{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "%matplotlib inline" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "Using TensorFlow backend.\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[nltk_data] Downloading package punkt to /home/jonas/nltk_data...\n", "[nltk_data] Package punkt is already up-to-date!\n", "[nltk_data] Downloading package averaged_perceptron_tagger to\n", "[nltk_data] /home/jonas/nltk_data...\n", "[nltk_data] Package averaged_perceptron_tagger is already up-to-\n", "[nltk_data] date!\n", "[nltk_data] Downloading package wordnet to /home/jonas/nltk_data...\n", "[nltk_data] Package wordnet is already up-to-date!\n" ] } ], "source": [ "import numpy as np \n", "import pandas as pd \n", "import simple_twitter_learning as stl\n", "import re" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "* download data" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "dataset already downloaded\n" ] } ], "source": [ "%%bash\n", "\n", "if [ ! -e 'dataset_sentiment.csv' ]\n", "then\n", " echo \"downloading dataset\"\n", " wget https://raw.githubusercontent.com/SmartDataAnalytics/MA-INF-4222-NLP-Lab/master/2018_SoSe/exercises/dataset_sentiment.csv\n", "else\n", " echo \"dataset already downloaded\"\n", "fi" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [], "source": [ "df = pd.read_csv('dataset_sentiment.csv')\n", "df = df[['text','sentiment']]" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", " | text | \n", "sentiment | \n", "
---|---|---|
0 | \n", "nancyleegrahn how did everyone feel about th... | \n", "Neutral | \n", "
1 | \n", "scottwalker didnt catch the full gopdebate l... | \n", "Positive | \n", "
2 | \n", "tjmshow no mention of tamir rice and the gop... | \n", "Neutral | \n", "
3 | \n", "robgeorge that carly fiorina is trending ho... | \n", "Positive | \n", "
4 | \n", "danscavino gopdebate w realdonaldtrump deliv... | \n", "Positive | \n", "