Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Replace pandas with Modin to exercise 2 #112

Open
wants to merge 3 commits into
base: master
Choose a base branch
from
Open

Replace pandas with Modin to exercise 2 #112

Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
09f347d
Replace pandas with Modin to exercise 2
devin-petersohn Apr 11, 2019
8e1fc8b
Update exercise02-Task_Dependencies.ipynb
devin-petersohn Apr 15, 2019
bf1a349
Update exercise02-Task_Dependencies.ipynb
devin-petersohn Apr 15, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
37 changes: 22 additions & 15 deletions exercises/exercise02-Task_Dependencies.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -227,7 +227,7 @@
"from bs4 import BeautifulSoup\n",
"import requests\n",
"\n",
"import pandas as pd"
"import modin.pandas as pd"
]
},
{
Expand All @@ -250,22 +250,21 @@
"\n",
"def parse_google_response(keyword, response):\n",
" soup = BeautifulSoup(response.text, 'lxml')\n",
" df = pd.DataFrame(columns=['title', 'link', 'description'])\n",
" data = {'title': [], 'link': [], 'description': [], 'library': []}\n",
" for g in soup.find_all(class_='g'):\n",
" entry = {}\n",
" headers = g.find_all(class_='r')\n",
" # Sometimes results have no headers\n",
" if len(headers) != 1:\n",
" continue\n",
" entry['title'] = headers[0].text\n",
" entry['link'] = headers[0].find('a').get('href')[7:]\n",
" data['title'].append(headers[0].text)\n",
" data['link'].append(headers[0].find('a').get('href')[7:])\n",
" description = g.find_all(class_='st')\n",
" entry['description'] = description[0].text if len(description) > 0 else \"\"\n",
" df = df.append(pd.DataFrame(entry, index=[0]))\n",
" \n",
" df['library'] = keyword\n",
" return df\n",
" data['description'].append(description[0].text if len(description) > 0 else \"\")\n",
" data['library'].append(keyword)\n",
" return data\n",
"\n",
"# @ray.remote\n",
devin-petersohn marked this conversation as resolved.
Show resolved Hide resolved
"def get_results(keyword):\n",
" response = query_google(\"learn {}\".format(keyword))\n",
" return parse_google_response(keyword, response)"
Expand All @@ -285,13 +284,13 @@
"outputs": [],
"source": [
"start = time.time()\n",
"keywords = [\"ray\", \"rllib\", \"tune\", \"modin\", \"plasma\", \"arrow\"]\n",
"keywords = [\"ray\", \"rllib\", \"tune\", \"modin.pandas\", \"plasma\", \"arrow\"]\n",
"results = []\n",
"for keyword in keywords:\n",
" df = get_results(keyword)\n",
" results.append(df)\n",
" \n",
"df = pd.concat(results)\n",
" data = get_results(keyword)\n",
" results.append(data)\n",
"\n",
"df = pd.concat([pd.DataFrame(r) for r in results])\n",
"duration = time.time() - start\n",
"print(\"Constructing the dataframe took {} seconds.\".format(duration))"
]
Expand All @@ -311,6 +310,14 @@
"source": [
"df"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**<center> The results of the queries are now stored in a Modin DataFrame (`df`), a DataFrame with an identical API to pandas.**\n",
"**<center> Learn more about using the Modin DataFrame in the `examples/accelerate_pandas.ipynb` tutorial**"
]
}
],
"metadata": {
Expand All @@ -329,7 +336,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.6.1"
"version": "3.6.7"
devin-petersohn marked this conversation as resolved.
Show resolved Hide resolved
},
"toc": {
"base_numbering": 1,
Expand Down