Updated all subgraph links and weekly data

data/all_trades_profitability.parquet

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bc0f6a578ad51a8243244fe2548cb2726dedc03a003a5103faed170353e5294
-size 2350354
+oid sha256:3863cd1823d9c96890cdb0fb06bb5c2b176c5e90161c42963493b5633c7a7135
+size 2035738

data/delivers.parquet

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:630af4a00273b0f620531301da650491fac225a96becf6cd9103331d3a40e634
-size 577925918
+oid sha256:a0c51d4db04dd9d767797d82b196815acea957db6ef85cf96f9e9b73dc46643f
+size 494395523

data/fpmmTrades.parquet

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb876c1221e2fc4bc493fec651cf167c5243b131bc932e52fc817450d9fdf954
-size 6246723
+oid sha256:fa04be34e99e3b2a632363a174ba6385f7f97b7466b01be9a940ce4a1872c575
+size 6334162

data/fpmms.parquet

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f750f72d608999c43ac581b761f153e89d23ecca7aebd4a9b41bc044fb5e429e
-size 341069
+oid sha256:97de347d8c8c9be2960166665eaaa6df3b939583b06208fa46091bb2c6eee122
+size 346572

data/requests.parquet

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b534581f7239aa57fa7895859c895f4cfff92f3372683bfc8188b72f8f3803a3
-size 15857748
+oid sha256:4ea345dab01b7fa4da218e43841927beea8d656f6dd18e96bd2364fad86dcf99
+size 15765143

data/summary_profitability.parquet

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42395ab29e85b1e4c0907132f30895400c20422287be4fb8921e1a884eac0738
-size 42213
+oid sha256:5eb2307c7ba3953abcb7f1217d90117ac113107ff3f2f27d8dbdda71651e20e5
+size 42038

data/t_map.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c180f7b0823819b45ea78c1956ebc4d33cc0d374ad528c9a86acb1797549d341
-size 9548930
+oid sha256:23679bddce247a4cb21cf6acb06c12d9d6d171d03e0e304420107828d1411e40
+size 9830355

data/tools.parquet

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dd77eb7642fb291caab50750842c1509fe121abe1fd873cb43d12643d781626
-size 580056931
+oid sha256:805dc8fd4063d966536a31c19e494315943e8708a7951519cbd0081bc17f376b
+size 495380729

