<\/span><\/h3>\n\n\n\nimport pandas as pd\nimport numpy as np\n\n# \u521b\u5efa\u793a\u4f8b\u65f6\u95f4\u5e8f\u5217\u6570\u636e\ndates = pd.date_range(start='2023-01-01', end='2025-06-30', freq='D')\nnp.random.seed(42)\nsales_data = np.cumsum(np.random.normal(loc=100, scale=20, size=len(dates)))\n\ndata = {\n 'order_id': range(1, len(dates) + 1),\n 'product_id': np.random.choice(['P{}'.format(i) for i in range(1, 101)], len(dates)),\n 'category_code': np.random.choice(['C{}'.format(i) for i in range(1, 11)], len(dates)),\n 'amount': sales_data,\n 'quantity': np.random.randint(1, 5, size=len(dates)),\n 'order_date': dates,\n 'customer_id': np.random.randint(1, 1001, size=len(dates)),\n 'region': np.random.choice(['Beijing', 'Shanghai', 'Guangzhou', 'Shenzhen'], len(dates)),\n 'promotion': np.random.choice([True, False], len(dates)),\n 'return_status': np.random.choice([True, False], len(dates)),\n 'platform_channel': np.random.choice(['Online', 'Offline'], len(dates))\n}\n\ndf = pd.DataFrame(data)\n\nprint(\"\u539f\u59cb\u6570\u636e:\")\nprint(df.head())<\/code><\/pre>\n\n\n\n<\/span>1. \u627e\u51fa\u9500\u552e\u989d\u6700\u9ad8\u7684Top 10\u5546\u54c1<\/span><\/h3>\n\n\n\n# \u6309\u4ea7\u54c1ID\u805a\u5408\u9500\u552e\u989d\ntop_products = df.groupby('product_id')['amount'].sum().sort_values(ascending=False).head(10)\n\nprint(\"\\n\u9500\u552e\u989d\u6700\u9ad8\u7684Top 10\u5546\u54c1:\")\nprint(top_products)<\/code><\/pre>\n\n\n\n<\/span>2. \u5206\u6790\u5404\u5730\u533a\u9500\u552e\u5dee\u5f02<\/span><\/h3>\n\n\n\n# \u6309\u5730\u533a\u805a\u5408\u9500\u552e\u989d\nregion_sales = df.groupby('region')['amount'].sum()\n\nprint(\"\\n\u5404\u5730\u533a\u9500\u552e\u5dee\u5f02:\")\nprint(region_sales)<\/code><\/pre>\n\n\n\n<\/span>3. \u8bc6\u522b\u9ad8\u4ef7\u503c\u7528\u6237\u7fa4\u4f53\uff08RFM\u6a21\u578b\uff09<\/span><\/h3>\n\n\n\nfrom datetime import datetime\n\n# \u8ba1\u7b97\u6700\u8fd1\u4e00\u6b21\u8d2d\u4e70\u65e5\u671f\u3001\u8d2d\u4e70\u9891\u7387\u548c\u603b\u6d88\u8d39\u91d1\u989d\nrfm_df = df.groupby('customer_id').agg({\n 'order_date': lambda x: (datetime.now() - x.max()).days, # Recency\n 'order_id': 'count', # Frequency\n 'amount': 'sum' # Monetary\n}).reset_index()\n\nrfm_df.rename(columns={\n 'order_date': 'Recency',\n 'order_id': 'Frequency',\n 'amount': 'Monetary'\n}, inplace=True)\n\n# \u6807\u51c6\u5316\u6bcf\u4e2a\u7279\u5f81\nfrom sklearn.preprocessing import StandardScaler\n\nscaler = StandardScaler()\nrfm_scaled = scaler.fit_transform(rfm_df[['Recency', 'Frequency', 'Monetary']])\n\n# \u4f7f\u7528KMeans\u805a\u7c7b\nfrom sklearn.cluster import KMeans\n\nkmeans = KMeans(n_clusters=5, random_state=42)\nrfm_df['Cluster'] = kmeans.fit_predict(rfm_scaled)\n\n# \u67e5\u770b\u6bcf\u4e2a\u7c07\u7684\u5e73\u5747\u503c\ncluster_analysis = rfm_df.groupby('Cluster').mean()\n\nprint(\"\\n\u9ad8\u4ef7\u503c\u7528\u6237\u7fa4\u4f53\uff08RFM\u6a21\u578b\uff09:\")\nprint(cluster_analysis)<\/code><\/pre>\n\n\n\n<\/span>4. \u5206\u6790\u4fc3\u9500\u6d3b\u52a8\u7684\u62c9\u52a8\u6548\u679c<\/span><\/h3>\n\n\n\n# \u6309\u4fc3\u9500\u72b6\u6001\u805a\u5408\u9500\u552e\u989d\npromotion_effect = df.groupby('promotion')['amount'].sum()\n\nprint(\"\\n\u4fc3\u9500\u6d3b\u52a8\u7684\u62c9\u52a8\u6548\u679c:\")\nprint(promotion_effect)<\/code><\/pre>\n\n\n\n<\/span>5. \u5206\u6790\u65b0\u54c1\u4e0a\u5e02\u5bf9\u8001\u54c1\u7684\u51b2\u51fb<\/span><\/h3>\n\n\n\n# \u5047\u8bbe\u65b0\u54c1\u662f\u57282024\u5e741\u67081\u65e5\u4e0a\u5e02\nnew_product_ids = df[df['order_date'] >= '2024-01-01']['product_id'].unique()\nold_product_ids = df[df['order_date'] < '2024-01-01']['product_id'].unique()\n\n# \u65b0\u54c1\u57282024\u5e74\u7684\u9500\u552e\u989d\nnew_product_sales = df[df['product_id'].isin(new_product_ids) & (df['order_date'] >= '2024-01-01')].groupby('product_id')['amount'].sum()\n\n# \u8001\u54c1\u57282024\u5e74\u7684\u9500\u552e\u989d\nold_product_sales = df[df['product_id'].isin(old_product_ids) & (df['order_date'] >= '2024-01-01')].groupby('product_id')['amount'].sum()\n\nprint(\"\\n\u65b0\u54c1\u57282024\u5e74\u7684\u9500\u552e\u989d:\")\nprint(new_product_sales)\nprint(\"\\n\u8001\u54c1\u57282024\u5e74\u7684\u9500\u552e\u989d:\")\nprint(old_product_sales)<\/code><\/pre>\n\n\n\n<\/span>6. \u5206\u6790\u9000\u8d27\u7387\u4e0e\u5546\u54c1\u7c7b\u522b\u7684\u5173\u7cfb<\/span><\/h3>\n\n\n\n# \u8ba1\u7b97\u6bcf\u4e2a\u7c7b\u522b\u7684\u9000\u8d27\u7387\nreturn_rates = df.groupby('category_code').agg({\n 'return_status': 'mean',\n 'amount': 'sum'\n})\n\nreturn_rates.rename(columns={'return_status': 'Return_Rate'}, inplace=True)\n\nprint(\"\\n\u9000\u8d27\u7387\u4e0e\u5546\u54c1\u7c7b\u522b\u7684\u5173\u7cfb:\")\nprint(return_rates)<\/code><\/pre>\n\n\n\n<\/span>7. \u5206\u6790\u7528\u6237\u590d\u8d2d\u8def\u5f84<\/span><\/h3>\n\n\n\n# \u8ba1\u7b97\u6bcf\u4e2a\u7528\u6237\u7684\u8ba2\u5355\u6b21\u6570\nuser_orders = df.groupby('customer_id')['order_id'].count().reset_index()\nuser_orders.columns = ['customer_id', 'Order_Count']\n\n# \u7b5b\u9009\u51fa\u590d\u8d2d\u7528\u6237\nrepeat_customers = user_orders[user_orders['Order_Count'] > 1]\n\nprint(\"\\n\u590d\u8d2d\u7528\u6237\u6570\u91cf:\")\nprint(len(repeat_customers))\n\n# \u67e5\u770b\u590d\u8d2d\u7528\u6237\u7684\u8be6\u7ec6\u4fe1\u606f\nrepeat_customer_details = df[df['customer_id'].isin(repeat_customers['customer_id'])]\nprint(\"\\n\u590d\u8d2d\u7528\u6237\u7684\u8be6\u7ec6\u4fe1\u606f:\")\nprint(repeat_customer_details.head())<\/code><\/pre>\n\n\n\n<\/span>8. \u5206\u6790\u8282\u5047\u65e5\u524d\u540e\u9500\u552e\u6ce2\u52a8<\/span><\/h3>\n\n\n\n# \u6dfb\u52a0\u8282\u5047\u65e5\u6807\u5fd7\nholidays = pd.to_datetime([\n '2023-01-01', '2023-02-22', '2023-04-05', '2023-05-01', '2023-10-01',\n '2024-01-01', '2024-02-10', '2024-04-04', '2024-05-01', '2024-10-01',\n '2025-01-01', '2025-02-19', '2025-04-04', '2025-05-01', '2025-10-01'\n])\n\ndf['is_holiday'] = df['order_date'].isin(holidays).astype(int)\n\n# \u6309\u662f\u5426\u662f\u8282\u5047\u65e5\u805a\u5408\u9500\u552e\u989d\nholiday_sales = df.groupby('is_holiday')['amount'].sum()\n\nprint(\"\\n\u8282\u5047\u65e5\u524d\u540e\u9500\u552e\u6ce2\u52a8:\")\nprint(holiday_sales)<\/code><\/pre>\n\n\n\n<\/span>9. \u5206\u6790\u6d41\u91cf\u4e0e\u8f6c\u5316\u7387\u4e4b\u95f4\u7684\u5173\u7cfb<\/span><\/h3>\n\n\n\n\u5047\u8bbe\u6211\u4eec\u6709\u4e00\u4e2a\u8bbf\u95ee\u8bb0\u5f55\u7684DataFrame\uff0c\u7528\u4e8e\u8ba1\u7b97\u8f6c\u5316\u7387\u3002<\/p>\n\n\n\n
# \u521b\u5efa\u8bbf\u95ee\u8bb0\u5f55\u7684DataFrame\nvisit_data = {\n 'customer_id': np.random.randint(1, 1001, size=len(dates)),\n 'visits': np.random.randint(1, 10, size=len(dates)),\n 'order_date': dates\n}\ndf_visits = pd.DataFrame(visit_data)\n\n# \u5408\u5e76\u8ba2\u5355\u548c\u8bbf\u95ee\u6570\u636e\nmerged_df = pd.merge(df, df_visits, on=['customer_id', 'order_date'], how='right')\n\n# \u586b\u5145\u7f3a\u5931\u7684\u8ba2\u5355\u91d1\u989d\u4e3a0\nmerged_df['amount'].fillna(0, inplace=True)\n\n# \u8ba1\u7b97\u8f6c\u5316\u7387\nconversion_rate = merged_df.groupby('customer_id').agg({\n 'amount': lambda x: (x > 0).sum(),\n 'visits': 'sum'\n}).reset_index()\n\nconversion_rate['Conversion_Rate'] = conversion_rate['amount'] \/ conversion_rate['visits']\n\nprint(\"\\n\u6d41\u91cf\u4e0e\u8f6c\u5316\u7387\u4e4b\u95f4\u7684\u5173\u7cfb:\")\nprint(conversion_rate.head())<\/code><\/pre>\n\n\n\n<\/span>10. \u5206\u6790\u4e0d\u540c\u5e73\u53f0\u6e20\u9053\u7684\u7528\u6237\u753b\u50cf\u5dee\u5f02<\/span><\/h3>\n\n\n\n# \u6309\u5e73\u53f0\u6e20\u9053\u805a\u5408\u9500\u552e\u989d\u548c\u5176\u4ed6\u6307\u6807\nchannel_analysis = df.groupby('platform_channel').agg({\n 'amount': 'sum',\n 'customer_id': 'nunique',\n 'order_id': 'count'\n}).reset_index()\n\nchannel_analysis.rename(columns={\n 'customer_id': 'Unique_Customers',\n 'order_id': 'Total_Orders'\n}, inplace=True)\n\nprint(\"\\n\u4e0d\u540c\u5e73\u53f0\u6e20\u9053\u7684\u7528\u6237\u753b\u50cf\u5dee\u5f02:\")\nprint(channel_analysis)<\/code><\/pre>\n\n\n\n\u7efc\u5408\u4ee5\u4e0a\u6b65\u9aa4\uff0c\u6700\u7ec8\u7684\u5206\u6790\u7ed3\u679c\u5982\u4e0b\uff1a<\/p>\n\n\n\n
\u8fd9\u6bb5\u4ee3\u7801\u5c55\u793a\u4e86\u4ece\u539f\u59cb\u6570\u636e\u5230\u7ecf\u8fc7\u5168\u9762\u5206\u6790\u7684\u7ed3\u679c\u7684\u8fc7\u7a0b\u3002\u4f60\u53ef\u4ee5\u6839\u636e\u5b9e\u9645\u9700\u6c42\u8c03\u6574\u6bcf\u4e00\u6b65\u7684\u64cd\u4f5c\u3002<\/p>\n\n\n\n
