<\/span><\/h3>\n\n\n\nimport pandas as pd\nimport numpy as np\nimport matplotlib.pyplot as plt\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_date': dates,\n 'amount': sales_data,\n 'category_code': np.random.choice(['C{}'.format(i) for i in range(1, 11)], len(dates)),\n 'region': np.random.choice(['Beijing', 'Shanghai', 'Guangzhou', 'Shenzhen'], len(dates)),\n 'promotion': np.random.choice([True, False], len(dates))\n}\n\ndf = pd.DataFrame(data)\n\n# \u8bbe\u7f6e\u65f6\u95f4\u4e3a\u7d22\u5f15\ndf.set_index('order_date', inplace=True)\n\nprint(\"\u539f\u59cb\u6570\u636e:\")\nprint(df.head())<\/code><\/pre>\n\n\n\n<\/span>1. \u4f7f\u7528 Pandas \u6784\u9020\u6807\u51c6\u65f6\u95f4\u5e8f\u5217<\/span><\/h3>\n\n\n\n# \u6309\u5929\u805a\u5408\u9500\u552e\u989d\ndaily_sales = df['amount'].resample('D').sum()\n\nprint(\"\\n\u6309\u5929\u805a\u5408\u9500\u552e\u989d:\")\nprint(daily_sales.head())<\/code><\/pre>\n\n\n\n<\/span>2. \u53ef\u89c6\u5316\u6bcf\u65e5\/\u6bcf\u5468\u9500\u552e\u989d\u8d8b\u52bf\u56fe<\/span><\/h3>\n\n\n\n# \u7ed8\u5236\u6bcf\u65e5\u9500\u552e\u989d\u8d8b\u52bf\u56fe\nplt.figure(figsize=(14, 7))\nplt.plot(daily_sales, label='Daily Sales')\nplt.title('Daily Sales Trend')\nplt.xlabel('Date')\nplt.ylabel('Sales Amount')\nplt.legend()\nplt.show()\n\n# \u6309\u5468\u805a\u5408\u9500\u552e\u989d\nweekly_sales = daily_sales.resample('W').sum()\n\n# \u7ed8\u5236\u6bcf\u5468\u9500\u552e\u989d\u8d8b\u52bf\u56fe\nplt.figure(figsize=(14, 7))\nplt.plot(weekly_sales, label='Weekly Sales')\nplt.title('Weekly Sales Trend')\nplt.xlabel('Week')\nplt.ylabel('Sales Amount')\nplt.legend()\nplt.show()<\/code><\/pre>\n\n\n\n<\/span>3. \u5206\u89e3\u65f6\u95f4\u5e8f\u5217\u7684\u8d8b\u52bf\u3001\u5b63\u8282\u6027\u4e0e\u6b8b\u5dee\uff08STL\u5206\u89e3\uff09<\/span><\/h3>\n\n\n\nfrom statsmodels.tsa.seasonal import STL\n\n# STL\u5206\u89e3\nstl = STL(daily_sales, period=365)\nres = stl.fit()\n\nfig = res.plot()\nplt.show()<\/code><\/pre>\n\n\n\n<\/span>4. \u4f7f\u7528\u79fb\u52a8\u5e73\u5747\u6cd5\u5e73\u6ed1\u77ed\u671f\u6ce2\u52a8<\/span><\/h3>\n\n\n\n# \u8ba1\u7b97\u79fb\u52a8\u5e73\u5747\nmoving_avg = daily_sales.rolling(window=30).mean()\n\n# \u7ed8\u5236\u79fb\u52a8\u5e73\u5747\u7ebf\nplt.figure(figsize=(14, 7))\nplt.plot(daily_sales, label='Original')\nplt.plot(moving_avg, label='30-Day Moving Average', color='red')\nplt.title('Daily Sales with 30-Day Moving Average')\nplt.xlabel('Date')\nplt.ylabel('Sales Amount')\nplt.legend()\nplt.show()<\/code><\/pre>\n\n\n\n<\/span>5. \u4f7f\u7528\u6307\u6570\u5e73\u6ed1\u6cd5\uff08Simple Exponential