notebooks/analysis.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 28,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2555,10 +2555,169 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 34,
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "def get_question(text: str) -> str:\n",
+    "    \"\"\"Get the question from a text.\"\"\"\n",
+    "    # Regex to find text within double quotes\n",
+    "    pattern = r'\"([^\"]*)\"'\n",
+    "\n",
+    "    # Find all occurrences\n",
+    "    questions = re.findall(pattern, text)\n",
+    "\n",
+    "    # Assuming you want the first question if there are multiple\n",
+    "    question = questions[0] if questions else None\n",
+    "\n",
+    "    return question"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 41,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from web3 import Web3\n",
+    "from typing import Optional\n",
+    "import re\n",
+    "import pickle\n",
+    "\n",
+    "def block_number_to_timestamp(block_number: int, web3: Web3) -> str:\n",
+    "    \"\"\"Convert a block number to a timestamp.\"\"\"\n",
+    "    block = web3.eth.get_block(block_number)\n",
+    "    timestamp = datetime.utcfromtimestamp(block[\"timestamp\"])\n",
+    "    return timestamp.strftime(\"%Y-%m-%d %H:%M:%S\")\n",
+    "\n",
+    "\n",
+    "def parallelize_timestamp_conversion(df: pd.DataFrame, function: callable) -> list:\n",
+    "    \"\"\"Parallelize the timestamp conversion.\"\"\"\n",
+    "    block_numbers = df[\"request_block\"].tolist()\n",
+    "    with ThreadPoolExecutor(max_workers=10) as executor:\n",
+    "        results = list(\n",
+    "            tqdm(executor.map(function, block_numbers), total=len(block_numbers))\n",
+    "        )\n",
+    "    return results"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def current_answer(text: str, fpmms: pd.DataFrame) -> Optional[str]:\n",
+    "    \"\"\"Get the current answer for a question.\"\"\"\n",
+    "    row = fpmms[fpmms[\"title\"] == text]\n",
+    "    if row.shape[0] == 0:\n",
+    "        return None\n",
+    "    return row[\"currentAnswer\"].values[0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 47,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from functools import partial\n",
+    "from concurrent.futures import ThreadPoolExecutor\n",
+    "def weekly_analysis():\n",
+    "    rpc = \"https://lb.nodies.app/v1/406d8dcc043f4cb3959ed7d6673d311a\"\n",
+    "    web3 = Web3(Web3.HTTPProvider(rpc))\n",
+    "    # Get currentAnswer from FPMMS\n",
+    "    fpmms = pd.read_parquet('../data/fpmms.parquet')\n",
+    "    tools = pd.read_parquet('../data/tools.parquet')\n",
+    "\n",
+    "    # Get the question from the tools\n",
+    "    print(\"Getting the question and current answer for the tools\")\n",
+    "    tools[\"title\"] = tools[\"prompt_request\"].apply(lambda x: get_question(x))\n",
+    "    tools[\"currentAnswer\"] = tools[\"title\"].apply(lambda x: current_answer(x, fpmms))\n",
+    "\n",
+    "    tools[\"currentAnswer\"] = tools[\"currentAnswer\"].str.replace(\"yes\", \"Yes\")\n",
+    "    tools[\"currentAnswer\"] = tools[\"currentAnswer\"].str.replace(\"no\", \"No\")\n",
+    "\n",
+    "    # Convert block number to timestamp\n",
+    "    print(\"Converting block number to timestamp\")\n",
+    "    t_map = pickle.load(open(\"../data/t_map.pkl\", \"rb\"))\n",
+    "    tools[\"request_time\"] = tools[\"request_block\"].map(t_map)\n",
+    "\n",
+    "    # Identify tools with missing request_time and fill them\n",
+    "    missing_time_indices = tools[tools[\"request_time\"].isna()].index\n",
+    "    if not missing_time_indices.empty:\n",
+    "        partial_block_number_to_timestamp = partial(\n",
+    "            block_number_to_timestamp, web3=web3\n",
+    "        )\n",
+    "        missing_timestamps = parallelize_timestamp_conversion(\n",
+    "            tools.loc[missing_time_indices], partial_block_number_to_timestamp\n",
+    "        )\n",
+    "\n",
+    "        # Update the original DataFrame with the missing timestamps\n",
+    "        for i, timestamp in zip(missing_time_indices, missing_timestamps):\n",
+    "            tools.at[i, \"request_time\"] = timestamp\n",
+    "\n",
