File size: 2,733 Bytes
8b414b0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "from pathlib import Path\n",
    "from typing import Optional, Union\n",
    "\n",
    "import pandas as pd\n",
    "from dotenv import load_dotenv\n",
    "\n",
    "\n",
    "load_dotenv()\n",
    "\n",
    "from pathlib import Path\n",
    "from typing import Optional\n",
    "\n",
    "import pandas as pd\n",
    "\n",
    "\n",
    "def set_env_if_kaggle_environ():\n",
    "    if 'KAGGLE_DATA_PROXY_TOKEN' in os.environ:\n",
    "        os.environ['DATA_PATH'] = '/kaggle/input/feedback-prize-english-language-learning/'\n",
    "\n",
    "\n",
    "class ConstantPredictorSolution():\n",
    "    def __init__(self, config: Optional[dict] = None):\n",
    "        super().__init__()\n",
    "\n",
    "    def fit(self, X: pd.DataFrame, y: pd.DataFrame):\n",
    "        pass\n",
    "\n",
    "    def predict(self, X: pd.DataFrame) -> pd.DataFrame:\n",
    "        submission_df = []\n",
    "\n",
    "        for _, row in X.iterrows():\n",
    "            submission_df.append({\n",
    "                'text_id': row.text_id,\n",
    "                'cohesion': 3.0,\n",
    "                'syntax': 3.0,\n",
    "                'vocabulary': 3.0,\n",
    "                'phraseology': 3.0,\n",
    "                'grammar': 3.0,\n",
    "                'conventions': 3.0\n",
    "            })\n",
    "\n",
    "        return pd.DataFrame(submission_df)\n",
    "\n",
    "    def save(self, directory: Union[str,Path]):\n",
    "        pass\n",
    "\n",
    "    def load(self, directory: Union[str, Path]):\n",
    "        pass\n",
    "\n",
    "\n",
    "def main():\n",
    "    set_env_if_kaggle_environ()\n",
    "\n",
    "    test_df_path = Path(os.environ['DATA_PATH']) / 'test.csv'\n",
    "    if not test_df_path.is_file():\n",
    "        raise OSError(f\"File not found: {test_df_path.absolute()}\")\n",
    "\n",
    "    predictor = ConstantPredictorSolution()\n",
    "\n",
    "    test_df = pd.read_csv(test_df_path)\n",
    "    submission_df = predictor.predict(test_df)\n",
    "\n",
    "    submission_df.to_csv(\"submission.csv\", index=False)\n",
    "\n",
    "\n",
    "if __name__ == '__main__':\n",
    "    main()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3.10.6 ('essay')",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "name": "python",
   "version": "3.10.6"
  },
  "orig_nbformat": 4,
  "vscode": {
   "interpreter": {
    "hash": "d78f2c2de95f7b748174daf85b42b570c91869441d974f177c5a7efccbbdf121"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}