Created
February 16, 2020 22:21
-
-
Save pskifast/868f06321d588cd3bab7e2243aaec45f to your computer and use it in GitHub Desktop.
Created on Cognitive Class Labs
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"cells": [ | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"# Segmenting and Clustering Neighborhoods in Toronto" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"# importing required libraries\n", | |
"\n", | |
"import pandas as pd\n", | |
"import numpy as np\n", | |
"import matplotlib.pyplot as plt\n", | |
"import seaborn as sns\n", | |
"%matplotlib inline\n", | |
"\n", | |
"!pip install lxml\n", | |
"\n", | |
"print('All imported!')" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"## Section 1: Web scraping Wikipedia HTML tables\n", | |
"\n", | |
"web site: https://en.wikipedia.org/wiki/List_of_postal_codes_of_Canada:_M" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"# Parsing the tables of the target webpage\n", | |
"data = pd.read_html('http://en.wikipedia.org/wiki/List_of_postal_codes_of_Canada:_M', header=0)\n", | |
"df = data[0]\n", | |
"\n", | |
"# Changing column names\n", | |
"df.columns = ['PostalCode', 'Borough', 'Neighborhood']\n", | |
"df" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"## Section 2: Performing required operations" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"# Data cleaning per the instructions\n", | |
"df.drop(df[df.Borough == 'Not assigned'].index, inplace=True)\n", | |
"df.loc[df.Neighborhood == 'Not assigned', 'Neighborhood'] = df['Borough']\n", | |
"df.reset_index(drop=True, inplace=True)\n", | |
"df = df.groupby('PostalCode').agg({'Borough':'first','Neighborhood': ', '.join}).reset_index()\n", | |
"\n", | |
"df" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"## Section 3: Verifying results" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"**Testing if grouping works, by comparing with table given in the instructions**" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"df.loc[df['PostalCode'] == 'M9V']" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"**Printing number of rows of the resulting table**" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"rows = df.shape\n", | |
"print('Final table has',df.shape[0], 'rows.')" | |
] | |
} | |
], | |
"metadata": { | |
"kernelspec": { | |
"display_name": "Python", | |
"language": "python", | |
"name": "conda-env-python-py" | |
}, | |
"language_info": { | |
"codemirror_mode": { | |
"name": "ipython", | |
"version": 3 | |
}, | |
"file_extension": ".py", | |
"mimetype": "text/x-python", | |
"name": "python", | |
"nbconvert_exporter": "python", | |
"pygments_lexer": "ipython3", | |
"version": "3.6.7" | |
} | |
}, | |
"nbformat": 4, | |
"nbformat_minor": 4 | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment