数据科学入门—数据可视化
2017-07-11 17:03
507 查看
import matplotlib.pyplot as plt
from collections import Counter
def make_chart_simple_line_chart(plt):
years = [1950, 1960, 1970, 1980, 1990, 2000, 2010]
gdp = [300.2, 543.3, 1075.9, 2862.5, 5979.6, 10289.7, 14958.3]
# create a line chart, years on x-axis, gdp on y-axis
plt.plot(years, gdp, color='green', marker='o', linestyle='solid')
# add a title
plt.title("Nominal GDP")
# add a label to the y-axis
plt.ylabel("Billions of $")
plt.show()
def make_chart_simple_bar_chart(plt):
movies = ["Annie Hall", "Ben-Hur", "Casablanca", "Gandhi", "West Side Story"]
num_oscars = [5, 11, 3, 8, 10]
# bars are by default width 0.8, so we'll add 0.1 to the left coordinates
# so that each bar is centered
xs = [i + 0.1 for i, _ in enumerate(movies)]
# plot bars with left x-coordinates [xs], heights [num_oscars]
plt.bar(xs, num_oscars)
plt.ylabel("# of Academy Awards")
plt.title("My Favorite Movies")
# label x-axis with movie names at bar centers
plt.xticks([i + 0.5 for i, _ in enumerate(movies)], movies)
plt.show()
def make_chart_histogram(plt):
grades = [83,95,91,87,70,0,85,82,100,67,73,77,0]
decile = lambda grade: grade // 10 * 10
histogram = Counter(decile(grade) for grade in grades)
plt.bar([x - 4 for x in histogram.keys()], # shift each bar to the left by 4
histogram.values(), # give each bar its correct height
8) # give each bar a width of 8
plt.axis([-5, 105, 0, 5]) # x-axis from -5 to 105,
# y-axis from 0 to 5
plt.xticks([10 * i for i in range(11)]) # x-axis labels at 0, 10, ..., 100
plt.xlabel("Decile")
plt.ylabel("# of Students")
plt.title("Distribution of Exam 1 Grades")
plt.show()
def make_chart_misleading_y_axis(plt, mislead=True):
mentions = [500, 505]
years = [2013, 2014]
plt.bar([2012.6, 2013.6], mentions, 0.8)
plt.xticks(years)
plt.ylabel("# of times I heard someone say 'data science'")
# if you don't do this, matplotlib will label the x-axis 0, 1
# and then add a +2.013e3 off in the corner (bad matplotlib!)
plt.ticklabel_format(useOffset=False)
if mislead:
# misleading y-axis only shows the part above 500
plt.axis([2012.5,2014.5,499,506])
plt.title("Look at the 'Huge' Increase!")
else:
plt.axis([2012.5,2014.5,0,550])
plt.title("Not So Huge Anymore.")
plt.show()
def make_chart_several_line_charts(plt):
variance = [1,2,4,8,16,32,64,128,256]
bias_squared = [256,128,64,32,16,8,4,2,1]
total_error = [x + y for x, y in zip(variance, bias_squared)]
xs = range(len(variance))
# we can make multiple calls to plt.plot
# to show multiple series on the same chart
plt.plot(xs, variance, 'g-', label='variance') # green solid line
plt.plot(xs, bias_squared, 'r-.', label='bias^2') # red dot-dashed line
plt.plot(xs, total_error, 'b:', label='total error') # blue dotted line
# because we've assigned labels to each series
# we can get a legend for free
# loc=9 means "top center"
plt.legend(loc=9)
plt.xlabel("model complexity")
plt.title("The Bias-Variance Tradeoff")
plt.show()
def make_chart_scatter_plot(plt):
friends = [ 70, 65, 72, 63, 71, 64, 60, 64, 67]
minutes = [175, 170, 205, 120, 220, 130, 105, 145, 190]
labels = ['a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i']
plt.scatter(friends, minutes)
# label each point
for label, friend_count, minute_count in zip(labels, friends, minutes):