+    "    tools[\"request_month_year\"] = pd.to_datetime(tools[\"request_time\"]).dt.strftime(\n",
+    "        \"%Y-%m\"\n",
+    "    )\n",
+    "    tools[\"request_month_year_week\"] = (\n",
+    "        pd.to_datetime(tools[\"request_time\"]).dt.to_period(\"W\").astype(str)\n",
+    "    )\n",
+    "\n",
+    "    # Save the tools data after the updates on the content\n",
+    "    tools.to_parquet('../data/tools.parquet', index=False)\n",
+    "\n",
+    "    # Update t_map with new timestamps\n",
+    "    new_timestamps = (\n",
+    "        tools[[\"request_block\", \"request_time\"]]\n",
+    "        .dropna()\n",
+    "        .set_index(\"request_block\")\n",
+    "        .to_dict()[\"request_time\"]\n",
+    "    )\n",
+    "    t_map.update(new_timestamps)\n",
+    "\n",
+    "    with open(\"../data/t_map.pkl\", \"wb\") as f:\n",
+    "        pickle.dump(t_map, f)\n",
+    "\n",
+    "    # clean and release all memory\n",
+    "    del tools\n",
+    "    del fpmms\n",
+    "    del t_map\n",
+    "    gc.collect()\n",
+    "\n",
+    "    print(\"Weekly analysis files generated and saved\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 46,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Getting the question and current answer for the tools\n",
+      "Converting block number to timestamp\n"
+     ]
+    },
+    {
+     "ename": "NameError",
+     "evalue": "name 'ThreadPoolExecutor' is not defined",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
+      "Cell \u001b[0;32mIn[46], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mweekly_analysis\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n",
+      "Cell \u001b[0;32mIn[45], line 28\u001b[0m, in \u001b[0;36mweekly_analysis\u001b[0;34m()\u001b[0m\n\u001b[1;32m     24\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m missing_time_indices\u001b[38;5;241m.\u001b[39mempty:\n\u001b[1;32m     25\u001b[0m     partial_block_number_to_timestamp \u001b[38;5;241m=\u001b[39m partial(\n\u001b[1;32m     26\u001b[0m         block_number_to_timestamp, web3\u001b[38;5;241m=\u001b[39mweb3\n\u001b[1;32m     27\u001b[0m     )\n\u001b[0;32m---> 28\u001b[0m     missing_timestamps \u001b[38;5;241m=\u001b[39m \u001b[43mparallelize_timestamp_conversion\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m     29\u001b[0m \u001b[43m        \u001b[49m\u001b[43mtools\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mloc\u001b[49m\u001b[43m[\u001b[49m\u001b[43mmissing_time_indices\u001b[49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mpartial_block_number_to_timestamp\u001b[49m\n\u001b[1;32m     30\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m     32\u001b[0m     \u001b[38;5;66;03m# Update the original DataFrame with the missing timestamps\u001b[39;00m\n\u001b[1;32m     33\u001b[0m     \u001b[38;5;28;01mfor\u001b[39;00m i, timestamp \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mzip\u001b[39m(missing_time_indices, missing_timestamps):\n",
+      "Cell \u001b[0;32mIn[41], line 16\u001b[0m, in \u001b[0;36mparallelize_timestamp_conversion\u001b[0;34m(df, function)\u001b[0m\n\u001b[1;32m     14\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"Parallelize the timestamp conversion.\"\"\"\u001b[39;00m\n\u001b[1;32m     15\u001b[0m block_numbers \u001b[38;5;241m=\u001b[39m df[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mrequest_block\u001b[39m\u001b[38;5;124m\"\u001b[39m]\u001b[38;5;241m.\u001b[39mtolist()\n\u001b[0;32m---> 16\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m \u001b[43mThreadPoolExecutor\u001b[49m(max_workers\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m10\u001b[39m) \u001b[38;5;28;01mas\u001b[39;00m executor:\n\u001b[1;32m     17\u001b[0m     results \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mlist\u001b[39m(\n\u001b[1;32m     18\u001b[0m         tqdm(executor\u001b[38;5;241m.\u001b[39mmap(function, block_numbers), total\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mlen\u001b[39m(block_numbers))\n\u001b[1;32m     19\u001b[0m     )\n\u001b[1;32m     20\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m results\n",
+      "\u001b[0;31mNameError\u001b[0m: name 'ThreadPoolExecutor' is not defined"
+     ]
+    }
+   ],
+   "source": [
+    "weekly_analysis()"
+   ]
   }
  ],
  "metadata": {

