feat: 制式标注改为2.6G/700M/TDD/FDD

README.md

@@ -30,7 +30,7 @@ metric_time,network_type,cgi,cell_name,interference_dbm,prev_interference_dbm,lo
 
 All selected workbook rows must belong to the selected natural 15-minute group. Every summary row receives the same normalized `metric_time`; a row outside the group fails the run before database or history output.
 
-`network_type` is derived from the seven source types: both `5G...` sources are `2.6G`, both `700M...` sources are `700M`, and SDR/反开 sources are `4G`. The summary and database keep only high-interference rows: `2.6G >= -107 dBm` and `700M/4G >= -110 dBm`. Converted source CSV files remain full source conversions.
+`network_type` is derived from the seven source types: `5G干扰监控` is `2.6G`, `700M干扰监控` is `700M`, `SDR_TDD干扰监控` and `反开RD干扰监控` are `TDD`, and `SDR_FDD干扰监控`, `5G下FDD干扰监控`, and `700M下FDD干扰监控` are `FDD`. The summary and database keep only high-interference rows. Thresholds keep the original directory grouping and are independent of the `network_type` label: the two `5G...` sources use `>= -107 dBm`, and the other five sources use `>= -110 dBm`. Converted source CSV files remain full source conversions.
 
 `nearby_count` is the number of other high-interference cells from the same selected time group within 1 km, across all network types. The cell itself is excluded, the 1 km boundary is included, and rows without coordinates use `0`. Candidate cells are found through a 1 km spatial grid index and confirmed with exact Haversine distance.
 

aidocs/project_context.md

@@ -109,6 +109,13 @@
 - The current `2026-08-07 14:00:00` database result was exported directly through the history-only path and replaced in Storage as a verified GBK CSV: 1,082 rows, 150,251 bytes, no UTF-8 BOM, and the expected eleven columns. The temporary UTF-8 backup was deleted after validation.
 - The newer `2026-08-07 15:00:00` source group currently contains duplicate CGI rows, for example `460-00-122737-22`. Its database transaction rolled back on the existing `(metric_time, cgi)` primary key, so the retained `14:00` database and history result were not replaced. Duplicate-row selection requires a separate business rule.
 
+## 2026-08-11: Network type relabeled to 2.6G/700M/TDD/FDD
+
+- `network_type` keeps its column name but now labels radio type per source prefix: `5G干扰监控` is `2.6G` (the user treats 2.6G as the unambiguous 5G label because 700M is also 5G), `700M干扰监控` is `700M`, `SDR_TDD干扰监控` and `反开RD干扰监控` are `TDD`, and the three FDD-schema sources (`SDR_FDD干扰监控`, `5G下FDD干扰监控`, `700M下FDD干扰监控`) are `FDD`. The old `2.6G/700M/4G` grouping is gone.
+- Real source filenames only carry these keywords in the fixed prefix; the middle text (for example `LWP_每小时_过滤110`) has no usable network keyword.
+- High-interference thresholds are unchanged and now keyed per source type through `MIN_INTERFERENCE_BY_SOURCE`: the two 5G-directory sources keep `-107` and the other five keep `-110`, so relabeling `5G下FDD干扰监控` to `FDD` does not change which rows are kept.
+- No database migration is needed: the column type stays `VARCHAR(16)` and old-label rows disappear on the next successful replacement run. Twenty-two tests pass locally.
+
 ## 2026-08-07: Duplicate CGI selection
 
 - Retained high-interference rows are deduplicated by CGI before nearby counting and database insertion. When duplicates exist, the row with the numerically largest `interference_dbm` is kept; equal values keep the first encountered row. Converted source CSVs remain complete.

main.py

@@ -48,19 +48,25 @@ EXPECTED_TYPES = (
 )
 
 NETWORK_TYPE_BY_SOURCE = {
-    "5G下FDD干扰监控": "2.6G",
+    "5G下FDD干扰监控": "FDD",
     "5G干扰监控": "2.6G",
-    "700M下FDD干扰监控": "700M",
+    "700M下FDD干扰监控": "FDD",
     "700M干扰监控": "700M",
-    "SDR_FDD干扰监控": "4G",
+    "SDR_FDD干扰监控": "FDD",
-    "SDR_TDD干扰监控": "4G",
+    "SDR_TDD干扰监控": "TDD",
-    "反开RD干扰监控": "4G",
+    "反开RD干扰监控": "TDD",
 }
 
