File size: 6,269 Bytes
cebb53d
 
 
 
52a040b
cebb53d
ac347d2
cebb53d
ac347d2
 
 
 
 
 
 
 
 
52a040b
ac347d2
 
 
 
 
cebb53d
 
 
 
52a040b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55f0654
8eba8ff
 
52a040b
 
 
 
 
 
 
8eba8ff
 
 
55f0654
52a040b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55f0654
52a040b
 
55f0654
52a040b
 
 
 
55f0654
 
 
 
52a040b
cebb53d
 
 
55f0654
 
 
 
 
 
 
52a040b
55f0654
 
 
52a040b
55f0654
 
 
 
 
52a040b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cebb53d
 
 
 
 
 
 
 
 
 
 
 
ac347d2
cebb53d
 
 
 
 
 
 
 
 
 
 
 
 
 
ac347d2
cebb53d
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "from datetime import datetime\n",
    "from tqdm import tqdm\n",
    "\n",
    "import time\n",
    "import requests\n",
    "import datetime\n",
    "import pandas as pd\n",
    "from collections import defaultdict\n",
    "from typing import Any, Union, List\n",
    "from string import Template\n",
    "from enum import Enum\n",
    "from tqdm import tqdm\n",
    "import numpy as np\n",
    "from pathlib import Path"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "INC_TOOLS = [\n",
    "    'prediction-online', \n",
    "    'prediction-offline', \n",
    "    'claude-prediction-online', \n",
    "    'claude-prediction-offline', \n",
    "    'prediction-offline-sme',\n",
    "    'prediction-online-sme',\n",
    "    'prediction-request-rag',\n",
    "    'prediction-request-reasoning',\n",
    "    'prediction-url-cot-claude', \n",
    "    'prediction-request-rag-claude',\n",
    "    'prediction-request-reasoning-claude'\n",
    "]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/var/folders/l_/g22b1g_n0gn4tmx9lkxqv5x00000gn/T/ipykernel_58769/3518445359.py:5: UserWarning: Converting to PeriodArray/Index representation will drop timezone information.\n",
      "  trades_df['month_year'] = trades_df['creation_timestamp'].dt.to_period('M').astype(str)\n",
      "/var/folders/l_/g22b1g_n0gn4tmx9lkxqv5x00000gn/T/ipykernel_58769/3518445359.py:6: UserWarning: Converting to PeriodArray/Index representation will drop timezone information.\n",
      "  trades_df['month_year_week'] = trades_df['creation_timestamp'].dt.to_period('W').astype(str)\n"
     ]
    }
   ],
   "source": [
    "def prepare_trades(trades_df: pd.DataFrame) -> pd.DataFrame:\n",
    "    \"\"\"Prepares the trades data for analysis.\"\"\"\n",
    "    trades_df['creation_timestamp'] = pd.to_datetime(trades_df['creation_timestamp'])\n",
    "    trades_df['creation_timestamp'] = trades_df['creation_timestamp'].dt.tz_convert('UTC')\n",
    "    trades_df['month_year'] = trades_df['creation_timestamp'].dt.to_period('M').astype(str)\n",
    "    trades_df['month_year_week'] = trades_df['creation_timestamp'].dt.to_period('W').astype(str)\n",
    "    trades_df['winning_trade'] = trades_df['winning_trade'].astype(int)\n",
    "    return trades_df\n",
    "\n",
    "def prepare_data():\n",
    "    tools_df = pd.read_parquet(\"./data/tools.parquet\")\n",
    "    trades_df = pd.read_parquet(\"./data/all_trades_profitability.parquet\")\n",
    "\n",
    "    tools_df['request_time'] = pd.to_datetime(tools_df['request_time'])\n",
    "    tools_df = tools_df[tools_df['request_time'].dt.year == 2024]\n",
    "\n",
    "    trades_df['creation_timestamp'] = pd.to_datetime(trades_df['creation_timestamp'])\n",
    "    trades_df = trades_df[trades_df['creation_timestamp'].dt.year == 2024]\n",
    "\n",
    "    trades_df = prepare_trades(trades_df)\n",
    "    return tools_df, trades_df\n",
    "\n",
    "tools_df, trades_df = prepare_data()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['trader_address', 'trade_id', 'creation_timestamp', 'title',\n",
       "       'market_status', 'collateral_amount', 'outcome_index',\n",
       "       'trade_fee_amount', 'outcomes_tokens_traded', 'current_answer',\n",
       "       'is_invalid', 'winning_trade', 'earnings', 'redeemed',\n",
       "       'redeemed_amount', 'num_mech_calls', 'mech_fee_amount', 'net_earnings',\n",
       "       'roi', 'month_year', 'month_year_week'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "trades_df.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_error_data(tools_df: pd.DataFrame, inc_tools: List[str]) -> pd.DataFrame:\n",
    "    \"\"\"Gets the error data for the given tools and calculates the error percentage.\"\"\"\n",
    "    tools_inc = tools_df[tools_df['tool'].isin(inc_tools)]\n",
    "    error = tools_inc.groupby(['tool', 'request_month_year_week', 'error']).size().unstack(fill_value=0).reset_index()\n",
    "    error['error_perc'] = (error[True] / (error[False] + error[True])) * 100\n",
    "    error['total_requests'] = error[False] + error[True]\n",
    "    return error\n",
    "\n",
    "def get_error_data_overall(error_df: pd.DataFrame) -> pd.DataFrame:\n",
    "    \"\"\"Gets the error data for the given tools and calculates the error percentage.\"\"\"\n",
    "    error_total = error_df.groupby('request_month_year_week').agg({'total_requests': 'sum', False: 'sum', True: 'sum'}).reset_index()\n",
    "    error_total['error_perc'] = (error_total[True] / error_total['total_requests']) * 100\n",
    "    error_total.columns = error_total.columns.astype(str)\n",
    "    error_total['error_perc'] = error_total['error_perc'].apply(lambda x: round(x, 4))\n",
    "    return error_total"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "error_df = get_error_data(\n",
    "    tools_df=tools_df,\n",
    "    inc_tools=INC_TOOLS\n",
    ")\n",
    "error_overall_df = get_error_data_overall(\n",
    "    error_df=error_df\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "akash",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.14"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}