{"id":968794,"date":"2024-12-27T05:10:18","date_gmt":"2024-12-26T21:10:18","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/968794.html"},"modified":"2024-12-27T05:10:20","modified_gmt":"2024-12-26T21:10:20","slug":"python%e5%a6%82%e4%bd%95%e8%ae%a1%e7%ae%97%e5%b0%b1%e9%a4%90%e4%ba%ba%e6%ac%a1","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/968794.html","title":{"rendered":"Python\u5982\u4f55\u8ba1\u7b97\u5c31\u9910\u4eba\u6b21"},"content":{"rendered":"

\"Python\u5982\u4f55\u8ba1\u7b97\u5c31\u9910\u4eba\u6b21\"<\/p>\n

\u5728Python\u4e2d\u8ba1\u7b97\u5c31\u9910\u4eba\u6b21\u7684\u65b9\u6cd5\u6709\u591a\u79cd\uff0c\u5305\u62ec\u4f7f\u7528\u8ba1\u6570\u5668\u3001\u6570\u636e\u5e93\u3001\u65e5\u5fd7\u6587\u4ef6\u7b49\u65b9\u5f0f\u3002\u5177\u4f53\u5b9e\u73b0\u53ef\u4ee5\u901a\u8fc7\u8bfb\u53d6\u6570\u636e\u6e90\u3001\u7edf\u8ba1\u7279\u5b9a\u65f6\u95f4\u6bb5\u5185\u7684\u5c31\u9910\u4eba\u6570\u3001\u4ee5\u53ca\u4f18\u5316\u6570\u636e\u5b58\u50a8\u548c\u5904\u7406\u6548\u7387\u7b49\u6b65\u9aa4\u6765\u5b8c\u6210\u3002<\/strong>\u5176\u4e2d\uff0c\u4f7f\u7528Python\u7684\u5185\u7f6e\u6570\u636e\u7ed3\u6784\u548c\u5e93\uff08\u5982pandas\uff09\u8fdb\u884c\u6570\u636e\u5206\u6790\u662f\u4e00\u4e2a\u5e38\u89c1\u4e14\u9ad8\u6548\u7684\u65b9\u6cd5\u3002<\/p>\n<\/p>\n

\u4e0b\u9762\u6211\u4eec\u5c06\u8be6\u7ec6\u8ba8\u8bba\u5982\u4f55\u4f7f\u7528Python\u6765\u8ba1\u7b97\u5c31\u9910\u4eba\u6b21\uff0c\u5e76\u4ecb\u7ecd\u4e00\u4e9b\u76f8\u5173\u7684\u6280\u672f\u548c\u5de5\u5177\u3002<\/p>\n<\/p>\n

\u4e00\u3001\u6570\u636e\u6536\u96c6\u4e0e\u9884\u5904\u7406<\/strong><\/h2>\n

\u5728\u8ba1\u7b97\u5c31\u9910\u4eba\u6b21\u4e4b\u524d\uff0c\u9996\u5148\u9700\u8981\u6536\u96c6\u4e0e\u5c31\u9910\u76f8\u5173\u7684\u6570\u636e\u3002\u6570\u636e\u53ef\u4ee5\u6765\u81ea\u591a\u79cd\u6765\u6e90\uff0c\u5982\u6570\u636e\u5e93\u3001CSV\u6587\u4ef6\u3001API\u63a5\u53e3\u7b49\u3002\u65e0\u8bba\u6570\u636e\u6765\u81ea\u4f55\u5904\uff0c\u7b2c\u4e00\u6b65\u90fd\u662f\u5c06\u6570\u636e\u5bfc\u5165Python\u73af\u5883\uff0c\u5e76\u8fdb\u884c\u5fc5\u8981\u7684\u9884\u5904\u7406\u3002<\/p>\n<\/p>\n

1.1 \u6570\u636e\u5bfc\u5165<\/h3>\n<\/p>\n

Python\u63d0\u4f9b\u4e86\u591a\u79cd\u5de5\u5177\u6765\u5bfc\u5165\u6570\u636e\u3002\u5bf9\u4e8eCSV\u6587\u4ef6\uff0c\u53ef\u4ee5\u4f7f\u7528pandas\u5e93\u7684read_csv<\/code>\u51fd\u6570\uff1b\u5bf9\u4e8e\u6570\u636e\u5e93\uff0c\u53ef\u4ee5\u4f7f\u7528SQLAlchemy\u6216pandas\u7684read_sql<\/code>\u65b9\u6cd5\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u5bfc\u5165CSV\u6587\u4ef6\u7684\u793a\u4f8b\uff1a<\/p>\n<\/p>\n

import pandas as pd<\/p>\n
