Basic clustering for UrbanTide analytics

basic_clustering.ipynb

car_clustering.ipynb

irish_lang_cluster.ipynb

raw_code.py

import pandas as pd
import io
import requests
from sklearn.cluster import KMeans

#Download datasets
url = "https://gist.githubusercontent.com/digitalWestie/b68b86cae1d893d4d3d3b01aca59be8d/raw/28908e0d394802181762dc7429f67c0f79fb9fad/Make%2520Model%2520Data%25202016-edited.csv"
s=requests.get(url).content
dataset=pd.read_csv(io.StringIO(s.decode('windows-1252')))
dataset.iloc[:3,:]

# Only include specified columns:
subset =  dataset.loc[:, ['Label', 'Engine, Noise and Exhaust %', 'Chassis and Body %']]
subset

#Discard label columns (we only want to feed numeric values to algorithm)
subset_data=subset.iloc[:, 1:]

#Run clustering (4 clusters)
kmeans = KMeans(n_clusters=4).fit(subset_data)
y_kmeans = kmeans.predict(subset_data)
y_kmeans

#Draw graph of cluster
from matplotlib import pyplot as plt
plt.scatter(subset_data.iloc[:,0], subset_data.iloc[:,1], c=y_kmeans, s=50, cmap='viridis')
centers = kmeans.cluster_centers_
plt.scatter(centers[:, 0], centers[:, 1], c='black', s=200, alpha=0.5);

#Combine labels with groups
result = pd.crosstab(subset.iloc[:,0], y_kmeans)
result

regression.ipynb