From a78b43545a45eda5bbf421c8c4f15376cc4ec78b Mon Sep 17 00:00:00 2001
From: Miriam Amin <miriam_amin@web.de>
Date: Wed, 25 Nov 2020 14:54:18 +0100
Subject: [PATCH] set up preprocessing notebook with first preprocessing tasks.
for #1
---
notebooks/1_Preprocessing.ipynb | 696 ++++++++++++++++++++++++++++++++
1 file changed, 696 insertions(+)
create mode 100644 notebooks/1_Preprocessing.ipynb
diff --git a/notebooks/1_Preprocessing.ipynb b/notebooks/1_Preprocessing.ipynb
new file mode 100644
index 0000000..7c1cd42
--- /dev/null
+++ b/notebooks/1_Preprocessing.ipynb
@@ -0,0 +1,696 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import pandas as pd\n",
+ "import numpy as np\n",
+ "import matplotlib.pyplot as plt\n",
+ "import seaborn as sns\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 6,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "training_file = '../data/train.csv'\n",
+ "test_file = '../data/test.csv'"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 7,
+ "metadata": {
+ "scrolled": true
+ },
+ "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>keyword</th>\n",
+ " <th>location</th>\n",
+ " <th>text</th>\n",
+ " <th>target</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>id</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>Our Deeds are the Reason of this #earthquake M...</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>Forest fire near La Ronge Sask. Canada</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>5</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>All residents asked to 'shelter in place' are ...</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>13,000 people receive #wildfires evacuation or...</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>7</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>Just got sent this photo from Ruby #Alaska as ...</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>...</th>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>137</th>\n",
+ " <td>accident</td>\n",
+ " <td>Charlotte</td>\n",
+ " <td>9 Mile backup on I-77 South...accident blockin...</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>138</th>\n",
+ " <td>accident</td>\n",
+ " <td>Baton Rouge, LA</td>\n",
+ " <td>Has an accident changed your life? We will hel...</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>139</th>\n",
+ " <td>accident</td>\n",
+ " <td>Hagerstown, MD</td>\n",
+ " <td>#BREAKING: there was a deadly motorcycle car a...</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>141</th>\n",
+ " <td>accident</td>\n",
+ " <td>Gloucestershire , UK</td>\n",
+ " <td>@flowri were you marinading it or was it an ac...</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>143</th>\n",
+ " <td>accident</td>\n",
+ " <td>NaN</td>\n",
+ " <td>only had a car for not even a week and got in ...</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "<p>100 rows × 4 columns</p>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " keyword location \\\n",
+ "id \n",
+ "1 NaN NaN \n",
+ "4 NaN NaN \n",
+ "5 NaN NaN \n",
+ "6 NaN NaN \n",
+ "7 NaN NaN \n",
+ ".. ... ... \n",
+ "137 accident Charlotte \n",
+ "138 accident Baton Rouge, LA \n",
+ "139 accident Hagerstown, MD \n",
+ "141 accident Gloucestershire , UK \n",
+ "143 accident NaN \n",
+ "\n",
+ " text target \n",
+ "id \n",
+ "1 Our Deeds are the Reason of this #earthquake M... 1 \n",
+ "4 Forest fire near La Ronge Sask. Canada 1 \n",
+ "5 All residents asked to 'shelter in place' are ... 1 \n",
+ "6 13,000 people receive #wildfires evacuation or... 1 \n",
+ "7 Just got sent this photo from Ruby #Alaska as ... 1 \n",
+ ".. ... ... \n",
+ "137 9 Mile backup on I-77 South...accident blockin... 1 \n",
+ "138 Has an accident changed your life? We will hel... 0 \n",
+ "139 #BREAKING: there was a deadly motorcycle car a... 1 \n",
