2018-07-23 09:23:17 +02:00
|
|
|
{
|
|
|
|
|
"cells": [
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
|
|
|
|
"execution_count": 1,
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
|
|
|
|
"%matplotlib inline"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2018-07-23 20:11:24 +02:00
|
|
|
"execution_count": 2,
|
2018-07-23 09:23:17 +02:00
|
|
|
"metadata": {},
|
2018-07-23 20:11:24 +02:00
|
|
|
"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"
|
|
|
|
|
]
|
|
|
|
|
}
|
|
|
|
|
],
|
2018-07-23 09:23:17 +02:00
|
|
|
"source": [
|
|
|
|
|
"import numpy as np \n",
|
|
|
|
|
"import pandas as pd \n",
|
|
|
|
|
"import simple_twitter_learning as stl\n",
|
2018-07-23 13:25:37 +02:00
|
|
|
"import re\n",
|
2018-07-23 20:11:24 +02:00
|
|
|
"import matplotlib.pyplot as plt\n",
|
|
|
|
|
"import matplotlib\n",
|
|
|
|
|
"matplotlib.rc('font', family='symbola', size=16)"
|
2018-07-23 09:23:17 +02:00
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"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"
|
|
|
|
|
]
|
|
|
|
|
},
|
2018-07-23 13:25:37 +02:00
|
|
|
{
|
|
|
|
|
"cell_type": "markdown",
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"source": [
|
|
|
|
|
"* plot function:"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2018-07-23 20:11:24 +02:00
|
|
|
"execution_count": 19,
|
2018-07-23 13:25:37 +02:00
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
|
|
|
|
"def sentiment_score(s):\n",
|
|
|
|
|
" #(pos, neg, neu)^T\n",
|
|
|
|
|
" return s[0] - s[1]\n",
|
|
|
|
|
"\n",
|
|
|
|
|
"def plot_sentiment_space(predicted_sentiment_vectors_list, top_sentiments, top_emojis, style=['bo']):\n",
|
|
|
|
|
" # sentiment score axis\n",
|
|
|
|
|
" top_X = np.array([sentiment_score(x) for x in top_sentiments])\n",
|
|
|
|
|
" \n",
|
|
|
|
|
"\n",
|
|
|
|
|
" # neutral axis:\n",
|
|
|
|
|
" top_Y = np.array([x[2] for x in top_sentiments])\n",
|
|
|
|
|
" \n",
|
|
|
|
|
"\n",
|
2018-07-23 20:11:24 +02:00
|
|
|
" fig_1, ax_1 = plt.subplots(figsize=(7.5,5))\n",
|
2018-07-23 13:25:37 +02:00
|
|
|
" plt.title(\"sentiment-score-plot\")\n",
|
|
|
|
|
" plt.xlabel(\"sentiment score\")\n",
|
|
|
|
|
" plt.ylabel(\"neutrality\")\n",
|
2018-07-23 20:11:24 +02:00
|
|
|
" plt.xlim([np.min(top_X),np.max(top_X)])\n",
|
|
|
|
|
" plt.ylim([np.min(top_Y),np.max(top_Y)])\n",
|
2018-07-23 13:25:37 +02:00
|
|
|
" for i in range(len(top_X)):\n",
|
|
|
|
|
" plt.text(top_X[i], top_Y[i], top_emojis[i])\n",
|
|
|
|
|
" for i in range(len(predicted_sentiment_vectors_list)):\n",
|
|
|
|
|
" pred_X = np.array([sentiment_score(x) for x in predicted_sentiment_vectors_list[i]])\n",
|
|
|
|
|
" pred_Y = np.array([x[2] for x in predicted_sentiment_vectors_list[i]])\n",
|
|
|
|
|
" plt.plot(pred_X, pred_Y, style[i], alpha=0.5)\n",
|
|
|
|
|
" #plt.savefig(\"val-error_sentiment-plot\" + str(datetime.datetime.now()) + \".png\", bbox_inches='tight')\n",
|
|
|
|
|
"\n",
|
|
|
|
|
" # sentiment score axis\n",
|
|
|
|
|
" top_X = np.array([x[0] for x in top_sentiments])\n",
|
|
|
|
|
" \n",
|
|
|
|
|
"\n",
|
|
|
|
|
" # neutral axis:\n",
|
|
|
|
|
" top_Y = np.array([x[1] for x in top_sentiments])\n",
|
|
|
|
|
" \n",
|
|
|
|
|
"\n",
|
2018-07-23 20:11:24 +02:00
|
|
|
" fig_2, ax_2 = plt.subplots(figsize=(7.5,5))\n",
|
2018-07-23 13:25:37 +02:00
|
|
|
" plt.title(\"positive-negative-plot\")\n",
|
|
|
|
|
" plt.xlabel(\"positive\")\n",
|
|
|
|
|
" plt.ylabel(\"negative\")\n",
|
2018-07-23 20:11:24 +02:00
|
|
|
" plt.xlim([np.min(top_X),np.max(top_X)])\n",
|
|
|
|
|
" plt.ylim([np.min(top_Y),np.max(top_Y)])\n",
|
2018-07-23 13:25:37 +02:00
|
|
|
" for i in range(len(top_X)):\n",
|
|
|
|
|