scripts/get_mech_info.py

@@ -2,9 +2,17 @@ from dataclasses import dataclass
 from string import Template
 from typing import Any
 from datetime import datetime, timedelta, UTC
+from utils import SUBGRAPH_API_KEY
 import requests
 
-MECH_SUBGRAPH_URL = "https://api.thegraph.com/subgraphs/name/stakewise/ethereum-gnosis"
+OLD_MECH_SUBGRAPH_URL = (
+    "https://api.thegraph.com/subgraphs/name/stakewise/ethereum-gnosis"
+)
+# MECH_SUBGRAPH_URL = "https://api.studio.thegraph.com/query/57238/mech/0.0.2"
+NETWORK_SUBGRAPH_URL = Template(
+    """https://gateway-arbitrum.network.thegraph.com/api/${subgraph_api_key}/subgraphs/id/FxV6YUix58SpYmLBwc9gEHkwjfkqwe1X5FJQjn8nKPyA"""
+)
+
 SUBGRAPH_HEADERS = {
     "Accept": "application/json, multipart/mixed",
     "Content-Type": "application/json",
@@ -23,7 +31,8 @@ BLOCK_NUMBER = Template(
                 timestamp_lte: "${timestamp_to}"
             }
         ){
-            id
+            id,
+            number,
         }
     }
     """
@@ -37,9 +46,11 @@ def fetch_block_number(timestamp_from: int, timestamp_to: int) -> dict:
         timestamp_from=timestamp_from, timestamp_to=timestamp_to
     )
     # print(f"Sending query for the subgraph = {query}")
-
+    network_subgraph_url = NETWORK_SUBGRAPH_URL.substitute(
+        subgraph_api_key=SUBGRAPH_API_KEY
+    )
     response = requests.post(
-        MECH_SUBGRAPH_URL,
+        network_subgraph_url,
         headers=SUBGRAPH_HEADERS,
         json={"query": query},
         timeout=300,
@@ -64,7 +75,7 @@ def get_mech_info_last_60_days() -> dict[str, Any]:
         timestamp_60_days_ago, timestamp_60_days_ago_plus_margin
     )
     # expecting only one block
-    last_month_block_number = last_month_block_number.get("id", "")
+    last_month_block_number = last_month_block_number.get("number", "")
     if last_month_block_number.isdigit():
         last_month_block_number = int(last_month_block_number)
 

scripts/markets.py

@@ -28,6 +28,7 @@ from tqdm import tqdm
 
 from typing import List, Dict
 from pathlib import Path
+from utils import SUBGRAPH_API_KEY
 
 ResponseItemType = List[Dict[str, str]]
 SubgraphResponseType = Dict[str, ResponseItemType]
@@ -35,7 +36,10 @@ SubgraphResponseType = Dict[str, ResponseItemType]
 
 CREATOR = "0x89c5cc945dd550BcFfb72Fe42BfF002429F46Fec"
 BATCH_SIZE = 1000
-OMEN_SUBGRAPH = "https://api.thegraph.com/subgraphs/name/protofire/omen-xdai"
+# OMEN_SUBGRAPH = "https://api.thegraph.com/subgraphs/name/protofire/omen-xdai"
+OMEN_SUBGRAPH_URL = Template(
+    """https://gateway-arbitrum.network.thegraph.com/api/${subgraph_api_key}/subgraphs/id/9fUVQpFwzpdWS9bq5WkAnmKbNNcoBwatMR4yZq81pbbz"""
+)
 FPMMS_FIELD = "fixedProductMarketMakers"
 QUERY_FIELD = "query"
 ERROR_FIELD = "errors"
@@ -158,6 +162,8 @@ def query_subgraph(url: str, query: str, key: str) -> SubgraphResponseType:
 
 def fpmms_fetcher() -> Generator[ResponseItemType, int, None]:
     """An indefinite fetcher for the FPMMs."""
+    omen_subgraph = OMEN_SUBGRAPH_URL.substitute(subgraph_api_key=SUBGRAPH_API_KEY)
+    print(f"omen_subgraph = {omen_subgraph}")
     while True:
         fpmm_id = yield
         fpmms_query = FPMMS_QUERY.substitute(
@@ -171,7 +177,8 @@ def fpmms_fetcher() -> Generator[ResponseItemType, int, None]:
             outcomes_field=OUTCOMES_FIELD,
             title_field=TITLE_FIELD,
         )
-        yield query_subgraph(OMEN_SUBGRAPH, fpmms_query, FPMMS_FIELD)
+
+        yield query_subgraph(omen_subgraph, fpmms_query, FPMMS_FIELD)
 
