fix

.ipynb_checkpoints/svm-checkpoint.ipynb

@@ -1,6 +1,188 @@
 {
- "cells": [],
+ "cells": [
- "metadata": {},
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "fc8ba0a3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "from nltk.tokenize import word_tokenize\n",
+    "from nltk import pos_tag\n",
+    "from nltk.corpus import stopwords\n",
+    "from nltk.stem import WordNetLemmatizer\n",
+    "from sklearn.preprocessing import LabelEncoder\n",
+    "from collections import defaultdict\n",
+    "from nltk.corpus import wordnet as wn\n",
+    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
+    "from sklearn import model_selection, naive_bayes, svm\n",
+    "from sklearn.metrics import accuracy_score\n",
+    "from sklearn.pipeline import make_pipeline"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "b082c37a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with open(\"train/in.tsv\", encoding='utf-8') as f:\n",
+    "    x_train = f.readlines()\n",
+    "\n",
+    "\n",
+    "with open(\"train/expected.tsv\", encoding='utf-8') as f:\n",
+    "    y_train = f.readlines()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "2ccc7d71",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "289579"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(x_train)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "f6bd3ba5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "np.random.seed(500)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "eefd7b1b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with open(\"svm/in.tsv\", encoding='utf-8') as f:\n",
+    "    x_dev = f.readlines()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "d50a164b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "289579"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "\n",
+    "len(y_train)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "6696a4d0",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([2, 0, 0, ..., 0, 0, 1], dtype=int64)"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "y_train = LabelEncoder().fit_transform(y_train)\n",
+    "y_train"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "5488f657",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "pipeline = make_pipeline(TfidfVectorizer(),svm.SVC())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "ddbb1608",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model = pipeline.fit(x_train, y_train)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "b286bec3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prediction = model.predict(x_dev)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "0b1fac69",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "np.savetxt(\"svm/outfull.tsv\", prediction, fmt='%d')"
+   ]
+  }
+ ],
+ "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": "3.8.8"
+  }
+ },
  "nbformat": 4,
  "nbformat_minor": 5
 }

svm.ipynb

@@ -79,26 +79,6 @@
     "    x_dev = f.readlines()\n"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "269c7b94",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "x_train = x_train[:100000]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "f3f6e9f0",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "y_train = y_train[:100000]"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": 8,