" plt.text(top_X[i], top_Y[i], top_emojis[i])\n",
|
|
|
|
|
" for i in range(len(predicted_sentiment_vectors_list)):\n",
|
|
|
|
|
" pred_X = np.array([x[0] for x in predicted_sentiment_vectors_list[i]])\n",
|
|
|
|
|
" pred_Y = np.array([x[1] for x in predicted_sentiment_vectors_list[i]])\n",
|
|
|
|
|
" plt.plot(pred_X, pred_Y, style[i], alpha=0.5)\n",
|
|
|
|
|
" #'plt.savefig(\"val-error_positive-negative-plot\" + str(datetime.datetime.now()) + \".png\", bbox_inches='tight')\n",
|
|
|
|
|
" plt.show()"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "markdown",
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"source": [
|
|
|
|
|
"* read data:"
|
|
|
|
|
]
|
|
|
|
|
},
|
2018-07-23 09:23:17 +02:00
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2018-07-23 20:11:24 +02:00
|
|
|
"execution_count": 5,
|
2018-07-23 09:23:17 +02:00
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
|
|
|
|
"df = pd.read_csv('dataset_sentiment.csv')\n",
|
|
|
|
|
"df = df[['text','sentiment']]"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2018-07-23 20:11:24 +02:00
|
|
|
"execution_count": 6,
|
2018-07-23 09:23:17 +02:00
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [
|
|
|
|
|
{
|
|
|
|
|
"data": {
|
|
|
|
|
"text/html": [
|
|
|
|
|
"<div>\n",
|
|
|
|
|
"<style scoped>\n",
|
|
|
|
|
" .dataframe tbody tr th:only-of-type {\n",
|
|
|
|
|
" vertical-align: middle;\n",
|
|
|
|
|
" }\n",
|
|
|
|
|
"\n",
|
|
|
|
|
" .dataframe tbody tr th {\n",
|
|
|
|
|
" vertical-align: top;\n",
|
|
|
|
|
" }\n",
|
|
|
|
|
"\n",
|
|
|
|
|
" .dataframe thead th {\n",
|
|
|
|
|
" text-align: right;\n",
|
|
|
|
|
" }\n",
|
|
|
|
|
"</style>\n",
|
|
|
|
|
"<table border=\"1\" class=\"dataframe\">\n",
|
|
|
|
|
" <thead>\n",
|
|
|
|
|
" <tr style=\"text-align: right;\">\n",
|
|
|
|
|
" <th></th>\n",
|
|
|
|
|
" <th>text</th>\n",
|
|
|
|
|
" <th>sentiment</th>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" </thead>\n",
|
|
|
|
|
" <tbody>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>0</th>\n",
|
|
|
|
|
" <td>nancyleegrahn how did everyone feel about th...</td>\n",
|
|
|
|
|
" <td>Neutral</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>1</th>\n",
|
|
|
|
|
" <td>scottwalker didnt catch the full gopdebate l...</td>\n",
|
|
|
|
|
" <td>Positive</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>2</th>\n",
|
|
|
|
|
" <td>tjmshow no mention of tamir rice and the gop...</td>\n",
|
|
|
|
|
" <td>Neutral</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>3</th>\n",
|
|
|
|
|
" <td>robgeorge that carly fiorina is trending ho...</td>\n",
|
|
|
|
|
" <td>Positive</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>4</th>\n",
|
|
|
|
|
" <td>danscavino gopdebate w realdonaldtrump deliv...</td>\n",
|
|
|
|
|
" <td>Positive</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" </tbody>\n",
|
|
|
|
|
"</table>\n",
|
|
|
|
|
"</div>"
|
|
|
|
|
],
|
|
|
|
|
"text/plain": [
|
|
|
|
|
" text sentiment\n",
|
|
|
|
|
"0 nancyleegrahn how did everyone feel about th... Neutral\n",
|
|
|
|
|
"1 scottwalker didnt catch the full gopdebate l... Positive\n",
|
|
|
|
|
"2 tjmshow no mention of tamir rice and the gop... Neutral\n",
|
|
|
|
|
"3 robgeorge that carly fiorina is trending ho... Positive\n",
|
|
|
|
|
"4 danscavino gopdebate w realdonaldtrump deliv... Positive"
|
|
|
|
|
]
|
|
|
|
|
},
|
2018-07-23 20:11:24 +02:00
|
|
|
"execution_count": 6,
|
2018-07-23 09:23:17 +02:00
|
|
|
"metadata": {},
|
|
|
|
|
"output_type": "execute_result"
|
|
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"source": [
|
|
|
|
|
"df['text'] = df['text'].apply(lambda x: x.lower())\n",
|
|
|
|
