529f\u80fd<\/h3>\n<\/p>\n
itertools.groupby<\/code> \u9002\u7528\u4e8e\u7b80\u5355\u7684\u5206\u7ec4\u64cd\u4f5c\uff0c\u4f46\u4e0d\u5982Pandas\u90a3\u6837\u529f\u80fd\u5f3a\u5927\u3002\u4ee5\u4e0b\u793a\u4f8b\u5c55\u793a\u4e86\u5982\u4f55\u4f7f\u7528 itertools.groupby<\/code> \u548c defaultdict<\/code> \u7ed3\u5408\uff0c\u6309\u591a\u4e2a\u5b57\u6bb5\u8fdb\u884c\u5206\u7ec4\u5e76\u7edf\u8ba1\u6bcf\u7ec4\u6570\u636e\u7684\u6570\u91cf\uff1a<\/p>\n<\/p>\n
import itertools<\/p>\n
from collections import defaultdict<\/p>\n
\u793a\u4f8b\u6570\u636e<\/strong><\/h2>\n
data = [<\/p>\n
    {'name': 'Alice', 'subject': 'Math', 'score': 85},<\/p>\n
    {'name': 'Bob', 'subject': 'Math', 'score': 90},<\/p>\n
    {'name': 'Alice', 'subject': 'English', 'score': 92},<\/p>\n
    {'name': 'Bob', 'subject': 'English', 'score': 88},<\/p>\n
    {'name': 'Charlie', 'subject': 'Math', 'score': 95},<\/p>\n
    {'name': 'Charlie', 'subject': 'English', 'score': 85}<\/p>\n
]<\/p>\n
\u6392\u5e8f\u6570\u636e<\/strong><\/h2>\n
data.sort(key=lambda x: (x['subject'], x['name']))<\/p>\n
\u4f7f\u7528itertools.groupby\u8fdb\u884c\u5206\u7ec4<\/strong><\/h2>\n
grouped = itertools.groupby(data, key=lambda x: (x['subject'], x['name']))<\/p>\n
\u4f7f\u7528defaultdict\u7edf\u8ba1\u6bcf\u7ec4\u6570\u636e\u7684\u6570\u91cf<\/strong><\/h2>\n
grouped_data = defaultdict(int)<\/p>\n
for key, group in grouped:<\/p>\n
    for entry in group:<\/p>\n
        grouped_data[key] += 1<\/p>\n
\u8f93\u51fa\u5206\u7ec4\u540e\u7684\u6570\u636e\u53ca\u6570\u91cf<\/strong><\/h2>\n
for key, count in grouped_data.items():<\/p>\n
    subject, name = key<\/p>\n
    print(f"Subject: {subject}, Name: {name}, Count: {count}")<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5728\u8fd9\u4e2a\u4f8b\u5b50\u4e2d\uff0c\u6211\u4eec\u5bf9\u6570\u636e\u6309 subject<\/code> \u548c name<\/code> \u5b57\u6bb5\u8fdb\u884c\u6392\u5e8f\uff0c\u7136\u540e\u4f7f\u7528 itertools.groupby<\/code> \u8fdb\u884c\u5206\u7ec4\uff0c\u5e76\u4f7f\u7528 defaultdict<\/code> \u7edf\u8ba1\u6bcf\u7ec4\u6570\u636e\u7684\u6570\u91cf\u3002\u6700\u7ec8\u8f93\u51fa\u6bcf\u7ec4\u6570\u636e\u7684\u6570\u91cf\u3002<\/p>\n<\/p>\n
\u56db\u3001\u4f7f\u7528SQLAlchemy\u8fdb\u884c\u6570\u636e\u5206\u7ec4<\/h2>\n<\/p>\n
1\u3001\u57fa\u672c\u5b9e\u73b0<\/h3>\n<\/p>\n
SQLAlchemy\u662fPython\u4e2d\u4e00\u4e2a\u5f3a\u5927\u7684SQL\u5de5\u5177\u5305\u548c\u5bf9\u8c61\u5173\u7cfb\u6620\u5c04\u5668\uff08ORM\uff09\uff0c\u9002\u7528\u4e8e\u5bf9\u6570\u636e\u5e93\u8fdb\u884c\u64cd\u4f5c\u3002\u4f7f\u7528SQLAlchemy\uff0c\u6211\u4eec\u53ef\u4ee5\u5bf9\u6570\u636e\u5e93\u4e2d\u7684\u6570\u636e\u8fdb\u884c\u5206\u7ec4\u548c\u5904\u7406\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u793a\u4f8b\uff0c\u6f14\u793a\u5982\u4f55\u4f7f\u7528SQLAlchemy\u5bf9\u5b66\u751f\u6210\u7ee9\u6570\u636e\u6309\u79d1\u76ee\u8fdb\u884c\u5206\u7ec4\uff1a<\/p>\n<\/p>\n
from sqlalchemy import create_engine, Column, Integer, String, select<\/p>\n