-MIN_INTERFERENCE_BY_NETWORK_TYPE = {
+# Thresholds keep the original band grouping (the two 5G-directory sources use
-    "2.6G": Decimal("-107"),
+# -107, all others -110); they are independent of the network_type label.
-    "700M": Decimal("-110"),
+MIN_INTERFERENCE_BY_SOURCE = {
-    "4G": Decimal("-110"),
+    "5G下FDD干扰监控": Decimal("-107"),
+    "5G干扰监控": Decimal("-107"),
+    "700M下FDD干扰监控": Decimal("-110"),
+    "700M干扰监控": Decimal("-110"),
+    "SDR_FDD干扰监控": Decimal("-110"),
+    "SDR_TDD干扰监控": Decimal("-110"),
+    "反开RD干扰监控": Decimal("-110"),
 }
 
 EARTH_RADIUS_KM = 6371.0088
@@ -848,7 +854,7 @@ def process(
             for row_number, row in enumerate(rows, start=2):
                 record = dict(zip(header, row, strict=True))
                 summary = summary_record(record, source_type, candidate.path, metric_time, row_number, cell_metadata)
-                if passes_interference_threshold(summary):
+                if passes_interference_threshold(summary, source_type):
                     summary_rows.append(summary)
                 else:
                     threshold_filtered_rows += 1
@@ -975,15 +981,14 @@ def summary_record(
     }
 
 
-def passes_interference_threshold(record: dict[str, str]) -> bool:
+def passes_interference_threshold(record: dict[str, str], source_type: str) -> bool:
-    network_type = record["network_type"]
     try:
         interference = Decimal(record["interference_dbm"])
     except InvalidOperation as exc:
         raise ProcessingError(f"Invalid interference value: {record['interference_dbm']}") from exc
     if not interference.is_finite():
         raise ProcessingError(f"Invalid interference value: {record['interference_dbm']}")
-    return interference >= MIN_INTERFERENCE_BY_NETWORK_TYPE[network_type]
+    return interference >= MIN_INTERFERENCE_BY_SOURCE[source_type]
 
 
 def populate_nearby_counts(rows: list[dict[str, str]]) -> None:

tests/test_pipeline.py

@@ -62,6 +62,7 @@ class PipelineTest(unittest.TestCase):
             )
             rows_by_cgi = {row["cgi"]: row for row in rows}
             self.assertEqual(rows_by_cgi["460-00-200-1"]["network_type"], "2.6G")
+            self.assertEqual(rows_by_cgi["460-00-100-1"]["network_type"], "FDD")
             self.assertTrue(all(row["metric_time"] == "2026-07-31 10:00:00" for row in rows))
             self.assertEqual(rows_by_cgi["460-00-200-1"]["cell_name"], "5G干扰监控-小区")
             self.assertTrue(all(row["interference_dbm"] == "-100.5" for row in rows))
@@ -97,13 +98,20 @@ class PipelineTest(unittest.TestCase):
             self.assertEqual(len(archived_rows), 2)
 
     def test_interference_thresholds_remove_only_lower_values(self) -> None:
-        for network_type, threshold in (("2.6G", "-107"), ("700M", "-110"), ("4G", "-110")):
+        for source_type, threshold in (
+            ("5G干扰监控", "-107"),
+            ("5G下FDD干扰监控", "-107"),
+            ("700M干扰监控", "-110"),
+            ("700M下FDD干扰监控", "-110"),
+            ("SDR_FDD干扰监控", "-110"),
+            ("SDR_TDD干扰监控", "-110"),
+            ("反开RD干扰监控", "-110"),
+        ):
             row = database_row()
-            row["network_type"] = network_type
             row["interference_dbm"] = threshold
-            self.assertTrue(main.passes_interference_threshold(row))
+            self.assertTrue(main.passes_interference_threshold(row, source_type))
             row["interference_dbm"] = str(float(threshold) - 0.1)
-            self.assertFalse(main.passes_interference_threshold(row))
+            self.assertFalse(main.passes_interference_threshold(row, source_type))
 
         with tempfile.TemporaryDirectory() as temp:
             root = Path(temp) / "source"