|
"df['text'] = df['text'].apply(lambda x: x.replace('rt',' '))\n",
|
|
|
|
|
"df['text'] = df['text'].apply((lambda x: re.sub('[^a-zA-Z0-9\\s]','',x)))\n",
|
|
|
|
|
"df.head()"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2018-07-23 20:11:24 +02:00
|
|
|
"execution_count": 7,
|
2018-07-23 09:23:17 +02:00
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
|
|
|
|
"neg = np.array([df['sentiment'][i] == 'Negative' for i in range(df.shape[0])])\n",
|
|
|
|
|
"pos = np.array([df['sentiment'][i] == 'Positive' for i in range(df.shape[0])])\n",
|
|
|
|
|
"neu = np.array([df['sentiment'][i] == 'Neutral' for i in range(df.shape[0])])\n",
|
|
|
|
|
"\n",
|
|
|
|
|
"text = np.array(df['text'].tolist())"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "markdown",
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"source": [
|
|
|
|
|
"* load pipeline"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2018-07-23 20:11:24 +02:00
|
|
|
"execution_count": 8,
|
2018-07-23 09:23:17 +02:00
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
|
|
|
|
"pipeline_file = \"/home/jonas/Dokumente/NLP_DATA/python_dumps/pipelines/tfidf_final/final_epoch01.pipeline\"\n",
|
|
|
|
|
"pm = stl.pipeline_manager.load_from_pipeline_file(pipeline_file)"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "markdown",
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"source": [
|
|
|
|
|
"* plot statements"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2018-07-23 20:11:24 +02:00
|
|
|
"execution_count": 9,
|
2018-07-23 09:23:17 +02:00
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
|
|
|
|
"top_20 = list(\"😳😋😀😌😏😔😒😎😢😅😁😉🙌🙏😘😊😩😍😭😂\")\n",
|
|
|
|
|
"top_20_sents = stl.emoji2sent(top_20)\n",
|
|
|
|
|
"\n",
|
|
|
|
|
"pred_pos = pm.predict(text[pos])\n",
|
|
|
|
|
"pred_neg = pm.predict(text[neg])\n",
|
|
|
|
|
"pred_neu = pm.predict(text[neu])"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2018-07-23 20:11:24 +02:00
|
|
|
"execution_count": 10,
|
2018-07-23 09:23:17 +02:00
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [
|
|
|
|
|
{
|
|
|
|
|
"data": {
|
2018-07-23 20:11:24 +02:00
|
|
|
"image/png": "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
|
2018-07-23 09:23:17 +02:00
|
|
|
"text/plain": [
|
2018-07-23 13:25:37 +02:00
|
|
|
"<Figure size 1080x720 with 1 Axes>"
|
2018-07-23 09:23:17 +02:00
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"output_type": "display_data"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"data": {
|
2018-07-23 20:11:24 +02:00
|
|
|
"image/png": "iVBORw0KGgoAAAANSUhEUgAAA4wAAAJrCAYAAACr/B0sAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDIuMi4yLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvhp/UCwAAIABJREFUeJzs3X2clXWd//HXh1tvUEgEERUnb1ZRzFFwBSU54X2pya6lv2VbcWstd5FwtQVFc0zwpjRp1XTNNcCVtDspNSm1TlpJhYpmqGU4iSIqIN5zM8z398d1ZjxO1wAjM3Nm4PV8PM7jzPW9rnOdzznwUN7zvYuUEpIkSZIkNdWl0gVIkiRJkjomA6MkSZIkKZeBUZIkSZKUy8AoSZIkScplYJQkSZIk5TIwSpIkSZJyGRglSVK7iYjzIuKnETE/IgZWuh5J0voZGCVJbSIihkTEsoj4cs658RFRldN+Uek1B7RHjZ1R6Xsdl9N+VES8nneug/k6cCMwFOjxQW8SEVe1WkWSpGYZGCVJbaUX0AcYkHNuz2ZeM6D0mu3aqqjNQHPf3YeA7YH+7VhLi6WU6oHHNuUeEdEH2KF1KpIkrY+BUZLUJlJK88gC4Pjy9ojoDvxDMy87GxiQUvpNG5fXmZ2a15hS+h6wU0rpq+1cTyV8Gv8NI0ntwv/YSpLaTEppWalHCYCI2BG4CRjUzPX1KaVlLXmPiOgSEZv9/88iYquIGA+c1tw1KaVXWnjPiIium1xcO4mIrhFxJHBZpWuRpC1Ft0oXIElqHxHxGWACsFfpeRegO9APqAJqUkqPNrl+KPAysC2wFTAtpfRa6fyHgHNK598tXVMAvgr8BfgW0Bf4ZUrpotJtpwI7l36+KiLeKv38eeBE4F9LrxmfUvp9RHwUuAA4DlgOXJVSuqL0/rcAZwBPA/8B/LzU/nngQOAlYDfgWeDrKaW6DXw/k4B/IQuzHwGOIptjt3PpO/uPlNLyJq9Z73tFRL/SZ14C1JU+25+B3sA/AienlF6MiFHA35P9f7kv2bDSC1JKL5S93ReAaiCAz0VEodR+DbAGuKL02ttSSjdERH9gOllvbjfg+yml00p1nQl8A3