final

model.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 5,
    "id": "8f5480f9-fa82-4150-acff-9309fdc43690",
    "metadata": {},
    "outputs": [
@@ -13,7 +13,7 @@
        "                ('linearregression', LinearRegression())])"
       ]
      },
-     "execution_count": 1,
+     "execution_count": 5,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -28,6 +28,7 @@
     "with open('train/train.tsv', 'r', encoding='utf8') as file:\n",
     "    train_data = pd.read_csv(file, sep='\\t', names=['Begin', 'End', 'Title', 'Publisher', 'Text'])\n",
     "\n",
+    "train_data = train_data[:20000]    \n",
     "    \n",
     "X = train_data['Text']\n",
     "Y = train_data['Begin']\n",
@@ -39,7 +40,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 6,
    "id": "02e89f1c-a2d0-4d41-94a2-aa86b257069d",
    "metadata": {},
    "outputs": [],
@@ -61,7 +62,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": null,
    "id": "b85f5e22-eafb-41ee-aa2c-20c338d42701",
    "metadata": {},
    "outputs": [],

run.py

@@ -23,7 +23,7 @@ def write_pred(filename, predictions):
 
             
             
-# train_data = train_data[:10000]
+train_data = train_data[:10000]
     
 X = train_data['Text']
 Y = train_data['Begin']