\u5bfc\u5165CSV\u6587\u4ef6<\/strong><\/h2>\n
data = pd.read_csv('dining_data.csv')<\/p>\n
<\/code><\/pre>\n<\/p>\n
1.2 \u6570\u636e\u6e05\u6d17<\/h3>\n<\/p>\n
\u6570\u636e\u6e05\u6d17\u662f\u6570\u636e\u9884\u5904\u7406\u7684\u91cd\u8981\u6b65\u9aa4\u3002\u6b64\u6b65\u9aa4\u53ef\u80fd\u5305\u62ec\u5904\u7406\u7f3a\u5931\u503c\u3001\u5220\u9664\u91cd\u590d\u6570\u636e\u3001\u683c\u5f0f\u8f6c\u6362\u7b49\u3002\u4ee5\u4e0b\u662f\u4e00\u4e9b\u5e38\u89c1\u7684\u6570\u636e\u6e05\u6d17\u64cd\u4f5c\uff1a<\/p>\n<\/p>\n
# \u5220\u9664\u7f3a\u5931\u503c<\/p>\n
data = data.dropna()<\/p>\n
\u5220\u9664\u91cd\u590d\u884c<\/strong><\/h2>\n
data = data.drop_duplicates()<\/p>\n
\u8f6c\u6362\u65e5\u671f\u683c\u5f0f<\/strong><\/h2>\n
data['date'] = pd.to_datetime(data['date'])<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e8c\u3001\u8ba1\u7b97\u5c31\u9910\u4eba\u6b21\u7684\u65b9\u6cd5<\/strong><\/h2>\n
\u5728\u5b8c\u6210\u6570\u636e\u6536\u96c6\u548c\u9884\u5904\u7406\u540e\uff0c\u6211\u4eec\u53ef\u4ee5\u5f00\u59cb\u8ba1\u7b97\u5c31\u9910\u4eba\u6b21\u3002\u5177\u4f53\u5b9e\u73b0\u53ef\u4ee5\u6839\u636e\u6570\u636e\u7ed3\u6784\u548c\u9700\u6c42\u7684\u4e0d\u540c\u800c\u6709\u6240\u5dee\u5f02\u3002<\/p>\n<\/p>\n
2.1 \u4f7f\u7528\u8ba1\u6570\u5668<\/h3>\n<\/p>\n
\u8ba1\u6570\u5668\u662f\u8ba1\u7b97\u5c31\u9910\u4eba\u6b21\u7684\u57fa\u672c\u65b9\u6cd5\u4e4b\u4e00\u3002\u53ef\u4ee5\u4f7f\u7528Python\u5185\u7f6e\u7684collections.Counter<\/code>\u7c7b\uff0c\u6216\u8005\u7b80\u5355\u5730\u4f7f\u7528\u5b57\u5178\u6765\u5b9e\u73b0\u8ba1\u6570\u529f\u80fd\u3002<\/p>\n<\/p>\n
from collections import Counter<\/p>\n
\u5047\u8bbe\u6570\u636e\u4e2d\u6709\u4e00\u4e2a"customer_id"\u5217<\/strong><\/h2>\n
counter = Counter(data['customer_id'])<\/p>\n
total_visits = sum(counter.values())<\/p>\n
print(f"\u603b\u5c31\u9910\u4eba\u6b21: {total_visits}")<\/p>\n
<\/code><\/pre>\n<\/p>\n
2.2 \u4f7f\u7528pandas\u8fdb\u884c\u7edf\u8ba1<\/h3>\n<\/p>\n
pandas\u5e93\u63d0\u4f9b\u4e86\u5f3a\u5927\u7684\u6570\u636e\u5206\u6790\u529f\u80fd\uff0c\u53ef\u4ee5\u8f7b\u677e\u5b9e\u73b0\u5c31\u9910\u4eba\u6b21\u7684\u8ba1\u7b97\u3002\u4f8b\u5982\uff0c\u53ef\u4ee5\u4f7f\u7528groupby<\/code>\u51fd\u6570\u5bf9\u6570\u636e\u8fdb\u884c\u5206\u7ec4\uff0c\u7136\u540e\u4f7f\u7528size<\/code>\u6216count<\/code>\u51fd\u6570\u8fdb\u884c\u7edf\u8ba1\u3002<\/p>\n<\/p>\n
# \u6309\u65e5\u671f\u7edf\u8ba1\u5c31\u9910\u4eba\u6b21<\/p>\n
dAI<\/a>ly_visits = data.groupby('date').size()<\/p>\n
print(daily_visits)<\/p>\n
<\/code><\/pre>\n<\/p>\n
2.3 \u65f6\u95f4\u6bb5\u5206\u6790<\/h3>\n<\/p>\n