from sqlalchemy.ext.declarative import declarative_base<\/p>\n
from sqlalchemy.orm import sessionmaker<\/p>\n
\u521b\u5efa\u6570\u636e\u5e93\u5f15\u64ce<\/strong><\/h2>\n
engine = create_engine('sqlite:\/\/\/:memory:', echo=True)<\/p>\n
\u521b\u5efa\u57fa\u7c7b<\/strong><\/h2>\n
Base = declarative_base()<\/p>\n
\u5b9a\u4e49\u5b66\u751f\u6210\u7ee9\u8868<\/strong><\/h2>\n
class StudentScore(Base):<\/p>\n
    __tablename__ = 'student_scores'<\/p>\n
    id = Column(Integer, primary_key=True)<\/p>\n
    name = Column(String)<\/p>\n
    subject = Column(String)<\/p>\n
    score = Column(Integer)<\/p>\n
\u521b\u5efa\u8868<\/strong><\/h2>\n
Base.metadata.create_all(engine)<\/p>\n
\u521b\u5efa\u4f1a\u8bdd<\/strong><\/h2>\n
Session = sessionmaker(bind=engine)<\/p>\n
session = Session()<\/p>\n
\u63d2\u5165\u793a\u4f8b\u6570\u636e<\/strong><\/h2>\n
data = [<\/p>\n
    {'name': 'Alice', 'subject': 'Math', 'score': 85},<\/p>\n
    {'name': 'Bob', 'subject': 'Math', 'score': 90},<\/p>\n
    {'name': 'Alice', 'subject': 'English', 'score': 92},<\/p>\n
    {'name': 'Bob', 'subject': 'English', 'score': 88},<\/p>\n
    {'name': 'Charlie', 'subject': 'Math', 'score': 95},<\/p>\n
    {'name': 'Charlie', 'subject': 'English', 'score': 85}<\/p>\n
]<\/p>\n
for entry in data:<\/p>\n
    student_score = StudentScore(entry)<\/p>\n
    session.add(student_score)<\/p>\n
session.commit()<\/p>\n
\u4f7f\u7528SQLAlchemy\u8fdb\u884c\u5206\u7ec4\u67e5\u8be2<\/strong><\/h2>\n
stmt = select(StudentScore.subject, StudentScore.name, StudentScore.score).order_by(StudentScore.subject)<\/p>\n
result = session.execute(stmt).fetchall()<\/p>\n
\u4f7f\u7528\u5b57\u5178\u8fdb\u884c\u5206\u7ec4<\/strong><\/h2>\n
grouped_data = {}<\/p>\n
for entry in result:<\/p>\n
    subject = entry[0]<\/p>\n
    if subject not in grouped_data:<\/p>\n
        grouped_data[subject] = []<\/p>\n
    grouped_data[subject].append(entry)<\/p>\n
\u8f93\u51fa\u5206\u7ec4\u540e\u7684\u6570\u636e<\/strong><\/h2>\n
for subject, entries in grouped_data.items():<\/p>\n
    print(f"Subject: {subject}")<\/p>\n
    for entry in entries:<\/p>\n
        print(entry)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5728\u8fd9\u4e2a\u4f8b\u5b50\u4e2d\uff0c\u6211\u4eec\u4f7f\u7528SQLAlchemy\u521b\u5efa\u4e00\u4e2a\u5185\u5b58\u6570\u636e\u5e93\uff0c\u5e76\u5b9a\u4e49\u4e00\u4e2a\u5b66\u751f\u6210\u7ee9\u8868\u3002\u7136\u540e\u63d2\u5165\u793a\u4f8b\u6570\u636e\uff0c\u5e76\u4f7f\u7528SQLAlchemy\u7684\u67e5\u8be2\u529f\u80fd\u6309 subject<\/code> \u8fdb\u884c\u5206\u7ec4\u3002\u6700\u540e\uff0c\u5c06\u67e5\u8be2\u7ed3\u679c\u6309 subject<\/code> \u5b57\u6bb5\u5206\u7ec4\u5e76\u8f93\u51fa\u3002<\/p>\n<\/p>\n
2\u3001\u6269\u5c55\u529f\u80fd<\/h3>\n<\/p>\n
SQLAlchemy\u63d0\u4f9b\u4e86\u4e30\u5bcc\u7684\u67e5\u8be2\u548c\u805a\u5408\u529f\u80fd\u3002\u4ee5\u4e0b\u793a\u4f8b\u5c55\u793a\u4e86\u5982\u4f55\u4f7f\u7528SQLAlchemy\u8fdb\u884c\u5206\u7ec4\u5e76\u8ba1\u7b97\u6bcf\u4e2a\u79d1\u76ee\u7684\u5e73\u5747\u5206\u6570\uff1a<\/p>\n<\/p>\n
