Skip to content

Instantly share code, notes, and snippets.

Show Gist options
  • Save oneryalcin/1570f93553638cc312a0 to your computer and use it in GitHub Desktop.
Save oneryalcin/1570f93553638cc312a0 to your computer and use it in GitHub Desktop.
Display the source blob
Display the rendered blob
Raw
{
"cells": [
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"import graphlab as gl"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"[INFO] This non-commercial license of GraphLab Create is assigned to oneryalcin@gmail.comand will expire on September 23, 2016. For commercial licensing options, visit https://dato.com/buy/.\n",
"\n",
"[INFO] Start server at: ipc:///tmp/graphlab_server-16871 - Server binary: /home/oner/anaconda/envs/dato-env/lib/python2.7/site-packages/graphlab/unity_server - Server log: /tmp/graphlab_server_1443362573.log\n",
"[INFO] GraphLab Server Version: 1.6.1\n"
]
}
],
"source": [
"# Import amazon baby products dataset\n",
"products = gl.SFrame('amazon_baby.gl/')"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"#Create a new column with word count from reviews\n",
"products['word_count'] = gl.text_analytics.count_words(products['review']) "
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/html": [
"<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\"><table frame=\"box\" rules=\"cols\">\n",
" <tr>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">name</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">review</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">rating</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">word_count</th>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Planetwise Flannel Wipes</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">These flannel wipes are<br>OK, but in my opinion ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">3.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'and': 5, 'stink': 1,<br>'because': 1, 'ordered': ...</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Planetwise Wipe Pouch</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">it came early and was not<br>disappointed. i love ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">5.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'and': 3, 'love': 1,<br>'it': 2, 'highly': 1, ...</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Annas Dream Full Quilt<br>with 2 Shams ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Very soft and comfortable<br>and warmer than it ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">5.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'and': 2, 'quilt': 1,<br>'it': 1, 'comfortable': ...</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Stop Pacifier Sucking<br>without tears with ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">This is a product well<br>worth the purchase. I ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">5.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'ingenious': 1, 'and':<br>3, 'love': 2, ...</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Stop Pacifier Sucking<br>without tears with ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">All of my kids have cried<br>non-stop when I tried to ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">5.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'and': 2, 'parents!!':<br>1, 'all': 2, 'puppet.': ...</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Stop Pacifier Sucking<br>without tears with ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">When the Binky Fairy came<br>to our house, we didn't ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">5.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'and': 2, 'cute': 1,<br>'help': 2, 'doll': 1, ...</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">A Tale of Baby's Days<br>with Peter Rabbit ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Lovely book, it's bound<br>tightly so you may no ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">4.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'shop': 1, 'be': 1,<br>'is': 1, 'it': 1, 'as': ...</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Baby Tracker&amp;reg; - Daily<br>Childcare Journal, ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Perfect for new parents.<br>We were able to keep ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">5.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'feeding,': 1, 'and': 2,<br>'all': 1, 'right': 1, ...</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Baby Tracker&amp;reg; - Daily<br>Childcare Journal, ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">A friend of mine pinned<br>this product on Pinte ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">5.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'and': 1, 'help': 1,<br>'give': 1, 'is': 1, ...</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Baby Tracker&amp;reg; - Daily<br>Childcare Journal, ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">This has been an easy way<br>for my nanny to record ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">4.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'journal.': 1, 'all': 1,<br>'standarad': 1, ...</td>\n",
" </tr>\n",
"</table>\n",
"[10 rows x 4 columns]<br/>\n",
"</div>"
],
"text/plain": [
"Columns:\n",
"\tname\tstr\n",
"\treview\tstr\n",
"\trating\tfloat\n",
"\tword_count\tdict\n",
"\n",
"Rows: 10\n",
"\n",
"Data:\n",
"+-------------------------------+-------------------------------+--------+\n",
"| name | review | rating |\n",
"+-------------------------------+-------------------------------+--------+\n",
"| Planetwise Flannel Wipes | These flannel wipes are OK... | 3.0 |\n",
"| Planetwise Wipe Pouch | it came early and was not ... | 5.0 |\n",
"| Annas Dream Full Quilt wit... | Very soft and comfortable ... | 5.0 |\n",
"| Stop Pacifier Sucking with... | This is a product well wor... | 5.0 |\n",
"| Stop Pacifier Sucking with... | All of my kids have cried ... | 5.0 |\n",
"| Stop Pacifier Sucking with... | When the Binky Fairy came ... | 5.0 |\n",
"| A Tale of Baby's Days with... | Lovely book, it's bound ti... | 4.0 |\n",
"| Baby Tracker&reg; - Daily ... | Perfect for new parents. W... | 5.0 |\n",
"| Baby Tracker&reg; - Daily ... | A friend of mine pinned th... | 5.0 |\n",
"| Baby Tracker&reg; - Daily ... | This has been an easy way ... | 4.0 |\n",
"+-------------------------------+-------------------------------+--------+\n",
"+-------------------------------+\n",
"| word_count |\n",
"+-------------------------------+\n",
"| {'and': 5, 'stink': 1, 'be... |\n",
"| {'and': 3, 'love': 1, 'it'... |\n",
"| {'and': 2, 'quilt': 1, 'it... |\n",
"| {'ingenious': 1, 'and': 3,... |\n",
"| {'and': 2, 'parents!!': 1,... |\n",
"| {'and': 2, 'cute': 1, 'hel... |\n",
"| {'shop': 1, 'be': 1, 'is':... |\n",
"| {'feeding,': 1, 'and': 2, ... |\n",
"| {'and': 1, 'help': 1, 'giv... |\n",
"| {'journal.': 1, 'all': 1, ... |\n",
"+-------------------------------+\n",
"[10 rows x 4 columns]"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Let's have a quick look at data\n",
"products.head()"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"# Set the output target as the python notebook, not a separate window\n",
"gl.canvas.set_target('ipynb')"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"def awesome_count(wrd_cnt):\n",
" if 'awesome' in wrd_cnt:\n",
" return wrd_cnt['awesome']\n",
" else:\n",
" return 0"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"products['awesome'] = products['word_count'].apply(awesome_count)"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/html": [
"<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\"><table frame=\"box\" rules=\"cols\">\n",