gLuBT471L7qNJ38DzZn2dv4PyU0ooNfHfHARcCg4HLgXVkQ5K3B4aQ/bk9sL57lO6zL1mP9MtAKn2n3y71VgMcTRaY64CRETGj1H5vSumODd1fkvQBpJR8+PDhw8cW8iALAAl4ANiurP0E4G1geOl4KvCtJq89Gvgj0Kd0fAdQaHLNTGBk6eetgYeBGU2uKZRqqGrSHmSBKOXc90HgZzmfpwj0KDu+DLi57LgLMBf46kZ+Px8tvf80suGdDe0/AK5tcu163wvoCiwAvlx2TQ3w09Jn/Q9gR7Lg/grwj2XX/TOwCNg2p8YEjMtp7wP8lSz4l7d/BXgD2KpJ+x3A7mXHnwAeBbYua5tS+jPsshHfXTfgVeBxYOey9oOBd4AxZW1VTf8OkP1yYiHQv6xtu9J3eELOn/uMDdXkw4cPHz42/bHZD+GRJL0npfR66cdbU0pvlrXfDfwB+N+IOJwsKExr8tr7gJXA10pN+5Ue5eYAa0vXvws804LaUkppQTOnbwSOjIjdGhoiYgRwY0ppTen4I8Bk4H/K7lkPfBsYv5HDVheXnt9MKb1c1v4UMLLsvTfmvarJeh9/W3af3wHHAH+XUro+ZcNvu5IFyF3KrvsB8GFg9EbU3PD+K4Hnck59C9iGrEezof6tgedSSn8tHfcsXfed0p9bg5uB4cChG/H+dWS/dLgzpfRSWfujwI+BmyJim7zXlr6v/wO+m8qG1Zb+jl4PzIiI7TdUgySp9TkkVZLU4F6yHrBLgXdTSrU51zwJjI2Is4DZwPUR8c9kPYD3Az9OKa1rg9p+QDZs8gyyHjOAk4HyLTtOIQte4yOiPPQ09FJtGxEfIxviWu6vKaWmC8k83uS4jmwV0o1+L7JePch6Whs0bCOxuqEhpfQ80C8i9ouI/wJ6Ag3zOMvf8wNJKS2OiLnAZ4Hbyur/Xtllh5MNvT0mIpquwjof6BoRg4Dbef/6B+vIeg43NHfyXrLFekYDd+ecHw7sSxbMm3qSbKjtJ4DvbOB9JEmtzMAoSWrQ0KNWIOtJzNMwV7Ef2Zy5JWRz3sYDk4DHIuKotIE5by2VUlodETOBf42IqWQ9ZqtTSqvLLmvYvuOc9bz/j0uPDXl3A+c35r3eLM2zPBWYExEB/BNZ725tw0Wl3rXpwMeAs1JKvyq1f5PWW5zuf4AfRcReKaVngYNTSrfmfJ4bUko/XM99DvuA79/wd2tgM+erSs953/u7Ta6RJLUjh6RKkhrsVHr+AVlvXORc05tsyOlrZPPKZqaUjiTrCft46fxFOa9rVkTsFhG5W0U0cROwO9mQztPIervKNSwQs0uTdiKitX9BurHv9RTw44i4hKzn9ifAuCYvGQ/8G3BcQ1hscr/eEdG7uUIi4ryNqPcnwItki+Xszd8OFW7285TeY1O/v4a/Wy80c74hUPbKOdfw2ZvtxdzI70CS9AEYGCVpy9Q9p+1EsqGYM8mGTjadnwjZAiY/TimtAi5q2JIhpbQ2pXQvWS/jhzfw3m83qWGjhl2mlJ4hG/r6eWBwSmlhk0tuJxsi+bGcl09ZX+j6ADb2vYaklL6TUro4pXRhSmlGKttmpORY4ImU0osNDeVzNcm+8+qy43d4/5/fBr+/0jDhhlVlT+dvh3b+hmz+4998nog4mmzBo43V3N+tpcAvmnnNr8h6qw/KOdewaE75UNa3aeF3IEn6YAyMkrRl+seIaJhPR0R8GtgTOL20AM7NwFfKF4qJiJPI/mE+sdTUn6x3rNzewM/KjruRLepS7imyIa8NgXQY2by/8p6s5vYGvAk4CXii6YmU0p+A84DJEdE49DEiDgDWli34sz4N79809HSj7P+ZLXivnSLiCxGxf0T8XUTsGhFN7/00sEdElPeujSPbfqMX2Uqq5b1rD1P67krzDf/apM7mvrubS/ca0PS7KC1Y8xngqNI+hw2fZzuybTl+2sw983w8IvqU3WME2bYop5ctqNOw+E2X0vuvJhvaPDYiPlz22g8BZ5FtaVK+CFH5d9AF/z0jSW0mUkqVrkGS1I4iIpGFnS5ki6/sTLbf3SUppT+Xrgmyff+GkwWSXmSLsVyaUlpauubHZAvf7Ea2D+D2ZIvlXFVaIOVCsvl7AXwX+GJK6e3Sa48HziXrWXo1pXR9RHyKrPfrE2SB8H9SSt9sUntPslVHD0spvdPM5xtDtp/jH0uf702yvRGb9uw1fd2ZZENdP1Z67e1kexV+lSykDiQb2nl1Sqlhz8f1vldEfJJs5dhya8gC2BdSSksiYiuyxXsGk/X09SRbQGgAcAlwe0rp8rI69wK+SbYFxmqyfQ/3Bb4IjAVWkK02OiHnM36PbE/E3zY9Vzr/EbIhxS+V7tMD+Foq7b25IRFRS7Zdx0tkPbA7lj7XV1NK80vX/BvZ362DgV8Cd6SUbiidO5jsFxIvkQ193h2YmVK6v8n7bAvcUPr8r5Btb5K3QqwkaRMZGCVpC1MKjGeklGZUupbNWUScBhxPFpRXlnrCegMHkM1nrE8p5Q1p7bRKgXFGSqmmwqVIklpJu6+SWvpt7CCyYUv7ppSO2sD1/1n68Q2y/8le1mRYiiRJHdH5wNjS/ogN+zS+BjwYEROBX1eyOEmSNka7j/lPKd2ZUvoG2R5T6w2sEfF5YI+U0tdTSjeTberbsDS5JKmFNmKOoFrPPcAZ5fNAoXHO3Vjevw/i5mJ9cyglSZ1QR9+HcTLw7w0HKaXflyb4jwQeqlhVktQJlUZ4nF46PD8i9kkp/Vcla9qcpZQuiIh/AL4WEcvJ5i5uRTZn9HfAret7fWcSEaOAz5Fty/G5iOgHTEgpralsZZKkTVWxOYwRUQMUUkqFZs4PJNsz6sCU0hNl7Y+RTZC/oj3qlCRJkqQtVUdehnrX0nPTVfDeLjsnSZIkSWojHXlI6lbrObd1XmNpSfQzAbbddtuh++67b1vUJUmSJEkd3iOPPLI
|
2018-07-23 09:23:17 +02:00
|
|
|
"text/plain": [
|
2018-07-23 13:25:37 +02:00
|
|
|
"<Figure size 1080x720 with 1 Axes>"
|
2018-07-23 09:23:17 +02:00
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"output_type": "display_data"
|
2018-07-23 13:25:37 +02:00
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"source": [
|
|
|
|
|
"#stl.plot_sentiment_space(predicted_sentiment_vectors=pred_pos, top_sentiments=top_20_sents, top_emojis=top_20, style='go')\n",
|
|
|
|
|
"#stl.plot_sentiment_space(predicted_sentiment_vectors=pred_neg, top_sentiments=top_20_sents, top_emojis=top_20, style='ro')\n",
|
|
|
|
|
"#stl.plot_sentiment_space(predicted_sentiment_vectors=pred_neu, top_sentiments=top_20_sents, top_emojis=top_20, style='bo')\n",
