<\/span><\/h2>\n\n\n\n\u6211\u4eec\u5c06\u4f7f\u7528 pandas<\/code> + numpy<\/code> + Faker<\/code> \u7b49\u5e93\uff0c\u6a21\u62df\u751f\u6210\u7535\u5546\u9886\u57df\u7684\u5e38\u89c1\u6570\u636e\u96c6\uff0c\u5e76\u63d0\u4f9b\u53ef\u6267\u884c\u7684 Python \u793a\u4f8b\u4ee3\u7801\uff0c\u4fbf\u4e8e\u4f60\u76f4\u63a5\u590d\u7528\u3002<\/p>\n\n\n\n
\n\n\n\n<\/span>\u2705 \u573a\u666f1\uff1a\u751f\u6210\u8ba2\u5355\u4ea4\u6613\u6570\u636e\uff08\u542b\u65f6\u95f4\u3001\u7528\u6237ID\u3001\u5546\u54c1ID\u3001\u91d1\u989d\u7b49\uff09<\/span><\/h3>\n\n\n\nimport pandas as pd\nimport numpy as np\nfrom datetime import datetime, timedelta\nfrom faker import Faker\n\nfake = Faker()\n\ndef generate_order_data(n=1000):\n data = []\n for i in range(n):\n order_id = f\"ORD{i:06d}\"\n user_id = np.random.randint(10000, 99999)\n product_id = np.random.choice(['P1001', 'P1002', 'P1003', 'P1004'], p=[0.4, 0.3, 0.2, 0.1])\n order_date = fake.date_between(start_date='-1y', end_date='today')\n quantity = np.random.randint(1, 5)\n unit_price = round(np.random.uniform(10, 500), 2)\n total_amount = round(quantity * unit_price, 2)\n payment_method = np.random.choice(['Alipay', 'WeChat', 'CreditCard'], p=[0.6, 0.3, 0.1])\n region = np.random.choice(['East', 'South', 'North', 'West'])\n data.append((order_id, user_id, product_id, order_date, quantity, unit_price, total_amount, payment_method, region))\n\n columns = ['OrderID', 'UserID', 'ProductID', 'OrderDate', 'Quantity', 'UnitPrice', 'TotalAmount', 'PaymentMethod', 'Region']\n return pd.DataFrame(data, columns=columns)\n\ndf_orders = generate_order_data(5000)\nprint(df_orders.head())<\/code><\/pre>\n\n\n\n\n\u2705 \u9002\u7528\u573a\u666f<\/strong>\uff1a\u7528\u4e8e\u8ba2\u5355\u5206\u6790\u3001\u9500\u552e\u989d\u7edf\u8ba1\u3001\u6e20\u9053\u5206\u6790\u3001\u533a\u57df\u5206\u5e03\u7b49\u3002<\/p>\n<\/blockquote>\n\n\n\n
\n\n\n\n<\/span>\u2705 \u573a\u666f2\uff1a\u751f\u6210\u7528\u6237\u753b\u50cf\u6570\u636e\uff08\u5e74\u9f84\u3001\u6027\u522b\u3001\u6ce8\u518c\u65e5\u671f\u3001\u5730\u533a\uff09<\/span><\/h3>\n\n\n\ndef generate_user_profile(n=1000):\n genders = ['Male', 'Female', 'Other']\n regions = ['East', 'South', 'North', 'West']\n data = []\n for i in range(n):\n user_id = i + 10000\n gender = np.random.choice(genders, p=[0.48, 0.48, 0.04])\n age = np.random.randint(18, 70)\n register_date = fake.date_between(start_date='-3y', end_date='today')\n region = np.random.choice(regions)\n is_vip = np.random.choice([0, 1], p=[0.85, 0.15])\n data.append((user_id, gender, age, register_date, region, is_vip))\n\n columns = ['UserID', 'Gender', 'Age', 'RegisterDate', 'Region', 'IsVIP']\n return pd.DataFrame(data, columns=columns)\n\ndf_users = generate_user_profile(2000)\nprint(df_users.head())<\/code><\/pre>\n\n\n\n\n\u2705 \u9002\u7528\u573a\u666f<\/strong>\uff1a\u7528\u4e8e\u7528\u6237\u5206\u5c42\u3001\u6d3b\u8dc3\u5ea6\u5206\u6790\u3001\u590d\u8d2d\u7387\u5efa\u6a21\u7b49\u3002<\/p>\n<\/blockquote>\n\n\n\n