+ "141 @flowri were you marinading it or was it an ac... 0 \n",
+ "143 only had a car for not even a week and got in ... 1 \n",
+ "\n",
+ "[100 rows x 4 columns]"
+ ]
+ },
+ "execution_count": 7,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "train = pd.read_csv(training_file, index_col=0)\n",
+ "test = pd.read_csv(test_file, index_col=0)\n",
+ "train.head(100)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 27,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "(7613, 4)"
+ ]
+ },
+ "execution_count": 27,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "train.shape"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 9,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "(3263, 3)"
+ ]
+ },
+ "execution_count": 9,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "test.shape"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Fehlstellen (NaNs) in Keyword und Location identifizieren und ersetzen"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 12,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Fehlende Werte in Trainingsdaten: 2533\n",
+ "Fehlende Werte in Testdaten: 1105\n"
+ ]
+ }
+ ],
+ "source": [
+ "datasets= {'Trainingsdaten':train, 'Testdaten':test}\n",
+ "for k,v in datasets.items():\n",
+ " is_NaN = v.isnull()\n",
+ " row_has_NaN = is_NaN.any(axis=1)\n",
+ " rows_with_NaN = v[row_has_NaN]\n",
+ " print('Fehlende Werte in ' + k + ': ' + str(rows_with_NaN.shape[0]))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 13,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# TODO\n",
+ "# Fehldaten in den einzelnen columns (location, keyword) identifizieren\n",
+ "# durch neue Klasse ersetzen"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Location standardisieren"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# TODO\n",
+ "# es gibt bestimmt gute packages die das können\n",
+ "# Ziel ist dass am Ende gleiche Orte, egal wie sie geschrieben sind, der gleichen Klasse zuegordnet werden können"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Umwandlung von Keyword und Location in numerische Features"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# TODO "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 10,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "7613\n",
+ "222\n"
+ ]
+ }
+ ],
+ "source": [
+ "print(len(train['keyword']))\n",
+ "print(len(train['keyword'].unique()))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 19,
+ "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>keyword</th>\n",
+ " <th>location</th>\n",
+ " <th>text</th>\n",
+ " <th>target</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>id</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>6292</th>\n",
+ " <td>hostage</td>\n",
+ " <td>NaN</td>\n",
+ " <td>Egyptian Militants Tied to ISIS Threaten to Ki...</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6293</th>\n",
+ " <td>hostage</td>\n",
+ " <td>Vancouver, British Columbia</td>\n",
+ " <td>‰Û÷Ransomware‰Ûª holds B.C. man‰Ûªs computer f...</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6294</th>\n",
+ " <td>hostage</td>\n",
+ " <td>NaN</td>\n",
+ " <td>I always tell my mom to bring me food or I wil...</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6296</th>\n",
+ " <td>hostage</td>\n",
+ " <td>Starling City</td>\n",
+ " <td>That moth that held me hostage yesterday has b...</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6297</th>\n",
+ " <td>hostage</td>\n",
+ " <td>The Great State of Maine</td>\n",
+ " <td>Islamic State group threatens to kill hostage ...</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6299</th>\n",
+ " <td>hostage</td>\n",
+ " <td>NaN</td>\n",
+ " <td>quoted here--&gt;CNN: Purported ISIS video thr...</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6300</th>\n",
+ " <td>hostage</td>\n",
+ " <td>Glenview to Knoxville</td>\n",