|
|
|
|
|
"plot_sentiment_space(predicted_sentiment_vectors_list=[pred_pos,pred_neg,pred_neu], top_sentiments=top_20_sents, top_emojis=top_20, style=['g+','b+','r+'])"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "markdown",
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"source": [
|
|
|
|
|
"## user labeled sentiment dataset"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2018-07-23 20:11:24 +02:00
|
|
|
"execution_count": 11,
|
2018-07-23 13:25:37 +02:00
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
|
|
|
|
"df = pd.read_csv('../sentiment_sentences.csv', delimiter=';')"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2018-07-23 20:11:24 +02:00
|
|
|
"execution_count": 12,
|
2018-07-23 13:25:37 +02:00
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
|
|
|
|
"neg = np.array([df['sent'][i] == 'n' for i in range(df.shape[0])])\n",
|
|
|
|
|
"pos = np.array([df['sent'][i] == 'p' for i in range(df.shape[0])])\n",
|
|
|
|
|
"\n",
|
|
|
|
|
"text = np.array(df['text'].tolist())\n",
|
|
|
|
|
"\n",
|
|
|
|
|
"pred_pos = pm.predict(text[pos])\n",
|
|
|
|
|
"pred_neg = pm.predict(text[neg])"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2018-07-23 20:11:24 +02:00
|
|
|
"execution_count": 20,
|
2018-07-23 13:25:37 +02:00
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [
|
2018-07-23 09:23:17 +02:00
|
|
|
{
|
|
|
|
|
"data": {
|
2018-07-23 20:11:24 +02:00
|
|
|
"image/png": "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
|
2018-07-23 09:23:17 +02:00
|
|
|
"text/plain": [
|
2018-07-23 20:11:24 +02:00
|
|
|
"<Figure size 540x360 with 1 Axes>"
|
2018-07-23 09:23:17 +02:00
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"output_type": "display_data"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"data": {
|
2018-07-23 20:11:24 +02:00
|
|
|
"image/png": "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
|
2018-07-23 09:23:17 +02:00
|
|
|
"text/plain": [
|
2018-07-23 20:11:24 +02:00
|
|
|
"<Figure size 540x360 with 1 Axes>"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"output_type": "display_data"
|
|
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"source": [
|
|
|
|
|
"plot_sentiment_space(predicted_sentiment_vectors_list=[pred_pos,pred_neg], top_sentiments=top_20_sents, top_emojis=top_20, style=['go','ro'])"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
|
|
|
|
"execution_count": 22,
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [
|
|
|
|
|
{
|
|
|
|
|
"data": {
|
|
|
|
|
"text/html": [
|
|
|
|
|
"<div>\n",
|
|
|
|
|
"<style scoped>\n",
|
|
|
|
|
" .dataframe tbody tr th:only-of-type {\n",
|
|
|
|
|
" vertical-align: middle;\n",
|
|
|
|
|
" }\n",
|
|
|
|
|
"\n",
|
|
|
|
|
" .dataframe tbody tr th {\n",
|
|
|
|
|
" vertical-align: top;\n",
|
|
|
|
|
" }\n",
|
|
|
|
|
"\n",
|
|
|
|
|
" .dataframe thead th {\n",
|
|
|
|
|
" text-align: right;\n",
|
|
|
|
|
" }\n",
|
|
|
|
|
"</style>\n",
|
|
|
|
|
"<table border=\"1\" class=\"dataframe\">\n",
|
|
|
|
|
" <thead>\n",
|
|
|
|
|
" <tr style=\"text-align: right;\">\n",
|
|
|
|
|
" <th></th>\n",
|
|
|
|
|
" <th>text</th>\n",
|
|
|
|
|
" <th>sent</th>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" </thead>\n",
|
|
|
|
|
" <tbody>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>0</th>\n",
|
|
|
|
|
" <td>I am so happy</td>\n",
|
|
|
|
|
" <td>p</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>1</th>\n",
|
|
|
|
|
" <td>i love my life</td>\n",
|
|
|
|
|
" <td>p</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>2</th>\n",
|
|
|
|
|
" <td>i really like this sunshine</td>\n",
|
|
|
|
|