<\/p>\n\n\n\n
import pandas as pd\nimport numpy as np\nfrom datetime import datetime\nfrom sklearn.preprocessing import StandardScaler\nfrom sklearn.cluster import KMeans\n\n# \u521b\u5efa\u793a\u4f8b\u65f6\u95f4\u5e8f\u5217\u6570\u636e\ndates = pd.date_range(start='2023-01-01', end='2025-06-30', freq='D')\nnp.random.seed(42)\nsales_data = np.cumsum(np.random.normal(loc=100, scale=20, size=len(dates)))\n\ndata = {\n 'order_id': range(1, len(dates) + 1),\n 'product_id': np.random.choice(['P{}'.format(i) for i in range(1, 101)], len(dates)),\n 'category_code': np.random.choice(['C{}'.format(i) for i in range(1, 11)], len(dates)),\n 'amount': sales_data,\n 'quantity': np.random.randint(1, 5, size=len(dates)),\n 'order_date': dates,\n 'customer_id': np.random.randint(1, 1001, size=len(dates)),\n 'region': np.random.choice(['Beijing', 'Shanghai', 'Guangzhou', 'Shenzhen'], len(dates)),\n 'promotion': np.random.choice([True, False], len(dates)),\n 'return_status': np.random.choice([True, False], len(dates)),\n 'platform_channel': np.random.choice(['Online', 'Offline'], len(dates))\n}\n\ndf = pd.DataFrame(data)\n\n# \u627e\u51fa\u9500\u552e\u989d\u6700\u9ad8\u7684Top 10\u5546\u54c1\ntop_products = df.groupby('product_id')['amount'].sum().sort_values(ascending=False).head(10)\n\n# \u5206\u6790\u5404\u5730\u533a\u9500\u552e\u5dee\u5f02\nregion_sales = df.groupby('region')['amount'].sum()\n\n# \u8bc6\u522b\u9ad8\u4ef7\u503c\u7528\u6237\u7fa4\u4f53\uff08RFM\u6a21\u578b\uff09\nrfm_df = df.groupby('customer_id').agg({\n 'order_date': lambda x: (datetime.now() - x.max()).days, # Recency\n 'order_id': 'count', # Frequency\n 'amount': 'sum' # Monetary\n}).reset_index()\n\nrfm_df.rename(columns={\n 'order_date': 'Recency',\n 'order_id': 'Frequency',\n 'amount': 'Monetary'\n}, inplace=True)\n\nscaler = StandardScaler()\nrfm_scaled = scaler.fit_transform(rfm_df[['Recency', 'Frequency', 'Monetary']])\n\nkmeans = KMeans(n_clusters=5, random_state=42)\nrfm_df['Cluster'] = kmeans.fit_predict(rfm_scaled)\n\ncluster_analysis = rfm_df.groupby('Cluster').mean()\n\n# \u5206\u6790\u4fc3\u9500\u6d3b\u52a8\u7684\u62c9\u52a8\u6548\u679c\npromotion_effect = df.groupby('promotion')['amount'].sum()\n\n# \u5206\u6790\u65b0\u54c1\u4e0a\u5e02\u5bf9\u8001\u54c1\u7684\u51b2\u51fb\nnew_product_ids = df[df['order_date'] >= '2024-01-01']['product_id'].unique()\nold_product_ids = df[df['order_date'] < '2024-01-01']['product_id'].unique()\n\nnew_product_sales = df[df['product_id'].isin(new_product_ids) & (df['order_date'] >= '2024-01-01')].groupby('product_id')['amount'].sum()\nold_product_sales = df[df['product_id'].isin(old_product_ids) & (df['order_date'] >= '2024-01-01')].groupby('product_id')['amount'].sum()\n\n# \u5206\u6790\u9000\u8d27\u7387\u4e0e\u5546\u54c1\u7c7b\u522b\u7684\u5173\u7cfb\nreturn_rates = df.groupby('category_code').agg({\n 'return_status': 'mean',\n 'amount': 'sum'\n})\nreturn_rates.rename(columns={'return_status': 'Return_Rate'}, inplace=True)\n\n# \u5206\u6790\u7528\u6237\u590d\u8d2d\u8def\u5f84\nuser_orders = df.groupby('customer_id')['order_id'].count().reset_index()\nuser_orders.columns = ['customer_id', 'Order_Count']\nrepeat_customers = user_orders[user_orders['Order_Count'] > 1]\nrepeat_customer_details = df[df['customer_id'].isin(repeat_customers['customer_id'])]\n\n# \u5206\u6790\u8282\u5047\u65e5\u524d\u540e\u9500\u552e\u6ce2\u52a8\nholidays = pd.to_datetime([\n '2023-01-01', '2023-02-22', '2023-04-05', '2023-05-01', '2023-10-01',\n '2024-01-01', '2024-02-10', '2024-04-04', '2024-05-01', '2024-10-01',\n '2025-01-01', '2025-02-19', '2025-04-04', '2025-05-01', '2025-10-01'\n])\ndf['is_holiday'] = df['order_date'].isin(holidays).astype(int)\nholiday_sales = df.groupby('is_holiday')['amount'].sum()\n\n# \u5206\u6790\u6d41\u91cf\u4e0e\u8f6c\u5316\u7387\u4e4b\u95f4\u7684\u5173\u7cfb\nvisit_data = {\n 'customer_id': np.random.randint(1, 1001, size=len(dates)),\n 'visits': np.random.randint(1, 10, size=len(dates)),\n 'order_date': dates\n}\ndf_visits = pd.DataFrame(visit_data)\nmerged_df = pd.merge(df, df_visits, on=['customer_id', 'order_date'], how='right')\nmerged_df['amount'].fillna(0, inplace=True)\nconversion_rate = merged_df.groupby('customer_id').agg({\n 'amount': lambda x: (x > 0).sum(),\n 'visits': 'sum'\n}).reset_index()\nconversion_rate['Conversion_Rate'] = conversion_rate['amount'] \/ conversion_rate['visits']\n\n# \u5206\u6790\u4e0d\u540c\u5e73\u53f0\u6e20\u9053\u7684\u7528\u6237\u753b\u50cf\u5dee\u5f02\nchannel_analysis = df.groupby('platform_channel').agg({\n 'amount': 'sum',\n 'customer_id': 'nunique',\n 'order_id': 'count'\n}).reset_index()\nchannel_analysis.rename(columns={\n 'customer_id': 'Unique_Customers',\n 'order_id': 'Total_Orders'\n}, inplace=True)\n\nprint(\"\u539f\u59cb\u6570\u636e:\")\nprint(df.head())\n\nprint(\"\\n\u9500\u552e\u989d\u6700\u9ad8\u7684Top 