+ " <td>I'm hungry as a hostage</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6301</th>\n",
+ " <td>hostage</td>\n",
+ " <td>Indiana</td>\n",
+ " <td>Who is Tomislav Salopek the Islamic State's Mo...</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6302</th>\n",
+ " <td>hostage</td>\n",
+ " <td>NaN</td>\n",
+ " <td>@susanj357 @msnbc @allinwithchris it's like wa...</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6303</th>\n",
+ " <td>hostage</td>\n",
+ " <td>Roaming around the world</td>\n",
+ " <td>Islamic State group in Egypt threatens to kill...</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6304</th>\n",
+ " <td>hostage</td>\n",
+ " <td>NaN</td>\n",
+ " <td>You will be held hostage by a radical group.</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6305</th>\n",
+ " <td>hostage</td>\n",
+ " <td>NaN</td>\n",
+ " <td>When u get mugged with ur gf u come up with th...</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6306</th>\n",
+ " <td>hostage</td>\n",
+ " <td>????</td>\n",
+ " <td>whO'S THAT SHADOW HOLDIN ME HOSTAGE I'VE BEEN ...</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6310</th>\n",
+ " <td>hostage</td>\n",
+ " <td>NaN</td>\n",
+ " <td>Related News: 'ISIS video' threatens hostage -...</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6311</th>\n",
+ " <td>hostage</td>\n",
+ " <td>Cape Neddick, ME</td>\n",
+ " <td>@EvaHanderek @MarleyKnysh great times until th...</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6312</th>\n",
+ " <td>hostage</td>\n",
+ " <td>Global</td>\n",
+ " <td>The horrific story of being a hostage - The ho...</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6314</th>\n",
+ " <td>hostage</td>\n",
+ " <td>Mariveles, Bataan</td>\n",
+ " <td>Islamic State group in Egypt threatens to kill...</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6315</th>\n",
+ " <td>hostage</td>\n",
+ " <td>ÃŒÃT: 40.562796,-75.488849</td>\n",
+ " <td>Murfreesboro peeps- I'm hearing Walmart on S R...</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6317</th>\n",
+ " <td>hostage</td>\n",
+ " <td>Roaming around the world</td>\n",
+ " <td>Islamic State group in Egypt threatens to kill...</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6318</th>\n",
+ " <td>hostage</td>\n",
+ " <td>NaN</td>\n",
+ " <td>I sent my emails why are the TRINNA hold me ho...</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6320</th>\n",
+ " <td>hostage</td>\n",
+ " <td>Melbourne, FL</td>\n",
+ " <td>Wtf? Her biological father is holding her host...</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6322</th>\n",
+ " <td>hostage</td>\n",
+ " <td>New Chicago</td>\n",
+ " <td>@mylittlepwnies3 @Early__May @AnathemaZhiv @To...</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6323</th>\n",
+ " <td>hostage</td>\n",
+ " <td>NaN</td>\n",
+ " <td>If you fill your mind with encouragement and p...</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6325</th>\n",
+ " <td>hostage</td>\n",
+ " <td>NaN</td>\n",
+ " <td>I went to pick up my lunch today and the barte...</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6326</th>\n",
+ " <td>hostage</td>\n",
+ " <td>San Francisco Bay Area</td>\n",
+ " <td>@pmarca content is held hostage by network due...</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6328</th>\n",
+ " <td>hostage</td>\n",
+ " <td>Australia</td>\n",
+ " <td>New ISIS Video: ISIS Threatens to Behead Croat...</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6329</th>\n",
+ " <td>hostage</td>\n",
+ " <td>NaN</td>\n",
+ " <td>Sydney hostage crisis has now been recovered f...</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6330</th>\n",
+ " <td>hostage</td>\n",
+ " <td>Victorville, CA</td>\n",
+ " <td>Wut a lonely lunch. I got ditched. And I'm hun...</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6331</th>\n",
+ " <td>hostage</td>\n",