" <tr>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">name</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">review</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">rating</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">word_count</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">awesome</th>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Planetwise Flannel Wipes</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">These flannel wipes are<br>OK, but in my opinion ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">3.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'and': 5, 'stink': 1,<br>'because': 1, 'ordered': ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Planetwise Wipe Pouch</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">it came early and was not<br>disappointed. i love ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">5.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'and': 3, 'love': 1,<br>'it': 2, 'highly': 1, ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Annas Dream Full Quilt<br>with 2 Shams ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Very soft and comfortable<br>and warmer than it ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">5.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'and': 2, 'quilt': 1,<br>'it': 1, 'comfortable': ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Stop Pacifier Sucking<br>without tears with ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">This is a product well<br>worth the purchase. I ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">5.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'ingenious': 1, 'and':<br>3, 'love': 2, ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Stop Pacifier Sucking<br>without tears with ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">All of my kids have cried<br>non-stop when I tried to ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">5.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'and': 2, 'parents!!':<br>1, 'all': 2, 'puppet.': ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Stop Pacifier Sucking<br>without tears with ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">When the Binky Fairy came<br>to our house, we didn't ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">5.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'and': 2, 'cute': 1,<br>'help': 2, 'doll': 1, ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">A Tale of Baby's Days<br>with Peter Rabbit ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Lovely book, it's bound<br>tightly so you may no ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">4.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'shop': 1, 'be': 1,<br>'is': 1, 'it': 1, 'as': ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Baby Tracker&amp;reg; - Daily<br>Childcare Journal, ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Perfect for new parents.<br>We were able to keep ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">5.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'feeding,': 1, 'and': 2,<br>'all': 1, 'right': 1, ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Baby Tracker&amp;reg; - Daily<br>Childcare Journal, ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">A friend of mine pinned<br>this product on Pinte ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">5.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'and': 1, 'help': 1,<br>'give': 1, 'is': 1, ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Baby Tracker&amp;reg; - Daily<br>Childcare Journal, ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">This has been an easy way<br>for my nanny to record ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">4.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'journal.': 1, 'all': 1,<br>'standarad': 1, ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
"</table>\n",
"[10 rows x 5 columns]<br/>\n",
"</div>"
],
"text/plain": [
"Columns:\n",
"\tname\tstr\n",
"\treview\tstr\n",
"\trating\tfloat\n",
"\tword_count\tdict\n",
"\tawesome\tint\n",
"\n",
"Rows: 10\n",
"\n",
"Data:\n",
"+-------------------------------+-------------------------------+--------+\n",
"| name | review | rating |\n",
"+-------------------------------+-------------------------------+--------+\n",
"| Planetwise Flannel Wipes | These flannel wipes are OK... | 3.0 |\n",
"| Planetwise Wipe Pouch | it came early and was not ... | 5.0 |\n",
"| Annas Dream Full Quilt wit... | Very soft and comfortable ... | 5.0 |\n",
"| Stop Pacifier Sucking with... | This is a product well wor... | 5.0 |\n",
"| Stop Pacifier Sucking with... | All of my kids have cried ... | 5.0 |\n",
"| Stop Pacifier Sucking with... | When the Binky Fairy came ... | 5.0 |\n",
"| A Tale of Baby's Days with... | Lovely book, it's bound ti... | 4.0 |\n",
"| Baby Tracker&reg; - Daily ... | Perfect for new parents. W... | 5.0 |\n",
"| Baby Tracker&reg; - Daily ... | A friend of mine pinned th... | 5.0 |\n",
"| Baby Tracker&reg; - Daily ... | This has been an easy way ... | 4.0 |\n",
"+-------------------------------+-------------------------------+--------+\n",
"+-------------------------------+---------+\n",
"| word_count | awesome |\n",
"+-------------------------------+---------+\n",
"| {'and': 5, 'stink': 1, 'be... | 0 |\n",
"| {'and': 3, 'love': 1, 'it'... | 0 |\n",
"| {'and': 2, 'quilt': 1, 'it... | 0 |\n",
"| {'ingenious': 1, 'and': 3,... | 0 |\n",
"| {'and': 2, 'parents!!': 1,... | 0 |\n",
"| {'and': 2, 'cute': 1, 'hel... | 0 |\n",
"| {'shop': 1, 'be': 1, 'is':... | 0 |\n",
"| {'feeding,': 1, 'and': 2, ... | 0 |\n",
"| {'and': 1, 'help': 1, 'giv... | 0 |\n",
"| {'journal.': 1, 'all': 1, ... | 0 |\n",
"+-------------------------------+---------+\n",
"[10 rows x 5 columns]"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"products.head()"
]
},
{
"cell_type": "code",
"execution_count": 23,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"def great_count(wrd_cnt):\n",
" if 'great' in wrd_cnt:\n",
" return wrd_cnt['great']\n",
" else:\n",
" return 0\n",
"\n",
"def fantastic_count(wrd_cnt):\n",
" if 'fantastic' in wrd_cnt:\n",
" return wrd_cnt['fantastic']\n",
" else:\n",
" return 0\n",
" \n",
"\n",
"def amazing_count(wrd_cnt):\n",
" if 'amazing' in wrd_cnt:\n",
" return wrd_cnt['amazing']\n",
" else:\n",
" return 0\n",
" \n",
"\n",
"def love_count(wrd_cnt):\n",
" if 'love' in wrd_cnt:\n",
" return wrd_cnt['love']\n",
" else:\n",
" return 0\n",
" \n",
"\n",
"def horrible_count(wrd_cnt):\n",
" if 'horrible' in wrd_cnt:\n",
" return wrd_cnt['horrible']\n",
" else:\n",
" return 0\n",
" \n",
"\n",
"def bad_count(wrd_cnt):\n",
" if 'bad' in wrd_cnt:\n",
" return wrd_cnt['bad']\n",
" else:\n",
" return 0\n",
" \n",
"\n",
"def terrible_count(wrd_cnt):\n",
" if 'terrible' in wrd_cnt:\n",
" return wrd_cnt['terrible']\n",
" else:\n",
" return 0\n",
" \n",
"\n",
"def awful_count(wrd_cnt):\n",
" if 'awful' in wrd_cnt:\n",
" return wrd_cnt['awful']\n",
" else:\n",
" return 0\n",
" \n",
"\n",
"def wow_count(wrd_cnt):\n",
" if 'wow' in wrd_cnt:\n",
" return wrd_cnt['wow']\n",
" else:\n",
" return 0\n",
" \n",
"\n",
"def hate_count(wrd_cnt):\n",
" if 'hate' in wrd_cnt:\n",
" return wrd_cnt['hate']\n",
" else:\n",
" return 0"
]
},
{
"cell_type": "code",
"execution_count": 25,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"products['great'] = products['word_count'].apply(great_count)\n",
"products['fantastic'] = products['word_count'].apply(fantastic_count)\n",
"products['amazing'] = products['word_count'].apply(amazing_count)\n",
"products['love'] = products['word_count'].apply(love_count)\n",
"products['horrible'] = products['word_count'].apply(horrible_count)\n",
"products['bad'] = products['word_count'].apply(bad_count)\n",
"products['terrible'] = products['word_count'].apply(terrible_count)\n",
"products['awful'] = products['word_count'].apply(awful_count)\n",
"products['wow'] = products['word_count'].apply(wow_count)\n",
"products['hate'] = products['word_count'].apply(hate_count)"
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/html": [