10\u5546\u54c1:\")\nprint(top_products)\n\nprint(\"\\n\u5404\u5730\u533a\u9500\u552e\u5dee\u5f02:\")\nprint(region_sales)\n\nprint(\"\\n\u9ad8\u4ef7\u503c\u7528\u6237\u7fa4\u4f53\uff08RFM\u6a21\u578b\uff09:\")\nprint(cluster_analysis)\n\nprint(\"\\n\u4fc3\u9500\u6d3b\u52a8\u7684\u62c9\u52a8\u6548\u679c:\")\nprint(promotion_effect)\n\nprint(\"\\n\u65b0\u54c1\u57282024\u5e74\u7684\u9500\u552e\u989d:\")\nprint(new_product_sales)\nprint(\"\\n\u8001\u54c1\u57282024\u5e74\u7684\u9500\u552e\u989d:\")\nprint(old_product_sales)\n\nprint(\"\\n\u9000\u8d27\u7387\u4e0e\u5546\u54c1\u7c7b\u522b\u7684\u5173\u7cfb:\")\nprint(return_rates)\n\nprint(\"\\n\u590d\u8d2d\u7528\u6237\u6570\u91cf:\")\nprint(len(repeat_customers))\nprint(\"\\n\u590d\u8d2d\u7528\u6237\u7684\u8be6\u7ec6\u4fe1\u606f:\")\nprint(repeat_customer_details.head())\n\nprint(\"\\n\u8282\u5047\u65e5\u524d\u540e\u9500\u552e\u6ce2\u52a8:\")\nprint(holiday_sales)\n\nprint(\"\\n\u6d41\u91cf\u4e0e\u8f6c\u5316\u7387\u4e4b\u95f4\u7684\u5173\u7cfb:\")\nprint(conversion_rate.head())\n\nprint(\"\\n\u4e0d\u540c\u5e73\u53f0\u6e20\u9053\u7684\u7528\u6237\u753b\u50cf\u5dee\u5f02:\")\nprint(channel_analysis)\n\n\n\n<\/code><\/pre>\n","protected":false},"excerpt":{"rendered":"\u5de5\u4f5c\u5e38\u7528\u7684\u5206\u6790\u7ed3\u679c\u6848\u4f8b\uff1a \u627e\u51fa\u9500\u552e\u989d\u6700\u9ad8\u7684Top 10\u5546\u54c1\u5206\u6790\u5404\u5730\u533a\u9500\u552e\u5dee\u5f02\u8bc6\u522b\u9ad8\u4ef7\u503c\u7528\u6237\u7fa4\u4f53\uff08RF… \u7ee7\u7eed\u9605\u8bfb \u3010Python10\u5e74\u7ecf\u9a8c\u603b\u7ed3\u3011\u7b2c\u516d\u8bfe \u7535\u5546\u5e73\u53f0\u9500\u552e\u6570\u636e\u5206\u6790\u5b9e\u8df5 \u2013 \u5206\u6790\u7ed3\u679c\uff08Analysis Insights\uff09<\/span><\/i><\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[1],"tags":[28],"views":767,"_links":{"self":[{"href":"http:\/\/viplao.com\/index.php\/wp-json\/wp\/v2\/posts\/3545"}],"collection":[{"href":"http:\/\/viplao.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/viplao.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/viplao.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/viplao.com\/index.php\/wp-json\/wp\/v2\/comments?post=3545"}],"version-history":[{"count":3,"href":"http:\/\/viplao.com\/index.php\/wp-json\/wp\/v2\/posts\/3545\/revisions"}],"predecessor-version":[{"id":3564,"href":"http:\/\/viplao.com\/index.php\/wp-json\/wp\/v2\/posts\/3545\/revisions\/3564"}],"wp:attachment":[{"href":"http:\/\/viplao.com\/index.php\/wp-json\/wp\/v2\/media?parent=3545"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/viplao.com\/index.php\/wp-json\/wp\/v2\/categories?post=3545"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/viplao.com\/index.php\/wp-json\/wp\/v2\/tags?post=3545"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}