+ " <td>Washington D.C.</td>\n",
+ " <td>Nearly 35 years after their release from capti...</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6332</th>\n",
+ " <td>hostage</td>\n",
+ " <td>NaN</td>\n",
+ " <td>@gideonstrumpet Have you been held hostage?</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6334</th>\n",
+ " <td>hostage</td>\n",
+ " <td>Eugene, Oregon</td>\n",
+ " <td>Dysfunctional McConnell plans on holding Judic...</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " keyword location \\\n",
+ "id \n",
+ "6292 hostage NaN \n",
+ "6293 hostage Vancouver, British Columbia \n",
+ "6294 hostage NaN \n",
+ "6296 hostage Starling City \n",
+ "6297 hostage The Great State of Maine \n",
+ "6299 hostage NaN \n",
+ "6300 hostage Glenview to Knoxville \n",
+ "6301 hostage Indiana \n",
+ "6302 hostage NaN \n",
+ "6303 hostage Roaming around the world \n",
+ "6304 hostage NaN \n",
+ "6305 hostage NaN \n",
+ "6306 hostage ???? \n",
+ "6310 hostage NaN \n",
+ "6311 hostage Cape Neddick, ME \n",
+ "6312 hostage Global \n",
+ "6314 hostage Mariveles, Bataan \n",
+ "6315 hostage ÃŒÃT: 40.562796,-75.488849 \n",
+ "6317 hostage Roaming around the world \n",
+ "6318 hostage NaN \n",
+ "6320 hostage Melbourne, FL \n",
+ "6322 hostage New Chicago \n",
+ "6323 hostage NaN \n",
+ "6325 hostage NaN \n",
+ "6326 hostage San Francisco Bay Area \n",
+ "6328 hostage Australia \n",
+ "6329 hostage NaN \n",
+ "6330 hostage Victorville, CA \n",
+ "6331 hostage Washington D.C. \n",
+ "6332 hostage NaN \n",
+ "6334 hostage Eugene, Oregon \n",
+ "\n",
+ " text target \n",
+ "id \n",
+ "6292 Egyptian Militants Tied to ISIS Threaten to Ki... 1 \n",
+ "6293 ‰Û÷Ransomware‰Ûª holds B.C. man‰Ûªs computer f... 0 \n",
+ "6294 I always tell my mom to bring me food or I wil... 0 \n",
+ "6296 That moth that held me hostage yesterday has b... 0 \n",
+ "6297 Islamic State group threatens to kill hostage ... 1 \n",
+ "6299 quoted here-->CNN: Purported ISIS video thr... 1 \n",
+ "6300 I'm hungry as a hostage 0 \n",
+ "6301 Who is Tomislav Salopek the Islamic State's Mo... 0 \n",
+ "6302 @susanj357 @msnbc @allinwithchris it's like wa... 0 \n",
+ "6303 Islamic State group in Egypt threatens to kill... 1 \n",
+ "6304 You will be held hostage by a radical group. 0 \n",
+ "6305 When u get mugged with ur gf u come up with th... 0 \n",
+ "6306 whO'S THAT SHADOW HOLDIN ME HOSTAGE I'VE BEEN ... 0 \n",
+ "6310 Related News: 'ISIS video' threatens hostage -... 1 \n",
+ "6311 @EvaHanderek @MarleyKnysh great times until th... 1 \n",
+ "6312 The horrific story of being a hostage - The ho... 1 \n",
+ "6314 Islamic State group in Egypt threatens to kill... 1 \n",
+ "6315 Murfreesboro peeps- I'm hearing Walmart on S R... 1 \n",
+ "6317 Islamic State group in Egypt threatens to kill... 1 \n",
+ "6318 I sent my emails why are the TRINNA hold me ho... 0 \n",
+ "6320 Wtf? Her biological father is holding her host... 0 \n",
+ "6322 @mylittlepwnies3 @Early__May @AnathemaZhiv @To... 1 \n",
+ "6323 If you fill your mind with encouragement and p... 0 \n",
+ "6325 I went to pick up my lunch today and the barte... 1 \n",
+ "6326 @pmarca content is held hostage by network due... 1 \n",
+ "6328 New ISIS Video: ISIS Threatens to Behead Croat... 1 \n",
+ "6329 Sydney hostage crisis has now been recovered f... 1 \n",
+ "6330 Wut a lonely lunch. I got ditched. And I'm hun... 0 \n",
+ "6331 Nearly 35 years after their release from capti... 0 \n",
+ "6332 @gideonstrumpet Have you been held hostage? 0 \n",
+ "6334 Dysfunctional McConnell plans on holding Judic... 0 "
+ ]
+ },
+ "execution_count": 19,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "keyword = 'hostage'\n",
+ "train[train.keyword ==keyword]"
+ ]
+ },
+ {
+ "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": "3.6.4"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
--
GitLab