From 2c5b3c6c96e8fdae99c5e87dff962c548d7d4c87 Mon Sep 17 00:00:00 2001
From: s440058 <pioula@st.amu.edu.pl>
Date: Sun, 20 Jun 2021 20:05:17 +0200
Subject: [PATCH] add bayes

---
 Untitled.ipynb | 82 --------------------------------------------------
 1 file changed, 82 deletions(-)
 delete mode 100644 Untitled.ipynb

diff --git a/Untitled.ipynb b/Untitled.ipynb
deleted file mode 100644
index 92522ca..0000000
--- a/Untitled.ipynb
+++ /dev/null
@@ -1,82 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "b'Skipping line 25706: expected 2 fields, saw 3\\nSkipping line 58881: expected 2 fields, saw 3\\nSkipping line 73761: expected 2 fields, saw 3\\n'\n",
-      "b'Skipping line 1983: expected 1 fields, saw 2\\nSkipping line 5199: expected 1 fields, saw 2\\n'\n"
-     ]
-    }
-   ],
-   "source": [
-    "from sklearn.naive_bayes import GaussianNB\n",
-    "import pandas as pd\n",
-    "from sklearn.naive_bayes import MultinomialNB\n",
-    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
-    "\n",
-    "r_in = './train/train.tsv'\n",
-    "\n",
-    "r_ind_ev = './dev-0/in.tsv'\n",
-    "tsv_read = pd.read_table(r_in, error_bad_lines=False, sep='\\t', header=None)\n",
-    "tsv_read_dev = pd.read_table(r_ind_ev, error_bad_lines=False, sep='\\t', header=None)\n",
-    "\n",
-    "y_train = tsv_read[0].values\n",
-    "X_train = tsv_read[1].values\n",
-    "X_dev = tsv_read_dev[0].values\n",
-    "\n",
-    "vectorizer = TfidfVectorizer()\n",
-    "counts = vectorizer.fit_transform(X_train)\n",
-    "\n",
-    "\n",
-    "classifier = MultinomialNB()\n",
-    "classifier.fit(counts, y_train)\n",
-    "\n",
-    "counts2 = vectorizer.transform(X_dev)\n",
-    "predictions = classifier.predict(counts2)\n",
-    "\n",
-    "predictions.tofile(\"./dev-0/out.tsv\", sep='\\n')\n",
-    "\n",
-    "tsv_read_test_in =  pd.read_table('./test-A/in.tsv', error_bad_lines=False, header= None)\n",
-    "X_test= tsv_read_test_in[0].values\n",
-    "\n",
-    "counts3 = vectorizer.transform(X_test)\n",
-    "predictions_test_A = classifier.predict(counts3)\n",
-    "predictions_test_A.tofile('./test-A/out.tsv', sep='\\n')"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3",
-   "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": "3.8.5"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 4
-}