Smoothing\uff09\u8fdb\u884c\u9884\u6d4b<\/span><\/h3>\n\n\n\nfrom statsmodels.tsa.holtwinters import SimpleExpSmoothing\n\n# \u62df\u5408\u6307\u6570\u5e73\u6ed1\u6a21\u578b\nmodel_es = SimpleExpSmoothing(daily_sales)\nmodel_es_fit = model_es.fit(smoothing_level=0.2, optimized=False)\n\n# \u9884\u6d4b\u672a\u6765\u4e00\u4e2a\u6708\u7684\u9500\u552e\u989d\nforecast_es = model_es_fit.forecast(steps=30)\n\n# \u7ed8\u5236\u9884\u6d4b\u7ed3\u679c\nplt.figure(figsize=(14, 7))\nplt.plot(daily_sales, label='Original')\nplt.plot(forecast_es, label='Forecast', color='red')\nplt.title('Simple Exponential Smoothing Forecast')\nplt.xlabel('Date')\nplt.ylabel('Sales Amount')\nplt.legend()\nplt.show()<\/code><\/pre>\n\n\n\n<\/span>6. \u4f7f\u7528 Holt-Winters \u5b63\u8282\u6027\u6a21\u578b\u9884\u6d4b\u8282\u5047\u65e5\u6548\u5e94<\/span><\/h3>\n\n\n\nfrom statsmodels.tsa.holtwinters import ExponentialSmoothing\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.reset_index(inplace=True)\ndf['is_holiday'] = df['order_date'].isin(holidays).astype(int)\ndf.set_index('order_date', inplace=True)\n\n# \u62df\u5408Holt-Winters\u6a21\u578b\nmodel_hw = ExponentialSmoothing(daily_sales, trend='add', seasonal='add', seasonal_periods=365)\nmodel_hw_fit = model_hw.fit()\n\n# \u9884\u6d4b\u672a\u6765\u4e00\u4e2a\u6708\u7684\u9500\u552e\u989d\nforecast_hw = model_hw_fit.forecast(steps=30)\n\n# \u7ed8\u5236\u9884\u6d4b\u7ed3\u679c\nplt.figure(figsize=(14, 7))\nplt.plot(daily_sales, label='Original')\nplt.plot(forecast_hw, label='Forecast', color='red')\nplt.title('Holt-Winters Seasonal Model Forecast')\nplt.xlabel('Date')\nplt.ylabel('Sales Amount')\nplt.legend()\nplt.show()<\/code><\/pre>\n\n\n\n<\/span>7. \u4f7f\u7528 ARIMA \u6a21\u578b\u9884\u6d4b\u672a\u676530\u5929\u9500\u552e\u989d<\/span><\/h3>\n\n\n\nfrom statsmodels.tsa.arima.model import ARIMA\n\n# \u62df\u5408ARIMA\u6a21\u578b\nmodel_arima = ARIMA(daily_sales, order=(5, 1, 0)) # \u8fd9\u91cc\u4f7f\u7528 (5, 1, 0) \u4f5c\u4e3a\u793a\u4f8b\u53c2\u6570\nmodel_arima_fit = model_arima.fit()\n\n# \u9884\u6d4b\u672a\u6765\u4e00\u4e2a\u6708\u7684\u9500\u552e\u989d\nforecast_arima = model_arima_fit.forecast(steps=30)\n\n# \u7ed8\u5236\u9884\u6d4b\u7ed3\u679c\nplt.figure(figsize=(14, 7))\nplt.plot(daily_sales, label='Original')\nplt.plot(pd.date_range(start=daily_sales.index[-1] + pd.Timedelta(days=1), periods=30), forecast_arima, label='Forecast', color='red')\nplt.title('ARIMA Model Forecast')\nplt.xlabel('Date')\nplt.ylabel('Sales Amount')\nplt.legend()\nplt.show()<\/code><\/pre>\n\n\n\n<\/span>8. \u4f7f\u7528 SARIMA \u6a21\u578b\u5904\u7406\u5177\u6709\u5b63\u8282\u6027\u7684\u9500\u552e\u6570\u636e<\/span><\/h3>\n\n\n\nfrom statsmodels.tsa.statespace.sarimax import SARIMAX\n\n# \u62df\u5408SARIMA\u6a21\u578b\nmodel_sarima = SARIMAX(daily_sales, order=(5, 1, 0), seasonal_order=(1, 1, 1, 365))\nmodel_sarima_fit = model_sarima.fit()\n\n# \u9884\u6d4b\u672a\u6765\u4e00\u4e2a\u6708\u7684\u9500\u552e\u989d\nforecast_sarima = model_sarima_fit.forecast(steps=30)\n\n# \u7ed8\u5236\u9884\u6d4b\u7ed3\u679c\nplt.figure(figsize=(14, 7))\nplt.plot(daily_sales, label='Original')\nplt.plot(pd.date_range(start=daily_sales.index[-1] + pd.Timedelta(days=1), periods=30), forecast_sarima, label='Forecast', color='red')\nplt.title('SARIMA Model Forecast')\nplt.xlabel('Date')\nplt.ylabel('Sales Amount')\nplt.legend()\nplt.show()<\/code><\/pre>\n\n\n\n<\/span>9. \u6784\u5efa\u591a\u7ef4\u65f6\u95f4\u5e8f\u5217\u6a21\u578b\uff08\u6309\u54c1\u7c7b + \u533a\u57df\uff09<\/span><\/h3>\n\n\n\n# \u6309\u54c1\u7c7b\u548c\u533a\u57df\u805a\u5408\u9500\u552e\u989d\nregion_category_sales = df.groupby(['region', 'category_code'])['amount'].sum().unstack(fill_value=0)\n\n# \u9009\u62e9\u4e00\u4e2a\u7ec4\u5408\u8fdb\u884c\u9884\u6d4b\nselected_region = region_category_sales.columns.levels[0][0]\nselected_category = region_category_sales.columns.levels[1][0]\nregion_category_series = region_category_sales[(selected_region, selected_category)]\n\n# \u62df\u5408SARIMA\u6a21\u578b\nmodel_sarima_multi = SARIMAX(region_category_series, order=(5, 1, 0), seasonal_order=(1, 1, 1, 365))\nmodel_sarima_multi_fit = model_sarima_multi.fit()\n\n# \u9884\u6d4b\u672a\u6765\u4e00\u4e2a\u6708\u7684\u9500\u552e\u989d\nforecast_sarima_multi = model_sarima_multi_fit.forecast(steps=30)\n\n# \u7ed8\u5236\u9884\u6d4b\u7ed3\u679c\nplt.figure(figsize=(14, 7))\nplt.plot(region_category_series, label='Original')\nplt.plot(pd.date_range(start=region_category_series.index[-1] + pd.Timedelta(days=1), periods=30), forecast_sarima_multi, label='Forecast', color='red')\nplt.title('Multi-Dimensional SARIMA Model Forecast (Region: {}, Category: {})'.format(selected_region, selected_category))\nplt.xlabel('Date')\nplt.ylabel('Sales Amount')\nplt.legend()\nplt.show()<\/code><\/pre>\n\n\n\n<\/span>10. \u9884\u6d4b\u4fc3\u9500\u671f\u95f4\u7684\u8ba2\u5355\u589e\u957f\u66f2\u7ebf<\/span><\/h3>\n\n\n\n# \u6309\u4fc3\u9500\u72b6\u6001\u805a\u5408\u9500\u552e\u989d\npromotion_effect = df.groupby('promotion')['amount'].sum()\n\n# \u5c06\u4fc3\u9500\u72b6\u6001\u8f6c\u6362\u4e3a\u6570\u503c\ndf['promotion_numeric'] = df['promotion'].astype(int)\n\n# \u62df\u5408SARIMA\u6a21\u578b\u8003\u8651\u4fc3\u9500\u5f71\u54cd\nmodel_sarima_promo = SARIMAX(daily_sales, exog=df['promotion_numeric'], order=(5, 1, 0), seasonal_order=(1, 1, 1, 365))\nmodel_sarima_promo_fit = model_sarima_promo.fit()\n\n# \u9884\u6d4b\u672a\u6765\u4e00\u4e2a\u6708\u7684\u9500\u552e\u989d\u5e76\u8003\u8651\u4fc3\u9500\u5f71\u54cd\nfuture_dates = pd.date_range(start=daily_sales.index[-1] + pd.Timedelta(days=1), periods=30)\nfuture_exog = pd.Series([1]*30, index=future_dates) # \u5047\u8bbe\u672a\u6765\u90fd\u662f\u4fc3\u9500\u671f\nforecast_sarima_promo = model_sarima_promo_fit.get_forecast(steps=30, exog=future_exog)\n\n# \u7ed8\u5236\u9884\u6d4b\u7ed3\u679c\nplt.figure(figsize=(14, 7))\nplt.plot(daily_sales, label='Original')\nplt.plot(forecast_sarima_promo.predicted_mean, label='Promotion Forecast', color='red')\nplt.title('SARIMA Model Forecast with Promotion Effect')\nplt.xlabel('Date')\nplt.ylabel('Sales Amount')\nplt.legend()\nplt.show()<\/code><\/pre>\n\n\n\n\u7efc\u5408\u4ee5\u4e0a\u6b65\u9aa4\uff0c\u6700\u7ec8\u7684\u65f6\u95f4\u5e8f\u5217\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\u65f6\u95f4\u5e8f\u5217\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
import pandas as pd\r\nimport numpy as np\r\nimport matplotlib.pyplot as plt\r\nfrom statsmodels.tsa.seasonal import STL\r\nfrom statsmodels.tsa.holtwinters import SimpleExpSmoothing, ExponentialSmoothing\r\nfrom statsmodels.tsa.arima.model import ARIMA\r\nfrom statsmodels.tsa.statespace.sarimax import SARIMAX\r\n\r\n# \u521b\u5efa\u793a\u4f8b\u65f6\u95f4\u5e8f\u5217\u6570\u636e\r\ndates = pd.date_range(start='2023-01-01', end='2025-06-30', freq='D')\r\nnp.random.seed(42)\r\nsales_data = np.cumsum(np.random.normal(loc=100, scale=20, size=len(dates)))\r\n\r\ndata = {\r\n 'order_date': dates,\r\n 'amount': sales_data,\r\n 'category_code': np.random.choice(['C{}'.format(i) for i in range(1, 11)], len(dates)),\r\n 'region': np.random.choice(['Beijing', 'Shanghai', 'Guangzhou', 'Shenzhen'], len(dates)),\r\n 'promotion': np.random.choice([True, False], len(dates))\r\n}\r\n\r\ndf = pd.DataFrame(data)\r\n\r\n# \u8bbe\u7f6e\u65f6\u95f4\u4e3a\u7d22\u5f15\r\ndf.set_index('order_date', inplace=True)\r\n\r\n# \u6309\u5929\u805a\u5408\u9500\u552e\u989d\r\ndaily_sales = df['amount'].resample('D').sum()\r\n\r\n# \u7ed8\u5236\u6bcf\u65e5\u9500\u552e\u989d\u8d8b\u52bf\u56fe\r\nplt.figure(figsize=(14, 7))\r\nplt.plot(daily_sales, label='Daily Sales')\r\nplt.title('Daily Sales Trend')\r\nplt.xlabel('Date')\r\nplt.ylabel('Sales Amount')\r\nplt.legend()\r\nplt.show()\r\n\r\n# \u6309\u5468\u805a\u5408\u9500\u552e\u989d\r\nweekly_sales = daily_sales.resample('W').sum()\r\n\r\n# \u7ed8\u5236\u6bcf\u5468\u9500\u552e\u989d\u8d8b\u52bf\u56fe\r\nplt.figure(figsize=(14, 7))\r\nplt.plot(weekly_sales, label='Weekly Sales')\r\nplt.title('Weekly Sales Trend')\r\nplt.xlabel('Week')\r\nplt.ylabel('Sales Amount')\r\nplt.legend()\r\nplt.show()\r\n\r\n# STL\u5206\u89e3\r\nstl = STL(daily_sales, period=365)\r\nres = stl.fit()\r\n\r\nfig = res.plot()\r\nplt.show()\r\n\r\n# \u8ba1\u7b97\u79fb\u52a8\u5e73\u5747\r\nmoving_avg = daily_sales.rolling(window=30).mean()\r\n\r\n# \u7ed8\u5236\u79fb\u52a8\u5e73\u5747\u7ebf\r\nplt.figure(figsize=(14, 7))\r\nplt.plot(daily_sales, label='Original')\r\nplt.plot(moving_avg, label='30-Day Moving Average', color='red')\r\nplt.title('Daily Sales with 30-Day Moving Average')\r\nplt.xlabel('Date')\r\nplt.ylabel('Sales Amount')\r\nplt.legend()\r\nplt.show()\r\n\r\n# \u62df\u5408\u6307\u6570\u5e73\u6ed1\u6a21\u578b\r\nmodel_es = SimpleExpSmoothing(daily_sales)\r\nmodel_es_fit = model_es.fit(smoothing_level=0.2, optimized=False)\r\n\r\n# \u9884\u6d4b\u672a\u6765\u4e00\u4e2a\u6708\u7684\u9500\u552e\u989d\r\nforecast_es = model_es_fit.forecast(steps=30)\r\n\r\n# \u7ed8\u5236\u9884\u6d4b\u7ed3\u679c\r\nplt.figure(figsize=(14, 7))\r\nplt.plot(daily_sales, label='Original')\r\nplt.plot(forecast_es, label='Forecast', color='red')\r\nplt.title('Simple Exponential Smoothing Forecast')\r\nplt.xlabel('Date')\r\nplt.ylabel('Sales Amount')\r\nplt.legend()\r\nplt.show()\r\n\r\n# \u6dfb\u52a0\u8282\u5047\u65e5\u6807\u5fd7\r\nholidays = pd.to_datetime([\r\n '2023-01-01', '2023-02-22', '2023-04-05', '2023-05-01', '2023-10-01',\r\n '2024-01-01', '2024-02-10', '2024-04-04', '2024-05-01', '2024-10-01',\r\n '2025-01-01', '2025-02-19', '2025-04-04', '2025-05-01', '2025-10-01'\r\n])\r\n\r\ndf.reset_index(inplace=True)\r\ndf['is_holiday'] = df['order_date'].isin(holidays).astype(int)\r\ndf.set_index('order_date', inplace=True)\r\n\r\n# \u62df\u5408Holt-Winters\u6a21\u578b\r\nmodel_hw = ExponentialSmoothing(daily_sales, trend='add', seasonal='add', seasonal_periods=365)\r\nmodel_hw_fit = model_hw.fit()\r\n\r\n# \u9884\u6d4b\u672a\u6765\u4e00\u4e2a\u6708\u7684\u9500\u552e\u989d\r\nforecast_hw = model_hw_fit.forecast(steps=30)\r\n\r\n# \u7ed8\u5236\u9884\u6d4b\u7ed3\u679c\r\nplt.figure(figsize=(14, 7))\r\nplt.plot(daily_sales, label='Original')\r\nplt.plot(forecast_hw, label='Forecast', color='red')\r\nplt.title('Holt-Winters Seasonal Model Forecast')\r\nplt.xlabel('Date')\r\nplt.ylabel('Sales Amount')\r\nplt.legend()\r\nplt.show()\r\n\r\n# \u62df\u5408ARIMA\u6a21\u578b\r\nmodel_arima = ARIMA(daily_sales, order=(5, 1, 0)) # \u8fd9\u91cc\u4f7f\u7528 (5, 1, 0) \u4f5c\u4e3a\u793a\u4f8b\u53c2\u6570\r\nmodel_arima_fit = model_arima.fit()\r\n\r\n# \u9884\u6d4b\u672a\u6765\u4e00\u4e2a\u6708\u7684\u9500\u552e\u989d\r\nforecast_arima = model_arima_fit.forecast(steps=30)\r\n\r\n# \u7ed8\u5236\u9884\u6d4b\u7ed3\u679c\r\nplt.figure(figsize=(14, 7))\r\nplt.plot(daily_sales, label='Original')\r\nplt.plot(pd.date_range(start=daily_sales.index[-1] + pd.Timedelta(days=1), periods=30), forecast_arima, label='Forecast', color='red')\r\nplt.title('ARIMA Model Forecast')\r\nplt.xlabel('Date')\r\nplt.ylabel('Sales Amount')\r\nplt.legend()\r\nplt.show()\r\n\r\n# \u62df\u5408SARIMA\u6a21\u578b\r\nmodel_sarima = SARIMAX(daily_sales, order=(5, 1, 0), seasonal_order=(1, 1, 1, 365))\r\nmodel_sarima_fit = model_sarima.fit()\r\n\r\n# \u9884\u6d4b\u672a\u6765\u4e00\u4e2a\u6708\u7684\u9500\u552e\u989d\r\nforecast_sarima = model_sarima_fit.forecast(steps=30)\r\n\r\n# \u7ed8\u5236\u9884\u6d4b\u7ed3\u679c\r\nplt.figure(figsize=(14, 7))\r\nplt.plot(daily_sales, label='Original')\r\nplt.plot(pd.date_range(start=daily_sales.index[-1] + pd.Timedelta(days=1), periods=30), forecast_sarima, label='Forecast', color='red')\r\nplt.title('SARIMA Model Forecast')\r\nplt.xlabel('Date')\r\nplt.ylabel('Sales Amount')\r\nplt.legend()\r\nplt.show()\r\n\r\n# \u6309\u54c1\u7c7b\u548c\u533a\u57df\u805a\u5408\u9500\u552e\u989d\r\nregion_category_sales = df.groupby(['region', 'category_code'])['amount'].sum().unstack(fill_value=0)\r\n\r\n# \u9009\u62e9\u4e00\u4e2a\u7ec4\u5408\u8fdb\u884c\u9884\u6d4b\r\nselected_region = region_category_sales.columns.levels[0][0]\r\nselected_category = region_category_sales.columns.levels[1][0]\r\nregion_category_series = region_category_sales[(selected_region, selected_category)]\r\n\r\n# \u62df\u5408SARIMA\u6a21\u578b\r\nmodel_sarima_multi = SARIMAX(region_category_series, order=(5, 1, 0), seasonal_order=(1, 1, 1, 365))\r\nmodel_sarima_multi_fit = model_sarima_multi.fit()\r\n\r\n# \u9884\u6d4b\u672a\u6765\u4e00\u4e2a\u6708\u7684\u9500\u552e\u989d\r\nforecast_sarima_multi = model_sarima_multi_fit.forecast(steps=30)\r\n\r\n# \u7ed8\u5236\u9884\u6d4b\u7ed3\u679c\r\nplt.figure(figsize=(14, 7))\r\nplt.plot(region_category_series, label='Original')\r\nplt.plot(pd.date_range(start=region_category_series.index[-1] + pd.Timedelta(days=1), periods=30), forecast_sarima_multi, label='Forecast', color='red')\r\nplt.title('Multi-Dimensional SARIMA Model Forecast (Region: {}, Category: {})'.format(selected_region, selected_category))\r\nplt.xlabel('Date')\r\nplt.ylabel('Sales