"<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\"><table frame=\"box\" rules=\"cols\">\n",
" <tr>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">name</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">review</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">rating</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">word_count</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">awesome</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">great</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">fantastic</th>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Planetwise Flannel Wipes</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">These flannel wipes are<br>OK, but in my opinion ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">3.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'and': 5, 'stink': 1,<br>'because': 1, 'ordered': ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Planetwise Wipe Pouch</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">it came early and was not<br>disappointed. i love ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">5.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'and': 3, 'love': 1,<br>'it': 2, 'highly': 1, ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Annas Dream Full Quilt<br>with 2 Shams ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Very soft and comfortable<br>and warmer than it ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">5.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'and': 2, 'quilt': 1,<br>'it': 1, 'comfortable': ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Stop Pacifier Sucking<br>without tears with ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">This is a product well<br>worth the purchase. I ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">5.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'ingenious': 1, 'and':<br>3, 'love': 2, ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Stop Pacifier Sucking<br>without tears with ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">All of my kids have cried<br>non-stop when I tried to ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">5.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'and': 2, 'parents!!':<br>1, 'all': 2, 'puppet.': ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Stop Pacifier Sucking<br>without tears with ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">When the Binky Fairy came<br>to our house, we didn't ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">5.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'and': 2, 'cute': 1,<br>'help': 2, 'doll': 1, ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">A Tale of Baby's Days<br>with Peter Rabbit ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Lovely book, it's bound<br>tightly so you may no ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">4.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'shop': 1, 'be': 1,<br>'is': 1, 'it': 1, 'as': ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Baby Tracker&amp;reg; - Daily<br>Childcare Journal, ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Perfect for new parents.<br>We were able to keep ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">5.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'feeding,': 1, 'and': 2,<br>'all': 1, 'right': 1, ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Baby Tracker&amp;reg; - Daily<br>Childcare Journal, ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">A friend of mine pinned<br>this product on Pinte ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">5.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'and': 1, 'help': 1,<br>'give': 1, 'is': 1, ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Baby Tracker&amp;reg; - Daily<br>Childcare Journal, ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">This has been an easy way<br>for my nanny to record ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">4.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'journal.': 1, 'all': 1,<br>'standarad': 1, ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
"</table>\n",
"<table frame=\"box\" rules=\"cols\">\n",
" <tr>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">amazing</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">love</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">horrible</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">bad</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">terrible</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">awful</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">wow</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">hate</th>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">2</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
"</table>\n",
"[10 rows x 15 columns]<br/>\n",
"</div>"
],
"text/plain": [
"Columns:\n",
"\tname\tstr\n",
"\treview\tstr\n",
"\trating\tfloat\n",
"\tword_count\tdict\n",
"\tawesome\tint\n",
"\tgreat\tint\n",
"\tfantastic\tint\n",
"\tamazing\tint\n",
"\tlove\tint\n",
"\thorrible\tint\n",
"\tbad\tint\n",
"\tterrible\tint\n",
"\tawful\tint\n",
"\twow\tint\n",
"\thate\tint\n",
"\n",
"Rows: 10\n",
"\n",
"Data:\n",
"+-------------------------------+-------------------------------+--------+\n",
"| name | review | rating |\n",
"+-------------------------------+-------------------------------+--------+\n",
"| Planetwise Flannel Wipes | These flannel wipes are OK... | 3.0 |\n",
"| Planetwise Wipe Pouch | it came early and was not ... | 5.0 |\n",
"| Annas Dream Full Quilt wit... | Very soft and comfortable ... | 5.0 |\n",
"| Stop Pacifier Sucking with... | This is a product well wor... | 5.0 |\n",
"| Stop Pacifier Sucking with... | All of my kids have cried ... | 5.0 |\n",
"| Stop Pacifier Sucking with... | When the Binky Fairy came ... | 5.0 |\n",
"| A Tale of Baby's Days with... | Lovely book, it's bound ti... | 4.0 |\n",
"| Baby Tracker&reg; - Daily ... | Perfect for new parents. W... | 5.0 |\n",
"| Baby Tracker&reg; - Daily ... | A friend of mine pinned th... | 5.0 |\n",
"| Baby Tracker&reg; - Daily ... | This has been an easy way ... | 4.0 |\n",
"+-------------------------------+-------------------------------+--------+\n",
"+-------------------------------+---------+-------+-----------+---------+------+\n",
"| word_count | awesome | great | fantastic | amazing | love |\n",
"+-------------------------------+---------+-------+-----------+---------+------+\n",
"| {'and': 5, 'stink': 1, 'be... | 0 | 0 | 0 | 0 | 0 |\n",
"| {'and': 3, 'love': 1, 'it'... | 0 | 0 | 0 | 0 | 1 |\n",
"| {'and': 2, 'quilt': 1, 'it... | 0 | 0 | 0 | 0 | 0 |\n",
"| {'ingenious': 1, 'and': 3,... | 0 | 0 | 0 | 0 | 2 |\n",
"| {'and': 2, 'parents!!': 1,... | 0 | 1 | 0 | 0 | 0 |\n",
"| {'and': 2, 'cute': 1, 'hel... | 0 | 1 | 0 | 0 | 0 |\n",
"| {'shop': 1, 'be': 1, 'is':... | 0 | 0 | 0 | 0 | 0 |\n",
"| {'feeding,': 1, 'and': 2, ... | 0 | 0 | 0 | 0 | 0 |\n",
"| {'and': 1, 'help': 1, 'giv... | 0 | 0 | 0 | 0 | 0 |\n",
"| {'journal.': 1, 'all': 1, ... | 0 | 0 | 0 | 0 | 0 |\n",
"+-------------------------------+---------+-------+-----------+---------+------+\n",
"+----------+-----+----------+-------+-----+------+\n",
"| horrible | bad | terrible | awful | wow | hate |\n",
"+----------+-----+----------+-------+-----+------+\n",
"| 0 | 0 | 0 | 0 | 0 | 0 |\n",
"| 0 | 0 | 0 | 0 | 0 | 0 |\n",
"| 0 | 0 | 0 | 0 | 0 | 0 |\n",
"| 0 | 0 | 0 | 0 | 0 | 0 |\n",
"| 0 | 0 | 0 | 0 | 0 | 0 |\n",
"| 0 | 0 | 0 | 0 | 0 | 0 |\n",
"| 0 | 0 | 0 | 0 | 0 | 0 |\n",
"| 0 | 0 | 0 | 0 | 0 | 0 |\n",
"| 0 | 0 | 0 | 0 | 0 | 0 |\n",
"| 0 | 0 | 0 | 0 | 0 | 0 |\n",
"+----------+-----+----------+-------+-----+------+\n",
"[10 rows x 15 columns]"
]
},
"execution_count": 26,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"products.head()"
]
},
{
"cell_type": "code",
"execution_count": 39,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"2090"
