아래와 같이 모듈을 임포트 받습니다.
from __future__ import division, unicode_literals
from collections import Counter
import math, random
import matplotlib.pyplot as plt
from linear_algebra import distance
from statistics import mean
from plot_state_borders import plot_state_borders
약간의 예시 데이터를 통해서 분석을 하면 다음과 같이 출력된다.
cities =
[(-86.75,33.5666666666667,'Python'),(-88.25,30.6833333333333,'Python'),(-112.016666666667,33.4333333333333,'Java'),(-110.933333333333,32.1166666666667,'Java'),(-92.2333333333333,34.7333333333333,'R'),(-121.95,37.7,'R')
cities = [([longitude, latitude], language) for longitude, latitude,
language in cities]
def plot_cities():
# key is language, value is
pair (longitudes, latitudes)
plots = { "Java" :
([], []), "Python" : ([], []), "R" : ([], []) }
# we want each language to
have a different marker and color
markers = { "Java"
: "o", "Python" : "s", "R" :
"^" }
colors = { "Java" : "r",
"Python" : "b", "R" : "g" }
for (longitude, latitude), language in
cities:
plots[language][0].append(longitude)
plots[language][1].append(latitude)
# create a scatter series for
each language
for language, (x, y) in
plots.iteritems():
plt.scatter(x, y,
color=colors[language], marker=markers[language],
label=language, zorder=10)
plot_state_borders() # assume we have a function that does this
plt.legend(loc=0) # let matplotlib choose the location
plt.axis([-130,-60,20,55]) #
set the axes
plt.title("Very popular
language")
plt.show()
plot_cities()
