+probability(debug&test)

pkg/dash/func/info_test.py

@@ -2,6 +2,8 @@ from pkg.dash.func.info_func import *
 from pkg.dash.app_init import app
 from dash.dependencies import Input, Output
 from dash import html
+import os
+import csv
 import pandas as pd
 import re
 from datetime import timedelta
@@ -120,4 +122,86 @@ def update_test_info(n_clicks, test_date, test_time):
                                         html.Td("Model prediction does not match actual outcome.", colSpan=6, style={'color': 'red'})]))
 
     test_table = html.Table(test_table_rows, style={'width': '100%', 'textAlign': 'left', 'borderCollapse': 'collapse'})
-    return [test_table]
+    return [test_table]
+
+
+def run_loop_test(start_date="2024-10-01", end_date="2025-03-12", interval_hours=1, output_file="test_results.csv"):
+    est = pytz.timezone('US/Eastern')
+
+    # 生成测试时间序列
+    start_dt = pd.to_datetime(start_date).tz_localize(est)
+    end_dt = pd.to_datetime(end_date).tz_localize(est)
+    time_points = []
+    current_dt = start_dt
+    while current_dt <= end_dt:
+        time_points.append(current_dt)
+        current_dt += timedelta(hours=interval_hours)
+
+    # 准备 CSV 文件
+    headers = [
+        "Test Date", "Test Time", "Cycle Start", "Cycle End", "Tweet Count at Test Time",
+        "Actual Final Tweet Count", "Predicted Range Start", "Predicted Range End",
+        "Probability Min (%)", "Probability Max (%)", "Actual in Range", "Expected Probability (%)", "Note"
+    ]
+
+    # 如果文件不存在，写入表头
+    if not os.path.exists(output_file):
+        with open(output_file, 'w', newline='') as f:
+            writer = csv.writer(f)
+            writer.writerow(headers)
+
+    # 循环测试
+    for test_datetime in time_points:
+        test_date = test_datetime.date().strftime('%Y-%m-%d')
+        test_time = test_datetime.time().strftime('%H:%M:%S')
+        n_clicks = 1  # 假设已点击
+
+        # 调用原始函数
+        result = update_test_info(n_clicks, test_date, test_time)
+
+        # 解析结果
+        if isinstance(result[0], html.Table):
+            table = result[0]
+            rows = table.children
+
+            # 提取数据
+            cycle_start = str(rows[0].children[1].children)
+            test_dt = str(rows[1].children[1].children)
+            cycle_end = str(rows[2].children[1].children)
+            tweet_count = int(rows[3].children[1].children)
+            actual_end_count = int(rows[4].children[1].children)
+            prob_range = rows[5].children[1].children  # 例如 "2.74% - 3.25%"
+            # 移除 % 符号并转换为浮点数
+            prob_min, prob_max = [float(x.strip('%')) for x in prob_range.split(" - ")]
+            # 从表头提取预测范围
+            prob_start, prob_end = map(int, rows[5].children[0].children.split("(")[1].split(")")[0].split("-"))
+            in_range = rows[6].children[1].children == "Yes"
+            # 检查是否有 Expected Probability 或 Note
+            expected_prob = None
+            note = ""
+            if len(rows) > 7:
+                if "Expected" in rows[7].children[0].children:
+                    expected_prob = float(rows[7].children[1].children.split()[0][1:-1])  # 移除 "~" 和 "%"
+                elif "Note" in rows[7].children[0].children:
+                    note = rows[7].children[1].children
+
+            # 写入 CSV
+            with open(output_file, 'a', newline='') as f:
+                writer = csv.writer(f)
+                writer.writerow([
+                    test_date, test_time, cycle_start, cycle_end, tweet_count,
+                    actual_end_count, prob_start, prob_end, prob_min, prob_max,
+                    "Yes" if in_range else "No", expected_prob if expected_prob is not None else "", note
+                ])
+        else:
+            # 如果返回错误信息，也记录
+            with open(output_file, 'a', newline='') as f:
+                writer = csv.writer(f)
+                writer.writerow([test_date, test_time, "", "", "", "", "", "", "", "", "", "", result[0].children])
+
+        print(f"Processed: {test_date} {test_time}")
+
+
+# 运行测试
+if __name__ == "__main__":
+    run_loop_test(start_date="2024-10-01", end_date="2025-03-12", interval_hours=1, output_file="test_results.csv")