" <td>p</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>3</th>\n",
|
|
|
|
|
" <td>while doing sport i feel free</td>\n",
|
|
|
|
|
" <td>p</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>4</th>\n",
|
|
|
|
|
" <td>i is terrible to learn when the weather is thi...</td>\n",
|
|
|
|
|
" <td>n</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>5</th>\n",
|
|
|
|
|
" <td>i am almost crying when i run out of ice cream</td>\n",
|
|
|
|
|
" <td>n</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>6</th>\n",
|
|
|
|
|
" <td>fuck off</td>\n",
|
|
|
|
|
" <td>n</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>7</th>\n",
|
|
|
|
|
" <td>you are my best friend ever</td>\n",
|
|
|
|
|
" <td>p</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>8</th>\n",
|
|
|
|
|
" <td>i love my mommy</td>\n",
|
|
|
|
|
" <td>p</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>9</th>\n",
|
|
|
|
|
" <td>i prefer oral exams</td>\n",
|
|
|
|
|
" <td>p</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>10</th>\n",
|
|
|
|
|
" <td>best cocktail is the mojito especial</td>\n",
|
|
|
|
|
" <td>p</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>11</th>\n",
|
|
|
|
|
" <td>you got a beautiful wedding</td>\n",
|
|
|
|
|
" <td>p</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>12</th>\n",
|
|
|
|
|
" <td>you husband is this handsome</td>\n",
|
|
|
|
|
" <td>p</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>13</th>\n",
|
|
|
|
|
" <td>this is such a sneaky bitch</td>\n",
|
|
|
|
|
" <td>n</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>14</th>\n",
|
|
|
|
|
" <td>you're kidding</td>\n",
|
|
|
|
|
" <td>n</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>15</th>\n",
|
|
|
|
|
" <td>you are really too drunk</td>\n",
|
|
|
|
|
" <td>n</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>16</th>\n",
|
|
|
|
|
" <td>you start being annoying</td>\n",
|
|
|
|
|
" <td>n</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>17</th>\n",
|
|
|
|
|
" <td>i love my mac</td>\n",
|
|
|
|
|
" <td>p</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>18</th>\n",
|
|
|
|
|
" <td>but it would be better if they are less expensive</td>\n",
|
|
|
|
|
" <td>n</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>19</th>\n",
|
|
|
|
|
" <td>you are a bad friend</td>\n",
|
|
|
|
|
" <td>n</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>20</th>\n",
|
|
|
|
|
" <td>I am in love with my new laptop</td>\n",
|
|
|
|
|
" <td>p</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>21</th>\n",
|
|
|
|
|
" <td>You piss me off</td>\n",
|
|
|
|
|
" <td>n</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>22</th>\n",
|
|
|
|
|
" <td>I hate school</td>\n",
|
|
|
|
|
" <td>n</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>23</th>\n",
|
|
|
|
|
" <td>I'm so mad at you</td>\n",
|
|
|
|
|
" <td>n</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>24</th>\n",
|
|
|
|
|
" <td>Seeing you cry, makes me sad</td>\n",
|
|
|
|
|
" <td>n</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>25</th>\n",
|
|
|
|
|
" <td>You are so lovely</td>\n",
|
|
|
|
|
" <td>p</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>26</th>\n",
|
|
|
|
|
" <td>Fish is disgusting</td>\n",
|
|
|
|
|
" <td>n</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>27</th>\n",
|
|
|
|
|
" <td>At times I feel so depressed</td>\n",
|
|
|
|
|
" <td>n</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>28</th>\n",
|
|
|
|
|
" <td>Summer makes me happy</td>\n",
|
|
|
|
|
" <td>p</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>29</th>\n",
|
|
|
|
|
" <td>I want to dance and sing aloud</td>\n",