]
},
"execution_count": 39,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"sum(products['awesome'])"
]
},
{
"cell_type": "code",
"execution_count": 28,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"45206"
]
},
"execution_count": 28,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"sum(products['great'])"
]
},
{
"cell_type": "code",
"execution_count": 40,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"932"
]
},
"execution_count": 40,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"sum(products['fantastic'])"
]
},
{
"cell_type": "code",
"execution_count": 31,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"1363"
]
},
"execution_count": 31,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"sum(products['amazing'])"
]
},
{
"cell_type": "code",
"execution_count": 32,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"42065"
]
},
"execution_count": 32,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"sum(products['love'])"
]
},
{
"cell_type": "code",
"execution_count": 33,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"734"
]
},
"execution_count": 33,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"sum(products['horrible'])"
]
},
{
"cell_type": "code",
"execution_count": 34,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"3724"
]
},
"execution_count": 34,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"sum(products['bad'])"
]
},
{
"cell_type": "code",
"execution_count": 35,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"748"
]
},
"execution_count": 35,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"sum(products['terrible'])"
]
},
{
"cell_type": "code",
"execution_count": 36,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"383"
]
},
"execution_count": 36,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"sum(products['awful'])"
]
},
{
"cell_type": "code",
"execution_count": 37,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"144"
]
},
"execution_count": 37,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"sum(products['wow'])"
]
},
{
"cell_type": "code",
"execution_count": 38,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"1220"
]
},
"execution_count": 38,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"sum(products['hate'])"
]
},
{
"cell_type": "code",
"execution_count": 42,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"selected_words = ['awesome', 'great', 'fantastic', 'amazing', 'love', \n",
" 'horrible', 'bad', 'terrible', 'awful', 'wow', 'hate']"
]
},
{
"cell_type": "code",
"execution_count": 62,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"train_data, test_data = products.random_split(0.8, seed=0)\n",
"\n",
"# ignore all 3 star reviews\n",
"products = products[products['rating'] != 3]\n",
"\n",
"# positive sentiment = 4 or 5 star reviews\n",
"products['sentiment'] = products['rating'] >= 4"
]
},
{
"cell_type": "code",
"execution_count": 64,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"PROGRESS: Logistic regression:\n",
"PROGRESS: --------------------------------------------------------\n",
"PROGRESS: Number of examples : 133448\n",
"PROGRESS: Number of classes : 2\n",
"PROGRESS: Number of feature columns : 11\n",
"PROGRESS: Number of unpacked features : 11\n",
"PROGRESS: Number of coefficients : 12\n",
"PROGRESS: Starting Newton Method\n",
"PROGRESS: --------------------------------------------------------\n",
"PROGRESS: +-----------+----------+--------------+-------------------+---------------------+\n",
"PROGRESS: | Iteration | Passes | Elapsed Time | Training-accuracy | Validation-accuracy |\n",
"PROGRESS: +-----------+----------+--------------+-------------------+---------------------+\n",
"PROGRESS: | 1 | 2 | 0.123101 | 0.844299 | 0.842842 |\n",
"PROGRESS: | 2 | 3 | 0.209734 | 0.844186 | 0.842842 |\n",
"PROGRESS: | 3 | 4 | 0.303136 | 0.844276 | 0.843142 |\n",
"PROGRESS: | 4 | 5 | 0.393633 | 0.844269 | 0.843142 |\n",
"PROGRESS: | 5 | 6 | 0.477309 | 0.844269 | 0.843142 |\n",
"PROGRESS: | 6 | 7 | 0.562805 | 0.844269 | 0.843142 |\n",
"PROGRESS: +-----------+----------+--------------+-------------------+---------------------+\n"
]
}
],
"source": [
"# Let's create our logistics regression model using the 12 words above\n",
"selected_words_model =gl.logistic_classifier.create(train_data,\n",
" target='sentiment',\n",
" features=selected_words,\n",
" validation_set = test_data)"
]
},
{
"cell_type": "code",
"execution_count": 69,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/html": [
"<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\"><table frame=\"box\" rules=\"cols\">\n",
" <tr>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">name</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">index</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">class</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">value</th>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">love</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">None</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1.39989834302</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">(intercept)</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">None</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1.36728315229</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">awesome</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">None</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1.05800888878</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">amazing</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">None</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0.892802422508</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">fantastic</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">None</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0.891303090304</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">great</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">None</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0.883937894898</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">wow</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">None</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">-0.0541450123333</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">bad</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">None</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">-0.985827369929</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">hate</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">None</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">-1.40916406276</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">awful</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">None</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">-1.76469955631</td>\n",
" </tr>\n",
"</table>\n",
"[12 rows x 4 columns]<br/>Note: Only the head of the SFrame is printed.<br/>You can use print_rows(num_rows=m, num_columns=n) to print more rows and columns.\n",
"</div>"
],
"text/plain": [
"Columns:\n",
"\tname\tstr\n",
"\tindex\tstr\n",
"\tclass\tint\n",
"\tvalue\tfloat\n",
"\n",
"Rows: 12\n",
"\n",
"Data:\n",
"+-------------+-------+-------+------------------+\n",
"| name | index | class | value |\n",
"+-------------+-------+-------+------------------+\n",
"| love | None | 1 | 1.39989834302 |\n",
"| (intercept) | None | 1 | 1.36728315229 |\n",
"| awesome | None | 1 | 1.05800888878 |\n",
"| amazing | None | 1 | 0.892802422508 |\n",
"| fantastic | None | 1 | 0.891303090304 |\n",
"| great | None | 1 | 0.883937894898 |\n",
"| wow | None | 1 | -0.0541450123333 |\n",
"| bad | None | 1 | -0.985827369929 |\n",
"| hate | None | 1 | -1.40916406276 |\n",
"| awful | None | 1 | -1.76469955631 |\n",
"+-------------+-------+-------+------------------+\n",
"[12 rows x 4 columns]\n",
"Note: Only the head of the SFrame is printed.\n",
"You can use print_rows(num_rows=m, num_columns=n) to print more rows and columns."
