diff --git a/model.ipynb b/model.ipynb index aa589c3..fd16d88 100644 --- a/model.ipynb +++ b/model.ipynb @@ -2,17 +2,10 @@ "cells": [ { "cell_type": "code", - "execution_count": 99, + "execution_count": 1, "id": "8f5480f9-fa82-4150-acff-9309fdc43690", "metadata": {}, "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "107463\n" - ] - }, { "data": { "text/plain": [ @@ -20,7 +13,7 @@ " ('linearregression', LinearRegression())])" ] }, - "execution_count": 99, + "execution_count": 1, "metadata": {}, "output_type": "execute_result" } @@ -35,8 +28,6 @@ "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", - "print(len(train_data)) \n", - "train_data = train_data[:10000]\n", " \n", "X = train_data['Text']\n", "Y = train_data['Begin']\n", diff --git a/run.py b/run.py index a026c8e..bd2d259 100644 --- a/run.py +++ b/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']