|
|
|
|
|
" <td>p</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>30</th>\n",
|
|
|
|
|
" <td>Everything will be ok</td>\n",
|
|
|
|
|
" <td>p</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>31</th>\n",
|
|
|
|
|
" <td>why are you upset?</td>\n",
|
|
|
|
|
" <td>n</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>32</th>\n",
|
|
|
|
|
" <td>I dont like it when it rains</td>\n",
|
|
|
|
|
" <td>n</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>33</th>\n",
|
|
|
|
|
" <td>I dont care at all</td>\n",
|
|
|
|
|
" <td>n</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>34</th>\n",
|
|
|
|
|
" <td>you are such a bitch</td>\n",
|
|
|
|
|
" <td>n</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>35</th>\n",
|
|
|
|
|
" <td>I dont understand what this is all about</td>\n",
|
|
|
|
|
" <td>n</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>36</th>\n",
|
|
|
|
|
" <td>give me a break, idiot!</td>\n",
|
|
|
|
|
" <td>n</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>37</th>\n",
|
|
|
|
|
" <td>please dont leave me</td>\n",
|
|
|
|
|
" <td>n</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>38</th>\n",
|
|
|
|
|
" <td>I love cuddling with my dog</td>\n",
|
|
|
|
|
" <td>p</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>39</th>\n",
|
|
|
|
|
" <td>I want to die</td>\n",
|
|
|
|
|
" <td>n</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>40</th>\n",
|
|
|
|
|
" <td>that is really sad!</td>\n",
|
|
|
|
|
" <td>n</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>41</th>\n",
|
|
|
|
|
" <td>why are you saying that, you moron!</td>\n",
|
|
|
|
|
" <td>n</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>42</th>\n",
|
|
|
|
|
" <td>OMG! i love that cat soo much!</td>\n",
|
|
|
|
|
" <td>p</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>43</th>\n",
|
|
|
|
|
" <td>can you feel the love tonight</td>\n",
|
|
|
|
|
" <td>p</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>44</th>\n",
|
|
|
|
|
" <td>i get so emotional when i watch lion king</td>\n",
|
|
|
|
|
" <td>p</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>45</th>\n",
|
|
|
|
|
" <td>i really hate you</td>\n",
|
|
|
|
|
" <td>n</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>46</th>\n",
|
|
|
|
|
" <td>that is disgusting</td>\n",
|
|
|
|
|
" <td>n</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>47</th>\n",
|
|
|
|
|
" <td>my heart is broken</td>\n",
|
|
|
|
|
" <td>n</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>48</th>\n",
|
|
|
|
|
" <td>i love these sunny days</td>\n",
|
|
|
|
|
" <td>p</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>49</th>\n",
|
|
|
|
|
" <td>this gave me positive feelings</td>\n",
|
|
|
|
|
" <td>p</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>50</th>\n",
|
|
|
|
|
" <td>i am sick</td>\n",
|
|
|
|
|
" <td>n</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>51</th>\n",
|
|
|
|
|
" <td>i am tired</td>\n",
|
|
|
|
|
" <td>n</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>52</th>\n",
|
|
|
|
|
" <td>are you sick or tired?</td>\n",
|
|
|
|
|
" <td>n</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>53</th>\n",
|
|
|
|
|
" <td>you are so cute and sweet</td>\n",
|
|
|
|
|
" <td>p</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>54</th>\n",
|
|
|
|
|
" <td>i just lost my mind</td>\n",
|
|
|
|
|
" <td>n</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>55</th>\n",
|
|
|
|
|
" <td>i hate all people</td>\n",
|
|
|
|
|
" <td>n</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>56</th>\n",
|
|
|
|
|
" <td>you are just dumb</td>\n",
|
|
|
|
|