\n\n\n\n<\/span>\u2705 \u573a\u666f3\uff1a\u751f\u6210\u5546\u54c1\u57fa\u7840\u4fe1\u606f\uff08\u54c1\u7c7b\u3001\u54c1\u724c\u3001\u4ef7\u683c\u533a\u95f4\uff09<\/span><\/h3>\n\n\n\ndef generate_product_info(n=100):\n categories = ['Electronics', 'Clothing', 'Home', 'Beauty', 'Books']\n brands = ['BrandA', 'BrandB', 'BrandC', 'BrandD']\n data = []\n for i in range(n):\n product_id = f\"P{i+100:04d}\"\n category = np.random.choice(categories)\n brand = np.random.choice(brands)\n price = round(np.random.uniform(50, 1000), 2)\n stock = np.random.randint(100, 1000)\n launch_date = fake.date_between(start_date='-2y', end_date='today')\n data.append((product_id, category, brand, price, stock, launch_date))\n\n columns = ['ProductID', 'Category', 'Brand', 'Price', 'Stock', 'LaunchDate']\n return pd.DataFrame(data, columns=columns)\n\ndf_products = generate_product_info(100)\nprint(df_products.head())<\/code><\/pre>\n\n\n\n\n\u2705 \u9002\u7528\u573a\u666f<\/strong>\uff1a\u7528\u4e8e\u5546\u54c1\u751f\u547d\u5468\u671f\u7ba1\u7406\u3001\u5e93\u5b58\u9884\u8b66\u3001\u5b9a\u4ef7\u7b56\u7565\u7b49\u3002<\/p>\n<\/blockquote>\n\n\n\n
\n\n\n\n<\/span>\u2705 \u573a\u666f4\uff1a\u751f\u6210\u4fc3\u9500\u6d3b\u52a8\u8bb0\u5f55\uff08\u6d3b\u52a8\u540d\u79f0\u3001\u65f6\u95f4\u3001\u6298\u6263\u529b\u5ea6\uff09<\/span><\/h3>\n\n\n\ndef generate_promotion_data(n=20):\n channels = ['App', 'PC', 'MiniProgram']\n data = []\n for i in range(n):\n promo_id = f\"PROMO{i+1:03d}\"\n name = fake.catch_phrase()\n start_date = fake.date_between(start_date='-6m', end_date='+3m')\n end_date = start_date + timedelta(days=np.random.randint(3, 30))\n discount_rate = round(np.random.uniform(0.7, 0.95), 2)\n channel = np.random.choice(channels)\n sales_lift = round(np.random.uniform(1.2, 2.5), 2)\n data.append((promo_id, name, start_date, end_date, discount_rate, channel, sales_lift))\n\n columns = ['PromoID', 'Name', 'StartDate', 'EndDate', 'DiscountRate', 'Channel', 'SalesLift']\n return pd.DataFrame(data, columns=columns)\n\ndf_promos = generate_promotion_data(20)\nprint(df_promos.head())<\/code><\/pre>\n\n\n\n\n\u2705 \u9002\u7528\u573a\u666f<\/strong>\uff1a\u7528\u4e8e\u8bc4\u4f30\u4fc3\u9500\u6548\u679c\u3001ROI\u5206\u6790\u3001\u8425\u9500\u9884\u7b97\u4f18\u5316\u7b49\u3002<\/p>\n<\/blockquote>\n\n\n\n