]
},
"execution_count": 69,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Looks like word 'love' has most positive effect and word 'awful' has the most negative effect\n",
"selected_words_model['coefficients'].sort('value',ascending=False)"
]
},
{
"cell_type": "code",
"execution_count": 70,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"{'accuracy': 0.8431419649291376, 'confusion_matrix': Columns:\n",
" \ttarget_label\tint\n",
" \tpredicted_label\tint\n",
" \tcount\tint\n",
" \n",
" Rows: 4\n",
" \n",
" Data:\n",
" +--------------+-----------------+-------+\n",
" | target_label | predicted_label | count |\n",
" +--------------+-----------------+-------+\n",
" | 0 | 0 | 234 |\n",
" | 1 | 0 | 130 |\n",
" | 0 | 1 | 5094 |\n",
" | 1 | 1 | 27846 |\n",
" +--------------+-----------------+-------+\n",
" [4 rows x 3 columns]}"
]
},
"execution_count": 70,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"selected_words_model.evaluate(test_data)"
]
},
{
"cell_type": "code",
"execution_count": 71,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"0.8431419649291376"
]
},
"execution_count": 71,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Accuracy of the model is:\n",
"(234+27846)*1.0/(234+130+5094+27846)"
]
},
{
"cell_type": "code",
"execution_count": 94,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"0.8400192169108815"
]
},
"execution_count": 94,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"(130+27846.0)/(234+130+5094+27846)"
]
},
{
"cell_type": "code",
"execution_count": 73,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"# Let's review ‘Baby Trend Diaper Champ’ product\n",
"diaper_champ_reviews = products[products['name'] == 'Baby Trend Diaper Champ']"
]
},
{
"cell_type": "code",
"execution_count": 74,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"298"
]
},
"execution_count": 74,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"len(diaper_champ_reviews)"
]
},
{
"cell_type": "code",
"execution_count": 76,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/html": [
"<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\"><table frame=\"box\" rules=\"cols\">\n",
" <tr>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">name</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">review</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">rating</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">word_count</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">awesome</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">great</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">fantastic</th>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Baby Trend Diaper Champ</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Ok - newsflash. Diapers<br>are just smelly. We've ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">4.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'just': 2, 'less': 1,<br>'-': 3, 'smell- ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Baby Trend Diaper Champ</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">My husband and I selected<br>the Diaper \"Champ\" ma ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'just': 1, 'less': 1,<br>'when': 3, 'over': 1, ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Baby Trend Diaper Champ</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Excellent diaper disposal<br>unit. I used it in ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">5.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'control': 1, 'am': 1,<br>'it': 1, 'used': 1, ' ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Baby Trend Diaper Champ</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">We love our diaper champ.<br>It is very easy to use ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">5.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'and': 3, 'over.': 1,<br>'all': 1, 'love': 1, ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Baby Trend Diaper Champ</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Two girlfriends and two<br>family members put me ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">5.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'just': 1, 'when': 1,<br>'both': 1, 'results': 1, ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Baby Trend Diaper Champ</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">I waited to review this<br>until I saw how it ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">4.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'lysol': 1, 'all': 1,<br>'mom.': 1, 'busy': 1, ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Baby Trend Diaper Champ</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">I have had a diaper genie<br>for almost 4 years since ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'all': 1, 'bags.': 1,<br>'just': 1, \"don't\": 2, ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Baby Trend Diaper Champ</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">I originally put this<br>item on my baby registry ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">5.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'lysol': 1, 'all': 2,<br>'bags.': 1, 'feedback': ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Baby Trend Diaper Champ</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">I am so glad I got the<br>Diaper Champ instead of ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">5.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'and': 2, 'all': 1,<br>'just': 1, 'is': 2, ' ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Baby Trend Diaper Champ</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">We had 2 diaper Genie's<br>both given to us as a ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">4.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'hand.': 1, '(required':<br>1, 'before': 1, ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
"</table>\n",
"<table frame=\"box\" rules=\"cols\">\n",
" <tr>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">amazing</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">love</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">horrible</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">bad</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">terrible</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">awful</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">wow</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">hate</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">sentiment</th>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">2</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" </tr>\n",
"</table>\n",
"[10 rows x 16 columns]<br/>\n",
"</div>"
],
"text/plain": [
"Columns:\n",
"\tname\tstr\n",
"\treview\tstr\n",
"\trating\tfloat\n",
"\tword_count\tdict\n",
"\tawesome\tint\n",
"\tgreat\tint\n",
"\tfantastic\tint\n",
"\tamazing\tint\n",
"\tlove\tint\n",
"\thorrible\tint\n",
"\tbad\tint\n",
"\tterrible\tint\n",
"\tawful\tint\n",
"\twow\tint\n",
"\thate\tint\n",
"\tsentiment\tint\n",
"\n",
"Rows: 10\n",
"\n",
"Data:\n",
"+-------------------------+-------------------------------+--------+\n",
"| name | review | rating |\n",
"+-------------------------+-------------------------------+--------+\n",
"| Baby Trend Diaper Champ | Ok - newsflash. Diapers a... | 4.0 |\n",
"| Baby Trend Diaper Champ | My husband and I selected ... | 1.0 |\n",
"| Baby Trend Diaper Champ | Excellent diaper disposal ... | 5.0 |\n",
"| Baby Trend Diaper Champ | We love our diaper champ. ... | 5.0 |\n",
"| Baby Trend Diaper Champ | Two girlfriends and two fa... | 5.0 |\n",
"| Baby Trend Diaper Champ | I waited to review this un... | 4.0 |\n",
"| Baby Trend Diaper Champ | I have had a diaper genie ... | 1.0 |\n",
"| Baby Trend Diaper Champ | I originally put this item... | 5.0 |\n",
"| Baby Trend Diaper Champ | I am so glad I got the Dia... | 5.0 |\n",
"| Baby Trend Diaper Champ | We had 2 diaper Genie's bo... | 4.0 |\n",
"+-------------------------+-------------------------------+--------+\n",
"+-------------------------------+---------+-------+-----------+---------+------+\n",
"| word_count | awesome | great | fantastic | amazing | love |\n",
"+-------------------------------+---------+-------+-----------+---------+------+\n",
"| {'just': 2, 'less': 1, '-'... | 0 | 0 | 0 | 0 | 0 |\n",
"| {'just': 1, 'less': 1, 'wh... | 0 | 0 | 0 | 0 | 0 |\n",
"| {'control': 1, 'am': 1, 'i... | 0 | 0 | 0 | 0 | 0 |\n",
"| {'and': 3, 'over.': 1, 'al... | 0 | 0 | 0 | 0 | 1 |\n",
"| {'just': 1, 'when': 1, 'bo... | 0 | 0 | 0 | 0 | 0 |\n",
"| {'lysol': 1, 'all': 1, 'mo... | 0 | 0 | 0 | 0 | 0 |\n",
"| {'all': 1, 'bags.': 1, 'ju... | 0 | 0 | 0 | 0 | 0 |\n",
"| {'lysol': 1, 'all': 2, 'ba... | 0 | 0 | 0 | 0 | 0 |\n",
"| {'and': 2, 'all': 1, 'just... | 0 | 0 | 0 | 0 | 0 |\n",
"| {'hand.': 1, '(required': ... | 0 | 0 | 0 | 0 | 2 |\n",
"+-------------------------------+---------+-------+-----------+---------+------+\n",
"+----------+-----+----------+-------+-----+------+-----------+\n",
"| horrible | bad | terrible | awful | wow | hate | sentiment |\n",
"+----------+-----+----------+-------+-----+------+-----------+\n",
"| 0 | 0 | 0 | 0 | 0 | 0 | 1 |\n",
"| 0 | 0 | 0 | 0 | 0 | 0 | 0 |\n",
"| 0 | 0 | 0 | 0 | 0 | 0 | 1 |\n",