plt.annotate(label,
xy=(friend_count, minute_count), # put the label with its point
xytext=(5, -5), # but slightly offset
textcoords='offset points')
plt.title("Daily Minutes vs. Number of Friends")
plt.xlabel("# of friends")
plt.ylabel("daily minutes spent on the site")
plt.show()
def make_chart_scatterplot_axes(plt, equal_axes=False):
test_1_grades = [ 99, 90, 85, 97, 80]
test_2_grades = [100, 85, 60, 90, 70]
plt.scatter(test_1_grades, test_2_grades)
plt.xlabel("test 1 grade")
plt.ylabel("test 2 grade")
if equal_axes:
plt.title("Axes Are Comparable")
plt.axis("equal")
else:
plt.title("Axes Aren't Comparable")
plt.show()
def make_chart_pie_chart(plt):
plt.pie([0.95, 0.05], labels=["Uses pie charts", "Knows better"])
# make sure pie is a circle and not an oval
plt.axis("equal")
plt.show()
if __name__ == "__main__":
make_chart_simple_line_chart(plt)
make_chart_simple_bar_chart(plt)
make_chart_histogram(plt)
make_chart_misleading_y_axis(plt, mislead=True)
make_chart_misleading_y_axis(plt, mislead=False)
make_chart_several_line_charts(plt)
make_chart_scatter_plot(plt)
make_chart_scatterplot_axes(plt, equal_axes=False)
make_chart_scatterplot_axes(plt, equal_axes=True)
make_chart_pie_chart(plt)
from collections import Counter
def make_chart_simple_line_chart(plt):
years = [1950, 1960, 1970, 1980, 1990, 2000, 2010]
gdp = [300.2, 543.3, 1075.9, 2862.5, 5979.6, 10289.7, 14958.3]
# create a line chart, years on x-axis, gdp on y-axis
plt.plot(years, gdp, color='green', marker='o', linestyle='solid')
# add a title
plt.title("Nominal GDP")
# add a label to the y-axis
plt.ylabel("Billions of $")
plt.show()
def make_chart_simple_bar_chart(plt):
movies = ["Annie Hall", "Ben-Hur", "Casablanca", "Gandhi", "West Side Story"]
num_oscars = [5, 11, 3, 8, 10]
# bars are by default width 0.8, so we'll add 0.1 to the left coordinates
# so that each bar is centered
xs = [i + 0.1 for i, _ in enumerate(movies)]
# plot bars with left x-coordinates [xs], heights [num_oscars]
plt.bar(xs, num_oscars)
plt.ylabel("# of Academy Awards")
plt.title("My Favorite Movies")
# label x-axis with movie names at bar centers
plt.xticks([i + 0.5 for i, _ in enumerate(movies)], movies)
plt.show()
def make_chart_histogram(plt):
grades = [83,95,91,87,70,0,85,82,100,67,73,77,0]
decile = lambda grade: grade // 10 * 10
histogram = Counter(decile(grade) for grade in grades)
plt.bar([x - 4 for x in histogram.keys()], # shift each bar to the left by 4
histogram.values(), # give each bar its correct height
8) # give each bar a width of 8
plt.axis([-5, 105, 0, 5]) # x-axis from -5 to 105,
# y-axis from 0 to 5
plt.xticks([10 * i for i in range(11)]) # x-axis labels at 0, 10, ..., 100
plt.xlabel("Decile")
plt.ylabel("# of Students")
plt.title("Distribution of Exam 1 Grades")
plt.show()
def make_chart_misleading_y_axis(plt, mislead=True):
mentions = [500, 505]
years = [2013, 2014]
plt.bar([2012.6, 2013.6], mentions, 0.8)
plt.xticks(years)
plt.ylabel("# of times I heard someone say 'data science'")
# if you don't do this, matplotlib will label the x-axis 0, 1
# and then add a +2.013e3 off in the corner (bad matplotlib!)
plt.ticklabel_format(useOffset=False)
if mislead:
# misleading y-axis only shows the part above 500
plt.axis([2012.5,2014.5,499,506])
plt.title("Look at the 'Huge' Increase!")