\u6709\u65f6\u5019\uff0c\u6211\u4eec\u9700\u8981\u5206\u6790\u7279\u5b9a\u65f6\u95f4\u6bb5\u5185\u7684\u5c31\u9910\u4eba\u6b21\u3002\u53ef\u4ee5\u4f7f\u7528pandas\u7684resample<\/code>\u51fd\u6570\u6765\u5b9e\u73b0\u8fd9\u4e00\u529f\u80fd\u3002<\/p>\n<\/p>\n
# \u6309\u6708\u7edf\u8ba1\u5c31\u9910\u4eba\u6b21<\/p>\n
monthly_visits = data.resample('M', on='date').size()<\/p>\n
print(monthly_visits)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e09\u3001\u4f18\u5316\u8ba1\u7b97\u6548\u7387<\/strong><\/h2>\n
\u5728\u5904\u7406\u5927\u89c4\u6a21\u6570\u636e\u65f6\uff0c\u4f18\u5316\u8ba1\u7b97\u6548\u7387\u975e\u5e38\u91cd\u8981\u3002\u4ee5\u4e0b\u662f\u4e00\u4e9b\u63d0\u9ad8\u8ba1\u7b97\u6548\u7387\u7684\u65b9\u6cd5\uff1a<\/p>\n<\/p>\n
3.1 \u4f7f\u7528\u9002\u5f53\u7684\u6570\u636e\u7c7b\u578b<\/h3>\n<\/p>\n
\u9009\u62e9\u5408\u9002\u7684\u6570\u636e\u7c7b\u578b\u53ef\u4ee5\u663e\u8457\u63d0\u9ad8\u8ba1\u7b97\u6548\u7387\u3002\u4f8b\u5982\uff0c\u4f7f\u7528int32<\/code>\u800c\u4e0d\u662fint64<\/code>\u53ef\u4ee5\u8282\u7701\u5185\u5b58\uff0c\u63d0\u9ad8\u5904\u7406\u901f\u5ea6\u3002<\/p>\n<\/p>\n
data['customer_id'] = data['customer_id'].astype('int32')<\/p>\n
<\/code><\/pre>\n<\/p>\n
3.2 \u5e76\u884c\u5904\u7406<\/h3>\n<\/p>\n
\u5bf9\u4e8e\u975e\u5e38\u5927\u7684\u6570\u636e\u96c6\uff0c\u53ef\u4ee5\u8003\u8651\u4f7f\u7528\u5e76\u884c\u5904\u7406\u6765\u52a0\u5feb\u8ba1\u7b97\u901f\u5ea6\u3002Python\u7684multiprocessing<\/code>\u6a21\u5757\u53ef\u4ee5\u7528\u4e8e\u5b9e\u73b0\u5e76\u884c\u5904\u7406\u3002<\/p>\n<\/p>\n
from multiprocessing import Pool<\/p>\n
def process_chunk(chunk):<\/p>\n
    # \u5bf9\u6570\u636e\u5757\u8fdb\u884c\u5904\u7406<\/p>\n
    return chunk.groupby('date').size()<\/p>\n
\u5c06\u6570\u636e\u5206\u6210\u591a\u4e2a\u5757\u8fdb\u884c\u5e76\u884c\u5904\u7406<\/strong><\/h2>\n
with Pool() as pool:<\/p>\n
    results = pool.map(process_chunk, np.array_split(data, 4))<\/p>\n
    total_visits = sum(results)<\/p>\n
    print(total_visits)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u56db\u3001\u6570\u636e\u53ef\u89c6\u5316<\/strong><\/h2>\n
\u5c06\u8ba1\u7b97\u7ed3\u679c\u8fdb\u884c\u53ef\u89c6\u5316\u53ef\u4ee5\u5e2e\u52a9\u6211\u4eec\u66f4\u597d\u5730\u7406\u89e3\u548c\u5206\u6790\u5c31\u9910\u4eba\u6b21\u7684\u53d8\u5316\u8d8b\u52bf\u3002matplotlib\u548cseaborn\u662f\u4e24\u4e2a\u5e38\u7528\u7684Python\u53ef\u89c6\u5316\u5e93\u3002<\/p>\n<\/p>\n
4.1 \u4f7f\u7528matplotlib\u7ed8\u5236\u56fe\u8868<\/h3>\n<\/p>\n
import matplotlib.pyplot as plt<\/p>\n
\u7ed8\u5236\u6bcf\u65e5\u5c31\u9910\u4eba\u6b21\u6298\u7ebf\u56fe<\/strong><\/h2>\n
plt.figure(figsize=(10, 6))<\/p>\n