"| 0 | 0 | 0 | 0 | 0 | 0 | 1 |\n",
"| 1 | 0 | 0 | 0 | 0 | 0 | 1 |\n",
"| 0 | 1 | 0 | 0 | 0 | 0 | 1 |\n",
"| 0 | 0 | 0 | 0 | 0 | 0 | 0 |\n",
"| 0 | 0 | 0 | 0 | 0 | 0 | 1 |\n",
"| 0 | 0 | 0 | 0 | 0 | 0 | 1 |\n",
"| 0 | 0 | 0 | 0 | 0 | 0 | 1 |\n",
"+----------+-----+----------+-------+-----+------+-----------+\n",
"[10 rows x 16 columns]"
]
},
"execution_count": 76,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"diaper_champ_reviews.head()"
]
},
{
"cell_type": "code",
"execution_count": 77,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"PROGRESS: Logistic regression:\n",
"PROGRESS: --------------------------------------------------------\n",
"PROGRESS: Number of examples : 133448\n",
"PROGRESS: Number of classes : 2\n",
"PROGRESS: Number of feature columns : 1\n",
"PROGRESS: Number of unpacked features : 219217\n",
"PROGRESS: Number of coefficients : 219218\n",
"PROGRESS: Starting L-BFGS\n",
"PROGRESS: --------------------------------------------------------\n",
"PROGRESS: +-----------+----------+-----------+--------------+-------------------+---------------------+\n",
"PROGRESS: | Iteration | Passes | Step size | Elapsed Time | Training-accuracy | Validation-accuracy |\n",
"PROGRESS: +-----------+----------+-----------+--------------+-------------------+---------------------+\n",
"PROGRESS: | 1 | 5 | 0.000002 | 0.939897 | 0.841481 | 0.839989 |\n",
"PROGRESS: | 2 | 9 | 3.000000 | 1.851510 | 0.947425 | 0.894877 |\n",
"PROGRESS: | 3 | 10 | 3.000000 | 2.215372 | 0.923768 | 0.866232 |\n",
"PROGRESS: | 4 | 11 | 3.000000 | 2.562258 | 0.971779 | 0.912743 |\n",
"PROGRESS: | 5 | 12 | 3.000000 | 2.926806 | 0.975511 | 0.908900 |\n",
"PROGRESS: | 6 | 13 | 3.000000 | 3.267204 | 0.899991 | 0.825967 |\n",
"PROGRESS: | 10 | 18 | 1.000000 | 4.860940 | 0.988715 | 0.916256 |\n",
"PROGRESS: +-----------+----------+-----------+--------------+-------------------+---------------------+\n"
]
}
],
"source": [
"sentiment_model =graphlab.logistic_classifier.create(train_data,\n",
" target='sentiment',\n",
" features=['word_count'],\n",
" validation_set=test_data)"
]
},
{
"cell_type": "code",
"execution_count": 78,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"diaper_champ_reviews['predicted_sentiment'] = sentiment_model.predict(diaper_champ_reviews, \n",
" output_type = 'probability')"
]
},
{
"cell_type": "code",
"execution_count": 85,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/html": [
"<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\"><table frame=\"box\" rules=\"cols\">\n",
" <tr>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">name</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">review</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">rating</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">word_count</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">awesome</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">great</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">fantastic</th>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Baby Trend Diaper Champ</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Baby Luke can turn a<br>clean diaper to a dirty ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">5.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'all': 1, 'less': 1,<br>\"friend's\": 1, '(which': ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Baby Trend Diaper Champ</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">I LOOOVE this diaper<br>pail! Its the easies ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">5.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'just': 1, 'over': 1,<br>'rweek': 1, 'sooo': 1, ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Baby Trend Diaper Champ</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">We researched all of the<br>different types of di ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">4.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'all': 2, 'just': 4,<br>\"don't\": 2, 'one,': 1, ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Baby Trend Diaper Champ</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">My baby is now 8 months<br>and the can has been ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">5.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{\"don't\": 1, 'when': 1,<br>'over': 1, 'soon': 1, ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">2</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Baby Trend Diaper Champ</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">This is absolutely, by<br>far, the best diaper ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">5.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'just': 3, 'money': 1,<br>'not': 2, 'mechanism' ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Baby Trend Diaper Champ</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Diaper Champ or Diaper<br>Genie? That was my ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">5.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'all': 1, 'bags.': 1,<br>'son,': 1, '(i': 1, ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Baby Trend Diaper Champ</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Wow! This is fabulous.<br>It was a toss-up between ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">5.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'and': 4, '\"genie\".': 1,<br>'since': 1, 'garbage' ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Baby Trend Diaper Champ</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">I originally put this<br>item on my baby registry ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">5.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'lysol': 1, 'all': 2,<br>'bags.': 1, 'feedback': ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Baby Trend Diaper Champ</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Two girlfriends and two<br>family members put me ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">5.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'just': 1, 'when': 1,<br>'both': 1, 'results': 1, ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Baby Trend Diaper Champ</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">I am one of those super-<br>critical shoppers who ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">5.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'taller': 1, 'bags.': 1,<br>'just': 1, \"don't\": 4, ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
"</table>\n",
"<table frame=\"box\" rules=\"cols\">\n",
" <tr>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">amazing</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">love</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">horrible</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">bad</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">terrible</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">awful</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">wow</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">hate</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">sentiment</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">predicted_sentiment</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">predicted_sentiment_2</th>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0.999999937267</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0.796940851291</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0.999999917406</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0.940876393428</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0.999999899509</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0.5942241719</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0.999999836182</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0.895606298305</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">2</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0.999999824745</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0.984739056527</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0.999999759315</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0.796940851291</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0.999999692111</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0.796940851291</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0.999999642488</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0.796940851291</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0.999999604504</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0.347684052736</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0.999999486804</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0.940876393428</td>\n",
" </tr>\n",
"</table>\n",
"[10 rows x 18 columns]<br/>\n",
"</div>"
],
"text/plain": [
"Columns:\n",
"\tname\tstr\n",
"\treview\tstr\n",
"\trating\tfloat\n",
"\tword_count\tdict\n",
"\tawesome\tint\n",
"\tgreat\tint\n",
"\tfantastic\tint\n",
"\tamazing\tint\n",
"\tlove\tint\n",
"\thorrible\tint\n",
"\tbad\tint\n",
"\tterrible\tint\n",
"\tawful\tint\n",
"\twow\tint\n",
"\thate\tint\n",
"\tsentiment\tint\n",
"\tpredicted_sentiment\tfloat\n",
"\tpredicted_sentiment_2\tfloat\n",
"\n",
"Rows: 10\n",
"\n",
"Data:\n",
"+-------------------------+-------------------------------+--------+\n",