 
 def fetch_fpmms() -> pd.DataFrame:
@@ -225,4 +232,3 @@ def etl(filename: Optional[str] = None) -> pd.DataFrame:
 
 if __name__ == "__main__":
     etl(DEFAULT_FILENAME)
-

scripts/profitability.py

@@ -29,6 +29,7 @@ from tqdm import tqdm
 import numpy as np
 from pathlib import Path
 from get_mech_info import DATETIME_60_DAYS_AGO
+from utils import SUBGRAPH_API_KEY
 
 IRRELEVANT_TOOLS = [
     "openai-text-davinci-002",
@@ -250,8 +251,12 @@ def _query_omen_xdai_subgraph(
     fpmm_to_timestamp: float,
 ) -> dict[str, Any]:
     """Query the subgraph."""
-    url = "https://api.thegraph.com/subgraphs/name/protofire/omen-xdai"
-
+    # url = "https://api.thegraph.com/subgraphs/name/protofire/omen-xdai"
+    OMEN_SUBGRAPH_URL = Template(
+        """https://gateway-arbitrum.network.thegraph.com/api/${subgraph_api_key}/subgraphs/id/9fUVQpFwzpdWS9bq5WkAnmKbNNcoBwatMR4yZq81pbbz"""
+    )
+    omen_subgraph = OMEN_SUBGRAPH_URL.substitute(subgraph_api_key=SUBGRAPH_API_KEY)
+    print(f"omen_subgraph = {omen_subgraph}")
     grouped_results = defaultdict(list)
     id_gt = ""
 
@@ -266,8 +271,10 @@ def _query_omen_xdai_subgraph(
             id_gt=id_gt,
         )
         content_json = _to_content(query)
-        res = requests.post(url, headers=headers, json=content_json)
+
+        res = requests.post(omen_subgraph, headers=headers, json=content_json)
         result_json = res.json()
+        # print(f"result = {result_json}")
         user_trades = result_json.get("data", {}).get("fpmmTrades", [])
 
         if not user_trades:
@@ -294,8 +301,11 @@ def _query_omen_xdai_subgraph(
 
 def _query_conditional_tokens_gc_subgraph(creator: str) -> dict[str, Any]:
     """Query the subgraph."""
-    url = "https://api.thegraph.com/subgraphs/name/gnosis/conditional-tokens-gc"
-
+    # url = "https://api.thegraph.com/subgraphs/name/gnosis/conditional-tokens-gc"
+    SUBGRAPH_URL = Template(
+        """https://gateway-arbitrum.network.thegraph.com/api/${subgraph_api_key}/subgraphs/id/7s9rGBffUTL8kDZuxvvpuc46v44iuDarbrADBFw5uVp2"""
+    )
+    subgraph = SUBGRAPH_URL.substitute(subgraph_api_key=SUBGRAPH_API_KEY)
     all_results: dict[str, Any] = {"data": {"user": {"userPositions": []}}}
     userPositions_id_gt = ""
     while True:
@@ -305,8 +315,10 @@ def _query_conditional_tokens_gc_subgraph(creator: str) -> dict[str, Any]:
             userPositions_id_gt=userPositions_id_gt,
         )
         content_json = {"query": query}
-        res = requests.post(url, headers=headers, json=content_json)
+        print("sending query to subgraph")
+        res = requests.post(subgraph, headers=headers, json=content_json)
         result_json = res.json()
+        # print(f"result = {result_json}")
         user_data = result_json.get("data", {}).get("user", {})
 
         if not user_data:
@@ -368,8 +380,12 @@ def create_fpmmTrades(rpc: str, from_timestamp: float = DEFAULT_FROM_TIMESTAMP):
         fpmm_to_timestamp=DEFAULT_TO_TIMESTAMP,
     )
 