plt.plot(daily_visits.index, daily_visits.values)<\/p>\n
plt.title('Daily Dining Visits')<\/p>\n
plt.xlabel('Date')<\/p>\n
plt.ylabel('Number of Visits')<\/p>\n
plt.grid(True)<\/p>\n
plt.show()<\/p>\n
<\/code><\/pre>\n<\/p>\n
4.2 \u4f7f\u7528seaborn\u7ed8\u5236\u56fe\u8868<\/h3>\n<\/p>\n
import seaborn as sns<\/p>\n
\u4f7f\u7528seaborn\u7ed8\u5236\u6708\u5ea6\u5c31\u9910\u4eba\u6b21\u67f1\u72b6\u56fe<\/strong><\/h2>\n
plt.figure(figsize=(10, 6))<\/p>\n
sns.barplot(x=monthly_visits.index.strftime('%Y-%m'), y=monthly_visits.values)<\/p>\n
plt.title('Monthly Dining Visits')<\/p>\n
plt.xlabel('Month')<\/p>\n
plt.ylabel('Number of Visits')<\/p>\n
plt.xticks(rotation=45)<\/p>\n
plt.show()<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e94\u3001\u603b\u7ed3\u4e0e\u5c55\u671b<\/strong><\/h2>\n
\u901a\u8fc7\u4ee5\u4e0a\u6b65\u9aa4\uff0c\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528Python\u6765\u6709\u6548\u5730\u8ba1\u7b97\u5c31\u9910\u4eba\u6b21\u3002\u4ece\u6570\u636e\u6536\u96c6\u4e0e\u9884\u5904\u7406\u3001\u8ba1\u7b97\u65b9\u6cd5\u7684\u9009\u62e9\u3001\u5230\u6548\u7387\u4f18\u5316\u4e0e\u7ed3\u679c\u53ef\u89c6\u5316\uff0c\u6bcf\u4e00\u6b65\u90fd\u9700\u8981\u4ed4\u7ec6\u8003\u8651\u548c\u5b9e\u73b0\u3002\u968f\u7740\u6280\u672f\u7684\u53d1\u5c55\uff0c\u672a\u6765\u53ef\u4ee5\u8003\u8651\u5f15\u5165\u66f4\u591a\u7684\u673a\u5668\u5b66\u4e60<\/a>\u548c\u5927\u6570\u636e\u5904\u7406\u6280\u672f\u6765\u8fdb\u4e00\u6b65\u63d0\u5347\u8ba1\u7b97\u548c\u5206\u6790\u7684\u80fd\u529b\u3002<\/p>\n<\/p>\n
\u5728\u5b9e\u9645\u5e94\u7528\u4e2d\uff0c\u7075\u6d3b\u9009\u62e9\u5408\u9002\u7684\u65b9\u6cd5\u548c\u5de5\u5177\u662f\u5173\u952e\u3002\u901a\u8fc7\u4e0d\u65ad\u5b9e\u8df5\u548c\u4f18\u5316\uff0c\u53ef\u4ee5\u63d0\u9ad8\u6570\u636e\u5904\u7406\u7684\u6548\u7387\u548c\u6548\u679c\uff0c\u4e3a\u4e1a\u52a1\u51b3\u7b56\u63d0\u4f9b\u66f4\u6709\u529b\u7684\u652f\u6301\u3002<\/strong><\/p>\n<\/p>\n
\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n
 \u5982\u4f55\u4f7f\u7528Python\u6765\u7edf\u8ba1\u5c31\u9910\u4eba\u6b21\uff1f<\/strong>
\u5728Python\u4e2d\uff0c\u53ef\u4ee5\u901a\u8fc7\u521b\u5efa\u4e00\u4e2a\u7b80\u5355\u7684\u7a0b\u5e8f\uff0c\u5229\u7528\u5217\u8868\u6216\u5b57\u5178\u6765\u8bb0\u5f55\u6bcf\u6b21\u5c31\u9910\u7684\u4eba\u5458\u4fe1\u606f\uff0c\u4ece\u800c\u5b9e\u73b0\u5c31\u9910\u4eba\u6b21\u7684\u7edf\u8ba1\u3002\u60a8\u53ef\u4ee5\u4f7f\u7528\u5faa\u73af\u548c\u6761\u4ef6\u5224\u65ad\u6765\u589e\u52a0\u7075\u6d3b\u6027\u3002\u4f8b\u5982\uff0c\u53ef\u4ee5\u4ece\u7528\u6237\u90a3\u91cc\u83b7\u53d6\u8f93\u5165\uff0c\u8bb0\u5f55\u6bcf\u6b21\u5c31\u9910\u7684\u53c2\u4e0e\u8005\uff0c\u5e76\u6700\u7ec8\u8f93\u51fa\u603b\u7684\u5c31\u9910\u4eba\u6b21\u3002<\/p>\n
