task

.gitignore

@@ -0,0 +1,3 @@
+*~
+*.pyc
+*.swp

README.md

@@ -0,0 +1,21 @@
+
+Sport Texts Classification Challenge
+====================================
+
+Guess the sport discipline for a Polish article.
+
+Possible disciplines: pilka-nozna, siatkowka, sporty-walki, pilka-reczna, koszykowka, tenis, moto, zimowe. Evaluation metric is Accuracy.
+
+Directory structure
+-------------------
+
+* `README.md` — this file
+* `config.txt` — configuration file
+* `train/` — directory with training data
+* `train/train.tsv` — sample train set
+* `dev-0/` — directory with dev (test) data
+* `dev-0/in.tsv` — input data for the dev set
+* `dev-0/expected.tsv` — expected (reference) data for the dev set
+* `test-A` — directory with test data
+* `test-A/in.tsv` — input data for the test set
+* `test-A/expected.tsv` — expected (reference) data for the test set

config.txt

@@ -0,0 +1 @@
+--metric LikelihoodHashed --metric Accuracy --precision 5

run.ipynb

@@ -0,0 +1,167 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "\n",
+    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
+    "from sklearn.naive_bayes import MultinomialNB\n",
+    "from sklearn.pipeline import make_pipeline"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "c:\\Users\\User\\anaconda3\\lib\\site-packages\\IPython\\core\\interactiveshell.py:3444: FutureWarning: The error_bad_lines argument has been deprecated and will be removed in a future version.\n",
+      "\n",
+      "\n",
+      "  exec(code_obj, self.user_global_ns, self.user_ns)\n",
+      "b'Skipping line 3249: expected 2 fields, saw 3\\nSkipping line 66393: expected 2 fields, saw 3\\nSkipping line 76415: expected 2 fields, saw 3\\n'\n"
+     ]
+    }
+   ],
+   "source": [
+    "data = pd.read_csv('train/train.tsv', sep='\\t', header=None, error_bad_lines=False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X = data[1]\n",
+    "\n",
+    "with open('dev-0/in.tsv', 'r', encoding='utf8') as f:\n",
+    "    Xdev = f.readlines()\n",
+    "Xdev = pd.Series(Xdev)\n",
+    "\n",
+    "with open('test-A/in.tsv', 'r', encoding='utf8') as f:\n",
+    "    Xtest = f.readlines()\n",
+    "Xtest = pd.Series(Xtest)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y = data[0].astype('string')\n",
+    "\n",
+    "ydev = pd.read_csv('dev-0/expected.tsv', sep='\\t', header=None)\n",
+    "ydev = ydev.squeeze()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model = make_pipeline(TfidfVectorizer(), MultinomialNB())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Pipeline(steps=[('tfidfvectorizer', TfidfVectorizer()),\n",
+       "                ('multinomialnb', MultinomialNB())])"
+      ]
+     },
+     "execution_count": 35,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "model.fit(X, y)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "predictions_dev0 = model.predict(Xdev)\n",
+    "predictions_dev0 = pd.Series(predictions_dev0)\n",
+    "predictions_dev0 = predictions_dev0"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with open('dev-0/out.tsv', 'wt') as f:\n",
+    "    for pred in predictions_dev0:\n",
+    "        f.write(str(pred)+'\\n')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "predictions_testA = model.predict(Xtest)\n",
+    "predictions_testA = pd.Series(predictions_testA)\n",
+    "predictions_testA = predictions_testA"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with open('test-A/out.tsv', 'wt') as f:\n",
+    "    for pred in predictions_testA:\n",
+    "        f.write(str(pred)+'\\n')"
+   ]
+  }
+ ],
+ "metadata": {
+  "interpreter": {
+   "hash": "f08154012ddadd8e950e6e9e035c7a7b32c136e7647e9b7c77e02eb723a8bedb"
+  },
+  "kernelspec": {
+   "display_name": "Python 3.9.7 ('base')",
+   "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": "3.9.7"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

run.py

@@ -0,0 +1,53 @@
+import pandas as pd
+import numpy as np
+
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.naive_bayes import MultinomialNB
+from sklearn.pipeline import make_pipeline
+
+
+data = pd.read_csv('train/train.tsv', sep='\t', header=None, error_bad_lines=False)
+
+
+X = data[1]
+
+with open('dev-0/in.tsv', 'r', encoding='utf8') as f:
+    Xdev = f.readlines()
+Xdev = pd.Series(Xdev)
+
+with open('test-A/in.tsv', 'r', encoding='utf8') as f:
+    Xtest = f.readlines()
+Xtest = pd.Series(Xtest)
+
+
+
+y = data[0].astype('string')
+
+ydev = pd.read_csv('dev-0/expected.tsv', sep='\t', header=None)
+ydev = ydev.squeeze()
+
+
+model = make_pipeline(TfidfVectorizer(), MultinomialNB())
+
+model.fit(X, y)
+
+
+predictions_dev0 = model.predict(Xdev)
+predictions_dev0 = pd.Series(predictions_dev0)
+predictions_dev0 = predictions_dev0
+
+
+with open('dev-0/out.tsv', 'wt') as f:
+    for pred in predictions_dev0:
+        f.write(str(pred)+'\n')
+
+
+predictions_testA = model.predict(Xtest)
+predictions_testA = pd.Series(predictions_testA)
+predictions_testA = predictions_testA
+
+
+
+with open('test-A/out.tsv', 'wt') as f:
+    for pred in predictions_testA:
+        f.write(str(pred)+'\n')

sport-text-classification

@@ -1 +0,0 @@
-Subproject commit 793a89fc6fef6a5c9691a716f6e8b2737e6e8cd5