+    print(f"length of the trades_json dataset {len(trades_json)}")
+
     # convert to dataframe
     df = pd.DataFrame(trades_json["data"]["fpmmTrades"])
+    print(df.head())
+    print(df.info())
 
     # convert creator to address
     df["creator"] = df["creator"].apply(lambda x: x["id"])

scripts/pull_data.py

@@ -1,12 +1,10 @@
 import logging
-import re
 import os
 import pickle
 from datetime import datetime
 from concurrent.futures import ThreadPoolExecutor
 from tqdm import tqdm
 from web3 import Web3
-from typing import Optional
 import pandas as pd
 from pathlib import Path
 from functools import partial
@@ -20,6 +18,7 @@ from tools import (
     update_tools_accuracy,
 )
 from profitability import run_profitability_analysis
+from utils import get_question, current_answer
 
 import gc
 
@@ -30,28 +29,6 @@ ROOT_DIR = SCRIPTS_DIR.parent
 DATA_DIR = ROOT_DIR / "data"
 
 
-def get_question(text: str) -> str:
-    """Get the question from a text."""
-    # Regex to find text within double quotes
-    pattern = r'"([^"]*)"'
-
-    # Find all occurrences
-    questions = re.findall(pattern, text)
-
-    # Assuming you want the first question if there are multiple
-    question = questions[0] if questions else None
-
-    return question
-
-
-def current_answer(text: str, fpmms: pd.DataFrame) -> Optional[str]:
-    """Get the current answer for a question."""
-    row = fpmms[fpmms["title"] == text]
-    if row.shape[0] == 0:
-        return None
-    return row["currentAnswer"].values[0]
-
-
 def block_number_to_timestamp(block_number: int, web3: Web3) -> str:
     """Convert a block number to a timestamp."""
     block = web3.eth.get_block(block_number)

scripts/utils.py

@@ -6,6 +6,7 @@ from tqdm import tqdm
 from typing import List, Any, Optional
 import pandas as pd
 import gc
+import re
 from dataclasses import dataclass
 from pathlib import Path
 from enum import Enum
@@ -41,6 +42,8 @@ INC_TOOLS = [
     "prediction-request-reasoning-claude",
 ]
 
+SUBGRAPH_API_KEY = os.environ.get("SUBGRAPH_API_KEY", None)
+
 
 class MechEventName(Enum):
     """The mech's event names."""
@@ -305,3 +308,25 @@ def get_earliest_block(event_name: MechEventName) -> int:
     del df
     gc.collect()
     return earliest_block
+
+
+def get_question(text: str) -> str:
+    """Get the question from a text."""
+    # Regex to find text within double quotes
+    pattern = r'"([^"]*)"'
+
+    # Find all occurrences
+    questions = re.findall(pattern, text)
+
+    # Assuming you want the first question if there are multiple
+    question = questions[0] if questions else None
+
+    return question
+
+
+def current_answer(text: str, fpmms: pd.DataFrame) -> Optional[str]:
+    """Get the current answer for a question."""
+    row = fpmms[fpmms["title"] == text]
+    if row.shape[0] == 0:
+        return None
+    return row["currentAnswer"].values[0]

tabs/about.py

@@ -8,5 +8,5 @@ about_this_dashboard = """\
 This dashboard is pulling data from the omen subgraph during some specific time window. As the data is distributed by weeks, it is possible that some weeks contain incomplete data not showing the total volume of information. 
 This is in particular relevant for:
 * the first week: since we might have started collecting information not from the beginning of the week.
-* the last week: some markets have not been closed yet and the information is not published yet. 
+* the last week: some markets have not been closed yet and the information is not published yet.
 """