from sqlalchemy import create_engine, Column, Integer, String, func<\/p>\n
from sqlalchemy.ext.declarative import declarative_base<\/p>\n
from sqlalchemy.orm import sessionmaker<\/p>\n
\u521b\u5efa\u6570\u636e\u5e93\u5f15\u64ce<\/strong><\/h2>\n
engine = create_engine('sqlite:\/\/\/:memory:', echo=True)<\/p>\n
\u521b\u5efa\u57fa\u7c7b<\/strong><\/h2>\n
Base = declarative_base()<\/p>\n
\u5b9a\u4e49\u5b66\u751f\u6210\u7ee9\u8868<\/strong><\/h2>\n
class StudentScore(Base):<\/p>\n
    __tablename__ = 'student_scores'<\/p>\n
    id = Column(Integer, primary_key=True)<\/p>\n
    name = Column(String)<\/p>\n
    subject = Column(String)<\/p>\n
    score = Column(Integer)<\/p>\n
\u521b\u5efa\u8868<\/strong><\/h2>\n
Base.metadata.create_all(engine)<\/p>\n
\u521b\u5efa\u4f1a\u8bdd<\/strong><\/h2>\n
Session = sessionmaker(bind=engine)<\/p>\n
session = Session()<\/p>\n
\u63d2\u5165\u793a\u4f8b\u6570\u636e<\/strong><\/h2>\n
data = [<\/p>\n
    {'name': 'Alice', 'subject': 'Math', 'score': 85},<\/p>\n
    {'name': 'Bob', 'subject': 'Math', 'score': 90},<\/p>\n
    {'name': 'Alice', 'subject': 'English', 'score': 92},<\/p>\n
    {'name': 'Bob', 'subject': 'English', 'score': 88},<\/p>\n
    {'name': 'Charlie', 'subject': 'Math', 'score': 95},<\/p>\n
    {'name': 'Charlie', 'subject': 'English', 'score': 85}<\/p>\n
]<\/p>\n
for entry in data:<\/p>\n
    student_score = StudentScore(entry)<\/p>\n
    session.add(student_score)<\/p>\n
session.commit()<\/p>\n
\u4f7f\u7528SQLAlchemy\u8fdb\u884c\u5206\u7ec4\u67e5\u8be2\uff0c\u5e76\u8ba1\u7b97\u5e73\u5747\u5206\u6570<\/strong><\/h2>\n
stmt = session.query(StudentScore.subject, func.avg(StudentScore.score)).group_by(StudentScore.subject)<\/p>\n
result = session.execute(stmt).fetchall()<\/p>\n
\u8f93\u51fa\u5206\u7ec4\u540e\u7684\u5e73\u5747\u5206\u6570<\/strong><\/h2>\n
for entry in result:<\/p>\n
    print(f"Subject: {entry[0]}, Average Score: {entry[1]}")<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5728\u8fd9\u4e2a\u4f8b\u5b50\u4e2d\uff0c\u6211\u4eec\u4f7f\u7528SQLAlchemy\u7684\u805a\u5408\u51fd\u6570 func.avg<\/code> \u8ba1\u7b97\u6bcf\u4e2a\u79d1\u76ee\u7684\u5e73\u5747\u5206\u6570\uff0c\u5e76\u4f7f\u7528 group_by<\/code> \u65b9\u6cd5\u6309 subject<\/code> \u5206\u7ec4\u3002\u6700\u7ec8\u8f93\u51fa\u6bcf\u4e2a\u79d1\u76ee\u7684\u5e73\u5747\u5206\u6570\u3002<\/p>\n<\/p>\n
\u901a\u8fc7\u8fd9\u4e9b\u793a\u4f8b\uff0c\u6211\u4eec\u53ef\u4ee5\u770b\u5230\uff0cPython\u63d0\u4f9b\u4e86\u591a\u79cd\u65b9\u6cd5\u6765\u5bf9\u6570\u636e\u8fdb\u884c\u5206<\/p>\n<\/p>\n
\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n
 \u5982\u4f55\u5728Python\u4e2d\u5bf9\u6570\u636e\u8fdb\u884c\u5206\u7ec4\uff1f<\/strong>