Python\u4e2d\u6709\u54ea\u4e9b\u5e93\u53ef\u4ee5\u5e2e\u52a9\u6211\u5904\u7406\u5c31\u9910\u6570\u636e\uff1f<\/strong>
\u5728Python\u4e2d\uff0c\u60a8\u53ef\u4ee5\u4f7f\u7528\u5982Pandas\u8fd9\u6837\u7684\u5e93\u6765\u5904\u7406\u548c\u5206\u6790\u6570\u636e\u3002Pandas\u63d0\u4f9b\u4e86\u5f3a\u5927\u7684\u6570\u636e\u7ed3\u6784\u548c\u6570\u636e\u5206\u6790\u5de5\u5177\uff0c\u53ef\u4ee5\u65b9\u4fbf\u5730\u8bfb\u53d6\u3001\u5904\u7406\u548c\u7edf\u8ba1\u5c31\u9910\u6570\u636e\u3002\u6b64\u5916\uff0cNumPy\u5e93\u4e5f\u53ef\u4ee5\u7528\u4e8e\u8fdb\u884c\u6570\u503c\u8ba1\u7b97\uff0c\u5e2e\u52a9\u60a8\u66f4\u9ad8\u6548\u5730\u5904\u7406\u5927\u89c4\u6a21\u7684\u5c31\u9910\u8bb0\u5f55\u3002<\/p>\n
\u5982\u4f55\u4f18\u5316\u6211\u7684Python\u4ee3\u7801\u4ee5\u63d0\u9ad8\u5c31\u9910\u4eba\u6b21\u7684\u8ba1\u7b97\u6548\u7387\uff1f<\/strong>
\u8981\u63d0\u9ad8\u8ba1\u7b97\u6548\u7387\uff0c\u53ef\u4ee5\u8003\u8651\u4f7f\u7528\u96c6\u5408\u6765\u5b58\u50a8\u5c31\u9910\u4eba\u5458\u7684\u552f\u4e00\u6807\u8bc6\uff0c\u8fd9\u6837\u53ef\u4ee5\u907f\u514d\u91cd\u590d\u8ba1\u7b97\u3002\u540c\u65f6\uff0c\u4f7f\u7528\u751f\u6210\u5668\u8868\u8fbe\u5f0f\u548c\u5185\u7f6e\u51fd\u6570\u53ef\u4ee5\u51cf\u5c11\u5185\u5b58\u5360\u7528\u3002\u786e\u4fdd\u4ee3\u7801\u7ed3\u6784\u6e05\u6670\uff0c\u903b\u8f91\u7b80\u6d01\uff0c\u8fd9\u6837\u4e0d\u4ec5\u63d0\u9ad8\u4e86\u6548\u7387\uff0c\u4e5f\u4fbf\u4e8e\u540e\u671f\u7ef4\u62a4\u548c\u66f4\u65b0\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u5728Python\u4e2d\u8ba1\u7b97\u5c31\u9910\u4eba\u6b21\u7684\u65b9\u6cd5\u6709\u591a\u79cd\uff0c\u5305\u62ec\u4f7f\u7528\u8ba1\u6570\u5668\u3001\u6570\u636e\u5e93\u3001\u65e5\u5fd7\u6587\u4ef6\u7b49\u65b9\u5f0f\u3002\u5177\u4f53\u5b9e\u73b0\u53ef\u4ee5\u901a\u8fc7\u8bfb\u53d6\u6570\u636e\u6e90\u3001 […]","protected":false},"author":3,"featured_media":968801,"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\/968794"}],"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=968794"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/968794\/revisions"}],"predecessor-version":[{"id":968805,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/968794\/revisions\/968805"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/968801"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=968794"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=968794"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=968794"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}