feat: Initial analysis tasks

notebooks/r6data.ipynb

@@ -4,9 +4,7 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "071f6969-c01a-4369-a763-871f5b9e65b3",
-   "metadata": {
+   "metadata": {},
-    "scrolled": true
-   },
    "outputs": [],
    "source": [
     "%pip install redis hiredis fastid tqdm kagglehub"
@@ -24,7 +22,7 @@
     "from redis.retry import Retry\n",
     "from redis.backoff import ExponentialBackoff\n",
     "from pathlib import Path\n",
-    "import kagglehub\n",
+    "import kagglehub  # pyright: ignore[reportMissingTypeStubs]\n",
     "from csv import DictReader\n",
     "from fastid import ulid\n",
     "from tqdm.notebook import tqdm\n",
@@ -79,7 +77,7 @@
    "outputs": [],
    "source": [
     "with full_dump.open(\"rb\") as f:\n",
-    "    rows = sum(1 for line in f) - 1"
+    "    rows = sum(1 for _ in f) - 1"
    ]
   },
   {
@@ -89,7 +87,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "daily_matches = {}\n",
+    "daily_matches: dict[str, set[str]] = {}\n",
     "with full_dump.open(errors=\"ignore\") as csvfile:\n",
     "    reader = DictReader(csvfile, delimiter=\";\")\n",
     "    with client.pipeline() as p:\n",
@@ -102,8 +100,8 @@
     "                    continue\n",
     "                daily_matches[row[\"dateid\"]].add(row[\"matchid\"])\n",
     "                display(f\"Selected {row[\"matchid\"]} for day {row[\"dateid\"]}\")\n",
-    "            p.hset(f\"raw:{ulid()}\", mapping=row)\n",
+    "            _ = p.hset(f\"raw:{ulid()}\", mapping=row)\n",
-    "        p.execute()"
+    "        _ = p.execute()"
    ]
   },
   {
@@ -113,7 +111,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from redis.commands.search.field import TagField, NumericField, TextField\n",
+    "from redis.commands.search.field import TagField, NumericField\n",
     "from redis.commands.search.index_definition import IndexDefinition, IndexType\n",
     "\n",
     "schema = (\n",
@@ -150,6 +148,10 @@
     "    TagField(\"secondarygadget\")\n",
     ")\n",
     "\n",
+    "try:\n",
+    "    client.ft().dropindex()\n",
+    "except:\n",
+    "    pass\n",
     "client.ft().create_index(schema, definition=IndexDefinition(prefix=(\"raw:\",), index_type=IndexType.HASH))"
    ]
   },