Amount')\r\nplt.legend()\r\nplt.show()\r\n\r\n# \u5c06\u4fc3\u9500\u72b6\u6001\u8f6c\u6362\u4e3a\u6570\u503c\r\ndf['promotion_numeric'] = df['promotion'].astype(int)\r\n\r\n# \u62df\u5408SARIMA\u6a21\u578b\u8003\u8651\u4fc3\u9500\u5f71\u54cd\r\nmodel_sarima_promo = SARIMAX(daily_sales, exog=df['promotion_numeric'], order=(5, 1, 0), seasonal_order=(1, 1, 1, 365))\r\nmodel_sarima_promo_fit = model_sarima_promo.fit()\r\n\r\n# \u9884\u6d4b\u672a\u6765\u4e00\u4e2a\u6708\u7684\u9500\u552e\u989d\u5e76\u8003\u8651\u4fc3\u9500\u5f71\u54cd\r\nfuture_dates = pd.date_range(start=daily_sales.index[-1] + pd.Timedelta(days=1), periods=30)\r\nfuture_exog = pd.Series([1]*30, index=future_dates) # \u5047\u8bbe\u672a\u6765\u90fd\u662f\u4fc3\u9500\u671f\r\nforecast_sarima_promo = model_sarima_promo_fit.get_forecast(steps=30, exog=future_exog)\r\n\r\n# \u7ed8\u5236\u9884\u6d4b\u7ed3\u679c\r\nplt.figure(figsize=(14, 7))\r\nplt.plot(daily_sales, label='Original')\r\nplt.plot(forecast_sarima_promo.predicted_mean, label='Promotion Forecast', color='red')\r\nplt.title('SARIMA Model Forecast with Promotion Effect')\r\nplt.xlabel('Date')\r\nplt.ylabel('Sales Amount')\r\nplt.legend()\r\nplt.show()\r\n\r\n\r\n\r\n<\/code><\/pre>\n","protected":false},"excerpt":{"rendered":"\u5de5\u4f5c\u5e38\u7528\u7684\u65f6\u95f4\u5e8f\u5217\u5206\u6790\u6848\u4f8b\uff1a \u4f7f\u7528 Pandas \u6784\u9020\u6807\u51c6\u65f6\u95f4\u5e8f\u5217\u53ef\u89c6\u5316\u6bcf\u65e5\/\u6bcf\u5468\u9500\u552e\u989d\u8d8b\u52bf\u56fe\u5206\u89e3\u65f6… \u7ee7\u7eed\u9605\u8bfb \u3010Python10\u5e74\u7ecf\u9a8c\u603b\u7ed3\u3011\u7b2c\u4e03\u8bfe \u7535\u5546\u5e73\u53f0\u9500\u552e\u6570\u636e\u5206\u6790\u5b9e\u8df5 -\u65f6\u95f4\u5e8f\u5217\u5206\u6790\uff08Time Series Analysis\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":1234,"_links":{"self":[{"href":"http:\/\/viplao.com\/index.php\/wp-json\/wp\/v2\/posts\/3547"}],"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=3547"}],"version-history":[{"count":2,"href":"http:\/\/viplao.com\/index.php\/wp-json\/wp\/v2\/posts\/3547\/revisions"}],"predecessor-version":[{"id":3565,"href":"http:\/\/viplao.com\/index.php\/wp-json\/wp\/v2\/posts\/3547\/revisions\/3565"}],"wp:attachment":[{"href":"http:\/\/viplao.com\/index.php\/wp-json\/wp\/v2\/media?parent=3547"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/viplao.com\/index.php\/wp-json\/wp\/v2\/categories?post=3547"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/viplao.com\/index.php\/wp-json\/wp\/v2\/tags?post=3547"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}