updating daily data

data/closed_markets_div.parquet

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c4c745aac0b39f8819e642b9eb079dc944838719f55ba7bd5bbaa1c53e66fde
-size 59155
+oid sha256:444276990e2d95ffbc3b30fadbe05cb884dad0c87b1d22b22c849e3ccb68d20c
+size 67375

data/unknown_daily_traders.parquet

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c264104712763aa1e6ca15ce4cd8a6b445f1b3db3626bf96ee1f7dd5b917ca0
-size 23862
+oid sha256:cb7ccb7798037ab116928f78c0f3c3113d99db3eed8338ce93f6be6e29c1469e
+size 182708

data/unknown_traders.parquet

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:facb6d44b0ca6896cd98108283bc9527aee15ca3ca99df7a7c364ad2fb53b172
-size 320009
+oid sha256:3b11d6db3a813c3a7b98fc947d1275d16db706bf70439356fc58740703f7e497
+size 362606

data/weekly_mech_calls.parquet

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:680848115c5adfed614890c96d457dd17876acd3d593b1ffce71fbcacb23d275
-size 54727
+oid sha256:39b4cf253e9fffc20d584d25410efb8428612413a9f002ba0314216dc56b0ca2
+size 54927

notebooks/retention_metrics.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 89,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -12,13 +12,6 @@
     "import gc"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -28,7 +21,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 40,
+   "execution_count": 90,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -37,7 +30,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 41,
+   "execution_count": 91,
    "metadata": {},
    "outputs": [
     {
@@ -48,7 +41,7 @@
        "      dtype='object')"
       ]
      },
-     "execution_count": 41,
+     "execution_count": 91,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -90,7 +83,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 43,
+   "execution_count": 92,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -101,7 +94,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 44,
+   "execution_count": 93,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -501,6 +494,31 @@
     "retention_df.head()"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 105,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "staking\n",
+       "non_Olas       738323\n",
+       "non_staking    199043\n",
+       "pearl           44001\n",
+       "quickstart      39276\n",
+       "Name: count, dtype: int64"
+      ]
+     },
+     "execution_count": 105,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "retention_df.staking.value_counts()"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 14,
@@ -535,12 +553,21 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 50,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
     "# read trades dataset\n",
-    "traders_df = pd.read_parquet(\"../data/all_trades_profitability.parquet\")\n",
+    "traders_df = pd.read_parquet(\"../data/all_trades_profitability.parquet\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 94,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n",
     "unknown_df = pd.read_parquet(\"../data/unknown_traders.parquet\")\n"
    ]
   },
@@ -2381,16 +2408,28 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 82,
+   "execution_count": 96,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/var/folders/gp/02mb1d514ng739czlxw1lhh00000gn/T/ipykernel_51242/3309953326.py:1: SettingWithCopyWarning: \n",
+      "A value is trying to be set on a copy of a slice from a DataFrame\n",
+      "\n",
+      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
+      "  olas_data.rename(columns={\"request_time\": \"creation_timestamp\"}, inplace=True)\n"
+     ]
+    }
+   ],
    "source": [
     "olas_data.rename(columns={\"request_time\": \"creation_timestamp\"}, inplace=True)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 83,
+   "execution_count": 97,
    "metadata": {},
    "outputs": [
     {
@@ -2418,7 +2457,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 84,
+   "execution_count": 98,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2574,7 +2613,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 85,
+   "execution_count": 99,
    "metadata": {},
    "outputs": [
     {
@@ -2585,7 +2624,7 @@
        "       'Jan-12-2025', 'Jan-19-2025'], dtype=object)"
       ]
      },
-     "execution_count": 85,
+     "execution_count": 99,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -2597,7 +2636,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 86,
+   "execution_count": 101,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2609,7 +2648,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 70,
+   "execution_count": 102,
    "metadata": {},
    "outputs": [
     {
@@ -2620,7 +2659,7 @@
        "       'Jan-12-2025', 'Jan-19-2025'], dtype=object)"
       ]
      },
-     "execution_count": 70,
+     "execution_count": 102,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -2631,7 +2670,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 87,
+   "execution_count": 103,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2653,6 +2692,35 @@
     ")"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 104,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "cohort_week\n",
+      "Dec-01-2024     12\n",
+      "Dec-08-2024     12\n",
+      "Dec-15-2024     10\n",
+      "Dec-22-2024      2\n",
+      "Dec-29-2024      1\n",
+      "Jan-05-2025      1\n",
+      "Jan-19-2025      1\n",
+      "Nov-17-2024    202\n",
+      "Nov-24-2024     30\n",
+      "Name: trader_address, dtype: int64\n"
+     ]
+    }
+   ],
+   "source": [
+    "cohort_sizes = cohort_data.groupby(\"cohort_week\")[\"trader_address\"].nunique()\n",
+    "\n",
+    "print(cohort_sizes)"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 88,