" <td>n</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>57</th>\n",
|
|
|
|
|
" <td>i will get lucky</td>\n",
|
|
|
|
|
" <td>p</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>58</th>\n",
|
|
|
|
|
" <td>i like ice cream</td>\n",
|
|
|
|
|
" <td>p</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>59</th>\n",
|
|
|
|
|
" <td>go home you idiot</td>\n",
|
|
|
|
|
" <td>n</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" </tbody>\n",
|
|
|
|
|
"</table>\n",
|
|
|
|
|
"</div>"
|
|
|
|
|
],
|
|
|
|
|
"text/plain": [
|
|
|
|
|
" text sent\n",
|
|
|
|
|
"0 I am so happy p\n",
|
|
|
|
|
"1 i love my life p\n",
|
|
|
|
|
"2 i really like this sunshine p\n",
|
|
|
|
|
"3 while doing sport i feel free p\n",
|
|
|
|
|
"4 i is terrible to learn when the weather is thi... n\n",
|
|
|
|
|
"5 i am almost crying when i run out of ice cream n\n",
|
|
|
|
|
"6 fuck off n\n",
|
|
|
|
|
"7 you are my best friend ever p\n",
|
|
|
|
|
"8 i love my mommy p\n",
|
|
|
|
|
"9 i prefer oral exams p\n",
|
|
|
|
|
"10 best cocktail is the mojito especial p\n",
|
|
|
|
|
"11 you got a beautiful wedding p\n",
|
|
|
|
|
"12 you husband is this handsome p\n",
|
|
|
|
|
"13 this is such a sneaky bitch n\n",
|
|
|
|
|
"14 you're kidding n\n",
|
|
|
|
|
"15 you are really too drunk n\n",
|
|
|
|
|
"16 you start being annoying n\n",
|
|
|
|
|
"17 i love my mac p\n",
|
|
|
|
|
"18 but it would be better if they are less expensive n\n",
|
|
|
|
|
"19 you are a bad friend n\n",
|
|
|
|
|
"20 I am in love with my new laptop p\n",
|
|
|
|
|
"21 You piss me off n\n",
|
|
|
|
|
"22 I hate school n\n",
|
|
|
|
|
"23 I'm so mad at you n\n",
|
|
|
|
|
"24 Seeing you cry, makes me sad n\n",
|
|
|
|
|
"25 You are so lovely p\n",
|
|
|
|
|
"26 Fish is disgusting n\n",
|
|
|
|
|
"27 At times I feel so depressed n\n",
|
|
|
|
|
"28 Summer makes me happy p\n",
|
|
|
|
|
"29 I want to dance and sing aloud p\n",
|
|
|
|
|
"30 Everything will be ok p\n",
|
|
|
|
|
"31 why are you upset? n\n",
|
|
|
|
|
"32 I dont like it when it rains n\n",
|
|
|
|
|
"33 I dont care at all n\n",
|
|
|
|
|
"34 you are such a bitch n\n",
|
|
|
|
|
"35 I dont understand what this is all about n\n",
|
|
|
|
|
"36 give me a break, idiot! n\n",
|
|
|
|
|
"37 please dont leave me n\n",
|
|
|
|
|
"38 I love cuddling with my dog p\n",
|
|
|
|
|
"39 I want to die n\n",
|
|
|
|
|
"40 that is really sad! n\n",
|
|
|
|
|
"41 why are you saying that, you moron! n\n",
|
|
|
|
|
"42 OMG! i love that cat soo much! p\n",
|
|
|
|
|
"43 can you feel the love tonight p\n",
|
|
|
|
|
"44 i get so emotional when i watch lion king p\n",
|
|
|
|
|
"45 i really hate you n\n",
|
|
|
|
|
"46 that is disgusting n\n",
|
|
|
|
|
"47 my heart is broken n\n",
|
|
|
|
|
"48 i love these sunny days p\n",
|
|
|
|
|
"49 this gave me positive feelings p\n",
|
|
|
|
|
"50 i am sick n\n",
|
|
|
|
|
"51 i am tired n\n",
|
|
|
|
|
"52 are you sick or tired? n\n",
|
|
|
|
|
"53 you are so cute and sweet p\n",
|
|
|
|
|
"54 i just lost my mind n\n",
|
|
|
|
|
"55 i hate all people n\n",
|
|
|
|
|
"56 you are just dumb n\n",
|
|
|
|
|
"57 i will get lucky p\n",
|
|
|
|
|
"58 i like ice cream p\n",
|
|
|
|
|
"59 go home you idiot n"
|
2018-07-23 09:23:17 +02:00
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"output_type": "display_data"
|
|
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"source": [
|
2018-07-23 20:11:24 +02:00
|
|
|
"display(df)"
|
2018-07-23 09:23:17 +02:00
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"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": "3.6.5"
|
|
|
|
|
}
|
|
|
|
|
},
|
|
|
|
|
"nbformat": 4,
|
|
|
|
|
"nbformat_minor": 2
|
|
|
|
|
}
|