\n\n\n\n<\/span>\u2705 \u573a\u666f5\uff1a\u751f\u6210\u6bcf\u65e5\u8bbf\u95ee\u65e5\u5fd7\uff08\u7528\u6237ID\u3001\u8bbf\u95ee\u65f6\u95f4\u3001\u9875\u9762\u505c\u7559\u65f6\u957f\uff09<\/span><\/h3>\n\n\n\ndef generate_visit_log(n=5000):\n pages = ['\/home', '\/product', '\/cart', '\/checkout', '\/profile']\n data = []\n for _ in range(n):\n user_id = np.random.randint(10000, 99999)\n visit_time = fake.date_time_between(start_date='-1y', end_date='now')\n page = np.random.choice(pages)\n duration = np.random.exponential(5) # \u5e73\u5747\u505c\u75595\u5206\u949f\n device = np.random.choice(['Mobile', 'Desktop'], p=[0.7, 0.3])\n data.append((user_id, visit_time, page, round(duration, 2), device))\n\n columns = ['UserID', 'VisitTime', 'Page', 'DurationMin', 'Device']\n return pd.DataFrame(data, columns=columns)\n\ndf_visits = generate_visit_log(2000)\nprint(df_visits.head())<\/code><\/pre>\n\n\n\n\n\u2705 \u9002\u7528\u573a\u666f<\/strong>\uff1a\u7528\u4e8e\u7528\u6237\u884c\u4e3a\u5206\u6790\u3001\u8f6c\u5316\u6f0f\u6597\u5efa\u6a21\u3001\u9875\u9762\u4f18\u5316\u5efa\u8bae\u7b49\u3002<\/p>\n<\/blockquote>\n\n\n\n
\n\n\n\n<\/span>\u2705 \u573a\u666f6~10\u7b80\u8981\u8bf4\u660e\uff08\u5b8c\u6574\u4ee3\u7801\u53ef\u5728Jupyter\u4e2d\u5c55\u5f00\uff09<\/span><\/h3>\n\n\n\n| \u573a\u666f\u7f16\u53f7<\/th> | \u540d\u79f0<\/th> | \u63cf\u8ff0<\/th><\/tr><\/thead> |
|---|
| \u573a\u666f6<\/td> | \u6d4f\u89c8\u8bb0\u5f55\u6570\u636e\u751f\u6210<\/td> | \u751f\u6210\u5305\u542b\u6d4f\u89c8\u8bb0\u5f55ID\u3001\u987e\u5ba2ID\u3001\u4ea7\u54c1ID\u3001\u6d4f\u89c8\u65f6\u95f4\u548cIP\u5730\u5740\u7684\u6d4f\u89c8\u8bb0\u5f55\u6570\u636e\u96c6<\/td><\/tr> |
| \u573a\u666f7<\/td> | \u8d2d\u7269\u8f66\u6570\u636e\u751f\u6210<\/td> | \u751f\u6210\u5305\u542b\u8d2d\u7269\u8f66ID\u3001\u987e\u5ba2ID\u3001\u4ea7\u54c1ID\u3001\u6dfb\u52a0\u65f6\u95f4\u548c\u79fb\u9664\u65f6\u95f4\u7684\u8d2d\u7269\u8f66\u6570\u636e\u96c6<\/td><\/tr> |
| \u573a\u666f8<\/td> | \u4fc3\u9500\u6d3b\u52a8\u6570\u636e\u751f\u6210<\/td> | \u751f\u6210\u5305\u542b\u4fc3\u9500ID\u3001\u540d\u79f0\u3001\u5f00\u59cb\u65e5\u671f\u3001\u7ed3\u675f\u65e5\u671f\u548c\u6298\u6263\u7387\u7684\u4fc3\u9500\u6d3b\u52a8\u6570\u636e\u96c6<\/td><\/tr> |
| \u573a\u666f9<\/td> | \u7528\u6237\u8bc4\u8bba\u6570\u636e\u751f\u6210<\/td> | \u5305\u62ec\u8bc4\u5206\u3001\u8bc4\u8bba\u5185\u5bb9\u3001\u65f6\u95f4\u3001\u662f\u5426\u597d\u8bc4\u7b49<\/td><\/tr> |
| \u573a\u666f10<\/td> | \u7269\u6d41\u6570\u636e\u751f\u6210<\/td> | \u5305\u62ec\u5165\u5e93\u3001\u51fa\u5e93\u3001\u5e93\u5b58\u53d8\u5316\u3001\u4ed3\u5e93\u5730\u70b9\u7b49<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n<\/span>\u573a\u666f6: \u6d4f\u89c8\u8bb0\u5f55\u6570\u636e\u751f\u6210<\/span><\/h3>\n\n\n\n\u63cf\u8ff0:<\/strong> \u751f\u6210\u5305\u542b\u6d4f\u89c8\u8bb0\u5f55ID\u3001\u987e\u5ba2ID\u3001\u4ea7\u54c1ID\u3001\u6d4f\u89c8\u65f6\u95f4\u548cIP\u5730\u5740\u7684\u6d4f\u89c8\u8bb0\u5f55\u6570\u636e\u96c6\u3002<\/p>\n\n\n\nimport