\u5728Python\u4e2d\uff0c\u60a8\u53ef\u4ee5\u4f7f\u7528pandas<\/code>\u5e93\u6765\u8f7b\u677e\u5bf9\u6570\u636e\u8fdb\u884c\u5206\u7ec4\u3002\u901a\u8fc7groupby()<\/code>\u65b9\u6cd5\uff0c\u60a8\u53ef\u4ee5\u6839\u636e\u7279\u5b9a\u7684\u5217\u5bf9\u6570\u636e\u8fdb\u884c\u5206\u7ec4\uff0c\u5e76\u5bf9\u6bcf\u4e2a\u5206\u7ec4\u5e94\u7528\u805a\u5408\u51fd\u6570\uff0c\u4f8b\u5982\u6c42\u548c\u3001\u5e73\u5747\u503c\u6216\u8ba1\u6570\u7b49\u3002\u793a\u4f8b\u4ee3\u7801\u5982\u4e0b\uff1a<\/p>\n
import pandas as pd\n\ndata = {\n    '\u7c7b\u522b': ['A', 'B', 'A', 'B', 'A'],\n    '\u503c': [10, 20, 30, 40, 50]\n}\ndf = pd.DataFrame(data)\ngrouped = df.groupby('\u7c7b\u522b').sum()\nprint(grouped)\n<\/code><\/pre>\n
\u8fd9\u5c06\u8f93\u51fa\u6bcf\u4e2a\u7c7b\u522b\u7684\u503c\u603b\u548c\u3002<\/p>\n
\u4f7f\u7528Python\u6709\u54ea\u4e9b\u5de5\u5177\u53ef\u4ee5\u5b9e\u73b0\u6570\u636e\u5206\u7ec4\uff1f<\/strong>
\u9664\u4e86pandas<\/code>\u5916\uff0cPython\u4e2d\u8fd8\u53ef\u4ee5\u4f7f\u7528numpy<\/code>\u548citertools<\/code>\u7b49\u5e93\u6765\u5b9e\u73b0\u6570\u636e\u5206\u7ec4\u3002numpy<\/code>\u9002\u5408\u5904\u7406\u6570\u503c\u6570\u7ec4\uff0c\u800citertools.groupby()<\/code>\u5219\u53ef\u4ee5\u7528\u4e8e\u5bf9\u5df2\u6392\u5e8f\u7684\u6570\u636e\u8fdb\u884c\u5206\u7ec4\u3002\u9009\u62e9\u5408\u9002\u7684\u5de5\u5177\u53d6\u51b3\u4e8e\u60a8\u7684\u6570\u636e\u7c7b\u578b\u548c\u5177\u4f53\u9700\u6c42\u3002<\/p>\n
\u5982\u4f55\u5904\u7406\u5206\u7ec4\u540e\u7684\u6570\u636e\uff1f<\/strong>
\u4e00\u65e6\u60a8\u5bf9\u6570\u636e\u8fdb\u884c\u4e86\u5206\u7ec4\uff0c\u53ef\u4ee5\u4f7f\u7528\u805a\u5408\u51fd\u6570\u6765\u8ba1\u7b97\u5404\u7ec4\u7684\u7edf\u8ba1\u4fe1\u606f\u3002\u4f8b\u5982\uff0c\u53ef\u4ee5\u4f7f\u7528.mean()<\/code>\u3001.count()<\/code>\u6216.agg()<\/code>\u7b49\u65b9\u6cd5\u6765\u83b7\u53d6\u6bcf\u4e2a\u5206\u7ec4\u7684\u5e73\u5747\u503c\u3001\u8ba1\u6570\u6216\u5176\u4ed6\u81ea\u5b9a\u4e49\u7edf\u8ba1\u4fe1\u606f\u3002\u8fd9\u4f7f\u5f97\u60a8\u80fd\u591f\u5feb\u901f\u4e86\u89e3\u6570\u636e\u7684\u6574\u4f53\u8d8b\u52bf\u548c\u7279\u5f81\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u5728Python\u4e2d\uff0c\u53ef\u4ee5\u4f7f\u7528\u591a\u79cd\u65b9\u6cd5\u5c06\u6570\u636e\u5206\u7ec4\u8f93\u51fa\uff0c\u5e38\u89c1\u7684\u65b9\u6cd5\u5305\u62ec\u4f7f\u7528\u5b57\u5178\u3001\u4f7f\u7528Pandas\u5e93\u3001\u4f7f\u7528iterto […]","protected":false},"author":3,"featured_media":1159466,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[37],"tags":[],"acf":[],"_links":{"self":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1159456"}],"collection":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/comments?post=1159456"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1159456\/revisions"}],"predecessor-version":[{"id":1159469,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1159456\/revisions\/1159469"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1159466"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1159456"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1159456"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1159456"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}