"| name | review | rating |\n",
"+-------------------------+-------------------------------+--------+\n",
"| Baby Trend Diaper Champ | Baby Luke can turn a clean... | 5.0 |\n",
"| Baby Trend Diaper Champ | I LOOOVE this diaper pail!... | 5.0 |\n",
"| Baby Trend Diaper Champ | We researched all of the d... | 4.0 |\n",
"| Baby Trend Diaper Champ | My baby is now 8 months an... | 5.0 |\n",
"| Baby Trend Diaper Champ | This is absolutely, by far... | 5.0 |\n",
"| Baby Trend Diaper Champ | Diaper Champ or Diaper Gen... | 5.0 |\n",
"| Baby Trend Diaper Champ | Wow! This is fabulous. I... | 5.0 |\n",
"| Baby Trend Diaper Champ | I originally put this item... | 5.0 |\n",
"| Baby Trend Diaper Champ | Two girlfriends and two fa... | 5.0 |\n",
"| Baby Trend Diaper Champ | I am one of those super-cr... | 5.0 |\n",
"+-------------------------+-------------------------------+--------+\n",
"+-------------------------------+---------+-------+-----------+---------+------+\n",
"| word_count | awesome | great | fantastic | amazing | love |\n",
"+-------------------------------+---------+-------+-----------+---------+------+\n",
"| {'all': 1, 'less': 1, \"fri... | 0 | 0 | 0 | 0 | 0 |\n",
"| {'just': 1, 'over': 1, 'rw... | 0 | 0 | 0 | 0 | 1 |\n",
"| {'all': 2, 'just': 4, \"don... | 0 | 0 | 0 | 0 | 0 |\n",
"| {\"don't\": 1, 'when': 1, 'o... | 0 | 2 | 0 | 0 | 0 |\n",
"| {'just': 3, 'money': 1, 'n... | 0 | 0 | 0 | 0 | 2 |\n",
"| {'all': 1, 'bags.': 1, 'so... | 0 | 0 | 0 | 0 | 0 |\n",
"| {'and': 4, '\"genie\".': 1, ... | 0 | 0 | 0 | 0 | 0 |\n",
"| {'lysol': 1, 'all': 2, 'ba... | 0 | 0 | 0 | 0 | 0 |\n",
"| {'just': 1, 'when': 1, 'bo... | 0 | 0 | 0 | 0 | 0 |\n",
"| {'taller': 1, 'bags.': 1, ... | 0 | 0 | 0 | 0 | 1 |\n",
"+-------------------------------+---------+-------+-----------+---------+------+\n",
"+----------+-----+----------+-------+-----+------+-----------+---------------------+\n",
"| horrible | bad | terrible | awful | wow | hate | sentiment | predicted_sentiment |\n",
"+----------+-----+----------+-------+-----+------+-----------+---------------------+\n",
"| 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.999999937267 |\n",
"| 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.999999917406 |\n",
"| 0 | 1 | 0 | 0 | 0 | 0 | 1 | 0.999999899509 |\n",
"| 0 | 1 | 0 | 0 | 0 | 0 | 1 | 0.999999836182 |\n",
"| 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.999999824745 |\n",
"| 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.999999759315 |\n",
"| 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.999999692111 |\n",
"| 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.999999642488 |\n",
"| 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0.999999604504 |\n",
"| 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.999999486804 |\n",
"+----------+-----+----------+-------+-----+------+-----------+---------------------+\n",
"+-----------------------+\n",
"| predicted_sentiment_2 |\n",
"+-----------------------+\n",
"| 0.796940851291 |\n",
"| 0.940876393428 |\n",
"| 0.5942241719 |\n",
"| 0.895606298305 |\n",
"| 0.984739056527 |\n",
"| 0.796940851291 |\n",
"| 0.796940851291 |\n",
"| 0.796940851291 |\n",
"| 0.347684052736 |\n",
"| 0.940876393428 |\n",
"+-----------------------+\n",
"[10 rows x 18 columns]"
]
},
"execution_count": 85,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"diaper_champ_reviews.sort('predicted_sentiment',ascending=False).head()"
]
},
{
"cell_type": "code",
"execution_count": 86,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"'Baby Luke can turn a clean diaper to a dirty diaper in 3 seconds flat. The diaper champ turns the smelly diaper into \"what diaper smell\" in less time than that. I hesitated and wondered what I REALLY needed for the nursery. This is one of the best purchases we made. The champ, the baby bjorn, fluerville diaper bag, and graco pack and play bassinet all vie for the best baby purchase.Great product, easy to use, economical, effective, absolutly fabulous.UpdateI knew that I loved the champ, and useing the diaper genie at a friend\\'s house REALLY reinforced that!! There is no comparison, the chanp is easy and smell free, the genie was difficult to use one handed (which is absolutly vital if you have a little one on a changing pad) and there was a deffinite odor eminating from the genieplus we found that the quick tie garbage bags where the ties are integrated into the bag work really well because there isn\\'t any added bulk around the sealing edge of the champ.'"
]
},
"execution_count": 86,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"diaper_champ_reviews.sort('predicted_sentiment',ascending=False).head()[0]['review']"
]
},
{
"cell_type": "code",
"execution_count": 87,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/html": [
"<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\"><table frame=\"box\" rules=\"cols\">\n",
" <tr>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">name</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">review</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">rating</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">word_count</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">awesome</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">great</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">fantastic</th>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Baby Trend Diaper Champ</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">I LOVE LOVE LOVE this<br>product! It is SO much ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">4.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'rating': 1,<br>'contacted': 1, 'over': ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Baby Trend Diaper Champ</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">I received my Diaper<br>Champ at my baby shower ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">5.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'bags.': 1, \"don't\": 1,<br>'son.': 1, 'of,': 1, ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Baby Trend Diaper Champ</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Love it, love it, love<br>it! This lives up to ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">5.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'all': 1, 'already': 1,<br>'love': 3, 'have': 4, ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Baby Trend Diaper Champ</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Works great - no smells.<br>LOVE that it uses reg ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">5.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'and': 2, 'love': 1,<br>'garbage': 1, 'wastef ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">2</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Baby Trend Diaper Champ</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">I love this diaper pale<br>and wouldn't dream of ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">5.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'and': 3, 'love': 1,<br>'use.': 1, 'is': 2, ' ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">2</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Baby Trend Diaper Champ</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">We had 2 diaper Genie's<br>both given to us as a ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">4.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'hand.': 1, '(required':<br>1, 'before': 1, ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Baby Trend Diaper Champ</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">I've worked with kids<br>more than half my life. ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">5.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'and': 4, 'genies': 1,<br>'now': 1, 'because': 1, ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Baby Trend Diaper Champ</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">This is absolutely, by<br>far, the best diaper ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">5.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'just': 3, 'money': 1,<br>'not': 2, 'mechanism' ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Baby Trend Diaper Champ</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">I have a two-year-old son<br>and I love the Diaper ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">5.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'and': 6, 'two-year-<br>old': 1, \"toddler's\": 1, ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">Baby Trend Diaper Champ</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">I love this diaper pail!<br>It's so easy to use a ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">5.0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">{'and': 3, 'this': 1,<br>'love': 2, 'being': 1, ...</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" </tr>\n",
"</table>\n",
"<table frame=\"box\" rules=\"cols\">\n",