ipaddress\n\nnp.random.seed(42)\nnum_views = 2000\nview_ids = range(1, num_views + 1)\ncustomer_ids = np.random.choice(range(1, 501), size=num_views)\nproduct_ids = np.random.choice(['P{:03d}'.format(i+1) for i in range(100)], size=num_views)\nview_times = [pd.Timestamp.now().normalize() + pd.Timedelta(minutes=np.random.randint(0, 1440)) for _ in range(num_views)]\nip_addresses = [str(ipaddress.IPv4Address(np.random.randint(0, 2**32))) for _ in range(num_views)]\n\nviews_df = pd.DataFrame({\n 'ViewID': view_ids,\n 'CustomerID': customer_ids,\n 'ProductID': product_ids,\n 'ViewTime': view_times,\n 'IPAddress': ip_addresses\n})\n\nprint(views_df.head())<\/code><\/pre>\n\n\n\n<\/span>\u573a\u666f7: \u8d2d\u7269\u8f66\u6570\u636e\u751f\u6210<\/span><\/h3>\n\n\n\n\u63cf\u8ff0:<\/strong> \u751f\u6210\u5305\u542b\u8d2d\u7269\u8f66ID\u3001\u987e\u5ba2ID\u3001\u4ea7\u54c1ID\u3001\u6dfb\u52a0\u65f6\u95f4\u548c\u79fb\u9664\u65f6\u95f4\u7684\u8d2d\u7269\u8f66\u6570\u636e\u96c6\u3002<\/p>\n\n\n\nnp.random.seed(42)\nnum_cart_items = 1500\ncart_item_ids = range(1, num_cart_items + 1)\ncustomer_ids = np.random.choice(range(1, 501), size=num_cart_items)\nproduct_ids = np.random.choice(['P{:03d}'.format(i+1) for i in range(100)], size=num_cart_items)\nadd_times = [pd.Timestamp.now().normalize() + pd.Timedelta(minutes=np.random.randint(0, 1440)) for _ in range(num_cart_items)]\nremove_times = [(t + pd.Timedelta(minutes=np.random.randint(0, 1440))) if np.random.rand() > 0.3 else None for t in add_times]\n\ncarts_df = pd.DataFrame({\n 'CartItemID': cart_item_ids,\n 'CustomerID': customer_ids,\n 'ProductID': product_ids,\n 'AddTime': add_times,\n 'RemoveTime': remove_times\n})\n\nprint(carts_df.head())<\/code><\/pre>\n\n\n\n<\/span>\u573a\u666f8: \u4fc3\u9500\u6d3b\u52a8\u6570\u636e\u751f\u6210<\/span><\/h3>\n\n\n\n\u63cf\u8ff0:<\/strong> \u751f\u6210\u5305\u542b\u4fc3\u9500ID\u3001\u540d\u79f0\u3001\u5f00\u59cb\u65e5\u671f\u3001\u7ed3\u675f\u65e5\u671f\u548c\u6298\u6263\u7387\u7684\u4fc3\u9500\u6d3b\u52a8\u6570\u636e\u96c6\u3002<\/p>\n\n\n\nnp.random.seed(42)\nnum_promotions = 20\npromotion_ids = range(1, num_promotions + 1)\nnames = ['Promotion {}'.format(i+1) for i in range(num_promotions)]\nstart_dates = [date.today() - timedelta(days=np.random.randint(0, 365)) for _ in range(num_promotions)]\nend_dates = [sd + timedelta(days=np.random.randint(1, 30)) for sd in start_dates]\ndiscount_rates = np.random.uniform(0.05, 0.5, size=num_promotions).round(2)\n\npromotions_df = pd.DataFrame({\n 'PromotionID': promotion_ids,\n 'Name': names,\n 'StartDate': start_dates,\n 'EndDate': end_dates,\n 'DiscountRate': discount_rates\n})\n\nprint(promotions_df.head())<\/code><\/pre>\n\n\n\n
|