else:
plt.axis([2012.5,2014.5,0,550])
plt.title("Not So Huge Anymore.")
plt.show()
def make_chart_several_line_charts(plt):
variance = [1,2,4,8,16,32,64,128,256]
bias_squared = [256,128,64,32,16,8,4,2,1]
total_error = [x + y for x, y in zip(variance, bias_squared)]
xs = range(len(variance))
# we can make multiple calls to plt.plot
# to show multiple series on the same chart
plt.plot(xs, variance, 'g-', label='variance') # green solid line
plt.plot(xs, bias_squared, 'r-.', label='bias^2') # red dot-dashed line
plt.plot(xs, total_error, 'b:', label='total error') # blue dotted line
# because we've assigned labels to each series
# we can get a legend for free
# loc=9 means "top center"
plt.legend(loc=9)
plt.xlabel("model complexity")
plt.title("The Bias-Variance Tradeoff")
plt.show()
def make_chart_scatter_plot(plt):
friends = [ 70, 65, 72, 63, 71, 64, 60, 64, 67]
minutes = [175, 170, 205, 120, 220, 130, 105, 145, 190]
labels = ['a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i']
plt.scatter(friends, minutes)
# label each point
for label, friend_count, minute_count in zip(labels, friends, minutes):
plt.annotate(label,
xy=(friend_count, minute_count), # put the label with its point
xytext=(5, -5), # but slightly offset
textcoords='offset points')
plt.title("Daily Minutes vs. Number of Friends")
plt.xlabel("# of friends")
plt.ylabel("daily minutes spent on the site")
plt.show()
def make_chart_scatterplot_axes(plt, equal_axes=False):
test_1_grades = [ 99, 90, 85, 97, 80]
test_2_grades = [100, 85, 60, 90, 70]
plt.scatter(test_1_grades, test_2_grades)
plt.xlabel("test 1 grade")
plt.ylabel("test 2 grade")
if equal_axes:
plt.title("Axes Are Comparable")
plt.axis("equal")
else:
plt.title("Axes Aren't Comparable")
plt.show()
def make_chart_pie_chart(plt):
plt.pie([0.95, 0.05], labels=["Uses pie charts", "Knows better"])
# make sure pie is a circle and not an oval
plt.axis("equal")
plt.show()
if __name__ == "__main__":
make_chart_simple_line_chart(plt)
make_chart_simple_bar_chart(plt)
make_chart_histogram(plt)
make_chart_misleading_y_axis(plt, mislead=True)
make_chart_misleading_y_axis(plt, mislead=False)
make_chart_several_line_charts(plt)
make_chart_scatter_plot(plt)
make_chart_scatterplot_axes(plt, equal_axes=False)
make_chart_scatterplot_axes(plt, equal_axes=True)
make_chart_pie_chart(plt)
相关文章推荐
- 读书笔记数据科学入门————可视化数据
- 读书笔记数据科学入门————数据科学导论
- 【WaaCaa】一款开源科学作图/数据可视化工具 —— 诞生篇
- Python数据可视化-Matplotlib学习笔记(1)--折线图为例画图入门
- 数据科学入门,使用 xgboost 初试 kaggle
- 读书笔记数据科学入门————概率
- [mac] R入门 四 数据可视化
- d3.js:数据可视化利器之快速入门
- 读书笔记数据科学入门————统计学
- matplotlib数据可视化入门-python
- 数据可视化(二)Matplotlib pandas简易入门
- Python 数据科学入门教程:NLTK
- python科学计算数据可视化模块-seaborn
- 基于Python数据可视化利器Matplotlib,绘图入门篇,Pyplot详解
- R如何与Tableau集成可视化分步指南 - 适用于数据科学和商业智能专业人员
- 动态可视化 数据可视化之魅D3,Processing,pandas数据分析,科学计算包Numpy,可视化包Matplotlib,Matlab语言可视化的工作,Matlab没有指针和引用是个大问题
- 数据可视化(三)- Seaborn简易入门
- 数据科学工程师面试宝典系列---R语言入门
- python3数据科学入门实战