" <tr>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">amazing</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">love</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">horrible</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">bad</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">terrible</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">awful</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">wow</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">hate</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">sentiment</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">predicted_sentiment</th>\n",
" <th style=\"padding-left: 1em; padding-right: 1em; text-align: center\">predicted_sentiment_2</th>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">3</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0.999993652036</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0.998423414594</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">3</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0.999301330286</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0.996192539732</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">3</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0.985732101571</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0.996192539732</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0.998904798032</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0.989387539605</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0.983086548255</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0.989387539605</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">2</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0.99267406035</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0.984739056527</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">2</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0.999879939529</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0.984739056527</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">2</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0.999999824745</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0.984739056527</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">2</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0.833101136873</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0.984739056527</td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">2</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">1</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0.971519376204</td>\n",
" <td style=\"padding-left: 1em; padding-right: 1em; text-align: center; vertical-align: top\">0.984739056527</td>\n",
" </tr>\n",
"</table>\n",
"[10 rows x 18 columns]<br/>\n",
"</div>"
],
"text/plain": [
"Columns:\n",
"\tname\tstr\n",
"\treview\tstr\n",
"\trating\tfloat\n",
"\tword_count\tdict\n",
"\tawesome\tint\n",
"\tgreat\tint\n",
"\tfantastic\tint\n",
"\tamazing\tint\n",
"\tlove\tint\n",
"\thorrible\tint\n",
"\tbad\tint\n",
"\tterrible\tint\n",
"\tawful\tint\n",
"\twow\tint\n",
"\thate\tint\n",
"\tsentiment\tint\n",
"\tpredicted_sentiment\tfloat\n",
"\tpredicted_sentiment_2\tfloat\n",
"\n",
"Rows: 10\n",
"\n",
"Data:\n",
"+-------------------------+-------------------------------+--------+\n",
"| name | review | rating |\n",
"+-------------------------+-------------------------------+--------+\n",
"| Baby Trend Diaper Champ | I LOVE LOVE LOVE this prod... | 4.0 |\n",
"| Baby Trend Diaper Champ | I received my Diaper Champ... | 5.0 |\n",
"| Baby Trend Diaper Champ | Love it, love it, love it!... | 5.0 |\n",
"| Baby Trend Diaper Champ | Works great - no smells. ... | 5.0 |\n",
"| Baby Trend Diaper Champ | I love this diaper pale an... | 5.0 |\n",
"| Baby Trend Diaper Champ | We had 2 diaper Genie's bo... | 4.0 |\n",
"| Baby Trend Diaper Champ | I've worked with kids more... | 5.0 |\n",
"| Baby Trend Diaper Champ | This is absolutely, by far... | 5.0 |\n",
"| Baby Trend Diaper Champ | I have a two-year-old son ... | 5.0 |\n",
"| Baby Trend Diaper Champ | I love this diaper pail! ... | 5.0 |\n",
"+-------------------------+-------------------------------+--------+\n",
"+-------------------------------+---------+-------+-----------+---------+------+\n",
"| word_count | awesome | great | fantastic | amazing | love |\n",
"+-------------------------------+---------+-------+-----------+---------+------+\n",
"| {'rating': 1, 'contacted':... | 0 | 1 | 0 | 0 | 3 |\n",
"| {'bags.': 1, \"don't\": 1, '... | 0 | 0 | 0 | 0 | 3 |\n",
"| {'all': 1, 'already': 1, '... | 0 | 0 | 0 | 0 | 3 |\n",
"| {'and': 2, 'love': 1, 'gar... | 0 | 2 | 0 | 0 | 1 |\n",
"| {'and': 3, 'love': 1, 'use... | 0 | 2 | 0 | 0 | 1 |\n",
"| {'hand.': 1, '(required': ... | 0 | 0 | 0 | 0 | 2 |\n",
"| {'and': 4, 'genies': 1, 'n... | 0 | 0 | 0 | 0 | 2 |\n",
"| {'just': 3, 'money': 1, 'n... | 0 | 0 | 0 | 0 | 2 |\n",
"| {'and': 6, 'two-year-old':... | 0 | 0 | 0 | 0 | 2 |\n",
"| {'and': 3, 'this': 1, 'lov... | 0 | 0 | 0 | 0 | 2 |\n",
"+-------------------------------+---------+-------+-----------+---------+------+\n",
"+----------+-----+----------+-------+-----+------+-----------+---------------------+\n",
"| horrible | bad | terrible | awful | wow | hate | sentiment | predicted_sentiment |\n",
"+----------+-----+----------+-------+-----+------+-----------+---------------------+\n",
"| 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.999993652036 |\n",
"| 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.999301330286 |\n",
"| 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.985732101571 |\n",
"| 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.998904798032 |\n",
"| 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.983086548255 |\n",
"| 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.99267406035 |\n",
"| 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.999879939529 |\n",
"| 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.999999824745 |\n",
"| 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.833101136873 |\n",
"| 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.971519376204 |\n",
"+----------+-----+----------+-------+-----+------+-----------+---------------------+\n",
"+-----------------------+\n",
"| predicted_sentiment_2 |\n",
"+-----------------------+\n",
"| 0.998423414594 |\n",
"| 0.996192539732 |\n",
"| 0.996192539732 |\n",
"| 0.989387539605 |\n",
"| 0.989387539605 |\n",
"| 0.984739056527 |\n",
"| 0.984739056527 |\n",
"| 0.984739056527 |\n",
"| 0.984739056527 |\n",
"| 0.984739056527 |\n",
"+-----------------------+\n",
"[10 rows x 18 columns]"
]
},
"execution_count": 87,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"diaper_champ_reviews['predicted_sentiment_2']= selected_words_model.predict(diaper_champ_reviews, \n",
" output_type='probability')\n",
"diaper_champ_reviews.sort('predicted_sentiment_2',ascending=False).head()"
]
},
{
"cell_type": "code",
"execution_count": 88,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"'I LOVE LOVE LOVE this product! It is SO much easier to use than the Diaper Genie, (you need a PHD in poopy to figure out how to use the darn thing!) and it even takes the same bags as my kitchen trash can, shich is super convenient, and cost efficient as I can buy them in bulk.The only reason for not rating it a 5 star was that I did have one small problem with it. The foam gasket in the barrell which keeps the poopy smell inside the unit ripped somehow, and it got VERY stinky. HOWEVER, I contacted the manufacturer though their website, and received an email back the same day stating that this was unusual, and that replacement gaskets were on their way to me. They arrived inside of a week and after replacing, it works great again! (They even sent me extras should it happen again)I HIGHLY reccomend this diaper pail over ANY competitors, you will not be sorry!'"
]
},
"execution_count": 88,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"diaper_champ_reviews.sort('predicted_sentiment_2',ascending=False).head()[0]['review']"
]
},
{
"cell_type": "code",
"execution_count": 89,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"{'accuracy': 0.916256305548883, 'confusion_matrix': Columns:\n",
" \ttarget_label\tint\n",
" \tpredicted_label\tint\n",
" \tcount\tint\n",
" \n",
" Rows: 4\n",
" \n",
" Data:\n",
" +--------------+-----------------+-------+\n",
" | target_label | predicted_label | count |\n",
" +--------------+-----------------+-------+\n",
" | 1 | 0 | 1461 |\n",
" | 0 | 1 | 1328 |\n",
" | 0 | 0 | 4000 |\n",
" | 1 | 1 | 26515 |\n",
" +--------------+-----------------+-------+\n",
" [4 rows x 3 columns]}"
]
},
"execution_count": 89,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"sentiment_model.evaluate(test_data)"
]
},
{
"cell_type": "code",
"execution_count": 92,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"0.916256305548883"
]
},
"execution_count": 92,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"(4000.0 +26515)/(1461+1328+4000+26515)"
]
},
{
"cell_type": "code",
"execution_count": 93,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"0.8400192169108815"
]
},
"execution_count": 93,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"(1461.0 + 26515)/(1461+1328+4000+26515)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 2",
"language": "python",
"name": "python2"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 2
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython2",
"version": "2.7.10"
}
},
"nbformat": 4,
"nbformat_minor": 0
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment